Context awareness is increasingly gaining applicability in interactive ubiquitous mobile computing
systems. Each context-aware application has its own set of behaviors to react to context modifications. This
paper is concerned with the context modeling and the development methodology for context-aware systems.
We proposed a rule-based approach and use the adaption tree to model the adaption rule of context-aware
systems. We illustrate this idea in an arithmetic game application.
NLP (Natural Language Processing) is a mechanism that helps computers to know natural languages like English. In general, computers can understand data, tables etc. which are well formed. But when it involves natural languages, it's unacceptable for computers to spot them. NLP helps to translate the tongue in such a fashion which will be easily processed by modern computers. Financial Tracker is an approach which will use NLP as a tool and can differentiate the user messages in various categories. the appliance of the approach will be seen at multiple levels. At a personal level, this permits users to filtrate useful financial messages from an large junk of text messages. On the opposite hand, from an industrial point of view, this can be useful in services like online loan disbursal, which are hitting the market nowadays. These services attempt to provide online loans to individuals in an exceedingly faster and quicker manner. But when it involves business view, loan recovery from customers becomes a really important & crucial aspect. As most such services can’t take strict legal actions against the fraud customers, it becomes a requirement that loan should be provided only to those customers who deserve it. At that time, this model can come under the image. As a business we will find the user’s messages from their inbox (after taking permission from the users). These messages are often filtered using NLP which might help to differentiate various types of messages within the user's inbox which might further be used as a content for further prediction and analysis on user’s behaviour in terms of cash related transactions.
Identifying e learner’s opinion using automated sentiment analysis in e-learningeSAT Publishing House
IJRET : International Journal of Research in Engineering and Technology is an international peer reviewed, online journal published by eSAT Publishing House for the enhancement of research in various disciplines of Engineering and Technology. The aim and scope of the journal is to provide an academic medium and an important reference for the advancement and dissemination of research results that support high-level learning, teaching and research in the fields of Engineering and Technology. We bring together Scientists, Academician, Field Engineers, Scholars and Students of related fields of Engineering and Technology.
This document discusses improving the usability of GIS (geographic information system) services by applying semantic ontology. It aims to develop a more user-friendly system that can understand user questions in natural language and provide accurate answers. The key aspects discussed are preprocessing user questions, using an ontology tool like Protégé to map questions to concepts and relationships in an OWL file, and then extracting answers from GIS data and services. The goal is to allow users to easily access and understand geographic information without extensive technical knowledge of GIS systems.
Matching GPS Traces with Personal
Schedules,” Proc. First ACM Int’l Workshop
Personalized Context Modeling and
Management for UbiComp Applications
(PCM), 2009.
[8] X. Li, Y.-Y. Chen, T. Suel, and A.
Markowetz, “Efficient Query Processing in
Geographic Web Search,” Proc. Int’l ACM
SIGIR Conf. Research and Development in
Information Retrieval (SIGIR), 2006.
[9] B.J. Jansen, A. Spink, and T. Saracevic,
“Real Life, Real Users, and Real Needs: A
Study and Analysis of User Queries
In context-aware trust evaluation, using ontology tree is a popular approach to represent the relation
between contexts. Usually, similarity between two contexts is computed using these trees. Therefore, the
performance of trust evaluation highly depends on the quality of ontology trees. Fairness or granularity
consistency is one of the major limitations affecting the quality of ontology tree. This limitation refers to
inequality of semantic similarity in the most ontology trees. In other words, semantic similarity of every two
adjacent nodes is unequal in these trees. It deteriorates the performance of contexts similarity computation.
We overcome this limitation by weighting tree edges based on their semantic similarity. Weight of each
edge is computed using Normalized Similarity Score (NSS) method. This method is based on frequencies of
concepts (words) co-occurrences in the pages indexed by search engines. Our experiments represent the
better performance of the proposed approach in comparison with established trust evaluation approaches.
The suggested approach can enhance efficiency of any solution which models semantic relations by
ontology tree.
A Novel Method for Creating and Recognizing User Behavior ProfilesIJMER
International Journal of Modern Engineering Research (IJMER) is Peer reviewed, online Journal. It serves as an international archival forum of scholarly research related to engineering and science education.
This document summarizes various techniques that have been proposed for providing security during online exams to prevent malpractice. It discusses authentication techniques such as unimodal, multimodal, and data visualization methods. The paper specifically proposes a method called Enhanced Security using Data Visualization (ESDV) that uses data visualization techniques to constantly monitor examinees during online exams in order to enhance security and prevent malpractice.
Text content dependent writer identificationeSAT Journals
Abstract
Text content based personal Identification system is vital in resolving problem of identifying unknown document’s writer using a
set of handwritten samples from alleged known writers. Text written on paper document is usually captured as image by scanner
or camera for computer processing. The most challenging problem encounter in text image processing is extraction of robust
feature vector from a set of inconstant handwritten text images obtained from the same writer at different time. In this work new
feature extraction method is engaged to produce active text features for developing an effective personal identification system.
The feature formed feature vector which is fed as input data into classification algorithm based on Support Vector Machine
(SVM). Experiment was conducted to identify writers of query handwritten texts. Result show satisfactory performance of the
proposed system, it was able to identify writers of query handwritten texts.
Keywords: Handwritten Text, Feature Vector, Identification and Support Vector Machine.
NLP (Natural Language Processing) is a mechanism that helps computers to know natural languages like English. In general, computers can understand data, tables etc. which are well formed. But when it involves natural languages, it's unacceptable for computers to spot them. NLP helps to translate the tongue in such a fashion which will be easily processed by modern computers. Financial Tracker is an approach which will use NLP as a tool and can differentiate the user messages in various categories. the appliance of the approach will be seen at multiple levels. At a personal level, this permits users to filtrate useful financial messages from an large junk of text messages. On the opposite hand, from an industrial point of view, this can be useful in services like online loan disbursal, which are hitting the market nowadays. These services attempt to provide online loans to individuals in an exceedingly faster and quicker manner. But when it involves business view, loan recovery from customers becomes a really important & crucial aspect. As most such services can’t take strict legal actions against the fraud customers, it becomes a requirement that loan should be provided only to those customers who deserve it. At that time, this model can come under the image. As a business we will find the user’s messages from their inbox (after taking permission from the users). These messages are often filtered using NLP which might help to differentiate various types of messages within the user's inbox which might further be used as a content for further prediction and analysis on user’s behaviour in terms of cash related transactions.
Identifying e learner’s opinion using automated sentiment analysis in e-learningeSAT Publishing House
IJRET : International Journal of Research in Engineering and Technology is an international peer reviewed, online journal published by eSAT Publishing House for the enhancement of research in various disciplines of Engineering and Technology. The aim and scope of the journal is to provide an academic medium and an important reference for the advancement and dissemination of research results that support high-level learning, teaching and research in the fields of Engineering and Technology. We bring together Scientists, Academician, Field Engineers, Scholars and Students of related fields of Engineering and Technology.
This document discusses improving the usability of GIS (geographic information system) services by applying semantic ontology. It aims to develop a more user-friendly system that can understand user questions in natural language and provide accurate answers. The key aspects discussed are preprocessing user questions, using an ontology tool like Protégé to map questions to concepts and relationships in an OWL file, and then extracting answers from GIS data and services. The goal is to allow users to easily access and understand geographic information without extensive technical knowledge of GIS systems.
Matching GPS Traces with Personal
Schedules,” Proc. First ACM Int’l Workshop
Personalized Context Modeling and
Management for UbiComp Applications
(PCM), 2009.
[8] X. Li, Y.-Y. Chen, T. Suel, and A.
Markowetz, “Efficient Query Processing in
Geographic Web Search,” Proc. Int’l ACM
SIGIR Conf. Research and Development in
Information Retrieval (SIGIR), 2006.
[9] B.J. Jansen, A. Spink, and T. Saracevic,
“Real Life, Real Users, and Real Needs: A
Study and Analysis of User Queries
In context-aware trust evaluation, using ontology tree is a popular approach to represent the relation
between contexts. Usually, similarity between two contexts is computed using these trees. Therefore, the
performance of trust evaluation highly depends on the quality of ontology trees. Fairness or granularity
consistency is one of the major limitations affecting the quality of ontology tree. This limitation refers to
inequality of semantic similarity in the most ontology trees. In other words, semantic similarity of every two
adjacent nodes is unequal in these trees. It deteriorates the performance of contexts similarity computation.
We overcome this limitation by weighting tree edges based on their semantic similarity. Weight of each
edge is computed using Normalized Similarity Score (NSS) method. This method is based on frequencies of
concepts (words) co-occurrences in the pages indexed by search engines. Our experiments represent the
better performance of the proposed approach in comparison with established trust evaluation approaches.
The suggested approach can enhance efficiency of any solution which models semantic relations by
ontology tree.
A Novel Method for Creating and Recognizing User Behavior ProfilesIJMER
International Journal of Modern Engineering Research (IJMER) is Peer reviewed, online Journal. It serves as an international archival forum of scholarly research related to engineering and science education.
This document summarizes various techniques that have been proposed for providing security during online exams to prevent malpractice. It discusses authentication techniques such as unimodal, multimodal, and data visualization methods. The paper specifically proposes a method called Enhanced Security using Data Visualization (ESDV) that uses data visualization techniques to constantly monitor examinees during online exams in order to enhance security and prevent malpractice.
Text content dependent writer identificationeSAT Journals
Abstract
Text content based personal Identification system is vital in resolving problem of identifying unknown document’s writer using a
set of handwritten samples from alleged known writers. Text written on paper document is usually captured as image by scanner
or camera for computer processing. The most challenging problem encounter in text image processing is extraction of robust
feature vector from a set of inconstant handwritten text images obtained from the same writer at different time. In this work new
feature extraction method is engaged to produce active text features for developing an effective personal identification system.
The feature formed feature vector which is fed as input data into classification algorithm based on Support Vector Machine
(SVM). Experiment was conducted to identify writers of query handwritten texts. Result show satisfactory performance of the
proposed system, it was able to identify writers of query handwritten texts.
Keywords: Handwritten Text, Feature Vector, Identification and Support Vector Machine.
Development of Intelligent Multi-agents System for Collaborative e-learning S...journalBEEI
The aim of this paper is the introduction of intelligence in e-learning collaborative system. In such system, the tutor plays an important role to facilitate collaboration between users and boost less active among them to get more involved for good pedagogical action. However, the problem lies in the large number of platform users, and the tutor tasks become difficult if not impossible. Therefore, we used fuzzy logic technics in order to solve this problem by automating tutor tasks and creating an artificial agent. This agent is elaborate in basing on the learners activities, especially the assessment of their collaborative behaviors. After the implementation of intelligent collaborative system by using Moodle platform, we have tested it. The reader will discover our approach and relevant results.
Digital image hiding algorithm for secret communicationeSAT Journals
Abstract
It is important to keep the image secret with the growing popularity of digital media’s through world wide web to avoid geometric attacking and stealing of images. A new digital image hiding algorithm that provides the security of hidden image, Imperceptibility , Robustness, Anti attacking capability is proposed. To achieve this, two different algorithms are used in frequency domain. The first algorithm is Discrete wavelet transform(DWT) and the second one is Singular Value Decomposition(SVD). Wavelet coefficients of secret and carrier image is found using DWT. In this the images are divided into four frequency part called LL, LH, HL, HH. Low frequency component possess main information. So the low frequency part alone taken for the process of SVD to increase imperceptibility. The processed secret image is embedded into the transformed carrier image. From this implementation of new digital image hiding algorithm, image can be stored and transmitted without any loss in that image even after getting affected by external factors such as rotation and noise. The parameter used to test the robustness is peak signal to ratio (PSNR). The experimental results shows that the proposed method is more robust against different kinds of attacks.
Keywords: Image hiding, DWT, SVD, Frequency domain, Attacks.
The document describes a study that investigates using gestures as a form of authentication on smartwatches. The researchers collected accelerometer data from smartwatches as users performed different gestures. They extracted time and frequency domain features from the data and used k-nearest neighbors and random forest classifiers to distinguish between gestures and identify individual users performing the same gesture. Through 5-fold cross validation experiments, they found it was possible to accurately classify gestures and identify users with error rates comparable or better than previous gait-based authentication studies. This suggests gesture-based authentication on smartwatches is a viable solution.
IRJET- Review on the Simple Text Messages ClassificationIRJET Journal
This document reviews a proposed mobile application called MojoText - Text Messenger that aims to add extra functionality to simple text messaging. The key features of the proposed application include categorizing messages by personal, social, transactional or user-defined categories with color codes, searching messages by customized date, scheduling text delivery, hiding personal messages, and reminders. The document discusses the system architecture and algorithms that could be used for message categorization, including stopword removal, pattern matching, and decision trees. It concludes that the proposed application could provide convenience by allowing users to classify and organize text messages to prevent important messages from getting lost.
Profile Analysis of Users in Data Analytics DomainDrjabez
Data Analytics and Data Science is in the fast forward
mode recently. We see a lot of companies hiring people for data
analysis and data science, especially in India. Also, many
recruiting firms use stackoverflow to fish their potential
candidates. The industry has also started to recruit people based
on the shapes of expertise. Expertise of a personal is
metaphorically outlined by shapes of letters like I, T, M and
hyphen betting on her experiencein a section (depth) and
therefore the variety of areas of interest (width).This proposal
builds upon the work of mining shapes of user expertise in a
typical online social Question and Answer (Q&A) community
where expert users often answer questions posed by other
users.We have dealt with the temporal analysis of the expertise
among the Q&A community users in terms how the user/ expert
have evolved over time.
Keywords— Shapes of expertise, Graph communities, Expertise
evolution, Q&A community
Advanced Question Paper Generator Implemented using Fuzzy LogicIRJET Journal
This document describes an advanced question paper generator system implemented using fuzzy logic. The system allows professors to generate question papers automatically by selecting the difficulty level and pattern. It uses fuzzy logic to determine the difficulty level of questions based on their analytical and descriptive quotients stored in the database. The system provides authentication and authorization for professors and admin. Professors can add, update and delete questions for the subjects allocated to them. The admin can manage user accounts and subject allocations. The generated question papers are in PDF format for ease of use and security.
Scalable recommendation with social contextual informationeSAT Journals
Abstract Recommender systems are used to achieve effective and useful results in a social networks. The social recommendation will provide a social network structure but it is challenging to fuse social contextual factors which are derived from user’s motivation of social behaviors into social recommendation. Here, we introduce two contextual factors in recommender systems which are used to adopt a useful results namely a) individual preference and b) interpersonal influence. Individual preference analyze the social interests of an item content with user’s interest and adopt only users recommended results. Interpersonal influence is analyzing user-user interaction and their specific social relations. Beyond this, we propose a novel probabilistic matrix factorization method to fuse them in a latent space. The scalable algorithm provides a useful results by analyzing the ranking probability of each user social contextual information and also incrementally process the contextual data in large datasets. Keywords: social recommendation, individual preference, interpersonal influence, matrix factorization
An automatic filtering task in osn using content based approachIAEME Publication
This document summarizes an academic paper on developing an automatic filtering system for online social networks using content-based approaches. It describes a three-tier architecture for the filtering system, with the lowest layer managing social networks, a middle layer performing message categorization and blacklisting, and a top layer providing a graphical user interface. The system works by intercepting messages, extracting metadata using machine learning classification, applying filtering and blacklisting rules, and publishing approved messages while filtering unwanted ones based on content and creator. It aims to allow users more control over messages on their walls by blocking offensive, political, or other undesirable content in an automatic way.
International Journal of Engineering Research and Applications (IJERA) is an open access online peer reviewed international journal that publishes research and review articles in the fields of Computer Science, Neural Networks, Electrical Engineering, Software Engineering, Information Technology, Mechanical Engineering, Chemical Engineering, Plastic Engineering, Food Technology, Textile Engineering, Nano Technology & science, Power Electronics, Electronics & Communication Engineering, Computational mathematics, Image processing, Civil Engineering, Structural Engineering, Environmental Engineering, VLSI Testing & Low Power VLSI Design etc.
This document discusses a system for detecting suspicious emails using machine learning algorithms. It presents a model that filters emails containing images and PDFs to improve performance over existing text-based spam filtering systems. The model uses data collection, preprocessing, machine learning classification algorithms like Naive Bayes, Support Vector Machines, and Decision Trees. It aims to achieve acceptable recall and precision values. The document also reviews related work on email spam detection using machine learning and discusses the future scope of applying the algorithm to embedded images/PDFs and larger datasets.
Useful and Effectiveness of Multi Agent Systemijtsrd
A multi agent system MAS or self cooperating system is a computerized system organized of multiple interacting intelligent agents. The problems that are difficult to solve for an individual agent or a monolithic system can be solved by multi agent system easily. MAS is a loosely coupled of software agents' network that interact to solve problems that are beyond the individual capacities or knowledge of each software agent. Distributed systems with a group of intelligent agents that communicate with other agents to achieve goals are directed by their masters. MAS group aims to develop new theory and computational models of higher order social cognition between people and computer systems by producing their abilities to reason about one another automatically. More specifically, multi agent control systems are fundamental parts of a wide range of safety critical engineering systems, and are commonly found in aerospace, traffic control, chemical process, power generation and distribution, flexible manufacturing, chemical processes, power generation and distribution, flexible manufacturing, robotic system design and self assembly structures. Moe Myint Myint ""Useful and Effectiveness of Multi-Agent System"" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-3 | Issue-3 , April 2019, URL: https://www.ijtsrd.com/papers/ijtsrd23036.pdf
Paper URL: https://www.ijtsrd.com/computer-science/artificial-intelligence/23036/useful-and-effectiveness-of-multi-agent-system/moe-myint-myint
This document describes a web application that can automatically generate Entity Relationship (ER) diagrams. It takes entity, attribute, and relationship details as input from the user and outputs an ER diagram. The proposed system has a 3-module architecture: 1) it accepts input from the user, 2) generates the ER diagram automatically based on the input, and 3) stores the output diagram. Experimental results demonstrate how diagrams are generated at different levels of complexity based on filtering of the input details. The automated generation of ER diagrams using this web application makes the process easier for users compared to traditional manual tools.
Learning strategy with groups on page based students' profilesaciijournal
Most of students desire to know about their knowledge level to perfect their exams. In learning environment the fields of study overwhelm on page with collaboration or cooperation. Students can do their exercises either individually or collaboratively with their peers. The system provides the guidelines for students' learning system about interest fields as Java in this system. Especially the system feedbacks information about exam to know their grades without teachers. The participants who answered the exam can discuss with each others because of sharing e mail and list of them.
11.hybrid ga svm for efficient feature selection in e-mail classificationAlexander Decker
The document summarizes a study that develops a hybrid genetic algorithm-support vector machine (GA-SVM) technique for feature selection in email classification. The technique uses a genetic algorithm to optimize the feature selection and parameters of an SVM classifier. The goal is to improve the SVM's classification accuracy and reduce computation time for large email datasets. The study tests the hybrid GA-SVM approach on a spam email dataset. The results show improvements in classification accuracy and computation time over using SVM alone.
Hybrid ga svm for efficient feature selection in e-mail classificationAlexander Decker
1. The document discusses using a hybrid genetic algorithm-support vector machine (GA-SVM) approach for feature selection in email classification to improve SVM performance.
2. SVM has been shown to be inefficient and consume a lot of computational resources when classifying large email datasets with many features.
3. The hybrid GA-SVM approach uses a genetic algorithm to optimize feature selection for SVM in order to improve classification accuracy and reduce computation time for email spam detection.
Reverse Nearest Neighbors in Unsupervised Distance-Based Outlier Detection1crore projects
IEEE PROJECTS 2015
1 crore projects is a leading Guide for ieee Projects and real time projects Works Provider.
It has been provided Lot of Guidance for Thousands of Students & made them more beneficial in all Technology Training.
Dot Net
DOTNET Project Domain list 2015
1. IEEE based on datamining and knowledge engineering
2. IEEE based on mobile computing
3. IEEE based on networking
4. IEEE based on Image processing
5. IEEE based on Multimedia
6. IEEE based on Network security
7. IEEE based on parallel and distributed systems
Java Project Domain list 2015
1. IEEE based on datamining and knowledge engineering
2. IEEE based on mobile computing
3. IEEE based on networking
4. IEEE based on Image processing
5. IEEE based on Multimedia
6. IEEE based on Network security
7. IEEE based on parallel and distributed systems
ECE IEEE Projects 2015
1. Matlab project
2. Ns2 project
3. Embedded project
4. Robotics project
Eligibility
Final Year students of
1. BSc (C.S)
2. BCA/B.E(C.S)
3. B.Tech IT
4. BE (C.S)
5. MSc (C.S)
6. MSc (IT)
7. MCA
8. MS (IT)
9. ME(ALL)
10. BE(ECE)(EEE)(E&I)
TECHNOLOGY USED AND FOR TRAINING IN
1. DOT NET
2. C sharp
3. ASP
4. VB
5. SQL SERVER
6. JAVA
7. J2EE
8. STRINGS
9. ORACLE
10. VB dotNET
11. EMBEDDED
12. MAT LAB
13. LAB VIEW
14. Multi Sim
CONTACT US
1 CRORE PROJECTS
Door No: 214/215,2nd Floor,
No. 172, Raahat Plaza, (Shopping Mall) ,Arcot Road, Vadapalani, Chennai,
Tamin Nadu, INDIA - 600 026
Email id: 1croreprojects@gmail.com
website:1croreprojects.com
Phone : +91 97518 00789 / +91 72999 51536
K-means and bayesian networks to determine building damage levelsTELKOMNIKA JOURNAL
Many troubles in life require decision-making with convoluted processes because they are caused by uncertainty about the process of relationships that appear in the system. This problem leads to the creation of a model called the Bayesian Network. Bayesian Network is a Bayesian supported development supported by computing advancements. The Bayesian network has also been developed in various fields. At this time, information can implement Bayesian Networks in determining the extent of damage to buildings using individual building data. In practice, there is mixed data which is a combination of continuous and discrete variables. Therefore, to simplify the study it is assumed that all variables are discrete in order to solve practical problems in the implementation of theory. Discretization method used is the K-Means clustering because the percentage of validity obtained by this method is greater than the binning method.
Hybrid-e-greedy for mobile context-aware recommender systemBouneffouf Djallel
This document proposes a hybrid-ε-greedy algorithm for mobile context-aware recommender systems that combines bandit algorithms and case-based reasoning. It summarizes related works that aim to follow the evolution of user interests or manage the user's context, but not both. The proposed approach uses case-based reasoning to consider the user's context in the bandit algorithm's exploration-exploitation strategy. It also uses content-based filtering with the ε-greedy algorithm.
Following the user’s interests in mobile context aware recommender systemsBouneffouf Djallel
The wide development of mobile applications provides a considerable amount of data of all types (images, texts, sounds, videos, etc.). In this sense, Mobile Context-aware Recommender Systems (MCRS) suggest the user suitable information depending on her/his situation and interests. Two key questions have to be considered 1) how to recommend the user information that follows his/her interests evolution? 2) how to model the user’s situation and its related interests? To the best of our knowledge, no existing work proposing a MCRS tries to answer both questions as we do. This paper describes an ongoing work on the implementation of a MCRS based on the hybrid-ε-greedy algorithm we propose, which combines the standard ε-greedy algorithm and both content-based filtering and case-based reasoning techniques.
Exploration exploitation trade off in mobile context-aware recommender systemsBouneffouf Djallel
Most existing approaches in Context-Aware Recommender Systems (CRS) focus on recommending relevant items to users taking into account contextual information, such as time, loca-tion, or social aspects. However, none of them have considered the problem of user’s content dynamicity. This problem has been studied in the reinforcement learning community, but without paying much attention to the contextual aspect of the recommendation. We introduce in this paper an algorithm that tackles the user’s content dynamicity by modeling the CRS as a contextual bandit algorithm. It is based on dynamic explora-tion/exploitation and it includes a metric to decide which user’s situation is the most relevant to exploration or exploitation. Within a deliberately designed offline simulation framework, we conduct extensive evaluations with real online event log data. The experimental results and detailed analysis demon-strate that our algorithm outperforms surveyed algorithms.
Conceptual Design of Fuzzy Rule Based Context Aware Meeting Room SystemEditor IJMTER
Due to the exponential growth of wireless network based miniaturized device and
sensors, the dream of context aware ubiquitous computing world is becoming realistic. In this
ubiquitous world of context aware applications the users can get the information and share the
information elsewhere instantaneously. Context aware meeting room is one of the interesting context
aware systems where in the meeting of a given set of users will be organized as per the situation of
users. In this paper we present the conceptual design and development of service recommendation
system for prototypical context aware meeting room using Fuzzy Rules .The proposed
recommendation system for context aware meeting room recommends the services by considering
the users contextual parameters like role, priority and environmental conditions. The fuzzy rule is
constructed using history database and knowledge base of the meeting.
Development of Intelligent Multi-agents System for Collaborative e-learning S...journalBEEI
The aim of this paper is the introduction of intelligence in e-learning collaborative system. In such system, the tutor plays an important role to facilitate collaboration between users and boost less active among them to get more involved for good pedagogical action. However, the problem lies in the large number of platform users, and the tutor tasks become difficult if not impossible. Therefore, we used fuzzy logic technics in order to solve this problem by automating tutor tasks and creating an artificial agent. This agent is elaborate in basing on the learners activities, especially the assessment of their collaborative behaviors. After the implementation of intelligent collaborative system by using Moodle platform, we have tested it. The reader will discover our approach and relevant results.
Digital image hiding algorithm for secret communicationeSAT Journals
Abstract
It is important to keep the image secret with the growing popularity of digital media’s through world wide web to avoid geometric attacking and stealing of images. A new digital image hiding algorithm that provides the security of hidden image, Imperceptibility , Robustness, Anti attacking capability is proposed. To achieve this, two different algorithms are used in frequency domain. The first algorithm is Discrete wavelet transform(DWT) and the second one is Singular Value Decomposition(SVD). Wavelet coefficients of secret and carrier image is found using DWT. In this the images are divided into four frequency part called LL, LH, HL, HH. Low frequency component possess main information. So the low frequency part alone taken for the process of SVD to increase imperceptibility. The processed secret image is embedded into the transformed carrier image. From this implementation of new digital image hiding algorithm, image can be stored and transmitted without any loss in that image even after getting affected by external factors such as rotation and noise. The parameter used to test the robustness is peak signal to ratio (PSNR). The experimental results shows that the proposed method is more robust against different kinds of attacks.
Keywords: Image hiding, DWT, SVD, Frequency domain, Attacks.
The document describes a study that investigates using gestures as a form of authentication on smartwatches. The researchers collected accelerometer data from smartwatches as users performed different gestures. They extracted time and frequency domain features from the data and used k-nearest neighbors and random forest classifiers to distinguish between gestures and identify individual users performing the same gesture. Through 5-fold cross validation experiments, they found it was possible to accurately classify gestures and identify users with error rates comparable or better than previous gait-based authentication studies. This suggests gesture-based authentication on smartwatches is a viable solution.
IRJET- Review on the Simple Text Messages ClassificationIRJET Journal
This document reviews a proposed mobile application called MojoText - Text Messenger that aims to add extra functionality to simple text messaging. The key features of the proposed application include categorizing messages by personal, social, transactional or user-defined categories with color codes, searching messages by customized date, scheduling text delivery, hiding personal messages, and reminders. The document discusses the system architecture and algorithms that could be used for message categorization, including stopword removal, pattern matching, and decision trees. It concludes that the proposed application could provide convenience by allowing users to classify and organize text messages to prevent important messages from getting lost.
Profile Analysis of Users in Data Analytics DomainDrjabez
Data Analytics and Data Science is in the fast forward
mode recently. We see a lot of companies hiring people for data
analysis and data science, especially in India. Also, many
recruiting firms use stackoverflow to fish their potential
candidates. The industry has also started to recruit people based
on the shapes of expertise. Expertise of a personal is
metaphorically outlined by shapes of letters like I, T, M and
hyphen betting on her experiencein a section (depth) and
therefore the variety of areas of interest (width).This proposal
builds upon the work of mining shapes of user expertise in a
typical online social Question and Answer (Q&A) community
where expert users often answer questions posed by other
users.We have dealt with the temporal analysis of the expertise
among the Q&A community users in terms how the user/ expert
have evolved over time.
Keywords— Shapes of expertise, Graph communities, Expertise
evolution, Q&A community
Advanced Question Paper Generator Implemented using Fuzzy LogicIRJET Journal
This document describes an advanced question paper generator system implemented using fuzzy logic. The system allows professors to generate question papers automatically by selecting the difficulty level and pattern. It uses fuzzy logic to determine the difficulty level of questions based on their analytical and descriptive quotients stored in the database. The system provides authentication and authorization for professors and admin. Professors can add, update and delete questions for the subjects allocated to them. The admin can manage user accounts and subject allocations. The generated question papers are in PDF format for ease of use and security.
Scalable recommendation with social contextual informationeSAT Journals
Abstract Recommender systems are used to achieve effective and useful results in a social networks. The social recommendation will provide a social network structure but it is challenging to fuse social contextual factors which are derived from user’s motivation of social behaviors into social recommendation. Here, we introduce two contextual factors in recommender systems which are used to adopt a useful results namely a) individual preference and b) interpersonal influence. Individual preference analyze the social interests of an item content with user’s interest and adopt only users recommended results. Interpersonal influence is analyzing user-user interaction and their specific social relations. Beyond this, we propose a novel probabilistic matrix factorization method to fuse them in a latent space. The scalable algorithm provides a useful results by analyzing the ranking probability of each user social contextual information and also incrementally process the contextual data in large datasets. Keywords: social recommendation, individual preference, interpersonal influence, matrix factorization
An automatic filtering task in osn using content based approachIAEME Publication
This document summarizes an academic paper on developing an automatic filtering system for online social networks using content-based approaches. It describes a three-tier architecture for the filtering system, with the lowest layer managing social networks, a middle layer performing message categorization and blacklisting, and a top layer providing a graphical user interface. The system works by intercepting messages, extracting metadata using machine learning classification, applying filtering and blacklisting rules, and publishing approved messages while filtering unwanted ones based on content and creator. It aims to allow users more control over messages on their walls by blocking offensive, political, or other undesirable content in an automatic way.
International Journal of Engineering Research and Applications (IJERA) is an open access online peer reviewed international journal that publishes research and review articles in the fields of Computer Science, Neural Networks, Electrical Engineering, Software Engineering, Information Technology, Mechanical Engineering, Chemical Engineering, Plastic Engineering, Food Technology, Textile Engineering, Nano Technology & science, Power Electronics, Electronics & Communication Engineering, Computational mathematics, Image processing, Civil Engineering, Structural Engineering, Environmental Engineering, VLSI Testing & Low Power VLSI Design etc.
This document discusses a system for detecting suspicious emails using machine learning algorithms. It presents a model that filters emails containing images and PDFs to improve performance over existing text-based spam filtering systems. The model uses data collection, preprocessing, machine learning classification algorithms like Naive Bayes, Support Vector Machines, and Decision Trees. It aims to achieve acceptable recall and precision values. The document also reviews related work on email spam detection using machine learning and discusses the future scope of applying the algorithm to embedded images/PDFs and larger datasets.
Useful and Effectiveness of Multi Agent Systemijtsrd
A multi agent system MAS or self cooperating system is a computerized system organized of multiple interacting intelligent agents. The problems that are difficult to solve for an individual agent or a monolithic system can be solved by multi agent system easily. MAS is a loosely coupled of software agents' network that interact to solve problems that are beyond the individual capacities or knowledge of each software agent. Distributed systems with a group of intelligent agents that communicate with other agents to achieve goals are directed by their masters. MAS group aims to develop new theory and computational models of higher order social cognition between people and computer systems by producing their abilities to reason about one another automatically. More specifically, multi agent control systems are fundamental parts of a wide range of safety critical engineering systems, and are commonly found in aerospace, traffic control, chemical process, power generation and distribution, flexible manufacturing, chemical processes, power generation and distribution, flexible manufacturing, robotic system design and self assembly structures. Moe Myint Myint ""Useful and Effectiveness of Multi-Agent System"" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-3 | Issue-3 , April 2019, URL: https://www.ijtsrd.com/papers/ijtsrd23036.pdf
Paper URL: https://www.ijtsrd.com/computer-science/artificial-intelligence/23036/useful-and-effectiveness-of-multi-agent-system/moe-myint-myint
This document describes a web application that can automatically generate Entity Relationship (ER) diagrams. It takes entity, attribute, and relationship details as input from the user and outputs an ER diagram. The proposed system has a 3-module architecture: 1) it accepts input from the user, 2) generates the ER diagram automatically based on the input, and 3) stores the output diagram. Experimental results demonstrate how diagrams are generated at different levels of complexity based on filtering of the input details. The automated generation of ER diagrams using this web application makes the process easier for users compared to traditional manual tools.
Learning strategy with groups on page based students' profilesaciijournal
Most of students desire to know about their knowledge level to perfect their exams. In learning environment the fields of study overwhelm on page with collaboration or cooperation. Students can do their exercises either individually or collaboratively with their peers. The system provides the guidelines for students' learning system about interest fields as Java in this system. Especially the system feedbacks information about exam to know their grades without teachers. The participants who answered the exam can discuss with each others because of sharing e mail and list of them.
11.hybrid ga svm for efficient feature selection in e-mail classificationAlexander Decker
The document summarizes a study that develops a hybrid genetic algorithm-support vector machine (GA-SVM) technique for feature selection in email classification. The technique uses a genetic algorithm to optimize the feature selection and parameters of an SVM classifier. The goal is to improve the SVM's classification accuracy and reduce computation time for large email datasets. The study tests the hybrid GA-SVM approach on a spam email dataset. The results show improvements in classification accuracy and computation time over using SVM alone.
Hybrid ga svm for efficient feature selection in e-mail classificationAlexander Decker
1. The document discusses using a hybrid genetic algorithm-support vector machine (GA-SVM) approach for feature selection in email classification to improve SVM performance.
2. SVM has been shown to be inefficient and consume a lot of computational resources when classifying large email datasets with many features.
3. The hybrid GA-SVM approach uses a genetic algorithm to optimize feature selection for SVM in order to improve classification accuracy and reduce computation time for email spam detection.
Reverse Nearest Neighbors in Unsupervised Distance-Based Outlier Detection1crore projects
IEEE PROJECTS 2015
1 crore projects is a leading Guide for ieee Projects and real time projects Works Provider.
It has been provided Lot of Guidance for Thousands of Students & made them more beneficial in all Technology Training.
Dot Net
DOTNET Project Domain list 2015
1. IEEE based on datamining and knowledge engineering
2. IEEE based on mobile computing
3. IEEE based on networking
4. IEEE based on Image processing
5. IEEE based on Multimedia
6. IEEE based on Network security
7. IEEE based on parallel and distributed systems
Java Project Domain list 2015
1. IEEE based on datamining and knowledge engineering
2. IEEE based on mobile computing
3. IEEE based on networking
4. IEEE based on Image processing
5. IEEE based on Multimedia
6. IEEE based on Network security
7. IEEE based on parallel and distributed systems
ECE IEEE Projects 2015
1. Matlab project
2. Ns2 project
3. Embedded project
4. Robotics project
Eligibility
Final Year students of
1. BSc (C.S)
2. BCA/B.E(C.S)
3. B.Tech IT
4. BE (C.S)
5. MSc (C.S)
6. MSc (IT)
7. MCA
8. MS (IT)
9. ME(ALL)
10. BE(ECE)(EEE)(E&I)
TECHNOLOGY USED AND FOR TRAINING IN
1. DOT NET
2. C sharp
3. ASP
4. VB
5. SQL SERVER
6. JAVA
7. J2EE
8. STRINGS
9. ORACLE
10. VB dotNET
11. EMBEDDED
12. MAT LAB
13. LAB VIEW
14. Multi Sim
CONTACT US
1 CRORE PROJECTS
Door No: 214/215,2nd Floor,
No. 172, Raahat Plaza, (Shopping Mall) ,Arcot Road, Vadapalani, Chennai,
Tamin Nadu, INDIA - 600 026
Email id: 1croreprojects@gmail.com
website:1croreprojects.com
Phone : +91 97518 00789 / +91 72999 51536
K-means and bayesian networks to determine building damage levelsTELKOMNIKA JOURNAL
Many troubles in life require decision-making with convoluted processes because they are caused by uncertainty about the process of relationships that appear in the system. This problem leads to the creation of a model called the Bayesian Network. Bayesian Network is a Bayesian supported development supported by computing advancements. The Bayesian network has also been developed in various fields. At this time, information can implement Bayesian Networks in determining the extent of damage to buildings using individual building data. In practice, there is mixed data which is a combination of continuous and discrete variables. Therefore, to simplify the study it is assumed that all variables are discrete in order to solve practical problems in the implementation of theory. Discretization method used is the K-Means clustering because the percentage of validity obtained by this method is greater than the binning method.
Hybrid-e-greedy for mobile context-aware recommender systemBouneffouf Djallel
This document proposes a hybrid-ε-greedy algorithm for mobile context-aware recommender systems that combines bandit algorithms and case-based reasoning. It summarizes related works that aim to follow the evolution of user interests or manage the user's context, but not both. The proposed approach uses case-based reasoning to consider the user's context in the bandit algorithm's exploration-exploitation strategy. It also uses content-based filtering with the ε-greedy algorithm.
Following the user’s interests in mobile context aware recommender systemsBouneffouf Djallel
The wide development of mobile applications provides a considerable amount of data of all types (images, texts, sounds, videos, etc.). In this sense, Mobile Context-aware Recommender Systems (MCRS) suggest the user suitable information depending on her/his situation and interests. Two key questions have to be considered 1) how to recommend the user information that follows his/her interests evolution? 2) how to model the user’s situation and its related interests? To the best of our knowledge, no existing work proposing a MCRS tries to answer both questions as we do. This paper describes an ongoing work on the implementation of a MCRS based on the hybrid-ε-greedy algorithm we propose, which combines the standard ε-greedy algorithm and both content-based filtering and case-based reasoning techniques.
Exploration exploitation trade off in mobile context-aware recommender systemsBouneffouf Djallel
Most existing approaches in Context-Aware Recommender Systems (CRS) focus on recommending relevant items to users taking into account contextual information, such as time, loca-tion, or social aspects. However, none of them have considered the problem of user’s content dynamicity. This problem has been studied in the reinforcement learning community, but without paying much attention to the contextual aspect of the recommendation. We introduce in this paper an algorithm that tackles the user’s content dynamicity by modeling the CRS as a contextual bandit algorithm. It is based on dynamic explora-tion/exploitation and it includes a metric to decide which user’s situation is the most relevant to exploration or exploitation. Within a deliberately designed offline simulation framework, we conduct extensive evaluations with real online event log data. The experimental results and detailed analysis demon-strate that our algorithm outperforms surveyed algorithms.
Conceptual Design of Fuzzy Rule Based Context Aware Meeting Room SystemEditor IJMTER
Due to the exponential growth of wireless network based miniaturized device and
sensors, the dream of context aware ubiquitous computing world is becoming realistic. In this
ubiquitous world of context aware applications the users can get the information and share the
information elsewhere instantaneously. Context aware meeting room is one of the interesting context
aware systems where in the meeting of a given set of users will be organized as per the situation of
users. In this paper we present the conceptual design and development of service recommendation
system for prototypical context aware meeting room using Fuzzy Rules .The proposed
recommendation system for context aware meeting room recommends the services by considering
the users contextual parameters like role, priority and environmental conditions. The fuzzy rule is
constructed using history database and knowledge base of the meeting.
Proactive Intelligent Home System Using Contextual Information and Neural Net...IJERA Editor
Nowadays, cities around the world intend to use information technology to improve the lives of their citizens.
Future smart cities will incorporate digital data and technology to interact differently with their human
inhabitants.
Among the key component of a smart city, we find the smart home component. It is an autonomic environment
that can provide various smart services by considering the user’s context information. Several methods are used
in context-aware system to provide such services. In this paper, we propose an approach to offer the most
relevant services to the user according to any significant change of his context environment. The proposed
approach is based on the use of context history information together with user profiling and machine learning
techniques. Experimentations show that the proposed solution can efficiently provide the most useful services to
the user in an intelligent home environment.
This document summarizes four architectural patterns for context-aware systems: WCAM, Event-Control-Action, Action, and architectural pattern for context-based navigation. It discusses examples, problems addressed, solutions, structures, and benefits of each pattern. The patterns are examined to determine which can best overcome complexity and be more extensible for context-aware systems.
A survey of memory based methods for collaborative filtering based techniquesIAEME Publication
This document summarizes a study that evaluates three collaborative filtering techniques - Euclidean distance, Pearson correlation, and cosine similarity. The study uses a movie rating dataset to calculate similarities between users and generate predictions for unseen movie ratings. The techniques are evaluated by comparing actual ratings to predicted ratings on a test set of 120 movie ratings. The mean absolute error and number of predictions within certain deviation thresholds are used to assess accuracy. The process is repeated three times to arrive at a conclusion on the relative performance of the three similarity measures for collaborative filtering.
DYNAMIC AND REALTIME MODELLING OF UBIQUITOUS INTERACTIONcscpconf
This document discusses modeling real-time interaction between a user and a ubiquitous system using dynamic Petri net models. It proposes using Petri nets to model a user's activity as a set of elementary actions. Elementary actions are modeled as Petri net structures that are then composed together through techniques like sequence, parallelism, etc. to form an overall model of user-system interaction. The models can be dynamically adapted based on changes to the user's context. OWL-S ontology is used to describe the dynamic aspects of the Petri net models, especially real-time composition of models. Simulation results validate the approach of dynamically modeling user-system interaction through mutation of Petri net models.
A survey on context aware system & intelligent Middleware’sIOSR Journals
Abstract: Context aware system or Sentient system is the most profound concept in the ubiquitous computing.
In the cloud system or in distributed computing building a context aware system is difficult task and
programmer should use more generic programming framework. On the basis of layered conceptual design, we
introduce Context aware systems with Context aware middleware’s. On the basis of presented system we will
analyze different approaches of context aware computing. There are many components in the distributed system
and these components should interact with each other because it is the need of many applications. Plenty
Context middleware’s have been made but they are giving partial solutions. In this paper we are giving analysis
of different middleware’s and comprehensive application of it in context caching.
Keywords: Context aware system, Context aware Middleware’s, Context Cache
Sentiment Analysis and Classification of Tweets using Data MiningIRJET Journal
This document summarizes research on using data mining techniques to perform sentiment analysis on tweets. The researchers collected tweets from Twitter and preprocessed the text to make it usable for building sentiment classifiers. They used three classifiers - K-Nearest Neighbor, Naive Bayes, and Decision Tree - and compared the results to determine which provided the best accuracy. Rapid Miner tool was used to preprocess the text, build the classifiers, and analyze the results. The goal was to determine people's sentiments expressed in their tweets and correctly classify them.
This document discusses a product analyst advisor software that uses natural language processing techniques like sentiment analysis to analyze customer reviews and sentiments about products. It extracts reviews from various websites about a product being researched and processes the data to provide useful insights. The insights help users easily select the best available option. The system architecture involves scraping live data from websites, using deep learning algorithms to analyze reviews for sentiments, and displaying product insights. It uses BERT for sentiment analysis and frameworks like Django and ReactJS. Web scraping is used to extract review data for analysis and providing recommendations to users.
Activity Context Modeling in Context-AwareEditor IJCATR
The explosion of mobile devices has fuelled the advancement of pervasive computing to provide personal assistance in this
information-driven world. Pervasive computing takes advantage of context-aware computing to track, use and adapt to contextual
information. The context that has attracted the attention of many researchers is the activity context. There are six major techniques that
are used to model activity context. These techniques are key-value, logic-based, ontology-based, object-oriented, mark-up schemes and
graphical. This paper analyses these techniques in detail by describing how each technique is implemented while reviewing their pros
and cons. The paper ends with a hybrid modeling method that fits heterogeneous environment while considering the entire of modeling
through data acquisition and utilization stages. The modeling stages of activity context are data sensation, data abstraction and
reasoning and planning. The work revealed that mark-up schemes and object-oriented are best applicable at the data sensation stage.
Key-value and object-oriented techniques fairly support data abstraction stage whereas the logic-based and ontology-based techniques
are the ideal techniques for reasoning and planning stage. In a distributed system, mark-up schemes are very useful in data
communication over a network and graphical technique should be used when saving context data into database.
INTELLIGENT SOCIAL NETWORKS MODEL BASED ON SEMANTIC TAG RANKINGdannyijwest
Social Networks has become one of the most popular platforms to allow users to communicate, and share their interests without being at the same geographical location. With the great and rapid growth of Social Media sites such as Facebook, LinkedIn, Twitter…etc. causes huge amount of user-generated content. Thus, the improvement in the information quality and integrity becomes a great challenge to all social media sites, which allows users to get the desired content or be linked to the best link relation using improved search / link technique. So introducing semantics to social networks will widen up the representation of the social networks. In this paper, a new model of social networks based on semantic tag ranking is introduced. This model is based on the concept of multi-agent systems. In this proposed model the representation of social links will be extended by the semantic relationships found in the vocabularies which are known as (tags) in most of social networks.The proposed model for the social media engine is based on enhanced Latent Dirichlet Allocation(E-LDA) as a semantic indexing algorithm, combined with Tag Rank as social network ranking algorithm. The improvements on (E-LDA) phase is done by optimizing (LDA) algorithm using the optimal parameters. Then a filter is introduced to enhance the final indexing output. In ranking phase, using Tag Rank based on the indexing phase has improved the output of the ranking. Simulation results of the proposed model have shown improvements in indexing and ranking output.
INTELLIGENT SOCIAL NETWORKS MODEL BASED ON SEMANTIC TAG RANKINGIJwest
The document presents a new model for intelligent social networks based on semantic tag ranking. It uses a multi-agent system approach with agents performing indexing and ranking. For indexing, it uses an enhanced Latent Dirichlet Allocation (E-LDA) model that optimizes LDA parameters. Tags above a threshold from E-LDA output are ranked using Tag Rank. Simulation results showed improvements in indexing and ranking over conventional methods. The model introduces semantics to social networks to improve search and link recommendation.
INTELLIGENT SOCIAL NETWORKS MODEL BASED ON SEMANTIC TAG RANKINGdannyijwest
Social Networks has become one of the most popular platforms to allow users to communicate, and share
their interests without being at the same geographical location. With the great and rapid growth of Social
Media sites such as Facebook, LinkedIn, Twitter...etc. causes huge amount of user-generated content.
Thus, the improvement in the information quality and integrity becomes a great challenge to all social
media sites, which allows users to get the desired content or be linked to the best link relation using
improved search / link technique. So introducing semantics to social networks will widen up the
representation of the social networks.
A Survey of Building Robust Business Models in Pervasive ComputingOsama M. Khaled
Pervasive computing is one of the most challenging and difficult computing domains nowadays. It includes many architectural challenges like context awareness, adaptability, mobility, availability, and scalability. There are currently few approaches which provide methodologies to build suitable architectural models that are more suited to the nature of the pervasive domain. This area still needs a lot of enhancements in order to let the software business analyst (BA) cognitively handle pervasive applications by using suitable tasks and tools. Accordingly, any proposed research topic that would attempt to define a development methodology can greatly help BAs in modeling pervasive applications with high efficiency. In this survey paper we address some of the most significant and current software engineering practices that are proving to be most effective in building pervasive systems.
For citation:
Osama M. Khaled and Hoda M. Hosny. A Survey of Building Robust Business Models in Pervasive Computing. An accepted paper in the 2014 World Congress in Computer Science Computer Engineering and Applied Computing
IRJET- Analysis of Music Recommendation System using Machine Learning Alg...IRJET Journal
This document analyzes different machine learning algorithms that can be used to build a music recommendation system. It first discusses how machine learning and data mining are used to extract patterns from large music datasets. It then analyzes different classification, clustering, and association algorithms that are suitable for a music recommendation system. Specifically, it applies two algorithms (Random Forest and XGBClassifier) to a music dataset and compares their performance at different training/test data splits. It finds that Random Forest achieved the highest accuracy of 75% when the split was 75% training and 25% testing data. In conclusion, ensemble techniques like Random Forest can improve the accuracy of music recommendation over single algorithms.
Recommendation system based on association rules applied to consistent behavi...IAEME Publication
This document summarizes a research paper that proposes a recommendation system that takes into account consistency in user behavior over time. It creates similarity networks from user movie sequences in two time periods. Communities of similar users are identified, and recommendations are made within each community using association rules. The system is evaluated on a public dataset and shown to have marginal but consistent improvements over methods that do not consider consistency over time. Precision, recall, and F-measure are used to evaluate recommendation accuracy.
IRJET- Deep Neural Network based Mechanism to Compute Depression in Socia...IRJET Journal
The document describes a proposed system to analyze social media posts using deep neural networks to detect signs of depression. It involves collecting social media posts from users over a period of 90 days. A 3-layer deep neural network would analyze the posts to identify emotions and habits. Regression analysis of the neural network outputs over time would determine a "depression quotient" score for each user, indicating their risk of depression. The system aims to provide automated advice and prognosis to help depressed users.
Running Head CONTEXT IN MOBILE COMPUTING1CONTEXT IN MOBILE C.docxtodd271
Running Head: CONTEXT IN MOBILE COMPUTING 1
CONTEXT IN MOBILE COMPUTING 5
Context in Mobile Computing
Student’s Name
Institutional Affiliation
Context in Mobile Computing
In recent decades, there have been rapid advances in mobile computing, such as context awareness, integrated sensor technologies and a wide range of wired and wireless practices. Most of the modern mobile computing systems can use context to provide appropriate information and services to the user, where relevance depends on the user's task (Zheng et al., 2016). The purpose of having mobile computing systems that are context-aware is to offer the various services at a reasonable development cost and with simple reconfiguration. That being said, it is important to discuss context awareness in mobile computing. This paper will discuss context as it applies to mobile computing and the various ways in which context has been used. Besides, the paper will describe sensor fusion as it applies to context and suggests new ways of using context.
Context as it applies to Mobile Computing
The concept of context has been explored by a number of researchers. Musumba and Nyongesa (2013) argue that context encompasses location, characteristics of neighboring users or objects and the consequent changes. Talipov et al. (2015) refer to context as location, environment attributes, time and the identities of neighboring users. According to Riboni (2015), context involves the user's feelings, concentration, location, date and time, and the objects in the user's environment. Based on these definitions, it is notable that the most important aspects of context are user location, the user's environment, and the objects near the user. Additionally, it can be said that context is subject to the constantly shifting execution environment. Even though the notion of context comprises the understandings of a scenario, much of the effort within the mobile computing community takes a bottom-up methodology to context.
In mobile computing, context involves the understanding of the physical environment and how the implicit input influences the behavior of an application. It encompasses three forms of the environment – computing environment, user environment and the physical environment (Vinh & Suzuki, 2013). Through the concept of context, these environments are able to interact constantly. The information in the computing and physical environments of mobile devices generates a context for interaction between users and devices. Since the current mobile devices process a wide range of data, context help in controlling the ways users interact with the ubiquitous environment based on their repetitive tasks (Zheng et al., 2016). For instance, a context-aware mobile system can detect that a user never uses his or her phone while at work, and hence all the calls or messages are directed to the user's voicemail when they are working.
Use of Context
The purpose of context-awareness is to determine .
Similar to MODELING THE ADAPTION RULE IN CONTEXTAWARE SYSTEMS (20)
UR BHatti Academy dedicated to providing the finest IT courses training in the world. Under the guidance of experienced trainer Usman Rasheed Bhatti, we have established ourselves as a professional online training firm offering unparalleled courses in Pakistan. Our academy is a trailblazer in Dijkot, being the first institute to officially provide training to all students at their preferred schedules, led by real-world industry professionals and Google certified staff.
The Impact of Work Stress and Digital Literacy on Employee Performance at PT ...AJHSSR Journal
ABSTRACT :This research aims to analyze the correlation between employee work stress and digital literacy
with employee performance at PT Telkom Akses Area Cirebon, both concurrently and partially. Employing a
quantitative approach, the study's objectives are descriptive and causal, adopting a positivist paradigm with a
deductive approach to theory development and a survey research strategy. Findings reveal that work stress
negatively and significantly impacts employee performance, while digital literacy positively and significantly
affects it. Simultaneously, work stress and digital literacy have a positive and significant influence on employee
performance. It is anticipated that company management will devise workload management strategies to
alleviate work stress and assess the implementation of more efficient digital technology to enhance employee
performance.
KEYWORDS -digital literacy, employee performance,job stress, multiple regression analysis, workload
management
Factors affecting undergraduate students’ motivation at a university in Tra VinhAJHSSR Journal
ABSTRACT: Motivation plays an important role in foreign language learning process. This study aimed to
investigate student’s motivation patterns towards English language learning at a University in Tra Vinh, and factors
affecting their motivation change toward English language learning of non-English-major students in the semester.
The researcher used semi-structured interview at the first phase of choosing the participants and writing reflection
through the instrument called “My English Learning Motivation History” adapted from Sawyer (2007) to collect
qualitative data within 15 weeks. The participants consisted of nine first year non-English-major students who learning
General English at pre-intermediate level. They were chosen and divided into three groups of three members each
(high motivation group; average motivation group; and low motivation group). The results of the present study
identified six visual motivation patterns of three groups of students with different motivation fluctuation, through the
use of cluster analysis. The study also indicated a diversity of factors affecting students’ motivation involving internal
factors as influencing factors (cognitive, psychology, and emotion) and external factors as social factors (instructor,
peers, family, and learning environment) during English language learning in a period of 15 weeks. The findings of
the study helped teacher understand relationship of motivation change and its influential factors. Furthermore, the
findings also inspired next research about motivation development in learning English process.
KEY WORDS: language learning motivation, motivation change, motivation patterns, influential factors, students’
motivation.
STUDY ON THE DEVELOPMENT STRATEGY OF HUZHOU TOURISMAJHSSR Journal
ABSTRACT: Huzhou has rich tourism resources, as early as a considerable development since the reform and
opening up, especially in recent years, Huzhou tourism has ushered in a new period of development
opportunities. At present, Huzhou tourism has become one of the most characteristic tourist cities on the East
China tourism line. With the development of Huzhou City, the tourism industry has been further improved, and
the tourism degree of the whole city has further increased the transformation and upgrading of the tourism
industry. However, the development of tourism in Huzhou City still lags far behind the tourism development of
major cities in East China. This round of research mainly analyzes the current development of tourism in
Huzhou City, on the basis of analyzing the specific situation, pointed out that the current development of
Huzhou tourism problems, and then analyzes these problems one by one, and put forward some specific
solutions, so as to promote the further rapid development of tourism in Huzhou City.
KEYWORDS:Huzhou; Travel; Development
MODELING THE ADAPTION RULE IN CONTEXTAWARE SYSTEMS
1. International Journal of Ad hoc, Sensor & Ubiquitous Computing (IJASUC) Vol.7, No.3/4, August 2016
DOI : 10.5121/ijasuc.2016.7401 1
MODELING THE ADAPTION RULE IN CONTEXT-
AWARE SYSTEMS
Mao Zheng1
, Qian Xu2
and Hao Fan3
1
Department of Computer Science, University of Wisconsin-LaCrosse, LaCrosse, USA,
2
Amazon, Seattle,USA and
3
School of Information Management, Wuhan University,Wuhan,China
ABSTRACT
Context awareness is increasingly gaining applicability in interactive ubiquitous mobile computing
systems. Each context-aware application has its own set of behaviors to react to context modifications. This
paper is concerned with the context modeling and the development methodology for context-aware systems.
We proposed a rule-based approach and use the adaption tree to model the adaption rule of context-aware
systems. We illustrate this idea in an arithmetic game application.
KEYWORDS
Ubiquitous Mobile Computing; Context; Context-awareness; Rule-based Approach; Adaption Tree
1.INTRODUCTION
Our world gets more connected everyday. These connections are driven in part by the changing
market of smart phones and tablets. Pervasive computing environments are fast becoming a
reality. The term “pervasive”, introduced first by Weiser [1], refers to the seamless integration of
devices into the user’s everyday life. One field in the wide range of pervasive computing is the
so-called context-aware system. Context-aware systems are able to adapt their operations to the
current context without an explicit user intervention and thus aim at increasing usability and
effectiveness by taking environmental context into account. Each context-aware application has
its own set of behaviors to react to context modifications. Hence, every software engineer needs
to clearly understand the goal of the development and to categorize the context in the application.
We incorporate context-based modifications into the appearance or the behavior of the interface,
either at the design time or at the run time. In this paper, we present application behavior adaption
to the context modification via a context-based user interface in a mobile application, arithmetic
game. The application’s mobile user interface (MUI) will be automatically adapted based on the
context information.
The user interface (UI) can include many features such as font color, sound level, data entry, etc.
Every feature has some variables. For example, data entry can be done using typing, voice and
tapping. From the designer’s perspective, the adaptability of these features is planned either at the
design time or during the runtime. Through the literature study, we proposed a rule-based
approach model, and used an adaption tree to present this model. The adaption tree is what we
named in our methodology. It is based on the extension of a decision table, the decision tree. We
use the adaption tree to represent the adaption of the mobile device user interface to various
context information. The context includes the user’s domain information and dynamic
environmental changes. Each path in the adaption tree, from the root to the leaf, presents an
adaption rule. To illustrate our methodology, we implemented a context-aware application in the
Android platform, the arithmetic game application.
2. International Journal of Ad hoc, Sensor & Ubiquitous Computing (IJASUC) Vol.7, No.3/4, August 2016
2
There are two major platforms in the mobile device community: iOS and Android. This project
chose Android development mainly for the reason of its openness. In addition, all the tools in the
Android development are free and no special hardware is required.
The rest of the paper is organized as follows: in Section 2 we compare how our views are similar
to other researchers and how they are different. Section 3, we briefly describe the arithmetic game
application. Section 4 presents the rule-based approach and the fundamental concepts of the
adaption tree. Section 5 discusses the development of the arithmetic game based on the adaption
tree. Section 6 concludes the paper and outlines the directions of our on-going research.
2. RELATED WORK
Some researchers define context as the user’s physical, social, emotional or informational state, or
as the subset of physical and conceptual states of interest to a particular entity [2]. The authors in
[2] have presented the definition or interpretation of the term by various researchers, including
Schilit and Theimer [3], Brown et al. [4], Ryan et al. [5], Dey [6], Franklin & Flaschbart [7],
Ward et al. [8], Roddenet al. [9], Hull et al. [10], and Pascoe [11]. In Dey and Abowd [2], the
authors are interested in context-aware systems, and so they focused on characterizing the term
itself. In Pascoe [11], the author’s interest is wearable computers, so his view of context is based
on environmental parameters as perceived by the senses. Our work depends on the internal
sensors of a mobile device, and the adaption of the mobile user interface features for both
entering and accessing data. Our model is based on separating how context is acquired from how
it is used, by adapting the mobile user interface features to the user’s context.
Most of the research in this area has been based on analyzing context-aware computing that uses
sensing and situational information to automate services, such as location, time, identity and
action. More detailed adaption has been generally ignored. For example, input data based on
context. In our research, we attempted to build the user’s characteristics from both domain
experience and mobile technology experience, and to collect all the context values corresponding
to the user’s task and then to automatically adapt the mobile user interfaces to the context
information.
The process of developing context-based user interface has been explored in a number of other
projects. Clerckset al. [12], for example, discuss various tools to support the model-based
approach. Many studies have been conducted on adaption using a decision table. In [13], an
approach is proposed for modeling adaptive 3D navigation in a virtual environment. In order to
adapt to different types of users, they designed a system of four templates corresponding to four
different types of users. Our work differs in that our adaption technique is based on composite
context information that extracts values from sensors in smartphones and relates with the user’s
domain and mobile technology experiences. Then we develop a set of rules for the mobile user
interface adaption. We used the adaption tree to model the context information and represent
adaption rules. It also serves as the model for the design and implementation.
3.THE ARITHMETIC GAME APPLICATION
The arithmetic application is developed for users of different ages, with different arithmetic skills.
The mobile user interface will adapt to the user’s profile, actual performance and current time and
local weather information. The device’s orientation will also be discussed as one of the context
information.
Users are required to register and obtain an account to login. During the user’s registration
process, the user’s age is stored as one of the logic context information that will be used in the
beginning of the app to assign the appropriate question level to the user.
3. International Journal of Ad hoc, Sensor & Ubiquitous Computing (IJASUC) Vol.7, No.3/4, August 2016
3
There are two modes in the application: standard mode and review mode. The standard mode is to
let the user practice or test their arithmetic skills through questions in different levels and units.
The review mode is to let the user redo the questions he/she made mistakes on before.
In the standard mode, there are three levels corresponding to three age domains. Each level is
divided into 10 units and each unit contains 10 problems. When a user answered all questions
correctly in the last unit, or answered more than or equal to 90 questions correctly in the last
level, the user can choose to level up, otherwise the user will stay at the same level.
When the user logs in for the first time, he/she is automatically assigned to a level based on the
age information. All the problems are generated randomly based on the rules shown in the Table
1 below. Generating questions randomly instead of retrieving questions from a database, can
avoid the users remembering the order of answers when they play the game again and again.
Table 1: Question Characteristics of Different Levels
Age Level Operands for + Operands for - Operands for * Operands for /
[0, 5] 1 Both [0, 10] Both [0, 10]
minuend> subtrahend
Not available Not available
[6, 12] 2 Both [0, 50] Both [0, 50]
minuend> subtrahend
Both[0, 10] Both [0, 10]
Quotient is integer
>= 13 3 Both [-100, 100] Both [-100, 100] Both[-10, 10] Both [-100, 100]
Quotient is integer
When the users answer questions, there are 10 seconds for each question. A graphic countdown
timer should work as a reminder.
The accuracy of the last unit is divided into three groups: [0%, 60%], (60%, 90%), [90%, 100%].
The arithmetic game presents three themes for three different accuracy groups respectively. For
the first group, whose last unit accuracy is between 0% and 60% inclusively, the application
simply presents a default theme. For the second group, whose last unit accuracy is between 60%
and 90% exclusively, the user is able to design their own theme with their preferred color. In the
application’s setting, the user can choose preferred colors for different UI widgets. For the third
group, whose last unit accuracy is between 90% and 100% inclusively, the user can design their
own theme with their preferred color, local time and local weather. The weather icon follows the
local weather information. The background image follows the local time period by default.
During 6:00 – 17:00, the picture of a daytime scene is displayed as the background image; during
17:01 – 19:00, the picture of a sunset is displayed as the background image; during 19:01 – 5:59,
the picture of a nighttime scene is displayed as the background image. The user can also choose
to close the “time-based background image” option in the setting, thus the background will be
presented in color style.
4.RULE-BASED APPROACH
Our work depends on the internal sensors of a mobile device, the user profile and the user’s task.
The key point of the approach is to capture and represent the knowledge required for the mobile
user interface to automatically adapt to dynamics at run time, or to implement the adaptions at
design time. The rule-based approach representation is what we are proposing. Figure 1 below
shows our proposed approach.
4. International Journal of Ad hoc, Sensor & Ubiquitous Computing (IJASUC) Vol.
We use the adaption tree in this paper
adaptation. The inspiration comes from mHealth [14
represent the adaption rules of Mobile User Interfaces. However, in the process of adapting the
decision table to our applications, we met some challenges; 1) the sequence is not clearly shown
in the decision table, 2) the decision table method is useful for those applications that include
several independent relationships among the input parameters, but it does not consider the
relationships among the conditions, such as overlapping or redundancy, 3) a decision table does
not scale up very well – when there are
be evaluated as true, false, or not applicable. It i
conditions when n increases. Because of those limitations within the decision table
our UI adaption rule using an adaption tree instead of a decision table.
The concept of adaption tree comes f
decision-making situation. Compared to a tabular decision table, it takes up more room, but it
shows the order of evaluating the conditions.
A decision tree is a flowchart-like structure in whi
attribute (e.g. whether a coin flip comes up heads or tails), each branch represents the outcome of
the test and each leaf node represents a class label (decision taken after computing all attributes).
The paths from root to leaf represent classification rules [15
4.1.Adaption Tree Used in Our Research
We call the decision tree used in our project an “adaption tree,” and our approach of adaption is
to change the UI based on context. Below are some basic co
UI feature: UI features are the smallest atomic unit for describing UI content on a mobile device.
Table 2 shows some UI features and their actions (also known as values) below:
International Journal of Ad hoc, Sensor & Ubiquitous Computing (IJASUC) Vol.7, No.3/4
Figure1.Rule-based Approach
in this paper to show our rule-based approach in the context
nspiration comes from mHealth [14] where the decision table was selected to
represent the adaption rules of Mobile User Interfaces. However, in the process of adapting the
ions, we met some challenges; 1) the sequence is not clearly shown
in the decision table, 2) the decision table method is useful for those applications that include
several independent relationships among the input parameters, but it does not consider the
relationships among the conditions, such as overlapping or redundancy, 3) a decision table does
when there are n rules, there are 2^n
rules. Since each condition needs to
be evaluated as true, false, or not applicable. It is not easy to make a full description for those
increases. Because of those limitations within the decision table
our UI adaption rule using an adaption tree instead of a decision table.
The concept of adaption tree comes from the decision tree. It is a graphical representation of a
making situation. Compared to a tabular decision table, it takes up more room, but it
shows the order of evaluating the conditions.
like structure in which each internal node represents a "test" on an
attribute (e.g. whether a coin flip comes up heads or tails), each branch represents the outcome of
the test and each leaf node represents a class label (decision taken after computing all attributes).
epresent classification rules [15].
Adaption Tree Used in Our Research
We call the decision tree used in our project an “adaption tree,” and our approach of adaption is
to change the UI based on context. Below are some basic concepts used in our research.
UI features are the smallest atomic unit for describing UI content on a mobile device.
Table 2 shows some UI features and their actions (also known as values) below:
/4, August 2016
4
sed approach in the context-based UI
] where the decision table was selected to
represent the adaption rules of Mobile User Interfaces. However, in the process of adapting the
ions, we met some challenges; 1) the sequence is not clearly shown
in the decision table, 2) the decision table method is useful for those applications that include
several independent relationships among the input parameters, but it does not consider the
relationships among the conditions, such as overlapping or redundancy, 3) a decision table does
rules. Since each condition needs to
make a full description for those
increases. Because of those limitations within the decision table, we presented
rom the decision tree. It is a graphical representation of a
making situation. Compared to a tabular decision table, it takes up more room, but it
ch each internal node represents a "test" on an
attribute (e.g. whether a coin flip comes up heads or tails), each branch represents the outcome of
the test and each leaf node represents a class label (decision taken after computing all attributes).
We call the decision tree used in our project an “adaption tree,” and our approach of adaption is
ncepts used in our research.
UI features are the smallest atomic unit for describing UI content on a mobile device.
5. International Journal of Ad hoc, Sensor & Ubiquitous Computing (IJASUC) Vol.7, No.3/4, August 2016
5
Table 2:UI features and their actions
UI features Action(values)
Font size Small, medium, large
Font color RGB color, black, white
Background color Auto adjust, change manually
Data entry Typing, voice, tapping...
Display information Text, sound
Message delivery Text, voice, alert…
Brightness level Increase/decrease
Ring volume Low, medium, high
Sound Mute, regular, loud
Video On, off
.... ....
UI feature set: A UI feature set is a non-empty set of UI features.
Disjoint UI feature sets: Two UI feature sets are said to be disjoint if they have no UI feature in
common. It also means that the UI features do not interfere with each other in the process of
adaption. For example: {video}, {media sound} and {brightness level} are three disjoint UI
feature sets, but {video, media sound} and {video, brightness level} are not disjoint UI feature
sets because their intersection is the set {video}.
Action set: Anaction set is a set of actions (also known as values) applied to UI. For example:
{Font size is small, Font color is black} is an action set.
Context category:We categorized the context information into two categories as shown in Table
3. Physical context information is collected by the mobile device’s sensors. The logical
information is gathered through the user’s registration process, the user’s performance, and the
user’s selections in the setting menu.
Table 3: Context Information Categorization
Physical
Context
local time, local weather (local here also implies the context location
considered), device orientation
Logical
Context
user’s profile (age, first time using the app or not, performance)
user’s preference (color preference, image preference)
Context condition:
A context condition is the predicate of the context value. For example: “whether the battery level
is low” is a context condition.
Context set:
A context set is a non-empty set of context. For example: {local time, local weather, device
orientation} is a context set.
Adaption function:
Let F be a UI feature set, let C be a context set and let A (C, F) be a function defined over inputs
F and C, the output is action set, that is C applied to F.
6. International Journal of Ad hoc, Sensor & Ubiquitous Computing (IJASUC) Vol.
Adaption function distributive rule:
In A (C, F), let F be divided to disjoint UI feature sets: F = f1
distributive rule:
A (C, F) = A (C, f1 ∪f2 ∪…
Below is an example of different ways of distributing an adaption function:
Problem: make adaptions on UI features: video, media sound,
battery is low.
Solution:
1. UI feature set F = {video, media sound, brightness level}
2. Context set C = {battery is low},
3. Function: A (C, F) = ({battery is low}, {video, media sound, brightness level})
4. According to our distributive rule:
a. If F is divided to disjoint UI feature sets: {video}, {media sound, brightness level}
Then A ({battery is low}, {video, media sound, brightness level}) = A({battery is
low}, {video}) ∪A({battery is low}, {media sound, brightness level})
b. If F is divided to disjoint UI feature sets: {video, media sound}, {brightness level}
Then A ({battery is low}, {video, media sound, brightness level}) = A({battery is
low}, {video, media sound, brightness level})= A(({battery is low}, {video, media
sound}) ∪A({battery is low}, {brightness level})
c. If F is divided to disjoint UI feature sets: {video}, {media sound, brightness level}
Then : A ({battery is low}, {video, media sound, brightness level}) = A({battery is
low}, { video, media sound, brightness level}) = A(({battery is low}, { video})
A({battery is low}, {media sound })
Adaption tree:
We define decision tree over function A (C, F), and we named the decision tree used in our
approach as an adaption tree. An adaption tree consists of two types of nodes: condition node and
conclusion node. Table 4 shows the nodes and their descript
Name Shape Description
Condition
Node
non
conditions.
Conclusion
Node
leaf node, denoted as a rectangle. It represents a UI
context
Drawn from top to down, each path from root node to leaf node represents an adaption rule. Each
condition node (also recognized as non
context it checked, and it has several branches coming out of it
recognized as leaf node) is denoted as rectangle, and labeled with UI action.
International Journal of Ad hoc, Sensor & Ubiquitous Computing (IJASUC) Vol.7, No.3/4
Adaption function distributive rule:
In A (C, F), let F be divided to disjoint UI feature sets: F = f1 ∪ f2 ∪... ∪ fn, then we have
…∪fn,) ≡A (C, f1) ∪A (C, f2) ∪....∪A (C, fn)
Below is an example of different ways of distributing an adaption function:
: make adaptions on UI features: video, media sound, brightness level, based on context:
UI feature set F = {video, media sound, brightness level}
Context set C = {battery is low},
Function: A (C, F) = ({battery is low}, {video, media sound, brightness level})
istributive rule:
If F is divided to disjoint UI feature sets: {video}, {media sound, brightness level}
Then A ({battery is low}, {video, media sound, brightness level}) = A({battery is
A({battery is low}, {media sound, brightness level})
If F is divided to disjoint UI feature sets: {video, media sound}, {brightness level}
Then A ({battery is low}, {video, media sound, brightness level}) = A({battery is
low}, {video, media sound, brightness level})= A(({battery is low}, {video, media
A({battery is low}, {brightness level})
If F is divided to disjoint UI feature sets: {video}, {media sound, brightness level}
Then : A ({battery is low}, {video, media sound, brightness level}) = A({battery is
low}, { video, media sound, brightness level}) = A(({battery is low}, { video})
A({battery is low}, {media sound }) ∪A(({battery is low}, {brightness level })
We define decision tree over function A (C, F), and we named the decision tree used in our
approach as an adaption tree. An adaption tree consists of two types of nodes: condition node and
conclusion node. Table 4 shows the nodes and their descriptions in an adaption tree.
Table 4: Node in the Adaption Tree
Description
non-leaf node, denoted as a diamond. It checks the context
conditions.
leaf node, denoted as a rectangle. It represents a UI action after
context-based adaption.
Drawn from top to down, each path from root node to leaf node represents an adaption rule. Each
condition node (also recognized as non-leaf node) is represented as a diamond, labeled with the
context it checked, and it has several branches coming out of it. Each conclusion node (also
recognized as leaf node) is denoted as rectangle, and labeled with UI action.
/4, August 2016
6
fn, then we have
brightness level, based on context:
Function: A (C, F) = ({battery is low}, {video, media sound, brightness level})
If F is divided to disjoint UI feature sets: {video}, {media sound, brightness level}
Then A ({battery is low}, {video, media sound, brightness level}) = A({battery is
If F is divided to disjoint UI feature sets: {video, media sound}, {brightness level}
Then A ({battery is low}, {video, media sound, brightness level}) = A({battery is
low}, {video, media sound, brightness level})= A(({battery is low}, {video, media
If F is divided to disjoint UI feature sets: {video}, {media sound, brightness level}
Then : A ({battery is low}, {video, media sound, brightness level}) = A({battery is
low}, { video, media sound, brightness level}) = A(({battery is low}, { video}) ∪
A(({battery is low}, {brightness level })
We define decision tree over function A (C, F), and we named the decision tree used in our
approach as an adaption tree. An adaption tree consists of two types of nodes: condition node and
ions in an adaption tree.
leaf node, denoted as a diamond. It checks the context
action after
Drawn from top to down, each path from root node to leaf node represents an adaption rule. Each
leaf node) is represented as a diamond, labeled with the
. Each conclusion node (also
7. International Journal of Ad hoc, Sensor & Ubiquitous Computing (IJASUC) Vol.7, No.3/4, August 2016
7
5.THE ADAPTION TREE IN THE ARITHMETIC GAME APPLICATION
We are presenting the adaption rules by constructing an adaption tree in the arithmetic game
application. There are various contexts that we can gather. We only collected contexts that could
result in at least one action over our application UI.
1. UI feature set: F= {font color, background color, button font color, button background
color, weather icon, background image, orientation mode}
If we divided F to disjoint UI feature sets: F = F1∪F2 = {font color, background color,
button font color, button background color, weather icon, background image}∪
{orientation mode} and name F1 as Theme which is a UI feature set, then we have F
= Theme ∪{orientation mode}
2. Context set: C = {first time, last unit accuracy, device orientation, local time, local
weather} ∪ User’s Preference, the User’s Preference = {font color preference,
background color preference, button font color preference, button background color
preference, background image preference}
3. Function: A (C, F) = A ({first time, last unit accuracy, device orientation, local time,
local weather, User’s Preference}, Theme ∪{orientation mode})
4. According to our distributive rule:
A ({first time, last unit accuracy, device orientation, local time, local weather,
User’s Preference}, Theme∪{orientation mode })
≡A ({first time, last unit accuracy, device orientation, local time, local weather,
User’s Preference}, Theme)
∪A ({first time, last unit accuracy, device orientation, local time, local weather,
User’s Preference }, {orientation mode })
Then define the output:
1. A ({first time, last unit accuracy, device orientation, local time, local weather, User’s
Preference}, Theme) has three discrete output values: Default Theme, Preferred Color
Theme, Weather & time based Theme.
2.
a. Default Theme = {font color is black, background color is white, button font
color is black, button background color is white, weather icon is null, background
image is null}
b. Preferred Color Theme = {font color is A (User’s Preference, {font color}),
background color is A (User’s Preference, {background color}), button font color
is A (User’s Preference, {button font color}), button background color is A
(User’s Preference, {button background color}), weather icon is null, background
image is null}
c. Weather & time based Theme = {font color is A (User’s Preference, {font
color}), background color is A (User’s Preference, {background color}), button
font color is A (User’s Preference, {button font color}), button background color
is A (User’s Preference, {button background color}), weather icon is A ({local
weather}∪User’s Preference, {weather icon}), background image is A ({local
time}∪User’s Preference, {background image})
3. A ({first time, last unit accuracy, device orientation, local time, local weather}∪ User’s
Preference, {orientation mode}) has two discrete output values: {portrait mode} and
{landscape mode}
8. International Journal of Ad hoc, Sensor & Ubiquitous Computing (IJASUC) Vol.
Figure 2 is an adaption tree over A ({first time, last unit accuracy, device orientation, local time,
local weather, User’s Preference}, Theme
Adaption Tree for Theme
Figure 2 shows four adaption rules for theme:
1. If a user is using this app for the first time, then the theme action is the default color theme.
2. If a user is not using this app for the first time, and the last unit accuracy is between 0%
and 60% both inclusive, then the theme action is the default theme.
3. If a user is not using this app for the first time, and the last unit accuracy is between 60%
and 90% both exclusive, then the theme action is the preferred color theme.
4. If a user is not using this app for the first time, and the last unit accuracy is between 90%
and 100% both inclusive, then the theme action is the weather & time based theme.
If the fourth adaption rule for theme is met (the theme action is the weather
then we can construct an adaption tree for font color, background color, button font color, button
background, weather icon, background image to show our rule for those UI features, respectively.
Among those UI features, we selected t
Figure 4 shows our adaption tree for background image that is based on the
adaption tree for theme.
International Journal of Ad hoc, Sensor & Ubiquitous Computing (IJASUC) Vol.7, No.3/4
Figure 2 is an adaption tree over A ({first time, last unit accuracy, device orientation, local time,
her, User’s Preference}, Theme
Figure 2:Adaption Tree for Theme
Figure 2 shows four adaption rules for theme:
If a user is using this app for the first time, then the theme action is the default color theme.
If a user is not using this app for the first time, and the last unit accuracy is between 0%
sive, then the theme action is the default theme.
If a user is not using this app for the first time, and the last unit accuracy is between 60%
and 90% both exclusive, then the theme action is the preferred color theme.
If a user is not using this app for the first time, and the last unit accuracy is between 90%
and 100% both inclusive, then the theme action is the weather & time based theme.
If the fourth adaption rule for theme is met (the theme action is the weather & time based theme.),
then we can construct an adaption tree for font color, background color, button font color, button
background, weather icon, background image to show our rule for those UI features, respectively.
Among those UI features, we selected the background image to present our approach.
igure 4 shows our adaption tree for background image that is based on the
/4, August 2016
8
Figure 2 is an adaption tree over A ({first time, last unit accuracy, device orientation, local time,
If a user is using this app for the first time, then the theme action is the default color theme.
If a user is not using this app for the first time, and the last unit accuracy is between 0%
If a user is not using this app for the first time, and the last unit accuracy is between 60%
If a user is not using this app for the first time, and the last unit accuracy is between 90%
and 100% both inclusive, then the theme action is the weather & time based theme.
& time based theme.),
then we can construct an adaption tree for font color, background color, button font color, button
background, weather icon, background image to show our rule for those UI features, respectively.
he background image to present our approach.
9. International Journal of Ad hoc, Sensor & Ubiquitous Computing (IJASUC) Vol.
Figure 3:
Figure 3 should be only being considered after Figure 2. The contexts in Figure 2 have higher
priority than the contexts in Figure 3.
Figure 2 and Figure 3 together present lots of rules. For example,if the fourth adaption rule for
theme is met, the background image preference
time is between 17:00 to 19:00, then the background image is a sunset background image.
The implementation of the arithmetic game strictly followed the adaption trees in Figures 2 and
Below are the screen shots for the application with different themes and with local weath
time information as well.
Figure 4 Black and White Theme Figure 5 User’s Preferred Colors
International Journal of Ad hoc, Sensor & Ubiquitous Computing (IJASUC) Vol.7, No.3/4
Figure 3:Adaption Tree for Background Image
Figure 3 should be only being considered after Figure 2. The contexts in Figure 2 have higher
priority than the contexts in Figure 3.
Figure 2 and Figure 3 together present lots of rules. For example,if the fourth adaption rule for
ground image preference is a time-based background image, and the local
time is between 17:00 to 19:00, then the background image is a sunset background image.
The implementation of the arithmetic game strictly followed the adaption trees in Figures 2 and
Below are the screen shots for the application with different themes and with local weath
Figure 4 Black and White Theme Figure 5 User’s Preferred Colors
/4, August 2016
9
Figure 3 should be only being considered after Figure 2. The contexts in Figure 2 have higher
Figure 2 and Figure 3 together present lots of rules. For example,if the fourth adaption rule for
based background image, and the local
time is between 17:00 to 19:00, then the background image is a sunset background image.
The implementation of the arithmetic game strictly followed the adaption trees in Figures 2 and 3.
Below are the screen shots for the application with different themes and with local weather and
Figure 4 Black and White Theme Figure 5 User’s Preferred Colors
10. International Journal of Ad hoc, Sensor & Ubiquitous Computing (IJASUC) Vol.
Figure 6 Snowy Day
5.CONCLUSIONS
With ubiquitous computing, users access their applications in a wide variety of environments.
To cope with various and dynamic execution environments, the adaptive mobile user interface
is desired to enhance human
address this issue. We used the rule
the adaption rule for the mobile user interface based on the various context information. Our
implementations strictly followed our proposed appr
It is important to point out we are separating how context is acquired from how it is used, by
adapting mobile user interface features to various context information. The user, as a
composite entity, is part of the context.
Each context-aware application has its own set of behaviors to react to context modifications.
Hence, every software engineer needs to clearly understand the goal of the development and
categorize the context in the application. We have proven this idea in two differen
aware applications [16].
The contributions of this research work lie in 1) considering both the user’s domain and mobile
technology experience in context, 2) detailed modeling inclusion on both input and output
data, 3) using the rule to present acquired
a mobile user interface can enhance the accessibility in the e
additional benefits are a) increased usability. For example, if the mobile user interface only
supports one interaction model, such as typing or voice input/sound output, the usability of the
service would be drastically decreased. b) increased awareness of social ethics, e.g. in a quiet
room after midnight, the sound could be turned off automatically. c) improved workfl
productivity because the mobile user interface is automatically adapted to the dynamic
environments.
International Journal of Ad hoc, Sensor & Ubiquitous Computing (IJASUC) Vol.7, No.3/4
Figure 6 Snowy Day Figure 7 Rainy Night
ith ubiquitous computing, users access their applications in a wide variety of environments.
To cope with various and dynamic execution environments, the adaptive mobile user interface
is desired to enhance human-computer interactions. This research work is our attempt to
address this issue. We used the rule-based approach, represented as adaption tree to describe
the adaption rule for the mobile user interface based on the various context information. Our
implementations strictly followed our proposed approach.
It is important to point out we are separating how context is acquired from how it is used, by
adapting mobile user interface features to various context information. The user, as a
composite entity, is part of the context.
lication has its own set of behaviors to react to context modifications.
Hence, every software engineer needs to clearly understand the goal of the development and
categorize the context in the application. We have proven this idea in two differen
The contributions of this research work lie in 1) considering both the user’s domain and mobile
technology experience in context, 2) detailed modeling inclusion on both input and output
data, 3) using the rule to present acquired knowledge in the application. The adaption built into
a mobile user interface can enhance the accessibility in the e-commerce domain. The
additional benefits are a) increased usability. For example, if the mobile user interface only
on model, such as typing or voice input/sound output, the usability of the
service would be drastically decreased. b) increased awareness of social ethics, e.g. in a quiet
room after midnight, the sound could be turned off automatically. c) improved workfl
productivity because the mobile user interface is automatically adapted to the dynamic
/4, August 2016
10
ith ubiquitous computing, users access their applications in a wide variety of environments.
To cope with various and dynamic execution environments, the adaptive mobile user interface
s our attempt to
based approach, represented as adaption tree to describe
the adaption rule for the mobile user interface based on the various context information. Our
It is important to point out we are separating how context is acquired from how it is used, by
adapting mobile user interface features to various context information. The user, as a
lication has its own set of behaviors to react to context modifications.
Hence, every software engineer needs to clearly understand the goal of the development and
categorize the context in the application. We have proven this idea in two different context-
The contributions of this research work lie in 1) considering both the user’s domain and mobile
technology experience in context, 2) detailed modeling inclusion on both input and output
knowledge in the application. The adaption built into
commerce domain. The
additional benefits are a) increased usability. For example, if the mobile user interface only
on model, such as typing or voice input/sound output, the usability of the
service would be drastically decreased. b) increased awareness of social ethics, e.g. in a quiet
room after midnight, the sound could be turned off automatically. c) improved workflow
productivity because the mobile user interface is automatically adapted to the dynamic
11. International Journal of Ad hoc, Sensor & Ubiquitous Computing (IJASUC) Vol.7, No.3/4, August 2016
11
REFERENCES
[1] Weiser, M., “The computer for the 21st century”, Scientific American, 1991, pp. 94-104.
[2] Dey AK, Abowd GD, “Towards a better understanding of context and context awareness”, New
York: ACM Press, 2000.
[3] Schilit B, Theimer M., “Disseminating active map information to mobile hosts”, IEEE Network
1994, 8(5):22-32.
[4] Brown PJ, Bovey JD, Chen X, “Context-aware applications: from laboratory to the marketplace”,
IEEE Personal Communications 1997, 4(5):58-64.
[5] Ryan N, Pascoe J, Morse D, “Enhanced reality fieldwork: the context-aware archaeological
assistant”, In Dingwall, L., Exon, S., Gaffney, V., Laflin, S., & van Leusen, M., Eds.,Archaeology
in the Age of the Internet. CAA97. Computer Applications and Quantitative Methods in
Archaeology. Proceedings of the 25th Anniversary Con- ference, University of Birmingham, April
1997 (BAR International Series 750).Archaeopress, Oxford, 269-274. Leu- sen, Exxon (Eds.),
Computer Applications in Archaeology.
[6] Dey AK, “Context aware computing: the cyberdesk project”, Technical Report SS-98-02, 1998, 51-
54.
[7] Franklin D, Flaschbart J., “All gadget and no representation makes jack a dull environment”,
Technical Report SS-98-02. 1998, 155-160.
[8] Ward A, Jones A, Hopper A, “A new location technique for the active office”, IEEE Personal
Commun. 1997, 4(5):42-47.
[9] Rodden T, Cheverst K, Davies K, Dix A, “Exploiting context in HCI design for mobile systems”,
Workshop on Human Computer Interaction with Mobile Devices 1998.
[10] Hull R, Neaves P, Bedford-Roberts J, “Towards situated computing”, 1st International Symposium
on Wearable Computers, 1997, 146-153.
[11] Pascoe J, “Adding generic contextual capabilities to wearable computers”, 2nd International
Symposium on Wearable Computers, 1998, 92-99.
[12] Clerckx, T., Winters, F. and Coninx, K. (2005) Tool Support for Designing Context-Sensitive User
Interface Using a Model-Based Approach. TAMODIA’05 Proceedings of the 4th International
Workshop on Task Models and Diagrams, Gdansk, 26-27 September 2005, 11-18.
[13] Cheng, S.W. and Sun, S.Q. (2009) Adaptive 3D Navigation User Interface Design Based on Rough
Sets. IEEE 10th International Conference on Computer-Aided Industrial Design & Conceptual
Design, Wenzhou, 26-29 November 2009, 1935-1940.
[14] ReemAlnaniha, b, Olga Ormandjievaa, T. Radhakrishnana, Context-based and Rule-based
Adaptation of Mobile User Interfaces in mHealth, The 3rd International Conference on Current
and Future Trends of Information and Communication Technologies in Healthcare (ICTH),
Procedia Computer Science 21(2013) pp. 390-397.
[15] https://en.wikipedia.org/wiki/Decision_tree
[16] Mao Zheng, Sihan Cheng, QianXu, Context-based Mobile User Interface, Journal of Computer and
Communications, Vol. 4, 2016, pp: 1-9.10.4236/jcc.2016.49001
12. International Journal of Ad hoc, Sensor & Ubiquitous Computing (IJASUC) Vol.
AUTHORS
Dr. Mao Zheng is a tenured faculty member and associated professor in the
Department of Computer Science at the
of research include Software Engineering, Software Testing and Formal Methods. The
courses she has taught include Software Engineering, Software Design, Object
Oriented Development, Software Testing and Object
in Java. Dr.Zheng received her Ph.D. in Computer Science at Concordia University in
Montreal Canada in 2002. Dr.Zheng has been actively involved with IEEE conferences and served as
reviewers and co-organizers for some IEEE conf
for an international journal.
QianXu is currently working in Amazon in Seattle USA. She obtained the Mater of
Software Engineering degree from the University of Wisconsin
May 2016.
Dr.Hao Fan is a professor at the School of Information Manageme
University in China. His research areas include Data Mining, Data Representation and
Management, and Software Engineering.
International Journal of Ad hoc, Sensor & Ubiquitous Computing (IJASUC) Vol.7, No.3/4
Dr. Mao Zheng is a tenured faculty member and associated professor in the
Department of Computer Science at the University of Wisconsin-La Crosse. Her areas
of research include Software Engineering, Software Testing and Formal Methods. The
courses she has taught include Software Engineering, Software Design, Object-
Oriented Development, Software Testing and Object-Oriented Software Development
in Java. Dr.Zheng received her Ph.D. in Computer Science at Concordia University in
Montreal Canada in 2002. Dr.Zheng has been actively involved with IEEE conferences and served as
organizers for some IEEE conferences. She also has served as an editorial board member
QianXu is currently working in Amazon in Seattle USA. She obtained the Mater of
Software Engineering degree from the University of Wisconsin – LaCrosse in USA in
Dr.Hao Fan is a professor at the School of Information Management in Wuhan
China. His research areas include Data Mining, Data Representation and
Management, and Software Engineering.
/4, August 2016
12
Montreal Canada in 2002. Dr.Zheng has been actively involved with IEEE conferences and served as
erences. She also has served as an editorial board member