Educator’s knowledge about the likely students’ achievement in blended courses prior to sitting for
examinations provides room for early intervention on students’ learning process, especially to those at risk.
Unfortunately, Leaning Management Systems (LMSs), Moodle in particular lacks an environment to assist
educators access such knowledge from time to time before undertaking their examinations. This raised the
need to propose a model, of which from time to time would be providing the likely students’ achievement
based on activities in Moodle and previous achievement, taking a case of postgraduate programmes at the
University of Dar es Salaam.
This study applied artificial neural networks in building a prediction model. Simulations were conducted in
Matrix Laboratory (MATLAB) utilizing seventy eight instances (78) of students’ logs of three blended
courses extracted from Moodle for 2013/2014 and 2014/2015 academic years.
Mean Square Error (MSE) and Coefficient of Determination (R
2
) performance metrics were used to find
the best prediction model considering ten possible models. The study revealed a model with architecture of
4:10:1 trained with Bayesian Regularization (BR) to be the best model resulting to least MSE of 0.0170 and
high R
2
of 0.93 on training. During testing, the model successfully predicted 78% of the students’
achievement with risk and pass status.
A way for blending vle and face to-face instruction by Gulden ILINsuhailaabdulaziz
This document discusses a study that explored blending a Teaching English to Young Learners course with both face-to-face instruction and the Moodle online platform. 100 student teachers participated in a 14-week blended course. Data was collected through a readiness scale, questionnaire, and interviews. Results found that students were ready and comfortable with online learning. They viewed the blended course positively and found it motivating and valuable for their education as language teachers. Students appreciated the flexibility to engage with course content and provide feedback to peers online in their own time.
This document summarizes a study on the acceptance of the Blackboard learning management system (LMS) among students at INTI International University in Malaysia. It includes sections on definitions, theoretical framework, hypotheses, preliminary analysis, findings, and contributions. Key findings are that over 60% of INTI students actively use Blackboard, and functions like assignment submission and discussions are widely accepted. However, improvements could increase acceptance, such as clearer instructions, faster speed, and more training. The study found students want to use Blackboard but it needs enhancements to improve acceptance levels. Recommendations include improving the interface, speed, training, and developing new online learning functions.
The document discusses a study on students' experiences using a Learning Management System (LMS) at Universiti Putra Malaysia. Key findings from interviews with students include:
1) Students use the LMS mainly to download lecture notes and check assignment grades. However, they desire a more permanent profile and notification of successful file uploads.
2) Students interact with lecturers and peers on the LMS and appreciate its anonymity for shy students.
3) Emerging themes from students suggest needs for a permanent profile, file submission notifications, and a more attractive layout with embedded features. Addressing student needs could help accelerate adoption of the LMS.
Customized moodle-based learning management system for socially disadvantaged...journalBEEI
This study aims to develop Moodle-based LMS with customized learning content and modified user interface to facilitate pedagogical processes during covid-19 pandemic and investigate how teachers of socially disadvantaged schools perceived usability and technology acceptance. Co-design process was conducted with two activities: 1) need assessment phase using an online survey and interview session with the teachers and 2) the development phase of the LMS. The system was evaluated by 30 teachers from socially disadvantaged schools for relevance to their distance learning activities. We employed computer software usability questionnaire (CSUQ) to measure perceived usability and the technology acceptance model (TAM) with insertion of 3 original variables (i.e., perceived usefulness, perceived ease of use, and intention to use) and 5 external variables (i.e., attitude toward the system, perceived interaction, self-efficacy, user interface design, and course design). The average CSUQ rating exceeded 5.0 of 7 point-scale, indicated that teachers agreed that the information quality, interaction quality, and user interface quality were clear and easy to understand. TAM results concluded that the LMS design was judged to be usable, interactive, and well-developed. Teachers reported an effective user interface that allows effective teaching operations and lead to the system adoption in immediate time.
This document provides an analysis and recommendations for improving online learning in the Jefferson County school district. It begins with an overview of best practices for traditional and online education. It then evaluates the pros and cons of online learning for students and best practices for teaching K-12 online. The document outlines current online class offerings through Jeffco and teacher training programs. It concludes with recommendations to expand online options and increase enrollment, such as offering blended classes and additional course choices.
This document summarizes a study examining factors affecting adoption and usage of the Blackboard learning management system (LMS) amongst academics at Durban University of Technology (DUT) in South Africa. A survey and interviews with academics revealed that lack of LMS experience, low computer skills, and age (particularly for those 41-50 years old) were associated with lower Blackboard usage. Upgrading the system and improving technical support response times were suggested to increase adoption. The study applied the technology acceptance model to identify personal, technological, and organizational factors influencing LMS use, finding that support from management and training positively impacted acceptance while system complexity hindered it.
Using a VLE to Enhance Assessment for Learning Mathematics in School ScectorIJMIT JOURNAL
This paper investigates the use of VLE in enhancing or supporting assessment for learning mathematics by the KS4 students with special education needs in the London borough secondary school. The main challenge in teaching and learning of mathematics is to provide the special education needs students with extensive support structure that is associated with their subject area. As part of continuous teaching and learning, many schools in the UK have embraced Assessment for learning as an effective and efficient way of providing students, their teachers and their home schools with feedback and feed forward. A virtual learning environment (VLE), which is an electronic system, provides online interaction of various kinds that can take place between learners and tutors, including online learning and assessment [1]. A VLE as a platform for teaching and learning supports assessment for learning (AfL), encourages personalised and collaborative learning, enabling students to carry out peer and self assessment of mathematics course within a unified supportive environment online. Evidence from literature suggests that VLE supports out of school hours of learning, and that the special education needs learners who do not respond well to the formal structure of learning within the school system take an active part in learning in informal settings. The finding presents key issues related to mathematics teaching and assessment for learning using a VLE, based on the perspectives of the special education needs (SENs) students in the school sector. The students who received in-class feedback and feed-forward during mathematics lesson, and through the VLE (Fronter) platform, moved their learning forward and much quicker when compared with students who only received feedback in class. Correspondingly, the instant feedback provided by a VLE after the Observation stage was greatly valued by the SENs students who used this period to take greater responsibility for personal learning. In general, the finding suggests that a VLE effectively enhances assessment for Learning by offering instant feedback and feed-forward to the SENs students who, now began to take responsibility for their own learning, and have also been motivated to correct their work. Furthermore, evidence of teacher – student interactivity which facilitates greater understanding of mathematical concepts is highlighted by the study.
The document describes research to develop an e-learning system to enhance cognitive skills for learners in higher education. The system includes two sub-systems: (1) an e-learning system in a Blended Learning Environment (BLE) and (2) an e-learning system in a Virtual Learning Environment (VLE). Both systems were tested on 240 higher education students across three disciplines. The results showed that the systems improved students' cognitive skills and should consist of four core elements: input, process, output, and feedback.
A way for blending vle and face to-face instruction by Gulden ILINsuhailaabdulaziz
This document discusses a study that explored blending a Teaching English to Young Learners course with both face-to-face instruction and the Moodle online platform. 100 student teachers participated in a 14-week blended course. Data was collected through a readiness scale, questionnaire, and interviews. Results found that students were ready and comfortable with online learning. They viewed the blended course positively and found it motivating and valuable for their education as language teachers. Students appreciated the flexibility to engage with course content and provide feedback to peers online in their own time.
This document summarizes a study on the acceptance of the Blackboard learning management system (LMS) among students at INTI International University in Malaysia. It includes sections on definitions, theoretical framework, hypotheses, preliminary analysis, findings, and contributions. Key findings are that over 60% of INTI students actively use Blackboard, and functions like assignment submission and discussions are widely accepted. However, improvements could increase acceptance, such as clearer instructions, faster speed, and more training. The study found students want to use Blackboard but it needs enhancements to improve acceptance levels. Recommendations include improving the interface, speed, training, and developing new online learning functions.
The document discusses a study on students' experiences using a Learning Management System (LMS) at Universiti Putra Malaysia. Key findings from interviews with students include:
1) Students use the LMS mainly to download lecture notes and check assignment grades. However, they desire a more permanent profile and notification of successful file uploads.
2) Students interact with lecturers and peers on the LMS and appreciate its anonymity for shy students.
3) Emerging themes from students suggest needs for a permanent profile, file submission notifications, and a more attractive layout with embedded features. Addressing student needs could help accelerate adoption of the LMS.
Customized moodle-based learning management system for socially disadvantaged...journalBEEI
This study aims to develop Moodle-based LMS with customized learning content and modified user interface to facilitate pedagogical processes during covid-19 pandemic and investigate how teachers of socially disadvantaged schools perceived usability and technology acceptance. Co-design process was conducted with two activities: 1) need assessment phase using an online survey and interview session with the teachers and 2) the development phase of the LMS. The system was evaluated by 30 teachers from socially disadvantaged schools for relevance to their distance learning activities. We employed computer software usability questionnaire (CSUQ) to measure perceived usability and the technology acceptance model (TAM) with insertion of 3 original variables (i.e., perceived usefulness, perceived ease of use, and intention to use) and 5 external variables (i.e., attitude toward the system, perceived interaction, self-efficacy, user interface design, and course design). The average CSUQ rating exceeded 5.0 of 7 point-scale, indicated that teachers agreed that the information quality, interaction quality, and user interface quality were clear and easy to understand. TAM results concluded that the LMS design was judged to be usable, interactive, and well-developed. Teachers reported an effective user interface that allows effective teaching operations and lead to the system adoption in immediate time.
This document provides an analysis and recommendations for improving online learning in the Jefferson County school district. It begins with an overview of best practices for traditional and online education. It then evaluates the pros and cons of online learning for students and best practices for teaching K-12 online. The document outlines current online class offerings through Jeffco and teacher training programs. It concludes with recommendations to expand online options and increase enrollment, such as offering blended classes and additional course choices.
This document summarizes a study examining factors affecting adoption and usage of the Blackboard learning management system (LMS) amongst academics at Durban University of Technology (DUT) in South Africa. A survey and interviews with academics revealed that lack of LMS experience, low computer skills, and age (particularly for those 41-50 years old) were associated with lower Blackboard usage. Upgrading the system and improving technical support response times were suggested to increase adoption. The study applied the technology acceptance model to identify personal, technological, and organizational factors influencing LMS use, finding that support from management and training positively impacted acceptance while system complexity hindered it.
Using a VLE to Enhance Assessment for Learning Mathematics in School ScectorIJMIT JOURNAL
This paper investigates the use of VLE in enhancing or supporting assessment for learning mathematics by the KS4 students with special education needs in the London borough secondary school. The main challenge in teaching and learning of mathematics is to provide the special education needs students with extensive support structure that is associated with their subject area. As part of continuous teaching and learning, many schools in the UK have embraced Assessment for learning as an effective and efficient way of providing students, their teachers and their home schools with feedback and feed forward. A virtual learning environment (VLE), which is an electronic system, provides online interaction of various kinds that can take place between learners and tutors, including online learning and assessment [1]. A VLE as a platform for teaching and learning supports assessment for learning (AfL), encourages personalised and collaborative learning, enabling students to carry out peer and self assessment of mathematics course within a unified supportive environment online. Evidence from literature suggests that VLE supports out of school hours of learning, and that the special education needs learners who do not respond well to the formal structure of learning within the school system take an active part in learning in informal settings. The finding presents key issues related to mathematics teaching and assessment for learning using a VLE, based on the perspectives of the special education needs (SENs) students in the school sector. The students who received in-class feedback and feed-forward during mathematics lesson, and through the VLE (Fronter) platform, moved their learning forward and much quicker when compared with students who only received feedback in class. Correspondingly, the instant feedback provided by a VLE after the Observation stage was greatly valued by the SENs students who used this period to take greater responsibility for personal learning. In general, the finding suggests that a VLE effectively enhances assessment for Learning by offering instant feedback and feed-forward to the SENs students who, now began to take responsibility for their own learning, and have also been motivated to correct their work. Furthermore, evidence of teacher – student interactivity which facilitates greater understanding of mathematical concepts is highlighted by the study.
The document describes research to develop an e-learning system to enhance cognitive skills for learners in higher education. The system includes two sub-systems: (1) an e-learning system in a Blended Learning Environment (BLE) and (2) an e-learning system in a Virtual Learning Environment (VLE). Both systems were tested on 240 higher education students across three disciplines. The results showed that the systems improved students' cognitive skills and should consist of four core elements: input, process, output, and feedback.
The e-learning contained many educational resources are generally used in learning systems like Moodle, It’s free open source software packages designed and flexible platform to create Learning Objects (LOs) and users’ accounts. The author demonstrates how to use semantic web technologies to improve online learning environments and bridge the gap between learners and LOs. The ontological construction presented here helps formalize LOs context as a complex interplay of different learning-related elements and shows how we can use semantic annotation to interrelate diverse between learner and LOs. On top of this construction, the author implemented several feedback channels for educators to improve the delivery of future Web-based learning. The particular aim of this paper was to provide a solution based in the Moodle Platform. The main idea behind the approach presented here is that ontology which can not only be useful as a learning instrument but it can also be employed to assess students’ skills. For it, each student is prompted to express his/her beliefs by building own discipline-related ontology through an application displayed in the interface of Moodle. This paper presents the ontology for an e-Learning System, which arranges metadata, and defines the relationships of metadata, which are about learning objects; belong to academic courses and user profiles. This ontology has been incorporated as a critical part of the proposed architecture. By this ontology, effective retrieval of learning content, customizing Learning Management System (LMS) is expected. Metadata used in this paper are based on current metadata standards. This ontology specified in human and machine-readable formats. In implementing it, several APIs were defined to manage the ontology. They were introduced into a typical LMS such as Moodle. Proposed ontology maps user preferences with learning content to satisfy learner requirements. These learning objects are presented to the learner based on ontological relationships. Hence it increases the usability and customizes the LMS. In conclusion, ontologies have a range of potential benefits and applications in further and higher education, including the sharing of information across e-learning systems, providing frameworks for learning object reuse, and enabling information between learner and system parts.
This document discusses online teaching and learning. It begins by defining online learning as instruction delivered over the internet by faculty, which can be synchronous (real-time) or asynchronous (anytime access). It then discusses the advantages of online learning for both students and teachers, such as flexible access, use of multimedia, and opportunities for collaborative work. Challenges of online teaching are also addressed, like maintaining student engagement and providing timely feedback. Overall assessments in online courses need to evaluate not just tests but also student interaction through discussions and group projects.
This document is a student paper analyzing the potential use of e-learning in a company. It finds that the company and its employees are prepared for e-learning based on technological skills. The paper recommends a two-stage e-learning system starting with enhancing current training and later adding equipment. Potential benefits identified include reducing travel costs and expanding training reach. Challenges like resistance and technology changes are also addressed.
Open Education Bridging the Gap Inequality of Higher Education opportunityIJRESJOURNAL
ABSTRACT: E-learning system through a variety of applications can encourage the realization of the ideals of education to provide equality of opportunity to all society. The essence of open education is to eliminate the limitations to be able to gain access to higher education for the community at large. Success story of online tutorial services of Universitas Terbuka (UT/Open University) is a proof that can demonstrate more efficient delivery of educational achievement. Perceived satisfaction of students to the online tutorial services became evident that the optimal use of technology to bridge the establishment of an optimal learning process so that students can obtain a quality education is not inferior to conventional universities. This condition will be able to change the paradigm of society that the opportunity to obtain higher education which was originally impossible becomes possible, which is easy, comfortable, flexible and affordable.
This document summarizes a study that examined the effect of using web applications in college classrooms on teaching, learning, and academic performance among female students in Saudi Arabia. The study found that female students were more interested in learning and performed better when using web applications like Google Apps in the classroom during and after classes. These applications provided an effective way to manage educational activities inside and outside the classroom for both teachers and students. The study concluded that web applications can help promote the classroom learning environment.
From Access To Success: Improving The Higher Education Learning Experience Fo...Helen Farley
Higher education institutions are increasingly relying on digital technologies that require internet access to support learning and teaching, particularly from a distance. Disadvantaged student groups that do not have access to the internet, such as incarcerated students, are often excluded as a result. This paper reports on a project that will develop and trial a sustainable and innovative learning management system (LMS) called Stand-Alone Moodle (SAM) that is able to operate without internet access. SAM will enable institutions to provide these students with similar course materials, activities and support available to other students, thereby improving the quality of the student learning experience. SAM will be trialled within a Queensland correctional centre and evaluated using a design-based research methodology. The findings and recommendations from the project will be disseminated to learning institutions and correctional centres across Australia to encourage equitable access to education for disadvantaged students. The digital literacies of staff and students, the maintenance of the technology and sufficient access to computer labs all had to be accommodated within the design of the project.
Based on the experience of using the “Moodle”, the application of new ontology-based intelligent information technologies is proposed. In the article, proposed is a new e-learning information technology based on an ontology driven learning engine, which is matched with modern pedagogical technologies. With the help of proposed engine and developed question database we have conducted an experiment, where students were tested. The developed ontology driven system of e-learning facilitates the creation of favorable conditions for the development of personal qualities and creation of a holistic understanding of the subject area among students throughout the educational process.
Using Ontology in Electronic Evaluation for Personalization of eLearning Systemsinfopapers
I. Pah, F. Stoica, L. F. Cacovean, E. M. Popa, Using Ontology in Electronic Evaluation for Personalization of eLearning Systems, Proceedings of the 8th WSEAS International Conference on APPLIED INFORMATICS and COMMUNICATIONS (AIC’08), Rhodes, Greece, August 20-22, ISSN: 1790-5109, ISBN: 978-960-6766-94-7, pp. 332-337, 2008
This study examined engineering students' perceptions of online learning through their university's learning
management system (LMS) compared to free online LMS and web tools allowing blended learning. A survey of 21
students found that they preferred free tools over the university's LMS, accessing resources on Blendspace more than
80% of the time. Interviews with instructors also revealed a preference for more interactive free tools over the limited
LMS. However, both students and instructors noted that slow internet connectivity hindered effective technology
use. While students felt more engaged through e-learning, most still preferred face-to-face learning.
The document discusses the potential of e-learning to address challenges facing higher education in Sub-Saharan Africa. It outlines how e-learning can increase access, improve quality of instruction, and control costs for institutions. While e-learning adoption is still developing, it presents opportunities if issues around infrastructure, skills, and mindsets are addressed. The document also anticipates that e-learning will transform higher education delivery by complementing traditional methods and allowing more flexible learning options.
International Journal of Engineering and Science Invention (IJESI)inventionjournals
International Journal of Engineering and Science Invention (IJESI) is an international journal intended for professionals and researchers in all fields of computer science and electronics. IJESI publishes research articles and reviews within the whole field Engineering Science and Technology, new teaching methods, assessment, validation and the impact of new technologies and it will continue to provide information on the latest trends and developments in this ever-expanding subject. The publications of papers are selected through double peer reviewed to ensure originality, relevance, and readability. The articles published in our journal can be accessed online
Training Informatics Teachers in Managing ICT Facilities in SchoolsChrysanthi Tziortzioti
The document summarizes a study that assessed a training project for 3,200 informatics teachers in Greece. The project aimed to provide teachers with new ICT knowledge and skills to manage school computer facilities. It used a blended learning approach combining workshops, in-school training, and online sessions. Based on survey responses from 1,270 teachers:
- Teachers responded most positively to the in-school training and workshops compared to the online components.
- They were very satisfied with the trainers' expertise and support.
- Suggestions for improvement included offering more practical and flexible content, and addressing technological issues for the online training.
- Overall teachers were satisfied with the blended learning approach and interested in future similar courses.
Applying Web-Enabled Problem-Based Learning and Self-Regulated Learning to Ad...nadiashaharil
This document summarizes a study that applied web-enabled problem-based learning (PBL) and self-regulated learning (SRL) approaches to a computing education course in Taiwan's vocational schools. The instructor redesigned the course and conducted experiments applying PBL, SRL, and their combinations to examine their effects. Survey results found that the web-enabled pedagogies had mostly positive impacts on students and reinforced the instructor's confidence in further applying them. The study provides valuable experience for other instructors looking to implement innovative instructional designs and e-learning.
Gamification Strategies in a Hybrid Exemplary College CourseSzymon Machajewski
Using technology in teaching and learning finds a wide adoption in recent years. 63.3% of chief academic leaders surveyed by the Babson Survey Research Group confirm that online education is critical to their long-term strategy. Modern engagement pedagogies, such as digital gamification, hold a promise of shaping student experience. While course builders and instructors investigate new technologies and teaching methods questions arise about the instructional quality of academic courses with online content or with gamification elements. In addition, students are not the digital natives many hoped them to be. 83% of millennials report sleeping with their smartphones, but 58% have poor skills in solving problems with technology. This paper reports on a gamefully designed course, delivered in a hybrid modality, which was selected through a peer review process as an exemplary course in consideration of instructional design. The course was evaluated according to the Blackboard Exemplary Course Program rubric. Gamification was introduced in three phases: player onboarding phase, player scaffolding phase, and player endgame. Various technologies involved in the course included: MyGame gamification mobile app, Blackboard Learn, Cengage Skills Assessment Manager, Kahoot, Amazon Alexa, Google Traveler, Twitter, and others. The course focused on gamification according to the short and long game theory to engage students during lectures (short game) and throughout the semester (long game).
E-Learning Project Write Up Case Study Ogun State Institute Of Technologydamilola isaac
Over the last decade, researchers and practitioners have developed a wide range of knowledge related to electronic learning or e-learning. This movement has affected different elements and components; infrastructures, tools, content-oriented applications, human-computer interactions, pedagogical issues, methodologies and models, case studies and projects. This chapter briefly describes the overall idea of the development of e-learning system for OGITECH by using Apache, PHP and MySQL. This chapter includes objectives of the project, scope of work, problem statement and features of project before developed the own sites.
E-Learning has its historical background in about 30 years of development in computer based on the training and education. With the growth of the internet this kind of training became much more accepted and the creation of multimedia contents and systems to manage learning activities went on faster. Additional e-learning is based on a long tradition of teaching and learning experience. The larger worlds Information Technology and Education and Training influenced the new term e-learning and so e-learning became a subset of both of them.
Nowadays, e-learning refers to learning that is delivered or enabled via electronic technology. It encompasses learning delivered via a range of technologies such as the internet, television, videotape, and computer-based training. In principle, e-learning is a kind of distance learning. Learning materials can be accessed from the web or intranet via a computer and tutors and learners can communicate with each other using e-mail, chat or discussion forums.
Therefore, it can be used as the main method of delivery of training or as a combined approach with classroom-based training. It can be valuable when used as a part of well-planned and properly supported education and training environment, but e-learning is not a magic bullet that replaces existing pedagogical theories and approaches.
Nevertheless, it has almost everything that those theories need to get implemented.
Many learning and technology professionals believe that e-learning will have become state of the art when we will stop referring to it by a separate name and begin considering it as an integral part of a complete learning environment.
How can high quality “on-line teaching” be guaranteed in a business school context? Under what conditions can “on-line teaching” be a satisfactory substitute for traditional face-to-face teaching? Or is a combination of the two the most effective option for executive education?”
E-teaching is an innovative teaching strategy
using the e-learning technology to empower both learners and
teachers thus providing opportunities for superior learning
experiences. The study enhances the education practice of those
teachers handling different graduate programs specifically
those offered by Lyceum of the Philippines University -
Batangas. This study focused on assessing and analyzing the
different important factors pertaining to the readiness and
inclination of the teachers. This involves introduction of
e-teaching on the part of the teachers and e-learning on the part
of the graduate students to their respective programs of study.
The findings revealed that the graduate school teachers are
aware of their vital role in developing effective delivery of
instruction and their openness on the active participation in
conducting classes in an online learning environment. Also, the
university is ready to take the e-teaching program as a mode of
instruction for the Graduate School.
E-learning in Medical Education and Blended Learning Approach discusses the history and applications of e-learning in medical education. It begins by explaining how education has shifted from teacher-centered to learner-centered and how e-learning can improve learning outcomes. E-learning uses technology like the internet to provide educational resources beyond the classroom. While e-learning has advantages, traditional learning still has benefits. The document then reviews the history of using computers in medical education from the 1960s onward. It describes different modes of e-learning delivery and applications in medical education today.
In the current digital era, education system has witness tremendous growth in data storage and efficient retrieval. Many Institutes have very huge databases which may be of terabytes of knowledge and information. The complexity of the data is an important issue as educational data consists of structural as well as non-structural type which includes various text editors like node pad, word, PDF files, images, video, etc. The problem lies in proper storage and correct retrieval of this information. Different types of learning platform like Moodle have implemented to integrate the requirement of educators, administrators and learner. Although this type of platforms are indeed a great support of educators, still mining of the large data is required to uncover various interesting patterns and facts for decision making process for the benefits of the students. In this research work, different data mining classification models are applied to analyse and predict students’ feedback based on their Moodle usage data. The models described in this paper surely assist the educators, decision maker, mentors to early engage with the issues as address by students. In this research, real data from a semester has been experimented and evaluated. To achieve the better classification models, discretization and weight adjustment techniques have also been applied as part of the pre – processing steps. Finally, we conclude that for efficient decision making with the student’s feedback the classifier model must be appropriate in terms of accuracy and other important evaluation measures. Our experiments also shows that by using weight adjustment techniques like information gain and support vector machines improves the performance of classification models.
In the current digital era, education system has witness tremendous growth in data storage and efficient retrieval. Many Institutes have very huge databases which may be of terabytes of knowledge and information. The complexity of the data is an important issue as educational data consists of structural as well as non-structural type which includes various text editors like node pad, word, PDF files, images, video, etc. The problem lies in proper storage and correct retrieval of this information. Different types of learning platform like Moodle have implemented to integrate the requirement of educators, administrators and learner. Although this type of platforms are indeed a great support of educators, still mining of the large data is required to uncover various interesting patterns and facts for decision making process for the
benefits of the students.
The e-learning contained many educational resources are generally used in learning systems like Moodle, It’s free open source software packages designed and flexible platform to create Learning Objects (LOs) and users’ accounts. The author demonstrates how to use semantic web technologies to improve online learning environments and bridge the gap between learners and LOs. The ontological construction presented here helps formalize LOs context as a complex interplay of different learning-related elements and shows how we can use semantic annotation to interrelate diverse between learner and LOs. On top of this construction, the author implemented several feedback channels for educators to improve the delivery of future Web-based learning. The particular aim of this paper was to provide a solution based in the Moodle Platform. The main idea behind the approach presented here is that ontology which can not only be useful as a learning instrument but it can also be employed to assess students’ skills. For it, each student is prompted to express his/her beliefs by building own discipline-related ontology through an application displayed in the interface of Moodle. This paper presents the ontology for an e-Learning System, which arranges metadata, and defines the relationships of metadata, which are about learning objects; belong to academic courses and user profiles. This ontology has been incorporated as a critical part of the proposed architecture. By this ontology, effective retrieval of learning content, customizing Learning Management System (LMS) is expected. Metadata used in this paper are based on current metadata standards. This ontology specified in human and machine-readable formats. In implementing it, several APIs were defined to manage the ontology. They were introduced into a typical LMS such as Moodle. Proposed ontology maps user preferences with learning content to satisfy learner requirements. These learning objects are presented to the learner based on ontological relationships. Hence it increases the usability and customizes the LMS. In conclusion, ontologies have a range of potential benefits and applications in further and higher education, including the sharing of information across e-learning systems, providing frameworks for learning object reuse, and enabling information between learner and system parts.
This document discusses online teaching and learning. It begins by defining online learning as instruction delivered over the internet by faculty, which can be synchronous (real-time) or asynchronous (anytime access). It then discusses the advantages of online learning for both students and teachers, such as flexible access, use of multimedia, and opportunities for collaborative work. Challenges of online teaching are also addressed, like maintaining student engagement and providing timely feedback. Overall assessments in online courses need to evaluate not just tests but also student interaction through discussions and group projects.
This document is a student paper analyzing the potential use of e-learning in a company. It finds that the company and its employees are prepared for e-learning based on technological skills. The paper recommends a two-stage e-learning system starting with enhancing current training and later adding equipment. Potential benefits identified include reducing travel costs and expanding training reach. Challenges like resistance and technology changes are also addressed.
Open Education Bridging the Gap Inequality of Higher Education opportunityIJRESJOURNAL
ABSTRACT: E-learning system through a variety of applications can encourage the realization of the ideals of education to provide equality of opportunity to all society. The essence of open education is to eliminate the limitations to be able to gain access to higher education for the community at large. Success story of online tutorial services of Universitas Terbuka (UT/Open University) is a proof that can demonstrate more efficient delivery of educational achievement. Perceived satisfaction of students to the online tutorial services became evident that the optimal use of technology to bridge the establishment of an optimal learning process so that students can obtain a quality education is not inferior to conventional universities. This condition will be able to change the paradigm of society that the opportunity to obtain higher education which was originally impossible becomes possible, which is easy, comfortable, flexible and affordable.
This document summarizes a study that examined the effect of using web applications in college classrooms on teaching, learning, and academic performance among female students in Saudi Arabia. The study found that female students were more interested in learning and performed better when using web applications like Google Apps in the classroom during and after classes. These applications provided an effective way to manage educational activities inside and outside the classroom for both teachers and students. The study concluded that web applications can help promote the classroom learning environment.
From Access To Success: Improving The Higher Education Learning Experience Fo...Helen Farley
Higher education institutions are increasingly relying on digital technologies that require internet access to support learning and teaching, particularly from a distance. Disadvantaged student groups that do not have access to the internet, such as incarcerated students, are often excluded as a result. This paper reports on a project that will develop and trial a sustainable and innovative learning management system (LMS) called Stand-Alone Moodle (SAM) that is able to operate without internet access. SAM will enable institutions to provide these students with similar course materials, activities and support available to other students, thereby improving the quality of the student learning experience. SAM will be trialled within a Queensland correctional centre and evaluated using a design-based research methodology. The findings and recommendations from the project will be disseminated to learning institutions and correctional centres across Australia to encourage equitable access to education for disadvantaged students. The digital literacies of staff and students, the maintenance of the technology and sufficient access to computer labs all had to be accommodated within the design of the project.
Based on the experience of using the “Moodle”, the application of new ontology-based intelligent information technologies is proposed. In the article, proposed is a new e-learning information technology based on an ontology driven learning engine, which is matched with modern pedagogical technologies. With the help of proposed engine and developed question database we have conducted an experiment, where students were tested. The developed ontology driven system of e-learning facilitates the creation of favorable conditions for the development of personal qualities and creation of a holistic understanding of the subject area among students throughout the educational process.
Using Ontology in Electronic Evaluation for Personalization of eLearning Systemsinfopapers
I. Pah, F. Stoica, L. F. Cacovean, E. M. Popa, Using Ontology in Electronic Evaluation for Personalization of eLearning Systems, Proceedings of the 8th WSEAS International Conference on APPLIED INFORMATICS and COMMUNICATIONS (AIC’08), Rhodes, Greece, August 20-22, ISSN: 1790-5109, ISBN: 978-960-6766-94-7, pp. 332-337, 2008
This study examined engineering students' perceptions of online learning through their university's learning
management system (LMS) compared to free online LMS and web tools allowing blended learning. A survey of 21
students found that they preferred free tools over the university's LMS, accessing resources on Blendspace more than
80% of the time. Interviews with instructors also revealed a preference for more interactive free tools over the limited
LMS. However, both students and instructors noted that slow internet connectivity hindered effective technology
use. While students felt more engaged through e-learning, most still preferred face-to-face learning.
The document discusses the potential of e-learning to address challenges facing higher education in Sub-Saharan Africa. It outlines how e-learning can increase access, improve quality of instruction, and control costs for institutions. While e-learning adoption is still developing, it presents opportunities if issues around infrastructure, skills, and mindsets are addressed. The document also anticipates that e-learning will transform higher education delivery by complementing traditional methods and allowing more flexible learning options.
International Journal of Engineering and Science Invention (IJESI)inventionjournals
International Journal of Engineering and Science Invention (IJESI) is an international journal intended for professionals and researchers in all fields of computer science and electronics. IJESI publishes research articles and reviews within the whole field Engineering Science and Technology, new teaching methods, assessment, validation and the impact of new technologies and it will continue to provide information on the latest trends and developments in this ever-expanding subject. The publications of papers are selected through double peer reviewed to ensure originality, relevance, and readability. The articles published in our journal can be accessed online
Training Informatics Teachers in Managing ICT Facilities in SchoolsChrysanthi Tziortzioti
The document summarizes a study that assessed a training project for 3,200 informatics teachers in Greece. The project aimed to provide teachers with new ICT knowledge and skills to manage school computer facilities. It used a blended learning approach combining workshops, in-school training, and online sessions. Based on survey responses from 1,270 teachers:
- Teachers responded most positively to the in-school training and workshops compared to the online components.
- They were very satisfied with the trainers' expertise and support.
- Suggestions for improvement included offering more practical and flexible content, and addressing technological issues for the online training.
- Overall teachers were satisfied with the blended learning approach and interested in future similar courses.
Applying Web-Enabled Problem-Based Learning and Self-Regulated Learning to Ad...nadiashaharil
This document summarizes a study that applied web-enabled problem-based learning (PBL) and self-regulated learning (SRL) approaches to a computing education course in Taiwan's vocational schools. The instructor redesigned the course and conducted experiments applying PBL, SRL, and their combinations to examine their effects. Survey results found that the web-enabled pedagogies had mostly positive impacts on students and reinforced the instructor's confidence in further applying them. The study provides valuable experience for other instructors looking to implement innovative instructional designs and e-learning.
Gamification Strategies in a Hybrid Exemplary College CourseSzymon Machajewski
Using technology in teaching and learning finds a wide adoption in recent years. 63.3% of chief academic leaders surveyed by the Babson Survey Research Group confirm that online education is critical to their long-term strategy. Modern engagement pedagogies, such as digital gamification, hold a promise of shaping student experience. While course builders and instructors investigate new technologies and teaching methods questions arise about the instructional quality of academic courses with online content or with gamification elements. In addition, students are not the digital natives many hoped them to be. 83% of millennials report sleeping with their smartphones, but 58% have poor skills in solving problems with technology. This paper reports on a gamefully designed course, delivered in a hybrid modality, which was selected through a peer review process as an exemplary course in consideration of instructional design. The course was evaluated according to the Blackboard Exemplary Course Program rubric. Gamification was introduced in three phases: player onboarding phase, player scaffolding phase, and player endgame. Various technologies involved in the course included: MyGame gamification mobile app, Blackboard Learn, Cengage Skills Assessment Manager, Kahoot, Amazon Alexa, Google Traveler, Twitter, and others. The course focused on gamification according to the short and long game theory to engage students during lectures (short game) and throughout the semester (long game).
E-Learning Project Write Up Case Study Ogun State Institute Of Technologydamilola isaac
Over the last decade, researchers and practitioners have developed a wide range of knowledge related to electronic learning or e-learning. This movement has affected different elements and components; infrastructures, tools, content-oriented applications, human-computer interactions, pedagogical issues, methodologies and models, case studies and projects. This chapter briefly describes the overall idea of the development of e-learning system for OGITECH by using Apache, PHP and MySQL. This chapter includes objectives of the project, scope of work, problem statement and features of project before developed the own sites.
E-Learning has its historical background in about 30 years of development in computer based on the training and education. With the growth of the internet this kind of training became much more accepted and the creation of multimedia contents and systems to manage learning activities went on faster. Additional e-learning is based on a long tradition of teaching and learning experience. The larger worlds Information Technology and Education and Training influenced the new term e-learning and so e-learning became a subset of both of them.
Nowadays, e-learning refers to learning that is delivered or enabled via electronic technology. It encompasses learning delivered via a range of technologies such as the internet, television, videotape, and computer-based training. In principle, e-learning is a kind of distance learning. Learning materials can be accessed from the web or intranet via a computer and tutors and learners can communicate with each other using e-mail, chat or discussion forums.
Therefore, it can be used as the main method of delivery of training or as a combined approach with classroom-based training. It can be valuable when used as a part of well-planned and properly supported education and training environment, but e-learning is not a magic bullet that replaces existing pedagogical theories and approaches.
Nevertheless, it has almost everything that those theories need to get implemented.
Many learning and technology professionals believe that e-learning will have become state of the art when we will stop referring to it by a separate name and begin considering it as an integral part of a complete learning environment.
How can high quality “on-line teaching” be guaranteed in a business school context? Under what conditions can “on-line teaching” be a satisfactory substitute for traditional face-to-face teaching? Or is a combination of the two the most effective option for executive education?”
E-teaching is an innovative teaching strategy
using the e-learning technology to empower both learners and
teachers thus providing opportunities for superior learning
experiences. The study enhances the education practice of those
teachers handling different graduate programs specifically
those offered by Lyceum of the Philippines University -
Batangas. This study focused on assessing and analyzing the
different important factors pertaining to the readiness and
inclination of the teachers. This involves introduction of
e-teaching on the part of the teachers and e-learning on the part
of the graduate students to their respective programs of study.
The findings revealed that the graduate school teachers are
aware of their vital role in developing effective delivery of
instruction and their openness on the active participation in
conducting classes in an online learning environment. Also, the
university is ready to take the e-teaching program as a mode of
instruction for the Graduate School.
E-learning in Medical Education and Blended Learning Approach discusses the history and applications of e-learning in medical education. It begins by explaining how education has shifted from teacher-centered to learner-centered and how e-learning can improve learning outcomes. E-learning uses technology like the internet to provide educational resources beyond the classroom. While e-learning has advantages, traditional learning still has benefits. The document then reviews the history of using computers in medical education from the 1960s onward. It describes different modes of e-learning delivery and applications in medical education today.
In the current digital era, education system has witness tremendous growth in data storage and efficient retrieval. Many Institutes have very huge databases which may be of terabytes of knowledge and information. The complexity of the data is an important issue as educational data consists of structural as well as non-structural type which includes various text editors like node pad, word, PDF files, images, video, etc. The problem lies in proper storage and correct retrieval of this information. Different types of learning platform like Moodle have implemented to integrate the requirement of educators, administrators and learner. Although this type of platforms are indeed a great support of educators, still mining of the large data is required to uncover various interesting patterns and facts for decision making process for the benefits of the students. In this research work, different data mining classification models are applied to analyse and predict students’ feedback based on their Moodle usage data. The models described in this paper surely assist the educators, decision maker, mentors to early engage with the issues as address by students. In this research, real data from a semester has been experimented and evaluated. To achieve the better classification models, discretization and weight adjustment techniques have also been applied as part of the pre – processing steps. Finally, we conclude that for efficient decision making with the student’s feedback the classifier model must be appropriate in terms of accuracy and other important evaluation measures. Our experiments also shows that by using weight adjustment techniques like information gain and support vector machines improves the performance of classification models.
In the current digital era, education system has witness tremendous growth in data storage and efficient retrieval. Many Institutes have very huge databases which may be of terabytes of knowledge and information. The complexity of the data is an important issue as educational data consists of structural as well as non-structural type which includes various text editors like node pad, word, PDF files, images, video, etc. The problem lies in proper storage and correct retrieval of this information. Different types of learning platform like Moodle have implemented to integrate the requirement of educators, administrators and learner. Although this type of platforms are indeed a great support of educators, still mining of the large data is required to uncover various interesting patterns and facts for decision making process for the
benefits of the students.
Instructional Technology Trends in Education discusses emerging trends in educational technology including increased use of mobile devices, open-source content competing with textbooks, and educators connecting through social media. It also examines the growing interest in online learning communities for teachers and the role of virtual learning environments and systems in facilitating distance and on-campus learning. Specific examples from Malaysia are provided on the Frog Virtual Learning Environment being implemented nationwide to improve education.
A Survey on E-Learning System with Data MiningIIRindia
E-learning process has been widely used in university campus and educational institutions are playing vital role to enhance the skill set of students. Modern E-learning done by many electronic devices, such as smartphones, Tabs, and so on, on existing E-learning tools is insufficient to achieve the purpose of online training of education. This paper presents a survey of online e-Learning authoring tools for creating and integrating reusable e-learning tool for generation and enhancing existing learning resources with them. The work concentrates on evaluation of the existing e-learning tools a, and authoring tools that have shown good performance in the past for online learners. This survey work takes more than 20 online tools that deal with the educational sector mechanism, for the purpose of observations, and the outcome were analyzed. The findings of this paper are the main reason for developing a new tool, and it shows that educators can enhance existing learning resources by adding assessment resources, if suitable authoring tools are provided. Finally, the different factors that assure the reusability of the created new e-learning tool has been analysed in this paper.E-learning environment is a guide for both students and tutorial management system. The useful on the e-learning system for apart from students and distance learning students. The purpose of using e-learning environment for online education system, developed in data mining for more number of clustering servers and resource chain has been good.
A Framework For A Cyber Classroom Towards A Human-Centric Virtual ClassroomMichele Thomas
This document describes a project called the Dynamic Education project that aimed to reduce the information gap between on-campus and off-campus students. The project was conducted over three phases: Phase 1 focused on capturing classroom teaching digitally; Phase 2 aimed to increase student interaction; and Phase 3 sought to develop a fully virtual human-centric classroom. Outcomes of Phase 1 showed capturing classroom sessions was time-consuming, and technologies like tablet PCs were most effective for digital note-taking while lecturing. The goal of reducing information inequities between on- and off-campus students guided the project.
This document discusses blended learning in higher education institutions in Malaysia. It begins by explaining the limitations of traditional classroom learning and pure online learning. Blended learning combines the strengths of face-to-face and online learning. The document then provides background on higher education in Malaysia, including the growth of online programs. It explains how universities are implementing information and communication technologies but still lack strategic plans for online learning. The benefits of blended learning are that it addresses constraints of both traditional and online-only methods.
An Evaluation Of The Effectiveness Of Online EducationSarah Morrow
This document evaluates the effectiveness of online education compared to traditional classroom teaching. It finds that online education has several advantages, including flexibility, a wider choice of programs, and lower costs. However, it also has disadvantages such as requirements for computer literacy and reliable internet access. During the COVID-19 pandemic, online learning was effective in allowing education to continue when classrooms were closed. While some aspects of traditional teaching are lost online, the advantages of online education allow more students to access higher education. Overall, online learning is found to be an effective alternative to classroom teaching that can help fill gaps in traditional education systems.
This document summarizes a literature review that analyzed research predicting student performance and dropout rates using machine learning techniques. The review identified 78 relevant papers published between 2009-2021. These papers mostly used student data from universities and MOOC platforms to test machine learning classifiers for predicting at-risk students and dropout likelihood. The review found that machine learning methods effectively predicted student performance and helped universities develop intervention strategies to improve student outcomes.
A Systematic Literature Review Of Student Performance Prediction Using Machi...Angie Miller
This document summarizes a systematic literature review of research predicting student performance using machine learning techniques. The review examined studies from 2009 to 2021 that identified students at risk of dropping out. It found that various machine learning methods were used to understand challenges and predict performance. Most studies used data from university databases and online learning platforms. Machine learning was shown to effectively predict student risk levels and dropout rates, helping improve student outcomes.
This document discusses predicting student performance in higher education using video learning analytics and data mining techniques. The study analyzed data from 772 students' interactions in an LMS, student information system, and mobile video application to predict end-of-semester performance. Eight classification algorithms were tested on the data, along with feature selection techniques like genetic search and principle component analysis. The Random Forest algorithm most accurately predicted student performance at 88.3% accuracy using an equal width feature selection method. The results indicate that analyzing interaction data from multiple systems using classification techniques can help predict student outcomes.
This document discusses predicting student performance in higher education using video learning analytics and data mining techniques. The study analyzed data from 772 students' interactions in an LMS, student information system, and mobile video application to predict end-of-semester performance. Eight classification algorithms were tested and random forest accurately predicted successful students 88.3% of the time. Feature selection techniques like genetic search and principle component analysis were also able to further improve performance. The results suggest video learning analytics combined with data mining can help educators identify at-risk students and improve learning outcomes.
This document discusses predicting student performance in higher education using video learning analytics and data mining techniques. The study analyzed data from 772 students' interactions in an LMS, student information system, and mobile video application to predict end-of-semester performance. Eight classification algorithms were tested and random forest accurately predicted successful students 88.3% of the time. Feature selection techniques like genetic search and principle component analysis were also able to further improve performance. The results suggest video learning analytics combined with data mining can help educators identify at-risk students and make decisions to improve student success.
Designing An Effective Mobile-learning Model By Integrating Student CultureCSCJournals
Mobile learning is a good technology because it allows communication, collaboration, and sharing information or resources among all of learning members. Mobile learning can be used as perfect solutions to support the learning process. Thither are many concepts and factors influencing effective learning results through creativity, collaboration, and communication. However, culture is an unaccounted factor which should be appended to the existing M-learning model. Culture may improve the learning outcomes of students. We would like to research on how to design an effective model by integrating culture to maximize the benefits of mobile learning.
Secondary schools collect and manage various types of LMS data to improve teaching and learning. Data regarding learning materials, assessments, student interactions and course/learner information is gathered from LMS platforms like Moodle and Blackboard. Schools store this data through centralized databases and learning management systems to track student progress, identify at-risk students, and guide curriculum improvements. However, effective use of LMS data raises privacy and ethical issues that schools must address regarding responsible data usage and student consent.
The document discusses using ontologies and semantic web technologies to improve matching between learning objects and user preferences in e-learning systems like Moodle. It proposes building an ontology to semantically annotate learning objects and user profiles, then using that ontology to more effectively retrieve and customize learning content for each user. The author implemented this approach in Moodle to automatically manage course registration based on various student factors represented in the ontology. The goal is to make the learning process more personalized and improve tracking of student progress.
A B-Learning Case Study In Computer NetworksTony Lisko
This document presents a case study of implementing a blended learning (b-learning) approach in a computer networks course at a university in Portugal over nine years. B-learning combines online learning with face-to-face instruction to address challenges of traditional and online-only methods. The case study found that b-learning improved student learning outcomes and engagement. It also gained experience that could be applied to other growing fields. Future research is needed to further address challenges of ensuring consistency across learning environments and mitigating infrastructure problems in b-learning implementations.
Multimodal Course Design and Implementation using LEML and LMS for Instructio...IJMIT JOURNAL
Traditionally, teaching has been centered around classroom delivery. However, the onslaught of the
COVID-19 pandemic has cultivated usage of technology, teaching, and learning methodologies for course
delivery. We investigate and describe different modes of course delivery that maintain the integrity of
teaching and learning. This paper answers to the research questions: 1) What course delivery method our
academic institutions use and why? 2) How can instructors validate the guidelines of the institutions? 3)
How courses should be taught to provide student learning outcomes? Using the Learning Environment
Modeling Language (LEML), we investigate the design and implementation of courses for delivery in the
following environments: face-to-face, online synchronous, asynchronous, hybrid, and hyflex. A good
course design and implementation are key components of instructional alignment. Furthermore, we
demonstrate how to design, implement, and deliver courses in synchronous, asynchronous, and hybrid
modes and describe our proposed enhancements to LEML.
MULTIMODAL COURSE DESIGN AND IMPLEMENTATION USING LEML AND LMS FOR INSTRUCTIO...IJMIT JOURNAL
The document discusses course delivery modalities including face-to-face, online asynchronous, online synchronous, hybrid, and HyFlex. It investigates the design and implementation of courses using the Learning Environment Modeling Language (LEML) for different delivery environments. The authors describe their experience delivering courses at Southern University and A&M College and Baton Rouge Community College. They aim to answer questions about the course delivery methods used by their institutions and how to validate guidelines and ensure student learning outcomes.
MULTIMODAL COURSE DESIGN AND IMPLEMENTATION USING LEML AND LMS FOR INSTRUCTIO...IJMIT JOURNAL
Traditionally, teaching has been centered around classroom delivery. However, the onslaught of the
COVID-19 pandemic has cultivated usage of technology, teaching, and learning methodologies for course
delivery. We investigate and describe different modes of course delivery that maintain the integrity of
teaching and learning. This paper answers to the research questions: 1) What course delivery method our
academic institutions use and why? 2) How can instructors validate the guidelines of the institutions? 3)
How courses should be taught to provide student learning outcomes? Using the Learning Environment
Modeling Language (LEML), we investigate the design and implementation of courses for delivery in the
following environments: face-to-face, online synchronous, asynchronous, hybrid, and hyflex. A good
course design and implementation are key components of instructional alignment. Furthermore, we
demonstrate how to design, implement, and deliver courses in synchronous, asynchronous, and hybrid
modes and describe our proposed enhancements to LEML.
Predicting students’ intention to continue business courses on online platfor...Samsul Alam
The objective of this study was to analyze the intention of a University's business department students to continue their studies on e-learning platforms during the ongoing COVID-19 pandemic. To this end, a questionnaire was developed to collect primary data from students in business fields. The study took into account more than 285 respondents from two different universities and relied on the expectation confirmation model (ECM) theory and the structural equation model. The partial least squares (SEM-PLS) method was used to analyze the data. The results of the study showed that task skills (TS) and task challenges (TC) were significant for the enjoyment (EN) of the students which in turn had a positive effect on the satisfaction levels. Confirmation (CON) had an impact on the post adoption perceived usefulness (PAPU), which was deemed positive for student satisfaction (SAT). The SAT and psychological safety (PS) of online learning platforms were found to positively influence the continuance intention (CI) on e-learning platforms. Finally, both SAT and PS of online learning platforms were observed to positively influence CI on e-learning platforms. Further research in this area could be useful in making decisions about promoting educational programs based on e-learning. The researchers recommend that academicians and policymakers must ensure appropriate arrangements for teaching on e-learning platforms.
Similar to Neural Network Model for Predicting Students' Achievement in Blended Courses at the University of Dar Es Salaam (20)
5th LF Energy Power Grid Model Meet-up SlidesDanBrown980551
5th Power Grid Model Meet-up
It is with great pleasure that we extend to you an invitation to the 5th Power Grid Model Meet-up, scheduled for 6th June 2024. This event will adopt a hybrid format, allowing participants to join us either through an online Mircosoft Teams session or in person at TU/e located at Den Dolech 2, Eindhoven, Netherlands. The meet-up will be hosted by Eindhoven University of Technology (TU/e), a research university specializing in engineering science & technology.
Power Grid Model
The global energy transition is placing new and unprecedented demands on Distribution System Operators (DSOs). Alongside upgrades to grid capacity, processes such as digitization, capacity optimization, and congestion management are becoming vital for delivering reliable services.
Power Grid Model is an open source project from Linux Foundation Energy and provides a calculation engine that is increasingly essential for DSOs. It offers a standards-based foundation enabling real-time power systems analysis, simulations of electrical power grids, and sophisticated what-if analysis. In addition, it enables in-depth studies and analysis of the electrical power grid’s behavior and performance. This comprehensive model incorporates essential factors such as power generation capacity, electrical losses, voltage levels, power flows, and system stability.
Power Grid Model is currently being applied in a wide variety of use cases, including grid planning, expansion, reliability, and congestion studies. It can also help in analyzing the impact of renewable energy integration, assessing the effects of disturbances or faults, and developing strategies for grid control and optimization.
What to expect
For the upcoming meetup we are organizing, we have an exciting lineup of activities planned:
-Insightful presentations covering two practical applications of the Power Grid Model.
-An update on the latest advancements in Power Grid -Model technology during the first and second quarters of 2024.
-An interactive brainstorming session to discuss and propose new feature requests.
-An opportunity to connect with fellow Power Grid Model enthusiasts and users.
Generating privacy-protected synthetic data using Secludy and MilvusZilliz
During this demo, the founders of Secludy will demonstrate how their system utilizes Milvus to store and manipulate embeddings for generating privacy-protected synthetic data. Their approach not only maintains the confidentiality of the original data but also enhances the utility and scalability of LLMs under privacy constraints. Attendees, including machine learning engineers, data scientists, and data managers, will witness first-hand how Secludy's integration with Milvus empowers organizations to harness the power of LLMs securely and efficiently.
In the rapidly evolving landscape of technologies, XML continues to play a vital role in structuring, storing, and transporting data across diverse systems. The recent advancements in artificial intelligence (AI) present new methodologies for enhancing XML development workflows, introducing efficiency, automation, and intelligent capabilities. This presentation will outline the scope and perspective of utilizing AI in XML development. The potential benefits and the possible pitfalls will be highlighted, providing a balanced view of the subject.
We will explore the capabilities of AI in understanding XML markup languages and autonomously creating structured XML content. Additionally, we will examine the capacity of AI to enrich plain text with appropriate XML markup. Practical examples and methodological guidelines will be provided to elucidate how AI can be effectively prompted to interpret and generate accurate XML markup.
Further emphasis will be placed on the role of AI in developing XSLT, or schemas such as XSD and Schematron. We will address the techniques and strategies adopted to create prompts for generating code, explaining code, or refactoring the code, and the results achieved.
The discussion will extend to how AI can be used to transform XML content. In particular, the focus will be on the use of AI XPath extension functions in XSLT, Schematron, Schematron Quick Fixes, or for XML content refactoring.
The presentation aims to deliver a comprehensive overview of AI usage in XML development, providing attendees with the necessary knowledge to make informed decisions. Whether you’re at the early stages of adopting AI or considering integrating it in advanced XML development, this presentation will cover all levels of expertise.
By highlighting the potential advantages and challenges of integrating AI with XML development tools and languages, the presentation seeks to inspire thoughtful conversation around the future of XML development. We’ll not only delve into the technical aspects of AI-powered XML development but also discuss practical implications and possible future directions.
How to Interpret Trends in the Kalyan Rajdhani Mix Chart.pdfChart Kalyan
A Mix Chart displays historical data of numbers in a graphical or tabular form. The Kalyan Rajdhani Mix Chart specifically shows the results of a sequence of numbers over different periods.
Salesforce Integration for Bonterra Impact Management (fka Social Solutions A...Jeffrey Haguewood
Sidekick Solutions uses Bonterra Impact Management (fka Social Solutions Apricot) and automation solutions to integrate data for business workflows.
We believe integration and automation are essential to user experience and the promise of efficient work through technology. Automation is the critical ingredient to realizing that full vision. We develop integration products and services for Bonterra Case Management software to support the deployment of automations for a variety of use cases.
This video focuses on integration of Salesforce with Bonterra Impact Management.
Interested in deploying an integration with Salesforce for Bonterra Impact Management? Contact us at sales@sidekicksolutionsllc.com to discuss next steps.
Your One-Stop Shop for Python Success: Top 10 US Python Development Providersakankshawande
Simplify your search for a reliable Python development partner! This list presents the top 10 trusted US providers offering comprehensive Python development services, ensuring your project's success from conception to completion.
Fueling AI with Great Data with Airbyte WebinarZilliz
This talk will focus on how to collect data from a variety of sources, leveraging this data for RAG and other GenAI use cases, and finally charting your course to productionalization.
Digital Marketing Trends in 2024 | Guide for Staying AheadWask
https://www.wask.co/ebooks/digital-marketing-trends-in-2024
Feeling lost in the digital marketing whirlwind of 2024? Technology is changing, consumer habits are evolving, and staying ahead of the curve feels like a never-ending pursuit. This e-book is your compass. Dive into actionable insights to handle the complexities of modern marketing. From hyper-personalization to the power of user-generated content, learn how to build long-term relationships with your audience and unlock the secrets to success in the ever-shifting digital landscape.
Main news related to the CCS TSI 2023 (2023/1695)Jakub Marek
An English 🇬🇧 translation of a presentation to the speech I gave about the main changes brought by CCS TSI 2023 at the biggest Czech conference on Communications and signalling systems on Railways, which was held in Clarion Hotel Olomouc from 7th to 9th November 2023 (konferenceszt.cz). Attended by around 500 participants and 200 on-line followers.
The original Czech 🇨🇿 version of the presentation can be found here: https://www.slideshare.net/slideshow/hlavni-novinky-souvisejici-s-ccs-tsi-2023-2023-1695/269688092 .
The videorecording (in Czech) from the presentation is available here: https://youtu.be/WzjJWm4IyPk?si=SImb06tuXGb30BEH .
UiPath Test Automation using UiPath Test Suite series, part 6DianaGray10
Welcome to UiPath Test Automation using UiPath Test Suite series part 6. In this session, we will cover Test Automation with generative AI and Open AI.
UiPath Test Automation with generative AI and Open AI webinar offers an in-depth exploration of leveraging cutting-edge technologies for test automation within the UiPath platform. Attendees will delve into the integration of generative AI, a test automation solution, with Open AI advanced natural language processing capabilities.
Throughout the session, participants will discover how this synergy empowers testers to automate repetitive tasks, enhance testing accuracy, and expedite the software testing life cycle. Topics covered include the seamless integration process, practical use cases, and the benefits of harnessing AI-driven automation for UiPath testing initiatives. By attending this webinar, testers, and automation professionals can gain valuable insights into harnessing the power of AI to optimize their test automation workflows within the UiPath ecosystem, ultimately driving efficiency and quality in software development processes.
What will you get from this session?
1. Insights into integrating generative AI.
2. Understanding how this integration enhances test automation within the UiPath platform
3. Practical demonstrations
4. Exploration of real-world use cases illustrating the benefits of AI-driven test automation for UiPath
Topics covered:
What is generative AI
Test Automation with generative AI and Open AI.
UiPath integration with generative AI
Speaker:
Deepak Rai, Automation Practice Lead, Boundaryless Group and UiPath MVP
TrustArc Webinar - 2024 Global Privacy SurveyTrustArc
How does your privacy program stack up against your peers? What challenges are privacy teams tackling and prioritizing in 2024?
In the fifth annual Global Privacy Benchmarks Survey, we asked over 1,800 global privacy professionals and business executives to share their perspectives on the current state of privacy inside and outside of their organizations. This year’s report focused on emerging areas of importance for privacy and compliance professionals, including considerations and implications of Artificial Intelligence (AI) technologies, building brand trust, and different approaches for achieving higher privacy competence scores.
See how organizational priorities and strategic approaches to data security and privacy are evolving around the globe.
This webinar will review:
- The top 10 privacy insights from the fifth annual Global Privacy Benchmarks Survey
- The top challenges for privacy leaders, practitioners, and organizations in 2024
- Key themes to consider in developing and maintaining your privacy program
Cosa hanno in comune un mattoncino Lego e la backdoor XZ?Speck&Tech
ABSTRACT: A prima vista, un mattoncino Lego e la backdoor XZ potrebbero avere in comune il fatto di essere entrambi blocchi di costruzione, o dipendenze di progetti creativi e software. La realtà è che un mattoncino Lego e il caso della backdoor XZ hanno molto di più di tutto ciò in comune.
Partecipate alla presentazione per immergervi in una storia di interoperabilità, standard e formati aperti, per poi discutere del ruolo importante che i contributori hanno in una comunità open source sostenibile.
BIO: Sostenitrice del software libero e dei formati standard e aperti. È stata un membro attivo dei progetti Fedora e openSUSE e ha co-fondato l'Associazione LibreItalia dove è stata coinvolta in diversi eventi, migrazioni e formazione relativi a LibreOffice. In precedenza ha lavorato a migrazioni e corsi di formazione su LibreOffice per diverse amministrazioni pubbliche e privati. Da gennaio 2020 lavora in SUSE come Software Release Engineer per Uyuni e SUSE Manager e quando non segue la sua passione per i computer e per Geeko coltiva la sua curiosità per l'astronomia (da cui deriva il suo nickname deneb_alpha).
OpenID AuthZEN Interop Read Out - AuthorizationDavid Brossard
During Identiverse 2024 and EIC 2024, members of the OpenID AuthZEN WG got together and demoed their authorization endpoints conforming to the AuthZEN API
Programming Foundation Models with DSPy - Meetup SlidesZilliz
Prompting language models is hard, while programming language models is easy. In this talk, I will discuss the state-of-the-art framework DSPy for programming foundation models with its powerful optimizers and runtime constraint system.
Project Management Semester Long Project - Acuityjpupo2018
Acuity is an innovative learning app designed to transform the way you engage with knowledge. Powered by AI technology, Acuity takes complex topics and distills them into concise, interactive summaries that are easy to read & understand. Whether you're exploring the depths of quantum mechanics or seeking insight into historical events, Acuity provides the key information you need without the burden of lengthy texts.
Neural Network Model for Predicting Students' Achievement in Blended Courses at the University of Dar Es Salaam
1. International Journal of Artificial Intelligence and Applications (IJAIA), Vol.8, No.2, March 2017
DOI : 10.5121/ijaia.2017.8203 23
NEURAL NETWORK MODEL FOR PREDICTING
STUDENTS’ ACHIEVEMENT IN BLENDED COURSES
AT THE UNIVERSITY OF DAR ES SALAAM
Eliah kazumali and Ellen Kalinga
Department of Computer Science and Engineering, University of Dar es Salaam,
Tanzania
ABSTRACT
Educator’s knowledge about the likely students’ achievement in blended courses prior to sitting for
examinations provides room for early intervention on students’ learning process, especially to those at risk.
Unfortunately, Leaning Management Systems (LMSs), Moodle in particular lacks an environment to assist
educators access such knowledge from time to time before undertaking their examinations. This raised the
need to propose a model, of which from time to time would be providing the likely students’ achievement
based on activities in Moodle and previous achievement, taking a case of postgraduate programmes at the
University of Dar es Salaam.
This study applied artificial neural networks in building a prediction model. Simulations were conducted in
Matrix Laboratory (MATLAB) utilizing seventy eight instances (78) of students’ logs of three blended
courses extracted from Moodle for 2013/2014 and 2014/2015 academic years.
Mean Square Error (MSE) and Coefficient of Determination (R2
) performance metrics were used to find
the best prediction model considering ten possible models. The study revealed a model with architecture of
4:10:1 trained with Bayesian Regularization (BR) to be the best model resulting to least MSE of 0.0170 and
high R2
of 0.93 on training. During testing, the model successfully predicted 78% of the students’
achievement with risk and pass status.
KEYWORDS
Artificial Neural Networks, Moodle logs, Blended Learning, Moodle, Learning Management Systems
1. INTRODUCTION
Classroom based learning as a traditional way, has been in practice for quite long time in Higher
Learning Institutions (HLIs). Today, the adoption of Learning Management Systems (LMSs)
have created chances to improve the traditional way of learning and teaching [1]. LMSs have
been adopted in HLIs to either complement classroom based learning sessions with eLearning
experiences to form blended learning or fully transform the traditional based learning and
teaching into web forming online learning.
The common adopted LMSs in delivering blended or online courses include Moodle, Blackboard,
and Sakai. Moreover, Moodle is said to be the most popular open source LMS [2]. As of
September 2014, Moodle had over 67 million users distributed in 230 countries across the world
supporting various institutions like universities and schools [3]. The UDSM in particular
deployed Moodle in 2008 to avoid high cost of annual licensing fee for the proprietary blackboard
LMS which was initially deployed in 1998 [4].
2. International Journal of Artificial Intelligence and Applications (IJAIA), Vol.8, No.2, March 2017
24
Blackboard LMS operated at the UDSM for ten years from 1998 to 2008. During this time, the
Blackboard LMS was used to complement face to face learning of some courses in programmes.
But, it is after migrating to Moodle in 2008 when programmes running entirely in blended
delivery mode commenced. Since then, a total of two hundred fifty seven (257) students have
been enrolled into blended learning programmes in seven academic years from 2008/2009 to
2014/2015. Therefore, it can be noticed that, blended learning programmes at the UDSM has
widened access to education to a number of people, especially those with limited time to attend
regular classes.
In traditional classroom settings, educators interact and monitor students more often throughout
the learning process. In this case, educators are likely to identify students at risk in the process of
learning in advance, hence respond to them in time. But in blended courses where students
interact more often with LMS, educators lack such prior knowledge before sitting for their
examinations. Thus, bringing unexpected results at the end of the course.
In order to equip educators with prior knowledge, various artificial neural network models have
been developed. The models that have been developed relied largely on predictors extracted from
admission information such as age, sex and previous achievement. Predictors generated during
interactions with Moodle LMS have not been adequately considered despite their significant
contributions on students’ achievement. Meanwhile, there is proof that, the activities of students
in LMS such as forum participations [5], login frequency [6] and topic views [7] have much
contributions on students’ achievement in blended learning courses. This indicates an existence of
correlation between LMS usage and students’ achievement which ensures the possibility of
constructing a prediction model relying on such activities generated in Moodle.
2. LITERATURE REVIEW
2.1. E-LEARNING AND LMS
E-Learning has emerged in the past few decades as a result of exploiting technology in education
for delivering learning in electronic format, most likely via Internet [8]. Since the deployment of
technology in education, shifting from traditional learning practices to eLearning or combining
both learning delivery modes have been possible. Some HLIs have opted to mix the traditional
classroom based learning with some few eLearning sessions creating the so called blended
learning while others shifting all the practices entirely online, creating the so called online
learning. But, in making sure that the benefits of traditional computer based is not totally
abandoned, most HLIs in Africa tend to adopt blended model of learning [9].
As defined by [10], blended learning is a formal education program in which students learn at
least in part through online delivery of content and instruction with some element of student
control over time, place and pace. These elements of blended learning provide room to students
with limited time to attend and pursue various programmes mostly in HLIs.
Based on the interaction between educators and students, eLearning can be conducted
synchronously and asynchronously. Synchronous eLearning environments require tutors and
educators to be online at the same time where live interactions like live chats and streamed
lectures take place between participants and they must adhere to a rigid schedule provided.
Asynchronous eLearning environment is the case where students are logging into and using LMS
independently of other students and educators. But, synchronous technologies like streamed
lectures are expensive and difficult to implement [11]. As a result in most HLIs such as the
University of Dar es Salaam asynchronous learning has been the dominant mode.
3. International Journal of Artificial Intelligence and Applications (IJAIA), Vol.8, No.2, March 2017
25
Although blended courses at the UDSM like the course of Engineering Finance and Economics
(MG 611), Project Appraisal (MG621) and Statistics and Research Methods (MG 602) appeared
to have exploited some synchronous features like live chats, none of them appeared to have
lecture live streaming yet. LMSs such as Moodle offer environments to deliver academic courses
or other types of training via Internet. Moodle is an asynchronous learning management system
[11], as a result, the present study mostly focused on asynchronous features available in Moodle
such as forums activities and views.
Many HLIs in Tanzania tend to offer some courses or sometimes all courses belonging in a
programme in eLearning mode either synchronously or asynchronously or both. At the UDSM
there are number of courses from various programmes which are delivered in blended mode of
learning, but, there are specific programmes where all courses are delivered in blended mode.
These are Masters in Engineering Management (MEM), Postgraduate Diploma in Engineering
Management (PGDEM) and Postgraduate Diploma in Education (PGDE). The present study is
making use of courses in programmes currently offered at the UDSM.
2.2. PREDICTORS OF STUDENTS’ ACHIEVEMENTS IN BLENDED COURSES
Different methodological approaches have been used to predict students’ achievement in blended
courses. Just like the way it has been possible in weather forecasting, population prediction, price
fluctuation prediction, the most common approaches have been traditional statistical methods
such as discriminant analysis, decision tree and multiple regressions [12], [13]. Various studies
have shown these traditional approaches to lag behind in terms of providing accurate prediction
compared to machine learning approaches such as using artificial neural networks [14], [15].
Although artificial neural networks provide accurate predication results than other approaches,
the question rises on the suitable variables to be used as predictors of students’ achievements in
blended courses. Predictors of students’ achievement are variables within or outside the learning
environment with effects on overall students’ achievements in blended courses. Regardless of
whatever kind of approach used for prediction, still the precise selection of predictors is
important. In case of traditional classroom based learning, various studies have come up with
predictors like gender, class attendance, age and previous score in GPA. But, when it comes to
blended learning it remains a challenge to find suitable predictors to be used in prediction of
students’ achievement.
With the adoption of LMS in HLIs to facilitate blended learning, more predictors have been
explored as a result of students’ activities in LMS. These activities are accumulated in relation to
various interactions carried by students in LMS from the start of the course to its end. Such
activities like resources viewed, assignments, and online forums are valuable activities since can
be used in prediction of students’ achievement [16]. These predictors hold some educational data
in LMS which are valuable data and can be used for predictions.
Furthermore, the LMS log data where the prediction parameters are extracted, are preferred to be
used in prediction because they are difficult or impossible to be apprehended by someone since
they can be collected without the knowledge of the educator [6]. In that sense, when such
parameters are used for prediction they can provide trustful results. In addition to that, [16] show
that, the predictors for students’ achievements are not only those associated with students’
activities in LMS only, but also from those resulting from classroom such as previous
achievement, attendance and participation. Therefore, predictors in blended courses involve
combination of predictors from eLearning mode and in traditional classroom setting as presented;
Login Sessions – Measures the extent at which individual students have been engaging in LMS
throughout the study. Students tend to login into LMS mainly for the purpose of accessing
learning resources, reading and interacting with other students and course educators.
4. International Journal of Artificial Intelligence and Applications (IJAIA), Vol.8, No.2, March 2017
26
Recourses Viewed - Learning resources are developed in text, video, audio and animations
formats for being viewed by students.
Forums and chats – Forum being an asynchronous tool is the most popular tools to make
students collaborate with themselves and with their educators in LMS environment.
Overall Grade Point Average - Regardless the mode of study, the GPA provides the summary of
previous academic achievement of students.
2.3. ABSTRACT NEURAL NETWORK MODEL
This is the conceptual representation of a neural network. Input neurons (predictor variables)
stand for predictors of students’ achievement in blended courses, which consist of login sessions,
forums participations, number of viewed resources, and overall undergraduate achievement in
GPA. The output neuron was formed by grade achievement in a course. A value for each
predictor with corresponding course achievement creates a pair in training and testing the neural
network. An abstract neural network model for student’s achievement in blended courses has
been shown in Figure 1.
Figure 1: An Abstract Network Model for Predicting Students’ Achievements
3. METHOD
3.1. RESEARCH DESIGN
The study adopted an experimental research design. This is a quantitative nature of research
whereby actual values of input variables (predictor variables) and output variable were gathered
and used. Figure 2 shows a summary of the phases adopted in modelling the neural network
prediction model as proposed by [19].
Figure 2: Basic Flow in Neural Network Modelling
5. International Journal of Artificial Intelligence and Applications (IJAIA), Vol.8, No.2, March 2017
27
3.2. SAMPLE
The present study used seventy eight (78) students’ instances/logs of three courses pursued by
students drawn randomly from academic years of 2013/2014 and 2014/2015. This constituted of
twenty eight (28) students participated in a course of Engineering Finance and Economics (MG
611), twenty seven (27) in Computer Programming (CS 680), and twenty three (23) in Project
Appraisal (MG 621) course.
3.3. DATA COLLECTION
Students’ Moodle logs of three courses were collected, the interest was to collect values of
variables/predictors of interest. These were values of login sessions, forum participation
frequency, number of resource views and the undergraduate GPA. The output variable was made
up with the students’ scored in each course. Figure 3 shows a sample of Activity Logs in one of
the courses namely; Project Appraisal Course (MG 621). The actual values associated with the
predictors extracted from Moodle logs were counted using an excel function “=SUMPRODUCT
(--(ISNUMBER (SEARCH ("resource views", E2:E84))))”. The results of the count formed one
component of a pair. The other component of the pair was formed by the students’ grade scored
in a course. Table 1, shows the results of the counts of each predictor variable for one of the
course namely; Project Appraisal Course (MG 621).
Figure 3: Sample Activity Logs in Project Appraisal Course (MG 621)
6. International Journal of Artificial Intelligence and Applications (IJAIA), Vol.8, No.2, March 2017
28
Table 1: Summary of Activity Counts Obtained from Project Appraisal Course
3.4. PRE-PROCESSING DATA
Before data is presented in MATLAB, they must be transformed in a manner suitable for
processing. The pre-processing actions performed in this study were data transformation and data
normalization. Data Transformation were done as follows;
Login sessions into ranges of ‘0-49’, ‘50-99’, and ‘100-above’ considered as ‘Low’, ‘Moderate’
and ‘High’ respectively.
Resource views into ranges of ‘0-49’, ‘50-99’, and ‘100-above’ considered as ‘Low’, ‘Moderate’
and ‘High’ respectively.
Forum participation into range of ‘1- above’ considered as ‘Participated’ and ‘0’ considered as
‘Not participated’.
Undergraduate GPA into ranges of ‘0.0-3.1’, ‘3.2-3.7’, and ‘3.8-5.0’ considered as ‘Low’,
‘Moderate’ and ‘High’ respectively.
Course achievement categorized into ‘Risky’ status for grades of B, C and D while ‘Pass’ status
for grades of B+ and A. Data normalization were done by equation;
Normalized = data/max (abs (data (:))) (1)
3.5. BUILDING A NEURAL NETWORK MODEL
In order to determine the optimal architecture and learning algorithm, the study examined ten
possible neural network model architectures with varied number of hidden neurons in hidden
layer and learning algorithm as shown in Table 2.
7. International Journal of Artificial Intelligence and Applications (IJAIA), Vol.8, No.2, March 2017
29
Table 2: Neural Network Models Subjected for Examinations
3.6. TRAINING NETWORK
Training a neural network uses training sets. Training sets build the predictive model by learning
the relationship existing between inputs and outputs. At this stage, each of the neural network
models under examination was passed through several trainings using 1000 as the maximum
number of epochs. In each training, the average MSE and R2
was observed and a training that
appeared to provide minimum average MSE and R2
was recorded for comparing it with other
neural network models MSE and R2
.
3.7. NETWORK TESTING
This is the final step in modelling. It deals with evaluation of the model found to provide the best
MSE and R2
in training stage, using data not participated in training known as testing data or out-
of-sample data. It is only one model with best results which is supposed to be tested, but for the
purpose of discussion, all the ten designed models were tested. Also, the process of training and
testing were done concurrently such that once the network is trained in the first iteration using the
training set then were tested with its corresponding testing sets. This process was repeated until
the sixth iteration.
3.8. 6-FOLD CROSS VALIDATION
In order to obtain pairs to be used for training and testing, 6-fold cross validation was used, the
dataset was partitioned into 6 folds of 13 datasets in each fold. Partitioning using K-fold cross
validation were done in MATLAB software shown by Equation 2 after loading all the datasets.
Cv = cvpartition (78, ‘kfold’, 6 (2)
In each iteration (K=1, 2, 3, 4, 5, 6), sixty five (65) data samples were used for training and
thirteen (13) data samples for testing. The training MSE and testing MSE obtained in each
iteration were recorded. The average MSE during training and testing were obtained using
Equation 3.
Average MSE = ∑=
6
16
1
i
iA (3)
Where: A is the MSE for each iteration.
Figure 4, shows the graphical representation of the 6-fold cross validation used in this
study.
8. International Journal of Artificial Intelligence and Applications (IJAIA), Vol.8, No.2, March 2017
30
Figure 4: 6-fold Cross Validation
4. RESULTS
4.1 RESULTS DURING TRAINING
The results of MSE and R2
during training for each of the iteration in all the network models were
recorded. The intention was to find a model architecture and learning algorithm that provide
minimum MSE during training. Such model has high ability of prediction when data not
participated in the training is used. Table 3, Table 4 and Table 5 show the detailed results for each
iteration and average values for MSE and R2
during training using BR, GDM and GD learning
algorithms.
Table 3: MSE and R2
Results during Training with BR Learning Algorithm
9. International Journal of Artificial Intelligence and Applications (IJAIA), Vol.8, No.2, March 2017
31
Table 4: MSE and R2
Results during Training with GDM Learning Algorithm
Table 5: MSE and R2
Results during Training with GD Learning Algorithm
From the table 3, it can be noted that the table with architecture of 4:10:1 trained with BR had
least MSE of 0.0170 and high R2
of 0.93 during training compared to other models. Therefore
chosen as the best model.
4.2. RESULTS DURING TESTING
The results of MSE and R2
during testing for each of the iteration in all the neural network models
were recorded. Table 6, show the results for individual iteration and average values for MSE and
R2
in testing using BR learning algorithms.
10. International Journal of Artificial Intelligence and Applications (IJAIA), Vol.8, No.2, March 2017
32
Table 6: MSE and R2
Results during Testing with BR Learning Algorithm
5.3. PREDICTION ACCURACY OF THE BEST MODEL IN PERCENTAGE
Using test data percentage accuracy of the selected model was calculated. The ‘Pass’ had a
representation of 2 while ‘Risky’ students represented by 1 in MATLAB, it was expected that the
trained neural network model would be predicting values of 2 and 1 accordingly. But, it is
difficult for the trained model to exactly reach these values. Therefore, a tolerance of ±0.5 was set
such that when the difference between target and predicted is within tolerance, then an instance
was regarded as ‘successful’. Finally, a total of 61 students’ instances were found to have
‘successful’ comment out of 78 students’ instances resulting to 78% of all students’ instances.
5.4 REPRESENTATION OF CORRELATION BETWEEN DESIRED AND PREDICTED VALUES
Figure 5 indicates a graphical representation of R2
of the best model. It shows the strength of
correlation between the targets and the predicted achievements in each iteration/round of the K-
fold.
Figure 5: Comparison of Target and Predicted Data in Testing for Model 4:10:1
11. International Journal of Artificial Intelligence and Applications (IJAIA), Vol.8, No.2, March 2017
33
5.5. NEURAL NETWORK PREDICTION MODEL
Figure 6 is the neural network model generated in MATLAB. It shows how input parameters are
connected to hidden layers, and further the way hidden layers are connected to the output layer.
Figure 6: Neural Network Model Created in MATLAB
5.6 THE PROPOSED NEURAL NETWORK MODEL
Using model generated in MATLAB indicated by Figure 6, a simple neural network model was
drawn as shown in Figure 7. It shows ten hidden neurons at hidden layer, four neurons at input
layer and one at output layer. It resembles the abstract model indicated by Figure 1 as proposed.
Figure 7: Proposed Artificial Neural Network Model
6. RESULTS DISCUSSION
The study aimed at finding and validating a neural network model to be used for prediction of
students’ achievements in blended courses for the context of the UDSM. In this section, key
findings are discussed by focusing on two perspectives: one is the difference in values of MSE
obtained during training and testing (validation), and students’ usage levels in Moodle.
6.1 MSE ON TESTING AND TRAINING SETS
In this study, it was expected that any model with small value of MSE on training would result
into small value of MSE on testing. This appeared to be the case for the present study. For
example, the model found to be the best in the present study resulted into MSE value of 0.0170
during training, which is smaller than MSE of 0.0196 obtained during testing. This findings agree
with majority of other studies conducted in similar area such as in [12] and in [17]. For stance, a
12. International Journal of Artificial Intelligence and Applications (IJAIA), Vol.8, No.2, March 2017
34
study conducted by [12] obtained MSE of 0.017 during training than what obtained in testing of
0.0191 when developing a prediction model of one thousands students’ results in higher
education. The best neural network model found to have 7:50:400:3 architecture, meaning that it
had 7 input neurons, first hidden layer with 50 neurons, a second hidden layer with 400 neurons
and an output layer with 3 neurons.
6.2 STUDENTS’ USAGE LEVELS IN MOODLE
The results showed that the main blended learning activities were reading and accessing course
materials. Even though courses had platform for peer collaborations and collaborations with their
educators, students did not often appear to seek such collaborations as is supposed be in their
blended learning. They mostly preferred reading course materials provided by their educators on
Moodle, but they did not always post, read or respond to messages in discussions. The findings
agree with many studies conducted in the same area. Examples are seen on studies conducted in
higher education institutions in sub-Saharan Africa [18].
7. CONCLUSIONS
At first, various literatures were reviewed to find out key predictors of students’ achievement in
blended courses. Key predictors identified were found to be login sessions, number of viewed
resources, forum participation frequency and the undergraduate GPA. Utilizing data gathered
based on predictor variable and output, the study examined ten possible neural network models.
The models examined had different architectures; meaning varied number of hidden neurons in
hidden layer. MSE and R2 were used to measure and compare the predictive ability of the
models. A model is said to have better performance than others if it generates smaller MSE value
and high R2 on training. Therefore, a model with 4:10:1 architecture trained with BR was found
in this this study to have lower MSE of 0.0170 than other model architectures and high coefficient
of determination of 0.93 during training. During testing provided minimum MSE as well,
equivalent to 78%. Therefore, selected as the best model architecture with the best predictive
ability than other examined models.
REFERENCES
[1] O. E. Obadara, “Effect of Learning Management System (LMS) on Students’ Academic Performance
in University of Lagos, Nigeria,” Int. J. Educ. Found. Manag., vol. 2, no. 1, pp. 25–33, 2014.
[2] Z. F. Muhsen, A. Maaita, A. Odah, and A. Nsour, “Moodle and E-Learning Tools,” Int. J. Mod. Educ.
Comput. Sci., vol. 5, no. 6, pp. 1–8, Jul. 2013.
[3] Moodle, “Moodle statistics,” 2014. [Online]. Available: http://moodle.net/stats/. [Accessed: 29-Sep-
2014].
[4] H. Twakyondo and M. Munaku, “Experience of Course Migration from Blackboard to Moodle LMS
– A Case Study from UDSM,” Int. J. Comput. ICT Res., vol. 6, no. 2, pp. 33–45, 2012.
[5] R. Cristobal, P. G. Espejo, Z. Amelia, J. R. Romero, and V. Sebastian, “Web Usage Mining for
Predicting Final Marks of Students that Use Moodle Courses,” Comput. Appl. Eng. Educ., vol. 21,
no. 1, pp. 135–146, 2013.
[6] I.-H. Jo, Y. Park, J. Kim, and J. Song, “Analysis of Online Behavior and Prediction of Learning
Performance in Blended Learning Environments,” Educ. Technol. Int., vol. 15, no. 2, pp. 71–88,
2014.
[7] F. Mödritscher, M. Andergassen, and G. Neumann, “Dependencies Between E-learning Usage
Patterns and Learning Results,” in Proceedings of the 13th International Conference on Knowledge
Management and Knowledge Technologies, 2013, pp. 1–8.
[8] M. Tayebinik and M. Puteh, “Blended Learning or E-learning?.,” Int. Mag. Adv. Comput. Sci.
Telecommun., vol. 3, no. 1, pp. 103–110, 2012.
13. International Journal of Artificial Intelligence and Applications (IJAIA), Vol.8, No.2, March 2017
35
[9] J. Lungo, “Optimization of Learning Management Systems Through Systems Integration: The Case of
Moodle and Zalongwa Software,” in Ist International conference of the AVU, November 20-22, 2013,
2013.
[10] F. Azizan, “Blended Learning in Higher Education Institution in Malaysia,” in Proceedings of
Regional Conference on Knowledge Integration in ICT 2010, 2010, pp. 454–466.
[11] A. I. Obasa, A. A. Eludire, and T. A. Ajao, “A Comparative Study of Synchronous and Asynchronous
E-Learning Resources,” Int. J. Innov. Res. Sci. Eng. Technol., vol. 2, no. 11, pp. 5938–5946, 2013.
[12] B. Oancea, R. Dragoescu, and S. Ciucu, “Predicting Students’ Results in Higher Education Using
Neural Networks,” in International Conference on Applied Information and Communication
Technology, 2013, pp. 190–193.
[13] S. A. Naser, I. Zaqout, M. A. Ghosh, R. Atallah, and E. Alajrami, “Predicting Student Performance
Using Artificial Neural Network : in the Faculty of Engineering and Information Technology,” Int. J.
Hybrid Inf. Technol., vol. 8, no. 2, pp. 221–228, 2015.
[14] G. M. Kanakana and A. O. Olanrewaju, “Predicting Student Performance in Engineering Education
Using an Artificial Neural Network at Tshwane Univerity of Technology,” in ISEM 2011
Proceedings, 2011, pp. 1–17.
[15] K. Kumar and G. S. M. Thakur, “Advanced Applications of Neural Networks and Artificial
Intelligence: A Review,” Int. J. Inf. Technol. Comput. Sci., vol. 4, no. 6, pp. 57–68, 2012.
[16] C. Romero, M.-I. López, J.-M. Luna, and V. Sebastián, “Predicting Students’ Final Performance from
Participation in On-line Discussion Forums,” Comput. Educ., vol. 68, pp. 458–472, 2013.
[17] J. Chen, H. Hsieh, and Q. H. Do, “Predicting Student Academic Performance: A Comparison of Two
Meta-Heuristic Algorithms Inspired by Cuckoo Birds for Training Neural Networks,” Algorithms,
vol. 7, no. 4, pp. 538–553, 2014.
[18] Mtebe, “Making Learning Management System Success for Blended Learning in Higher Education in
sub-Saharan Africa Joel S . Mtebe,” 2013.
[19] M. H. Al Shamisi, A. H. Assi, and H. Hejase, “Using MATLAB to Develop Artificial Neural
Network Models for Predicting Global Solar Radiation in Al ain City-UAE,” in Engineering
Education and Research Using MATLAB, A. H. Assi, Ed. Rijeka, Croatia: InTech, 2011, pp. 219–
238.
AUTHORS
Eliah Kazumali received Masters of Science in Computer Science from the University of
Dar es salaam in Tanzania. He is currently working as Assistance Lecturer at Teofilo
Kisanji University in Tanzania, also a member of eLearning Research Group (eLRG) at the
University of Dar es Salaam. His research interests include; Artificial intelligence,
eLearning, neural networks and web development
Eng. Dr. Ellen Kalinga received B.E. degree in Electrical and Electronics Engineering
from the University of Mysore India in 1990 and Master of Science (Electronics & IT of the
University of Dar as Salaam in 2002. In 2011, she also received her Ph.D. degree in
Computer Engineering and Information Technology from the University of Dar as Salaam –
Tanzania. Currently she is a Lecturer at the University of Dar es Salaam.