This document describes a proposed hybrid technique for automatic medical image classification and retrieval using information retrieval, support vector machines, and particle swarm optimization. Key aspects of the proposed approach include extracting low-level visual features from images like color, texture, shape and integrating them with semantic metadata. A content analysis system analyzes image descriptors and assigns semantic labels. Images are indexed and classified during a training phase. The proposed system aims to reduce the semantic gap between low-level features and high-level semantics by combining content-based image retrieval with text-based retrieval and machine learning algorithms.
Branch: An interactive, web-based tool for building decision tree classifiersBenjamin Good
A crucial task in modern biology is the prediction of complex phenotypes, such as breast cancer prognosis, from genome-wide measurements. Machine learning algorithms can sometimes infer predictive patterns, but there is rarely enough data to train and test them effectively and the patterns that they identify are often expressed in forms (e.g. support vector machines, neural networks, random forests composed of 10s of thousands of trees) that are highly difficult to understand. In addition, it is generally unclear how to include prior knowledge in the course of their construction.
Decision trees provide an intuitive visual form that can capture complex interactions between multiple variables. Effective methods exist for inferring decision trees automatically but it has been shown that these techniques can be improved upon via the manual interventions of experts. Here, we introduce Branch, a new Web-based tool for the interactive construction of decision trees from genomic datasets. Branch offers the ability to: (1) upload and share datasets intended for classification tasks (in progress), (2) construct decision trees by manually selecting features such as genes for a gene expression dataset, (3) collaboratively edit decision trees, (4) create feature functions that aggregate content from multiple independent features into single decision nodes (e.g. pathways) and (5) evaluate decision tree classifiers in terms of precision and recall. The tool is optimized for genomic use cases through the inclusion of gene and pathway-based search functions.
Branch enables expert biologists to easily engage directly with high-throughput datasets without the need for a team of bioinformaticians. The tree building process allows researchers to rapidly test hypotheses about interactions between biological variables and phenotypes in ways that would otherwise require extensive computational sophistication. In so doing, this tool can both inform biological research and help to produce more accurate, more meaningful classifiers.
A prototype of Branch is available at http://biobranch.org/
ABSTRACT
Genome-wide transcription profiling is a powerful technique in studying disease susceptible footprints. Moreover, when applied to disease tissue it may reveal quantitative and qualitative alterations in gene expression that give information on the context or underlying basis for the disease and may provide a new diagnostic approach. However, the data obtained from high-density microarrays is highly complex and poses considerable challenges in data mining. Past researches prove that neuro diseases damage the brain network interaction, protein- protein interaction and gene-gene interaction. A number of neurological research paper also analyze the relationship among damaged part. Analysis of gene-gene interaction network drawn by using state-of-the-art gene database of Alzheimer’s patient can conclude a lot of information. In this paper we used gene dataset affected with Alzheimer’s disease and normal patient’s dataset from NCBI databank. After proper processing the .CEL affymetrix data using RMA, we use the processed data to find gene interaction outputs. Then we filter the output files using probe set filtering attributes p-value and fold count and draw a gene-gene interaction network. Then we analyze the interaction network using GeneMania software.
Genome-wide transcription profiling is a powerful technique in studying disease susceptible footprints. Moreover, when applied to disease tissue it may reveal quantitative and qualitative alterations in gene expression that give information on the context or underlying basis for the disease and may provide a new diagnostic approach. However, the data obtained from high-density microarrays is highly complex and poses considerable challenges in data mining. Past researches prove that neuro diseases damage the brain network interaction, protein- protein interaction and gene-gene interaction. A number of neurological research paper also analyze the relationship among damaged part. Analysis of gene-gene interaction network drawn by using state-of-the-art gene database of Alzheimer’s patient can conclude a lot of information. In this paper we used gene dataset affected with Alzheimer’s disease and normal patient’s dataset from NCBI databank. After proper processing the .CEL affymetrix data using RMA, we use the processed data to find gene interaction outputs. Then we filter the output files using probe set filtering attributes p-value and fold count and draw a gene-gene interaction network. Then we analyze the interaction network using GeneMania software.
This document summarizes Rebeen Ali Hamad's PhD thesis on developing robust deep learning models for human activity recognition using sensor data. The thesis addressed key challenges in HAR including imbalanced class problems and reducing the need for large labeled datasets. Some of the contributions included a dilated causal convolution model with self-attention to improve recognition accuracy, a joint temporal model to handle imbalanced data, and a cross-domain learning approach using shared representations to reduce labeling efforts. Evaluation results demonstrated improved performance over existing methods on several HAR datasets. Future work opportunities involve hybrid algorithm-data level models, better attention mechanisms, and recognizing multi-user concurrent activities.
Designing Interactive Visualisations to Solve Analytical Problems in BiologyCagatay Turkay
Slides for my talk for the Cambridge Visualization of Biological Information Meetup held January 2015. I talk about why biology is exciting for visualisation researchers and go through examples where visualisation can help experts in understanding their data.
Off-line English Character Recognition: A Comparative Surveyidescitation
It has been decades since the evolution of idea that
human brain can be mimicked by artificial neuron like
mathematical structures. Till date, the development of this
endeavor has not reached the threshold of excellence. Neural
networks are commonly used to solve sample-recognition
problems. One of these is character recognition. The solution
of this problem is one of the easier implementations of neural
networks. This paper presents a detailed comparative
literature survey on the research accomplished for the last
few decades. The comparative literature review will help us
understand the platform on which we stand today to achieve
the highest efficiency in terms of Character Recognition
accuracy as well as computational resource and cost.
This document describes a proposed hybrid technique for automatic medical image classification and retrieval using information retrieval, support vector machines, and particle swarm optimization. Key aspects of the proposed approach include extracting low-level visual features from images like color, texture, shape and integrating them with semantic metadata. A content analysis system analyzes image descriptors and assigns semantic labels. Images are indexed and classified during a training phase. The proposed system aims to reduce the semantic gap between low-level features and high-level semantics by combining content-based image retrieval with text-based retrieval and machine learning algorithms.
Branch: An interactive, web-based tool for building decision tree classifiersBenjamin Good
A crucial task in modern biology is the prediction of complex phenotypes, such as breast cancer prognosis, from genome-wide measurements. Machine learning algorithms can sometimes infer predictive patterns, but there is rarely enough data to train and test them effectively and the patterns that they identify are often expressed in forms (e.g. support vector machines, neural networks, random forests composed of 10s of thousands of trees) that are highly difficult to understand. In addition, it is generally unclear how to include prior knowledge in the course of their construction.
Decision trees provide an intuitive visual form that can capture complex interactions between multiple variables. Effective methods exist for inferring decision trees automatically but it has been shown that these techniques can be improved upon via the manual interventions of experts. Here, we introduce Branch, a new Web-based tool for the interactive construction of decision trees from genomic datasets. Branch offers the ability to: (1) upload and share datasets intended for classification tasks (in progress), (2) construct decision trees by manually selecting features such as genes for a gene expression dataset, (3) collaboratively edit decision trees, (4) create feature functions that aggregate content from multiple independent features into single decision nodes (e.g. pathways) and (5) evaluate decision tree classifiers in terms of precision and recall. The tool is optimized for genomic use cases through the inclusion of gene and pathway-based search functions.
Branch enables expert biologists to easily engage directly with high-throughput datasets without the need for a team of bioinformaticians. The tree building process allows researchers to rapidly test hypotheses about interactions between biological variables and phenotypes in ways that would otherwise require extensive computational sophistication. In so doing, this tool can both inform biological research and help to produce more accurate, more meaningful classifiers.
A prototype of Branch is available at http://biobranch.org/
ABSTRACT
Genome-wide transcription profiling is a powerful technique in studying disease susceptible footprints. Moreover, when applied to disease tissue it may reveal quantitative and qualitative alterations in gene expression that give information on the context or underlying basis for the disease and may provide a new diagnostic approach. However, the data obtained from high-density microarrays is highly complex and poses considerable challenges in data mining. Past researches prove that neuro diseases damage the brain network interaction, protein- protein interaction and gene-gene interaction. A number of neurological research paper also analyze the relationship among damaged part. Analysis of gene-gene interaction network drawn by using state-of-the-art gene database of Alzheimer’s patient can conclude a lot of information. In this paper we used gene dataset affected with Alzheimer’s disease and normal patient’s dataset from NCBI databank. After proper processing the .CEL affymetrix data using RMA, we use the processed data to find gene interaction outputs. Then we filter the output files using probe set filtering attributes p-value and fold count and draw a gene-gene interaction network. Then we analyze the interaction network using GeneMania software.
Genome-wide transcription profiling is a powerful technique in studying disease susceptible footprints. Moreover, when applied to disease tissue it may reveal quantitative and qualitative alterations in gene expression that give information on the context or underlying basis for the disease and may provide a new diagnostic approach. However, the data obtained from high-density microarrays is highly complex and poses considerable challenges in data mining. Past researches prove that neuro diseases damage the brain network interaction, protein- protein interaction and gene-gene interaction. A number of neurological research paper also analyze the relationship among damaged part. Analysis of gene-gene interaction network drawn by using state-of-the-art gene database of Alzheimer’s patient can conclude a lot of information. In this paper we used gene dataset affected with Alzheimer’s disease and normal patient’s dataset from NCBI databank. After proper processing the .CEL affymetrix data using RMA, we use the processed data to find gene interaction outputs. Then we filter the output files using probe set filtering attributes p-value and fold count and draw a gene-gene interaction network. Then we analyze the interaction network using GeneMania software.
This document summarizes Rebeen Ali Hamad's PhD thesis on developing robust deep learning models for human activity recognition using sensor data. The thesis addressed key challenges in HAR including imbalanced class problems and reducing the need for large labeled datasets. Some of the contributions included a dilated causal convolution model with self-attention to improve recognition accuracy, a joint temporal model to handle imbalanced data, and a cross-domain learning approach using shared representations to reduce labeling efforts. Evaluation results demonstrated improved performance over existing methods on several HAR datasets. Future work opportunities involve hybrid algorithm-data level models, better attention mechanisms, and recognizing multi-user concurrent activities.
Designing Interactive Visualisations to Solve Analytical Problems in BiologyCagatay Turkay
Slides for my talk for the Cambridge Visualization of Biological Information Meetup held January 2015. I talk about why biology is exciting for visualisation researchers and go through examples where visualisation can help experts in understanding their data.
Off-line English Character Recognition: A Comparative Surveyidescitation
It has been decades since the evolution of idea that
human brain can be mimicked by artificial neuron like
mathematical structures. Till date, the development of this
endeavor has not reached the threshold of excellence. Neural
networks are commonly used to solve sample-recognition
problems. One of these is character recognition. The solution
of this problem is one of the easier implementations of neural
networks. This paper presents a detailed comparative
literature survey on the research accomplished for the last
few decades. The comparative literature review will help us
understand the platform on which we stand today to achieve
the highest efficiency in terms of Character Recognition
accuracy as well as computational resource and cost.
TOP 5 Most View Article From Academia in 2019sipij
TOP 5 Most View Article From Academia in 2019
Signal & Image Processing : An International Journal (SIPIJ)
ISSN : 0976 - 710X (Online) ; 2229 - 3922 (print)
http://www.airccse.org/journal/sipij/index.html
This document describes a study that developed an automated system to detect mind wandering during reading using gaze tracking, physiological sensors, and contextual cues. The system collected eye gaze data, skin conductance, skin temperature, and contextual information from 178 participants as they read instructional texts. Machine learning models were trained on these data to detect self-reported instances of mind wandering in response to auditory probes. Combining gaze and physiological features improved detection accuracy over single modality models, demonstrating the potential benefit of a multimodal approach to mind wandering detection.
Classifying Reading Behaviours using Deep Learning Methods with Eye-Tracking Data.
This work is interesting in identifying four reading behaviors: detailed-reading, non-reading, skimming, and scanning, by implementing three deep learning models – deep neural network (DNN), convolutional neural network (CNN), and recurrent neural networks (RNN), with eye-tracking data.
Replying to the findings, this paper proposes an idea to categorize reading behaviors by applying deep learning algorithms on eye-tracking data. More specifically, four activities – detailed-reading, non-reading, skimming, and scanning are classified by several deep learning algorithms listing as DNN, CNN, and RNN. Consequently, the work answers two research questions about which models and data type provide the highest accuracy when classifying reading behaviors.
This research poster presents a study aiming to predict the likelihood of autism spectrum disorder (ASD) in infants from 3-6 months old using electrocardiogram (ECG) recordings and machine learning. The researchers collected ECG data from infants during parent/object interaction experiments. They analyzed heart rate variability measures from the ECG data using neurokit and extracted features to use in machine learning models. Their best performing models were random forest and decision tree, which classified infants as having either elevated or low likelihood of ASD with over 75% accuracy. The results suggest certain heart rate variability measures may serve as potential biomarkers for ASD and that ECG could help diagnose ASD at a younger age before behavioral assessments are effective.
Sensing complicated meanings from unstructured data: a novel hybrid approachIJECEIAES
The majority of data on computers nowadays is in the form of unstructured data and unstructured text. The inherent ambiguity of natural language makes it incredibly difficult but also highly profitable to find hidden information or comprehend complex semantics in unstructured text. In this paper, we present the combination of natural language processing (NLP) and convolution neural network (CNN) hybrid architecture called automated analysis of unstructured text using machine learning (AAUT-ML) for the detection of complex semantics from unstructured data that enables different users to make understand formal semantic knowledge to be extracted from an unstructured text corpus. The AAUT-ML has been evaluated using three datasets data mining (DM), operating system (OS), and data base (DB), and compared with the existing models, i.e., YAKE, term frequency-inverse document frequency (TF-IDF) and text-R. The results show better outcomes in terms of precision, recall, and macro-averaged F1-score. This work presents a novel method for identifying complex semantics using unstructured data.
This document is a research statement by Chien-Wei (Masaki) Lin that summarizes his past and ongoing methodology and collaborative research projects. It discusses his interests in developing statistical methods for analyzing multi-omics data, including power calculation tools, meta-analysis and integrative analysis methods. It also summarizes some of Lin's collaboration projects applying these statistical methods to study topics like brain aging, major depressive disorder, and cardiovascular epidemiology. The document references 18 of Lin's publications and provides an overview of his diverse experience and future research plans developing statistical tools and methods and applying them to biological problems.
Evaluation of Logistic Regression and Neural Network Model With Sensitivity A...CSCJournals
Logistic Regression (LR) is a well known classification method in the field of statistical learning. It allows probabilistic classification and shows promising results on several benchmark problems. Logistic regression enables us to investigate the relationship between a categorical outcome and a set of explanatory variables. Artificial Neural Networks (ANNs) are popularly used as universal non-linear inference models and have gained extensive popularity in recent years. Research activities are considerable and literature is growing. The goal of this research work is to compare the performance of Logistic Regression and Neural Network models on publicly available medical datasets. The evaluation process of the model is as follows. The logistic regression and neural network methods with sensitivity analysis have been evaluated for the effectiveness of the classification. The Classification Accuracy is used to measure the performance of both the models. From the experimental results it is confirmed that the neural network model with sensitivity analysis model gives more efficient result.
This document provides a review of multispectral palm image fusion techniques. It begins with an introduction to biometrics and palm print identification. Different palm print images capture different spectral information about the palm. The document then reviews several pixel-level fusion methods for combining multispectral palm images, finding that Curvelet transform performs best at preserving discriminative patterns. It also discusses hardware for capturing multispectral palm images and the process of image fusion, including common transformation techniques like wavelet and Curvelet transforms.
This document provides a review of multispectral palm image fusion techniques. It begins with an introduction to biometrics and palm print identification. Different palm print images capture different spectral information about the palm. The document then reviews several pixel-level fusion methods for combining multispectral palm images, finding that Curvelet transform performs best at preserving discriminative patterns. It also discusses hardware for capturing multispectral palm images and the process of region of interest extraction and localization. Common fusion methods like wavelet transform and Curvelet transform are also summarized.
An informative and descriptive title for your literature survey John Wanjiru
The document summarizes research on developing artificial intelligence that can master the game of Go. It describes how researchers at DeepMind used a combination of deep neural networks and Monte Carlo tree search to create the AlphaGo agent. The AlphaGo agent uses a policy network trained through supervised and reinforcement learning to select moves, and a value network trained through reinforcement learning to evaluate board positions. Researchers found that AlphaGo was able to defeat human champions by a wide margin, demonstrating that its approach had achieved a level of play beyond human expertise.
This document provides an agenda for research on knowledge discovery from web search. It begins with an introduction on knowledge discovery and how search engines can help extract information. It then outlines the goals and objectives, provides a literature review on related work, and discusses some common limitations observed, such as models achieving low accuracy and WSD approaches not being efficient enough. The document serves to provide background and planning for a research study on improving knowledge discovery through web search.
This document discusses a thesis that uses machine learning algorithms to diagnose mental illness using MRI brain scans. Specifically, it analyzes schizophrenia, bipolar disorder, and healthy control subject data from multiple imaging modalities. It trains and tests eight machine learning classifiers - support vector machines, k-nearest neighbors, logistic regression, naive Bayes, and random forests - on the raw imaging data as well as data transformed through dimensionality reduction techniques. The results aim to demonstrate the efficacy of these algorithms at classifying subjects based on their brain scans and diagnosing their mental condition.
This document summarizes research using Echo State Networks (ESN) to model and classify electroencephalography (EEG) signals recorded during mental tasks in brain-computer interfaces (BCI). ESN were trained to forecast EEG signals one step ahead in time using data from 14 participants performing four mental tasks. Separate ESN models for each task act as experts in modeling EEG for that task. Novel EEG data is classified by selecting the label of the model with the lowest forecasting error. Offline experiments show ESN can model EEG with errors as low as 3% and classify two tasks with up to 95% accuracy and four tasks with up to 65% accuracy at two-second intervals.
Semantic Web for Health Care and Biomedical InformaticsAmit Sheth
Amit Sheth, "Semantic Web for Health Care and Biomedical Informatics," Keynote at NSF Biomed Web Workshop, Corbett, Oregon, December 4-5, 2007.
http://www.biomedweb.info/2007/
The document describes an automated pharmacy system that uses various technologies to digitize healthcare services. It discusses using optical character recognition to scan prescriptions, electronic health records to store patient medical histories, a chatbot for virtual healthcare assistance, and Google Maps API and an online portal to order medications. The system aims to make healthcare more convenient by allowing users to access services without visiting medical facilities in person.
Top Cited Articles in Signal & Image Processing 2021-2022sipij
Signal & Image Processing : An International Journal is an Open Access peer-reviewed journal intended for researchers from academia and industry, who are active in the multidisciplinary field of signal & image processing. The scope of the journal covers all theoretical and practical aspects of the Digital Signal Processing & Image processing, from basic research to development of application.
Authors are solicited to contribute to the journal by submitting articles that illustrate research results, projects, surveying works and industrial experiences that describe significant advances in the areas of Signal & Image processing.
The document provides an overview of solutions from Quahog Life Sciences including data management, security, analysis, visualization, and applications. The platform allows users to unify multiple data sources, merge them into a single structured data store, and organize data by patients. It uses advanced encryption techniques and offers machine learning capabilities like pattern extraction, segmentation, and predictive models. Visualization features include interactive dashboards with various chart types. Example use cases demonstrate pattern discovery in cancer research and influencer detection in cellular research. Bot applications are described for assisting diabetologists and physicians.
The document provides an overview of solutions from Quahog Life Sciences including data management, security, analysis, visualization, and applications. The platform allows merging of multiple data sources, creation of a logical data model, and organization of patient data. Advanced encryption is used to securely share data. The platform supports machine learning using a recursive neural network and analytics models. Use cases described include pattern discovery in cancer research and influencer detection in cellular research. Visualization capabilities include interactive dashboards with multiple chart types. Additional applications include bot assistance for diabetologists and physicians.
Pattern Recognition using Artificial Neural NetworkEditor IJCATR
An artificial neural network (ANN) usually called neural network. It can be considered as a resemblance to a paradigm
which is inspired by biological nervous system. In network the signals are transmitted by the means of connections links. The links
possess an associated way which is multiplied along with the incoming signal. The output signal is obtained by applying activation to
the net input NN are one of the most exciting and challenging research areas. As ANN mature into commercial systems, they are likely
to be implemented in hardware. Their fault tolerance and reliability are therefore vital to the functioning of the system in which they
are embedded. The pattern recognition system is implemented with Back propagation network and Hopfield network to remove the
distortion from the input. The Hopfield network has high fault tolerance which supports this system to get the accurate output.
TOP 5 Most View Article From Academia in 2019sipij
TOP 5 Most View Article From Academia in 2019
Signal & Image Processing : An International Journal (SIPIJ)
ISSN : 0976 - 710X (Online) ; 2229 - 3922 (print)
http://www.airccse.org/journal/sipij/index.html
This document describes a study that developed an automated system to detect mind wandering during reading using gaze tracking, physiological sensors, and contextual cues. The system collected eye gaze data, skin conductance, skin temperature, and contextual information from 178 participants as they read instructional texts. Machine learning models were trained on these data to detect self-reported instances of mind wandering in response to auditory probes. Combining gaze and physiological features improved detection accuracy over single modality models, demonstrating the potential benefit of a multimodal approach to mind wandering detection.
Classifying Reading Behaviours using Deep Learning Methods with Eye-Tracking Data.
This work is interesting in identifying four reading behaviors: detailed-reading, non-reading, skimming, and scanning, by implementing three deep learning models – deep neural network (DNN), convolutional neural network (CNN), and recurrent neural networks (RNN), with eye-tracking data.
Replying to the findings, this paper proposes an idea to categorize reading behaviors by applying deep learning algorithms on eye-tracking data. More specifically, four activities – detailed-reading, non-reading, skimming, and scanning are classified by several deep learning algorithms listing as DNN, CNN, and RNN. Consequently, the work answers two research questions about which models and data type provide the highest accuracy when classifying reading behaviors.
This research poster presents a study aiming to predict the likelihood of autism spectrum disorder (ASD) in infants from 3-6 months old using electrocardiogram (ECG) recordings and machine learning. The researchers collected ECG data from infants during parent/object interaction experiments. They analyzed heart rate variability measures from the ECG data using neurokit and extracted features to use in machine learning models. Their best performing models were random forest and decision tree, which classified infants as having either elevated or low likelihood of ASD with over 75% accuracy. The results suggest certain heart rate variability measures may serve as potential biomarkers for ASD and that ECG could help diagnose ASD at a younger age before behavioral assessments are effective.
Sensing complicated meanings from unstructured data: a novel hybrid approachIJECEIAES
The majority of data on computers nowadays is in the form of unstructured data and unstructured text. The inherent ambiguity of natural language makes it incredibly difficult but also highly profitable to find hidden information or comprehend complex semantics in unstructured text. In this paper, we present the combination of natural language processing (NLP) and convolution neural network (CNN) hybrid architecture called automated analysis of unstructured text using machine learning (AAUT-ML) for the detection of complex semantics from unstructured data that enables different users to make understand formal semantic knowledge to be extracted from an unstructured text corpus. The AAUT-ML has been evaluated using three datasets data mining (DM), operating system (OS), and data base (DB), and compared with the existing models, i.e., YAKE, term frequency-inverse document frequency (TF-IDF) and text-R. The results show better outcomes in terms of precision, recall, and macro-averaged F1-score. This work presents a novel method for identifying complex semantics using unstructured data.
This document is a research statement by Chien-Wei (Masaki) Lin that summarizes his past and ongoing methodology and collaborative research projects. It discusses his interests in developing statistical methods for analyzing multi-omics data, including power calculation tools, meta-analysis and integrative analysis methods. It also summarizes some of Lin's collaboration projects applying these statistical methods to study topics like brain aging, major depressive disorder, and cardiovascular epidemiology. The document references 18 of Lin's publications and provides an overview of his diverse experience and future research plans developing statistical tools and methods and applying them to biological problems.
Evaluation of Logistic Regression and Neural Network Model With Sensitivity A...CSCJournals
Logistic Regression (LR) is a well known classification method in the field of statistical learning. It allows probabilistic classification and shows promising results on several benchmark problems. Logistic regression enables us to investigate the relationship between a categorical outcome and a set of explanatory variables. Artificial Neural Networks (ANNs) are popularly used as universal non-linear inference models and have gained extensive popularity in recent years. Research activities are considerable and literature is growing. The goal of this research work is to compare the performance of Logistic Regression and Neural Network models on publicly available medical datasets. The evaluation process of the model is as follows. The logistic regression and neural network methods with sensitivity analysis have been evaluated for the effectiveness of the classification. The Classification Accuracy is used to measure the performance of both the models. From the experimental results it is confirmed that the neural network model with sensitivity analysis model gives more efficient result.
This document provides a review of multispectral palm image fusion techniques. It begins with an introduction to biometrics and palm print identification. Different palm print images capture different spectral information about the palm. The document then reviews several pixel-level fusion methods for combining multispectral palm images, finding that Curvelet transform performs best at preserving discriminative patterns. It also discusses hardware for capturing multispectral palm images and the process of image fusion, including common transformation techniques like wavelet and Curvelet transforms.
This document provides a review of multispectral palm image fusion techniques. It begins with an introduction to biometrics and palm print identification. Different palm print images capture different spectral information about the palm. The document then reviews several pixel-level fusion methods for combining multispectral palm images, finding that Curvelet transform performs best at preserving discriminative patterns. It also discusses hardware for capturing multispectral palm images and the process of region of interest extraction and localization. Common fusion methods like wavelet transform and Curvelet transform are also summarized.
An informative and descriptive title for your literature survey John Wanjiru
The document summarizes research on developing artificial intelligence that can master the game of Go. It describes how researchers at DeepMind used a combination of deep neural networks and Monte Carlo tree search to create the AlphaGo agent. The AlphaGo agent uses a policy network trained through supervised and reinforcement learning to select moves, and a value network trained through reinforcement learning to evaluate board positions. Researchers found that AlphaGo was able to defeat human champions by a wide margin, demonstrating that its approach had achieved a level of play beyond human expertise.
This document provides an agenda for research on knowledge discovery from web search. It begins with an introduction on knowledge discovery and how search engines can help extract information. It then outlines the goals and objectives, provides a literature review on related work, and discusses some common limitations observed, such as models achieving low accuracy and WSD approaches not being efficient enough. The document serves to provide background and planning for a research study on improving knowledge discovery through web search.
This document discusses a thesis that uses machine learning algorithms to diagnose mental illness using MRI brain scans. Specifically, it analyzes schizophrenia, bipolar disorder, and healthy control subject data from multiple imaging modalities. It trains and tests eight machine learning classifiers - support vector machines, k-nearest neighbors, logistic regression, naive Bayes, and random forests - on the raw imaging data as well as data transformed through dimensionality reduction techniques. The results aim to demonstrate the efficacy of these algorithms at classifying subjects based on their brain scans and diagnosing their mental condition.
This document summarizes research using Echo State Networks (ESN) to model and classify electroencephalography (EEG) signals recorded during mental tasks in brain-computer interfaces (BCI). ESN were trained to forecast EEG signals one step ahead in time using data from 14 participants performing four mental tasks. Separate ESN models for each task act as experts in modeling EEG for that task. Novel EEG data is classified by selecting the label of the model with the lowest forecasting error. Offline experiments show ESN can model EEG with errors as low as 3% and classify two tasks with up to 95% accuracy and four tasks with up to 65% accuracy at two-second intervals.
Semantic Web for Health Care and Biomedical InformaticsAmit Sheth
Amit Sheth, "Semantic Web for Health Care and Biomedical Informatics," Keynote at NSF Biomed Web Workshop, Corbett, Oregon, December 4-5, 2007.
http://www.biomedweb.info/2007/
The document describes an automated pharmacy system that uses various technologies to digitize healthcare services. It discusses using optical character recognition to scan prescriptions, electronic health records to store patient medical histories, a chatbot for virtual healthcare assistance, and Google Maps API and an online portal to order medications. The system aims to make healthcare more convenient by allowing users to access services without visiting medical facilities in person.
Top Cited Articles in Signal & Image Processing 2021-2022sipij
Signal & Image Processing : An International Journal is an Open Access peer-reviewed journal intended for researchers from academia and industry, who are active in the multidisciplinary field of signal & image processing. The scope of the journal covers all theoretical and practical aspects of the Digital Signal Processing & Image processing, from basic research to development of application.
Authors are solicited to contribute to the journal by submitting articles that illustrate research results, projects, surveying works and industrial experiences that describe significant advances in the areas of Signal & Image processing.
The document provides an overview of solutions from Quahog Life Sciences including data management, security, analysis, visualization, and applications. The platform allows users to unify multiple data sources, merge them into a single structured data store, and organize data by patients. It uses advanced encryption techniques and offers machine learning capabilities like pattern extraction, segmentation, and predictive models. Visualization features include interactive dashboards with various chart types. Example use cases demonstrate pattern discovery in cancer research and influencer detection in cellular research. Bot applications are described for assisting diabetologists and physicians.
The document provides an overview of solutions from Quahog Life Sciences including data management, security, analysis, visualization, and applications. The platform allows merging of multiple data sources, creation of a logical data model, and organization of patient data. Advanced encryption is used to securely share data. The platform supports machine learning using a recursive neural network and analytics models. Use cases described include pattern discovery in cancer research and influencer detection in cellular research. Visualization capabilities include interactive dashboards with multiple chart types. Additional applications include bot assistance for diabetologists and physicians.
Pattern Recognition using Artificial Neural NetworkEditor IJCATR
An artificial neural network (ANN) usually called neural network. It can be considered as a resemblance to a paradigm
which is inspired by biological nervous system. In network the signals are transmitted by the means of connections links. The links
possess an associated way which is multiplied along with the incoming signal. The output signal is obtained by applying activation to
the net input NN are one of the most exciting and challenging research areas. As ANN mature into commercial systems, they are likely
to be implemented in hardware. Their fault tolerance and reliability are therefore vital to the functioning of the system in which they
are embedded. The pattern recognition system is implemented with Back propagation network and Hopfield network to remove the
distortion from the input. The Hopfield network has high fault tolerance which supports this system to get the accurate output.
Similar to Multi-View Design Patterns and Responsive Visualization for Genomics Data.ppt (20)
Comparative analysis between traditional aquaponics and reconstructed aquapon...bijceesjournal
The aquaponic system of planting is a method that does not require soil usage. It is a method that only needs water, fish, lava rocks (a substitute for soil), and plants. Aquaponic systems are sustainable and environmentally friendly. Its use not only helps to plant in small spaces but also helps reduce artificial chemical use and minimizes excess water use, as aquaponics consumes 90% less water than soil-based gardening. The study applied a descriptive and experimental design to assess and compare conventional and reconstructed aquaponic methods for reproducing tomatoes. The researchers created an observation checklist to determine the significant factors of the study. The study aims to determine the significant difference between traditional aquaponics and reconstructed aquaponics systems propagating tomatoes in terms of height, weight, girth, and number of fruits. The reconstructed aquaponics system’s higher growth yield results in a much more nourished crop than the traditional aquaponics system. It is superior in its number of fruits, height, weight, and girth measurement. Moreover, the reconstructed aquaponics system is proven to eliminate all the hindrances present in the traditional aquaponics system, which are overcrowding of fish, algae growth, pest problems, contaminated water, and dead fish.
Harnessing WebAssembly for Real-time Stateless Streaming PipelinesChristina Lin
Traditionally, dealing with real-time data pipelines has involved significant overhead, even for straightforward tasks like data transformation or masking. However, in this talk, we’ll venture into the dynamic realm of WebAssembly (WASM) and discover how it can revolutionize the creation of stateless streaming pipelines within a Kafka (Redpanda) broker. These pipelines are adept at managing low-latency, high-data-volume scenarios.
Redefining brain tumor segmentation: a cutting-edge convolutional neural netw...IJECEIAES
Medical image analysis has witnessed significant advancements with deep learning techniques. In the domain of brain tumor segmentation, the ability to
precisely delineate tumor boundaries from magnetic resonance imaging (MRI)
scans holds profound implications for diagnosis. This study presents an ensemble convolutional neural network (CNN) with transfer learning, integrating
the state-of-the-art Deeplabv3+ architecture with the ResNet18 backbone. The
model is rigorously trained and evaluated, exhibiting remarkable performance
metrics, including an impressive global accuracy of 99.286%, a high-class accuracy of 82.191%, a mean intersection over union (IoU) of 79.900%, a weighted
IoU of 98.620%, and a Boundary F1 (BF) score of 83.303%. Notably, a detailed comparative analysis with existing methods showcases the superiority of
our proposed model. These findings underscore the model’s competence in precise brain tumor localization, underscoring its potential to revolutionize medical
image analysis and enhance healthcare outcomes. This research paves the way
for future exploration and optimization of advanced CNN models in medical
imaging, emphasizing addressing false positives and resource efficiency.
A review on techniques and modelling methodologies used for checking electrom...nooriasukmaningtyas
The proper function of the integrated circuit (IC) in an inhibiting electromagnetic environment has always been a serious concern throughout the decades of revolution in the world of electronics, from disjunct devices to today’s integrated circuit technology, where billions of transistors are combined on a single chip. The automotive industry and smart vehicles in particular, are confronting design issues such as being prone to electromagnetic interference (EMI). Electronic control devices calculate incorrect outputs because of EMI and sensors give misleading values which can prove fatal in case of automotives. In this paper, the authors have non exhaustively tried to review research work concerned with the investigation of EMI in ICs and prediction of this EMI using various modelling methodologies and measurement setups.
Embedded machine learning-based road conditions and driving behavior monitoringIJECEIAES
Car accident rates have increased in recent years, resulting in losses in human lives, properties, and other financial costs. An embedded machine learning-based system is developed to address this critical issue. The system can monitor road conditions, detect driving patterns, and identify aggressive driving behaviors. The system is based on neural networks trained on a comprehensive dataset of driving events, driving styles, and road conditions. The system effectively detects potential risks and helps mitigate the frequency and impact of accidents. The primary goal is to ensure the safety of drivers and vehicles. Collecting data involved gathering information on three key road events: normal street and normal drive, speed bumps, circular yellow speed bumps, and three aggressive driving actions: sudden start, sudden stop, and sudden entry. The gathered data is processed and analyzed using a machine learning system designed for limited power and memory devices. The developed system resulted in 91.9% accuracy, 93.6% precision, and 92% recall. The achieved inference time on an Arduino Nano 33 BLE Sense with a 32-bit CPU running at 64 MHz is 34 ms and requires 2.6 kB peak RAM and 139.9 kB program flash memory, making it suitable for resource-constrained embedded systems.
Optimizing Gradle Builds - Gradle DPE Tour Berlin 2024Sinan KOZAK
Sinan from the Delivery Hero mobile infrastructure engineering team shares a deep dive into performance acceleration with Gradle build cache optimizations. Sinan shares their journey into solving complex build-cache problems that affect Gradle builds. By understanding the challenges and solutions found in our journey, we aim to demonstrate the possibilities for faster builds. The case study reveals how overlapping outputs and cache misconfigurations led to significant increases in build times, especially as the project scaled up with numerous modules using Paparazzi tests. The journey from diagnosing to defeating cache issues offers invaluable lessons on maintaining cache integrity without sacrificing functionality.
Presentation of IEEE Slovenia CIS (Computational Intelligence Society) Chapte...University of Maribor
Slides from talk presenting:
Aleš Zamuda: Presentation of IEEE Slovenia CIS (Computational Intelligence Society) Chapter and Networking.
Presentation at IcETRAN 2024 session:
"Inter-Society Networking Panel GRSS/MTT-S/CIS
Panel Session: Promoting Connection and Cooperation"
IEEE Slovenia GRSS
IEEE Serbia and Montenegro MTT-S
IEEE Slovenia CIS
11TH INTERNATIONAL CONFERENCE ON ELECTRICAL, ELECTRONIC AND COMPUTING ENGINEERING
3-6 June 2024, Niš, Serbia
Understanding Inductive Bias in Machine LearningSUTEJAS
This presentation explores the concept of inductive bias in machine learning. It explains how algorithms come with built-in assumptions and preferences that guide the learning process. You'll learn about the different types of inductive bias and how they can impact the performance and generalizability of machine learning models.
The presentation also covers the positive and negative aspects of inductive bias, along with strategies for mitigating potential drawbacks. We'll explore examples of how bias manifests in algorithms like neural networks and decision trees.
By understanding inductive bias, you can gain valuable insights into how machine learning models work and make informed decisions when building and deploying them.
New techniques for characterising damage in rock slopes.pdf
Multi-View Design Patterns and Responsive Visualization for Genomics Data.ppt
1. Multi-View Design Patterns and
Responsive Visualization for
Genomics Data
Seminar On
Under the Guidance : Submitted By:
Dr. S. B. Gurav Vidya Vijay Mali
3. Abstract
Genome data is very crucial in clinical trails
Understanding the genome patterns are always a
challenging task
Using multi pattern analysis always enhances the model
Using of Gosling grammar enhances the process of
genome data Visualization
3
5. Motivation
Handling huge genome data is always a tedious
work
Identifying the pattern according to the need is
a challenging task in genome data
5
6. Objectives
To preprocess the data properly
To enhance the model with Gosling grammar
To identify the multi-pattern in genome tracks
6
7. LITERATURE SURVEY
Paper Author Methodology
Multi-View Design
Patterns and Responsive
Visualization for
Genomics Data
Sehi L’Yi and Nils
Gehlenborg
In this paper, Author’s provide a reusable and
generalizable system for designing responsive
genomics data multi-view visualizations in this
research. Reviewing web-based genomics
visualization tools in the wild helps us understand
design difficulties. Using a taxonomy of
responsive designs, Author’s discover that tools
rarely promote responsiveness. Author’s identify
typical view composition patterns such “vertically
long,” “horizontally wide,” “circular,” and “cross-
shaped” to organize survey findings. Then they
identify their usability difficulties at multiple
resolutions based on composition patterns and
discuss ways to fix them and make genomics
visualizations responsive.
7
8. LITERATURE SURVEY
Paper Author Methodology
Adaptively
Exploring
Population Mobility
Patterns in Flow
Visualization
Fei Wang, Wei Chen, Ye
Zhao, Tianyu Gu, Siyuan
Gao, and Hujun Bao
This paper presents a system that deciphers,
transforms, searches, and visualizes records from
millions of city users. Author’s created MobiHash, a
data structure that receives phone call records from
base stations and indexes them using a Voronoi
partition of metropolitan space. MobiHash enables
interactive retrieval of population flow trajectories in
areas of interest using responsive data searches. To
avoid visual clutter and occlusions, population
movement is depicted as vector fields. A unique
radiation model interpolates population passing
zones due to sparse moving points. Author’s
validated the usability and efficiency of our
approach by analyzing population movement trends
over time using case studies and expert feedback.
8
9. LITERATURE SURVEY
Paper Author Methodology
Active Brainwave Pattern
Generation for Brain-To-
Machine Communication
Swathi Ganesh, Dale
Timm, Kee S. Moon,
Sung Q Lee, and Woosub
Youm
This paper aims to develop a real-time
EEG-based brain-to-machine
communication system by generating
distinct signals and identifying their
patterns for self-induced visual and
auditory stimuli. The brain-to-machine
communication system captures, analyzes,
and visualizes brain signal patterns in real-
time for medical applications like
rehabilitation, robotic control, and smart
wheelchairs.
9
11. References
S. L'Yi and N. Gehlenborg, "Multi-View Design Patterns and Responsive
Visualization for Genomics Data," in IEEE Transactions on Visualization
and Computer Graphics, vol. 29, no. 1, pp. 559-569, Jan. 2023, doi:
10.1109/TVCG.2022.3209398.
F. Wang, W. Chen, Y. Zhao, T. Gu, S. Gao and H. Bao, "Adaptively
Exploring Population Mobility Patterns in Flow Visualization," in IEEE
Transactions on Intelligent Transportation Systems, vol. 18, no. 8, pp.
2250-2259, Aug. 2017, doi: 10.1109/TITS.2017.2711644.
S. Ganesh, D. Timm, K. S. Moon, S. Q. Lee and W. Youm, "Active
brainwave pattern generation for brain-to-machine communication," 2017
39th Annual International Conference of the IEEE Engineering in
Medicine and Biology Society (EMBC), Jeju, Korea (South), 2017, pp.
990-993, doi: 10.1109/EMBC.2017.8036992.
11