Pub Date : 2023-05-01DOI: 10.1109/REEDCON57544.2023.10150898
A. Sharma, M. Jamil, Abdul Azeem
Smart cities form the benchmark for the futuristic engineering trends in the field of electrical distribution system. A futuristic venture into these Smart cities required a solution to most complex solution which shall going to be a challenge to the power engineers. The most reliable solution to these complex problems are the application of Artificial Intelligence in the most refine manner. Only the successful application of artificial intelligence techniques in the everyday use will form the backbone for these cities. This paper proposes an AI based algorithm for the application in the field of Electrical Distribution system. Ant colony based optimization algorithm is used to realize how the smart cities grid is going to respond to the contingencies arising in the distribution network. A fuzzy logic based input module is used for getting the best appropriate result for the optimization problem. The algorithm is applied on the IEEE 30 bus system within the Mi-Power software paradigm.
{"title":"Electrical Distribution network service restoration in Smart grids using ACO-Fuzzy Approach","authors":"A. Sharma, M. Jamil, Abdul Azeem","doi":"10.1109/REEDCON57544.2023.10150898","DOIUrl":"https://doi.org/10.1109/REEDCON57544.2023.10150898","url":null,"abstract":"Smart cities form the benchmark for the futuristic engineering trends in the field of electrical distribution system. A futuristic venture into these Smart cities required a solution to most complex solution which shall going to be a challenge to the power engineers. The most reliable solution to these complex problems are the application of Artificial Intelligence in the most refine manner. Only the successful application of artificial intelligence techniques in the everyday use will form the backbone for these cities. This paper proposes an AI based algorithm for the application in the field of Electrical Distribution system. Ant colony based optimization algorithm is used to realize how the smart cities grid is going to respond to the contingencies arising in the distribution network. A fuzzy logic based input module is used for getting the best appropriate result for the optimization problem. The algorithm is applied on the IEEE 30 bus system within the Mi-Power software paradigm.","PeriodicalId":429116,"journal":{"name":"2023 International Conference on Recent Advances in Electrical, Electronics & Digital Healthcare Technologies (REEDCON)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134085617","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In cloud computing, many resources are pooled together to help users operating in a distributed environment collaborate. A load balancer distributes Virtual Machines (VMs) to users in compliance with their required resources and tasks. Existing load balancing algorithms are insufficient for obtaining fast response times and better optimisation of cloud services and their resources when the load increases. Rule-based fuzzy inferences enable optimal resource utilisation by assigning user requests in the most efficient manner. This paper presents an Optimal Fuzzy-based Load Balancing (OFLB) model for efficient resource distribution. The proposed model employs memory, bandwidth, and disc space needs as fuzzy variables and implements categorization-based fuzzy constraints to improve performance. The tasks are assigned to virtual devices based on defined threshold values for membership functions. In the experiments, the OFLB is compared to other extant load-balancing algorithms in terms of memory, bandwidth and disc space utilisation. The analysis of the results shows that the OFLB-based modal improves the efficacy of the cloud system in terms of resource utilization by approximately 18% as compared to existing algorithms that distribute VMs.
{"title":"An Optimized Fuzzy-based Load Balancing in Cloud Computing","authors":"Mushtaq Ahmed, Madhav Khatri, Faisal Ahmed, Jitendra Goyal","doi":"10.1109/REEDCON57544.2023.10150583","DOIUrl":"https://doi.org/10.1109/REEDCON57544.2023.10150583","url":null,"abstract":"In cloud computing, many resources are pooled together to help users operating in a distributed environment collaborate. A load balancer distributes Virtual Machines (VMs) to users in compliance with their required resources and tasks. Existing load balancing algorithms are insufficient for obtaining fast response times and better optimisation of cloud services and their resources when the load increases. Rule-based fuzzy inferences enable optimal resource utilisation by assigning user requests in the most efficient manner. This paper presents an Optimal Fuzzy-based Load Balancing (OFLB) model for efficient resource distribution. The proposed model employs memory, bandwidth, and disc space needs as fuzzy variables and implements categorization-based fuzzy constraints to improve performance. The tasks are assigned to virtual devices based on defined threshold values for membership functions. In the experiments, the OFLB is compared to other extant load-balancing algorithms in terms of memory, bandwidth and disc space utilisation. The analysis of the results shows that the OFLB-based modal improves the efficacy of the cloud system in terms of resource utilization by approximately 18% as compared to existing algorithms that distribute VMs.","PeriodicalId":429116,"journal":{"name":"2023 International Conference on Recent Advances in Electrical, Electronics & Digital Healthcare Technologies (REEDCON)","volume":"140 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133701039","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Transmission cables face significant challenges in today’s deregulated market due to load demand and the need to operate profitably. The utilization depends heavily on different outage situations. Line outages are graded according to their severity using Performance Index. The design of power systems makes them particularly prone to malfunction. Although it is challenging to forecast an unplanned power outage, it is essential to analyze potential failures and foresee their effects. The security of the electrical system can be assessed with the help of contingency analysis. To forecast the characteristics of the power system after any number of outages, single or multiple models are used. The major objective of this study is to identify critical double-line failures that, if they occurred, would lead to line flow violations in the power system. N2 contingency analysis is used to describe this. It takes a very long time to complete a thorough analysis of all conceivable N2 outcomes. An AC or DC power flow can be utilized to find significant double line outages without looking at all N2 possibilities. These results are contrasted with the entire AC power flow statistics. These methods can find many double-line outages that lead to line flow violations.
{"title":"Power System Contingency Analysis Using Improved Computational Techniques","authors":"Prahlad Mundotiya, Ankush Koli, Subhash Shrimal, Ch . Naga, Vikash Kumar Sharma, H. Tiwari","doi":"10.1109/REEDCON57544.2023.10151055","DOIUrl":"https://doi.org/10.1109/REEDCON57544.2023.10151055","url":null,"abstract":"Transmission cables face significant challenges in today’s deregulated market due to load demand and the need to operate profitably. The utilization depends heavily on different outage situations. Line outages are graded according to their severity using Performance Index. The design of power systems makes them particularly prone to malfunction. Although it is challenging to forecast an unplanned power outage, it is essential to analyze potential failures and foresee their effects. The security of the electrical system can be assessed with the help of contingency analysis. To forecast the characteristics of the power system after any number of outages, single or multiple models are used. The major objective of this study is to identify critical double-line failures that, if they occurred, would lead to line flow violations in the power system. N2 contingency analysis is used to describe this. It takes a very long time to complete a thorough analysis of all conceivable N2 outcomes. An AC or DC power flow can be utilized to find significant double line outages without looking at all N2 possibilities. These results are contrasted with the entire AC power flow statistics. These methods can find many double-line outages that lead to line flow violations.","PeriodicalId":429116,"journal":{"name":"2023 International Conference on Recent Advances in Electrical, Electronics & Digital Healthcare Technologies (REEDCON)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132575898","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The smart grid is a revolutionary and upsurging methodology for power supply. Smart grid has many advantages like reduced peak demand, inclusion of different energy sources, increase in the number of power suppliers, increased overall security and real time price prediction thus helping to optimize the power usage. Due to the inclusion of different renewable sources as prosumer (producer and consumer), a centralized system is not sufficient enough to dynamically predict the stability of the smart grid systems. In a centralized system, there is one directional flow of electricity and information. The local nodes are not autonomous and do not have a bi-directional flow of information, hence the prediction of price is time taking, fault detection and correction are also not fast. This paper considers decentralized system to predict the stability of the smart grid power supply which is dependent on the frequency of local nodes. The smart grid is said to be stable if the power generation matches the power demand and also there is a reserve to meet the power outage if it happens at any point of time. The paper considers an ANN model based on deep learning techniques and evaluates various factors to optimize its precision, such as the number of hidden layers, the number of nodes in each hidden layer, the appropriate optimizer and the right activation function. We have concluded the relationship between the predictive features and hidden layers, the use of ‘relu’, ‘sigmoid’ and ADAM as the optimized parameters for the ANN model for smart grid stability predictions.
{"title":"Estimating the Stability of Smart Grids Using Optimised Artificial Neural Network","authors":"Akshita Singh, Pallavi Singh, Nehal Agrawal, Pankaj Gupta","doi":"10.1109/REEDCON57544.2023.10151031","DOIUrl":"https://doi.org/10.1109/REEDCON57544.2023.10151031","url":null,"abstract":"The smart grid is a revolutionary and upsurging methodology for power supply. Smart grid has many advantages like reduced peak demand, inclusion of different energy sources, increase in the number of power suppliers, increased overall security and real time price prediction thus helping to optimize the power usage. Due to the inclusion of different renewable sources as prosumer (producer and consumer), a centralized system is not sufficient enough to dynamically predict the stability of the smart grid systems. In a centralized system, there is one directional flow of electricity and information. The local nodes are not autonomous and do not have a bi-directional flow of information, hence the prediction of price is time taking, fault detection and correction are also not fast. This paper considers decentralized system to predict the stability of the smart grid power supply which is dependent on the frequency of local nodes. The smart grid is said to be stable if the power generation matches the power demand and also there is a reserve to meet the power outage if it happens at any point of time. The paper considers an ANN model based on deep learning techniques and evaluates various factors to optimize its precision, such as the number of hidden layers, the number of nodes in each hidden layer, the appropriate optimizer and the right activation function. We have concluded the relationship between the predictive features and hidden layers, the use of ‘relu’, ‘sigmoid’ and ADAM as the optimized parameters for the ANN model for smart grid stability predictions.","PeriodicalId":429116,"journal":{"name":"2023 International Conference on Recent Advances in Electrical, Electronics & Digital Healthcare Technologies (REEDCON)","volume":"17 11","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114034924","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-01DOI: 10.1109/REEDCON57544.2023.10150609
Rajashree Sahoo, R. Pradhan
Microarray experiments are proficient of yielding observations for thousands of genes those are differentially expressed under several conditions. Although it is possible to measure simultaneously the changes in gene expression profiles at whole genomic scale, interpreting individual gene expression profile in terms of its actual biological function or associated biochemical processes remains challenging. Exploratory multivariate statistical techniques such as principal component analysis have been extensively used to reduce the complexity of large size microarray data. Although Saccaromycea Cerevisae is the most widely studied species using microarray techniques, a complete understanding of the efficacy of principal component analysis and data pre-processing is still lacking for clustering and functional mapping of yeast gene expression profiles, reported in various studies. Therefore in this work, we evaluate the impact of data pre-processing and principal component analysis on k-means clustering-based functional mapping of yeast gene expression profiles observed during diauxic-shift. Two time-series gene expression datasets were chosen such as, (1) yeast diauxic-shift data and (2) yeast sporulation data to examine the efficacy of principal component analysis in interpreting gene-based or score-based clusters and their relationship with known pathways. It was shown that unlike conventional pre-processing, principal component analysis provides a powerful tool to capture most of the information using only two component variables for inferring gene expression time-course data. Using yeast genome databases, it was demonstrated that clustering with principal components instead of the original variables does not necessarily improve the cluster quality but helps in identifying the relationships between genes of a cluster and key biological process of diauxic shift. Overall, the present analysis is useful in mining high dimensional microarray data at a reduced computational cost associated with functional enrichment of expression time-series, regardless of species or experimental conditions.
{"title":"Effectiveness of Principal Component Analysis in Functional Mapping of Gene Expression Profiles","authors":"Rajashree Sahoo, R. Pradhan","doi":"10.1109/REEDCON57544.2023.10150609","DOIUrl":"https://doi.org/10.1109/REEDCON57544.2023.10150609","url":null,"abstract":"Microarray experiments are proficient of yielding observations for thousands of genes those are differentially expressed under several conditions. Although it is possible to measure simultaneously the changes in gene expression profiles at whole genomic scale, interpreting individual gene expression profile in terms of its actual biological function or associated biochemical processes remains challenging. Exploratory multivariate statistical techniques such as principal component analysis have been extensively used to reduce the complexity of large size microarray data. Although Saccaromycea Cerevisae is the most widely studied species using microarray techniques, a complete understanding of the efficacy of principal component analysis and data pre-processing is still lacking for clustering and functional mapping of yeast gene expression profiles, reported in various studies. Therefore in this work, we evaluate the impact of data pre-processing and principal component analysis on k-means clustering-based functional mapping of yeast gene expression profiles observed during diauxic-shift. Two time-series gene expression datasets were chosen such as, (1) yeast diauxic-shift data and (2) yeast sporulation data to examine the efficacy of principal component analysis in interpreting gene-based or score-based clusters and their relationship with known pathways. It was shown that unlike conventional pre-processing, principal component analysis provides a powerful tool to capture most of the information using only two component variables for inferring gene expression time-course data. Using yeast genome databases, it was demonstrated that clustering with principal components instead of the original variables does not necessarily improve the cluster quality but helps in identifying the relationships between genes of a cluster and key biological process of diauxic shift. Overall, the present analysis is useful in mining high dimensional microarray data at a reduced computational cost associated with functional enrichment of expression time-series, regardless of species or experimental conditions.","PeriodicalId":429116,"journal":{"name":"2023 International Conference on Recent Advances in Electrical, Electronics & Digital Healthcare Technologies (REEDCON)","volume":"289 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114129605","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-01DOI: 10.1109/REEDCON57544.2023.10151294
Mohammad Amir, Suwaiba Mateen, Zaheeruddin, A. Haque
The concern about climate change and greenhouse gas emissions has resulted in a steady shift in the transportation sector from conventional fossil fuel-based combustion vehicles to electric vehicles. In the last decade only, the growth of electric vehicles (EVs) on the road has increased exponentially. The main drawback for widespread adoption, however, is range anxiety. Charging from an ultra-fast charging station (UFCS) solves this problem and makes EVs a worthwhile investment for manufacturers and customers. But UFCS comes with many technological constraints such as the requirement of high-capacity batteries, high-power charging converters and the grid impacts. In this paper, the negative grid impacts of UFCS, and power quality (PQ) problems of UFCS are summarized. The mitigation techniques are discussed and an online controller that works with open interfaces according to the international charging standards is proposed. A framework for optimized UFSC integrated with grid and distributed energy system is presented.
{"title":"Impacts Assessment of Ultra-Fast EVs Charging Stations Integrated with Distribution Energy System and Mitigations Measures Using Online Controller","authors":"Mohammad Amir, Suwaiba Mateen, Zaheeruddin, A. Haque","doi":"10.1109/REEDCON57544.2023.10151294","DOIUrl":"https://doi.org/10.1109/REEDCON57544.2023.10151294","url":null,"abstract":"The concern about climate change and greenhouse gas emissions has resulted in a steady shift in the transportation sector from conventional fossil fuel-based combustion vehicles to electric vehicles. In the last decade only, the growth of electric vehicles (EVs) on the road has increased exponentially. The main drawback for widespread adoption, however, is range anxiety. Charging from an ultra-fast charging station (UFCS) solves this problem and makes EVs a worthwhile investment for manufacturers and customers. But UFCS comes with many technological constraints such as the requirement of high-capacity batteries, high-power charging converters and the grid impacts. In this paper, the negative grid impacts of UFCS, and power quality (PQ) problems of UFCS are summarized. The mitigation techniques are discussed and an online controller that works with open interfaces according to the international charging standards is proposed. A framework for optimized UFSC integrated with grid and distributed energy system is presented.","PeriodicalId":429116,"journal":{"name":"2023 International Conference on Recent Advances in Electrical, Electronics & Digital Healthcare Technologies (REEDCON)","volume":"157 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133718225","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-01DOI: 10.1109/REEDCON57544.2023.10150455
M. M. Khan, Priyam Raj, Sanu Kumar
Anisocoria is the medical term associated when one of the pupil’s radius is not equal to the other one. This often leads to disease occurrence in the human eye when it remains undetected in its "silent" early phases. Therefore, this paper proposes a prototype of a low-cost early-warning anisocoria detection system by sensing and measuring the pupil diameter in the human eye. The unprocessed human-eye images were transformed to efficiently detect the pupil’s circumference using image binarization, leveling, and Hough transform techniques. Applying the machine learning (ML) algorithms using logistic regression, the model was trained and tested on the data set consisting of 75 random eye images. The prediction accuracy achieved was 81% when tested under red, green, blue, and ambient illumination. Furthermore, the proposed method was compared with the two other image processing methods, namely the Canny edge and Daugman algorithms, for optimum selection at the pre-ML stage. This method could prove to be a cost-effective solution for early diagnosis of anisocoria vis-a-vis database production to further accurate the proposed sensor system.
{"title":"Cost-Effective early warning solution for Anisocoria Eye-Disease through Optical Sensing and Machine Learning: A Preliminary Analysis","authors":"M. M. Khan, Priyam Raj, Sanu Kumar","doi":"10.1109/REEDCON57544.2023.10150455","DOIUrl":"https://doi.org/10.1109/REEDCON57544.2023.10150455","url":null,"abstract":"Anisocoria is the medical term associated when one of the pupil’s radius is not equal to the other one. This often leads to disease occurrence in the human eye when it remains undetected in its \"silent\" early phases. Therefore, this paper proposes a prototype of a low-cost early-warning anisocoria detection system by sensing and measuring the pupil diameter in the human eye. The unprocessed human-eye images were transformed to efficiently detect the pupil’s circumference using image binarization, leveling, and Hough transform techniques. Applying the machine learning (ML) algorithms using logistic regression, the model was trained and tested on the data set consisting of 75 random eye images. The prediction accuracy achieved was 81% when tested under red, green, blue, and ambient illumination. Furthermore, the proposed method was compared with the two other image processing methods, namely the Canny edge and Daugman algorithms, for optimum selection at the pre-ML stage. This method could prove to be a cost-effective solution for early diagnosis of anisocoria vis-a-vis database production to further accurate the proposed sensor system.","PeriodicalId":429116,"journal":{"name":"2023 International Conference on Recent Advances in Electrical, Electronics & Digital Healthcare Technologies (REEDCON)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133982371","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-01DOI: 10.1109/REEDCON57544.2023.10151041
N. Rafiuddin, Y. Khan, Omar Farooq
The aim of this study is to investigate the best type of mother wavelet capable of classifying multiple classes related to EEG. For instance, classification of the three brain states, namely seizure, pre-seizure (for seizure prediction), and normal states is an important part of the study in multiclass classification of epilepsy. In an attempt to yield the best mother wavelet, the study employs the MDWP approach by excavating through the wavelet packet tree up to the seventh level of decomposition, exploiting the wavelet coefficients on each level. The mother wavelets incorporated in the study are the commonly used wavelets, namely db4, sym5, coif4 and db2. Features were obtained by evaluating energy on all wavelet packets, which were further ranked using Naïve-Bayes classifier. Beginning with the feature ranked highest and progressively adding features with lower ranks one at a time, the classification results depicted in the form of patterns show the db4 mother wavelet to outperform others.
{"title":"Mother Wavelet for Optimal Feature Analysis in Multiclass EEG Signals","authors":"N. Rafiuddin, Y. Khan, Omar Farooq","doi":"10.1109/REEDCON57544.2023.10151041","DOIUrl":"https://doi.org/10.1109/REEDCON57544.2023.10151041","url":null,"abstract":"The aim of this study is to investigate the best type of mother wavelet capable of classifying multiple classes related to EEG. For instance, classification of the three brain states, namely seizure, pre-seizure (for seizure prediction), and normal states is an important part of the study in multiclass classification of epilepsy. In an attempt to yield the best mother wavelet, the study employs the MDWP approach by excavating through the wavelet packet tree up to the seventh level of decomposition, exploiting the wavelet coefficients on each level. The mother wavelets incorporated in the study are the commonly used wavelets, namely db4, sym5, coif4 and db2. Features were obtained by evaluating energy on all wavelet packets, which were further ranked using Naïve-Bayes classifier. Beginning with the feature ranked highest and progressively adding features with lower ranks one at a time, the classification results depicted in the form of patterns show the db4 mother wavelet to outperform others.","PeriodicalId":429116,"journal":{"name":"2023 International Conference on Recent Advances in Electrical, Electronics & Digital Healthcare Technologies (REEDCON)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130542102","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-01DOI: 10.1109/REEDCON57544.2023.10151406
Aftab Alam, S. Urooj, A. Q. Ansari
Researchers have always been curious if a computer can detect human emotions precisely and accurately. Many research publications have been reported on human-machine interaction systems. The emotion classifiers using machine learning techniques are developed using the feature dataset extracted from physiological and non-physiological parameters. Emotion recognition can be done either by using facial, speech or audio-visual data paths or using physiological signals like ECG, EEG, EMG, GSR and Respiration signals. Many have explored facial recognition techniques for emotion recognition but facial expressions can be masked. A sad person can pretend to have a smiling face and vice-versa. Physiological signals like ECG, EEG, GSR and respiration signals are non-maskable due to their involuntary source of generation. There are many datasets available publicly for researchers to use and develop an efficient emotion classifier system. In this work, the publicly available datasets of EEG, ECG and GSR recorded while watching emotional video are utilized to develop emotion classifiers using machine learning techniques. Here three physiological feature datasets named LUMED-2 (EEG+ GSR), SWELL (HRV), and YAAD (ECG+ GSR) are used to train models and classify emotions. The deep learning classifiers used are Random Forest, SVM, KNN, and/or Decision Tree. The maximum average classification accuracy achieved is close to 100% at least for one classifier in each dataset. It is observed that physiological signals like EEG, ECG, and GSR possess differentiable emotional features which can be used to detect the emotional state of a person precisely using the trained machine learning models.
{"title":"Human Emotion Recognition Models Using Machine Learning Techniques","authors":"Aftab Alam, S. Urooj, A. Q. Ansari","doi":"10.1109/REEDCON57544.2023.10151406","DOIUrl":"https://doi.org/10.1109/REEDCON57544.2023.10151406","url":null,"abstract":"Researchers have always been curious if a computer can detect human emotions precisely and accurately. Many research publications have been reported on human-machine interaction systems. The emotion classifiers using machine learning techniques are developed using the feature dataset extracted from physiological and non-physiological parameters. Emotion recognition can be done either by using facial, speech or audio-visual data paths or using physiological signals like ECG, EEG, EMG, GSR and Respiration signals. Many have explored facial recognition techniques for emotion recognition but facial expressions can be masked. A sad person can pretend to have a smiling face and vice-versa. Physiological signals like ECG, EEG, GSR and respiration signals are non-maskable due to their involuntary source of generation. There are many datasets available publicly for researchers to use and develop an efficient emotion classifier system. In this work, the publicly available datasets of EEG, ECG and GSR recorded while watching emotional video are utilized to develop emotion classifiers using machine learning techniques. Here three physiological feature datasets named LUMED-2 (EEG+ GSR), SWELL (HRV), and YAAD (ECG+ GSR) are used to train models and classify emotions. The deep learning classifiers used are Random Forest, SVM, KNN, and/or Decision Tree. The maximum average classification accuracy achieved is close to 100% at least for one classifier in each dataset. It is observed that physiological signals like EEG, ECG, and GSR possess differentiable emotional features which can be used to detect the emotional state of a person precisely using the trained machine learning models.","PeriodicalId":429116,"journal":{"name":"2023 International Conference on Recent Advances in Electrical, Electronics & Digital Healthcare Technologies (REEDCON)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123849932","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-01DOI: 10.1109/REEDCON57544.2023.10150952
K. Thenkumari, A. R. Prakhya, P. Niharika
This project aims to analyze the dielectric and electric shielding properties to ascertain the optimal shielding. Materials that have been applied range from being electrically non-conductive to conductive based on the application of them being either used as a conductor or as an insulator. This correlation had studied and analyzed in COMSOL Multiphysics software and variability of the capacitance and conductance for different blend of materials at different area fractions of the model that depends on the effective shielding of the EM waves respectively in the dielectric and electric shielding. However, electric and dielectric shielding serves for various purposes and are not directly comparable in terms of which is best. Amongst the materials that are available from the Software, a film made of Carbon nanotubes (CNTs) aerosol CVD; (nk 0.250-3.30 um) sized material produces the best shielding results for dielectric shielding and Copper, Nickel (solid, Annealed) blended material produces the best shielding results in case of electric shielding model.
{"title":"Comparative Study and Analysis of Electric and Dielectric Shielding","authors":"K. Thenkumari, A. R. Prakhya, P. Niharika","doi":"10.1109/REEDCON57544.2023.10150952","DOIUrl":"https://doi.org/10.1109/REEDCON57544.2023.10150952","url":null,"abstract":"This project aims to analyze the dielectric and electric shielding properties to ascertain the optimal shielding. Materials that have been applied range from being electrically non-conductive to conductive based on the application of them being either used as a conductor or as an insulator. This correlation had studied and analyzed in COMSOL Multiphysics software and variability of the capacitance and conductance for different blend of materials at different area fractions of the model that depends on the effective shielding of the EM waves respectively in the dielectric and electric shielding. However, electric and dielectric shielding serves for various purposes and are not directly comparable in terms of which is best. Amongst the materials that are available from the Software, a film made of Carbon nanotubes (CNTs) aerosol CVD; (nk 0.250-3.30 um) sized material produces the best shielding results for dielectric shielding and Copper, Nickel (solid, Annealed) blended material produces the best shielding results in case of electric shielding model.","PeriodicalId":429116,"journal":{"name":"2023 International Conference on Recent Advances in Electrical, Electronics & Digital Healthcare Technologies (REEDCON)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129899182","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：