Pub Date : 2023-04-05DOI: 10.1109/PCEMS58491.2023.10136032
Dinesh S. Tundalwar, R. Pandhare, Mayuri Digalwar
IoT facilitates communication between objects and different sensors without involving humans. With the growing popularity of IoT and its various applications, the need for rugged security is increasing significantly. IoT generates a great deal of data, but it has a number of constraints, including low processing power, battery power, and limited storage. Because of these constraints, as well as the critical data generated by IoT applications, Security threats impact IoT on a wide scale. There are a variety of modern IoT security attacks at the perception, network, and application layers, which are discussed in this paper. The paper also explores emerging solutions to IoT security threats, as well as carries out comparative analysisbased on state-of-the-art technologies including fog/edge computing, SDN, lightweight cryptography, ML, IoTA, and blockchain. Additionally, the paper addresses the challenges of combining blockchain and the internet of things.
{"title":"A Taxonomy of IoT Security Attacks and Emerging Solutions","authors":"Dinesh S. Tundalwar, R. Pandhare, Mayuri Digalwar","doi":"10.1109/PCEMS58491.2023.10136032","DOIUrl":"https://doi.org/10.1109/PCEMS58491.2023.10136032","url":null,"abstract":"IoT facilitates communication between objects and different sensors without involving humans. With the growing popularity of IoT and its various applications, the need for rugged security is increasing significantly. IoT generates a great deal of data, but it has a number of constraints, including low processing power, battery power, and limited storage. Because of these constraints, as well as the critical data generated by IoT applications, Security threats impact IoT on a wide scale. There are a variety of modern IoT security attacks at the perception, network, and application layers, which are discussed in this paper. The paper also explores emerging solutions to IoT security threats, as well as carries out comparative analysisbased on state-of-the-art technologies including fog/edge computing, SDN, lightweight cryptography, ML, IoTA, and blockchain. Additionally, the paper addresses the challenges of combining blockchain and the internet of things.","PeriodicalId":330870,"journal":{"name":"2023 2nd International Conference on Paradigm Shifts in Communications Embedded Systems, Machine Learning and Signal Processing (PCEMS)","volume":"237 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116332713","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}
Image inpainting (or Image completion) is the process of reconstructing lost or corrupted parts of images. It can be used to fill in missing or corrupted parts of an image, such as removing an object from an image, removing image noise, or restoring an old photograph. The goal is to generate new pixels that are consistent with the surrounding area and make the image look as if the missing or corrupted parts were never there. Image inpainting can be done using various techniques such as texture synthesis, patch-based methods, and deep learning models. Deep learning-based Image inpainting typically involves using a neural network to generate new pixels to fill the missing parts of an image. Different network architectures can be used for this purpose, including Convolutional Neural Networks (CNNs), Generative Adversarial Networks(GANs), Transformer-based models, Flow-based models, and Diffusion models. In this work, we focus on Image Inpainting using Diffusion models whose task is to provide a set of diverse and realistic inpainted images for a given deteriorated image. Diffusion models use a diffusion process to fill in missing pixels, where the missing pixels are iteratively updated based on the surrounding context. The diffusion process is controlled by a set of parameters, which can be learned from data. The advantage of diffusion models is that they can handle large missing regions, while still producing visually plausible results. The challenges involved in the training of these models will be discussed.
{"title":"Survey on Diverse Image Inpainting using Diffusion Models","authors":"Sibam Parida, Vignesh Srinivas, Bhavishya Jain, Rajesh Naik, Neeraj Rao","doi":"10.1109/PCEMS58491.2023.10136091","DOIUrl":"https://doi.org/10.1109/PCEMS58491.2023.10136091","url":null,"abstract":"Image inpainting (or Image completion) is the process of reconstructing lost or corrupted parts of images. It can be used to fill in missing or corrupted parts of an image, such as removing an object from an image, removing image noise, or restoring an old photograph. The goal is to generate new pixels that are consistent with the surrounding area and make the image look as if the missing or corrupted parts were never there. Image inpainting can be done using various techniques such as texture synthesis, patch-based methods, and deep learning models. Deep learning-based Image inpainting typically involves using a neural network to generate new pixels to fill the missing parts of an image. Different network architectures can be used for this purpose, including Convolutional Neural Networks (CNNs), Generative Adversarial Networks(GANs), Transformer-based models, Flow-based models, and Diffusion models. In this work, we focus on Image Inpainting using Diffusion models whose task is to provide a set of diverse and realistic inpainted images for a given deteriorated image. Diffusion models use a diffusion process to fill in missing pixels, where the missing pixels are iteratively updated based on the surrounding context. The diffusion process is controlled by a set of parameters, which can be learned from data. The advantage of diffusion models is that they can handle large missing regions, while still producing visually plausible results. The challenges involved in the training of these models will be discussed.","PeriodicalId":330870,"journal":{"name":"2023 2nd International Conference on Paradigm Shifts in Communications Embedded Systems, Machine Learning and Signal Processing (PCEMS)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114778400","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 : 2023-04-05DOI: 10.1109/PCEMS58491.2023.10136049
N. Nagrale, Vishakha L Bansod, A. Deshmukh
Because 70% of India’s population is involved in agriculture, the shortage of grains has a severe influence on the economy of the nation. Due to the fact that grains are the main source of food and the foundation for many basic foods, they are essential to all area of a person’s life. As a result, the cultivation and storage of grains are crucial to the economic and social wellbeing of the country. It is a severe problem that food waste occurs primarily during the operations of harvesting, processing, distributing, and retailing. In order to reduce food waste, a good storage method must be employed to safeguard the food grains. This is made possible by IOT-based automation, which continuously tracks and monitors food grains kept in storage warehouses. Temperature, humidity, and CO2 concentration are significant atmospheric elements that might impact the quality of stored grains in go-downs and warehouses during grain storage. This technical paper describes the creation of a smart grain storage system that uses ultrasonic mouse repellent to control rodent while also monitoring air conditions.
{"title":"Iot Based Smart Food Grain Warehouse","authors":"N. Nagrale, Vishakha L Bansod, A. Deshmukh","doi":"10.1109/PCEMS58491.2023.10136049","DOIUrl":"https://doi.org/10.1109/PCEMS58491.2023.10136049","url":null,"abstract":"Because 70% of India’s population is involved in agriculture, the shortage of grains has a severe influence on the economy of the nation. Due to the fact that grains are the main source of food and the foundation for many basic foods, they are essential to all area of a person’s life. As a result, the cultivation and storage of grains are crucial to the economic and social wellbeing of the country. It is a severe problem that food waste occurs primarily during the operations of harvesting, processing, distributing, and retailing. In order to reduce food waste, a good storage method must be employed to safeguard the food grains. This is made possible by IOT-based automation, which continuously tracks and monitors food grains kept in storage warehouses. Temperature, humidity, and CO2 concentration are significant atmospheric elements that might impact the quality of stored grains in go-downs and warehouses during grain storage. This technical paper describes the creation of a smart grain storage system that uses ultrasonic mouse repellent to control rodent while also monitoring air conditions.","PeriodicalId":330870,"journal":{"name":"2023 2nd International Conference on Paradigm Shifts in Communications Embedded Systems, Machine Learning and Signal Processing (PCEMS)","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126523596","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 : 2023-04-05DOI: 10.1109/PCEMS58491.2023.10136034
Abhinav Kumar, Ankita H. Harkare, B. Neole, Vaishnavi Ghatole
Agriculture sector is the backbone of the Indian Economy. As per the Centre for Monitoring Indian Economy (CMIE) data, it holds a 38 % share in total employment of the country’s workforce. Attacks on crops by animals, locust swarms, and other noxious beings severely affect the livelihood of many. Locally used methods to deal with such attacks involve the use of chemical spraying, electric fencing, loudspeakers, etc. Over time they have proven to be inefficiently unfavorable for the yield quality and ecosystem and require a lot of human intervention. This paper presents a repulsion system that emits ultrasonic waves to prevent pre-empted attacks on farms by noxious beings. It employs sensor nodes throughout the farm, which are built by an Atmega-2560 microprocessor with an externally connected Wi-Fi module and ultrasonic sensors together to interact in an Internet of Things arrangement. This is a cost-effective way of repelling the noxious species with minimum human error since the system is capable of functioning autonomously. This system will benefit farmers and lessen crop devastation.
{"title":"Noxious beings Repulsion System Using Ultrasonic Transducers","authors":"Abhinav Kumar, Ankita H. Harkare, B. Neole, Vaishnavi Ghatole","doi":"10.1109/PCEMS58491.2023.10136034","DOIUrl":"https://doi.org/10.1109/PCEMS58491.2023.10136034","url":null,"abstract":"Agriculture sector is the backbone of the Indian Economy. As per the Centre for Monitoring Indian Economy (CMIE) data, it holds a 38 % share in total employment of the country’s workforce. Attacks on crops by animals, locust swarms, and other noxious beings severely affect the livelihood of many. Locally used methods to deal with such attacks involve the use of chemical spraying, electric fencing, loudspeakers, etc. Over time they have proven to be inefficiently unfavorable for the yield quality and ecosystem and require a lot of human intervention. This paper presents a repulsion system that emits ultrasonic waves to prevent pre-empted attacks on farms by noxious beings. It employs sensor nodes throughout the farm, which are built by an Atmega-2560 microprocessor with an externally connected Wi-Fi module and ultrasonic sensors together to interact in an Internet of Things arrangement. This is a cost-effective way of repelling the noxious species with minimum human error since the system is capable of functioning autonomously. This system will benefit farmers and lessen crop devastation.","PeriodicalId":330870,"journal":{"name":"2023 2nd International Conference on Paradigm Shifts in Communications Embedded Systems, Machine Learning and Signal Processing (PCEMS)","volume":"100 9-10","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134324953","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 : 2023-04-05DOI: 10.1109/PCEMS58491.2023.10136102
Vedant Jolly, Yash J. Patel, Samkit Shah, J. Ramteke
The number of persons worldwide who are blind or partially impaired is close to 285 million. According to the most recent World Health Organization data, the doctor-to-patient ratio in India is approximately 0.74:1000. This enormous disparity results in treatment delays in the majority of instances. The sad thing is that disorders like diabetic retinopathy (DR) and glaucoma spread more rapidly and can result in total blindness as a result of the delayed treatment obtained. The sad part of the story is that these diseases can be cured in 75% of cases. The suggested machine learning model focuses on these elements and aids in the early diagnosis of eye disease based on the fundus scope image of the eye, which can aid in the patient’s survival. Based on the provided dataset, we used the MobiNet model to identify several eye illnesses. The experimental research verified that, when tested in various lighting circumstances, the suggested model produced improved accuracy in detecting eye illnesses. By enhancing the disease identification process, the algorithm has the potential to lessen the strain on the already overburdened healthcare system.
{"title":"Eye Disease Detection using MobiNet","authors":"Vedant Jolly, Yash J. Patel, Samkit Shah, J. Ramteke","doi":"10.1109/PCEMS58491.2023.10136102","DOIUrl":"https://doi.org/10.1109/PCEMS58491.2023.10136102","url":null,"abstract":"The number of persons worldwide who are blind or partially impaired is close to 285 million. According to the most recent World Health Organization data, the doctor-to-patient ratio in India is approximately 0.74:1000. This enormous disparity results in treatment delays in the majority of instances. The sad thing is that disorders like diabetic retinopathy (DR) and glaucoma spread more rapidly and can result in total blindness as a result of the delayed treatment obtained. The sad part of the story is that these diseases can be cured in 75% of cases. The suggested machine learning model focuses on these elements and aids in the early diagnosis of eye disease based on the fundus scope image of the eye, which can aid in the patient’s survival. Based on the provided dataset, we used the MobiNet model to identify several eye illnesses. The experimental research verified that, when tested in various lighting circumstances, the suggested model produced improved accuracy in detecting eye illnesses. By enhancing the disease identification process, the algorithm has the potential to lessen the strain on the already overburdened healthcare system.","PeriodicalId":330870,"journal":{"name":"2023 2nd International Conference on Paradigm Shifts in Communications Embedded Systems, Machine Learning and Signal Processing (PCEMS)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134362064","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 : 2023-04-05DOI: 10.1109/PCEMS58491.2023.10136038
Abhishek Bajpai, N. Tiwari, Ashutosh Kumar Tripathi, V. Tripathi, Devesh Katiyar
At present, more than 50 % of the world’s population is dependent on rice for its survival. But there are various diseases that decrease the productivity of the paddy crop. The most affecting paddy leaf diseases are Brown spot, Hispa, & Rice blast. These illnesses restrict rice plants from growing and producing as they should, which might result in significant economic and ecological losses. The harm to the crops and the losses to the farmers can both be significantly reduced if these diseases are quickly and accurately recognized at an early stage. Multiple methods have been proposed to solve this problem using different machine learning and deep Learning techniques. In this paper, we have considered four classes for the classification of the leaf category. We used deep learning techniques to detect the actual disease of affected plants. We implemented three architectures i,e. VGGNet16, RenNet101,& AlexNet. Out of these three, Alexnet has the highest Accuracy. The AlexNet model has achieved training & testing accuracy of 92.35% and 85.27% respectively in our dataset.
{"title":"Early leaf diseases prediction in Paddy crop using Deep learning model","authors":"Abhishek Bajpai, N. Tiwari, Ashutosh Kumar Tripathi, V. Tripathi, Devesh Katiyar","doi":"10.1109/PCEMS58491.2023.10136038","DOIUrl":"https://doi.org/10.1109/PCEMS58491.2023.10136038","url":null,"abstract":"At present, more than 50 % of the world’s population is dependent on rice for its survival. But there are various diseases that decrease the productivity of the paddy crop. The most affecting paddy leaf diseases are Brown spot, Hispa, & Rice blast. These illnesses restrict rice plants from growing and producing as they should, which might result in significant economic and ecological losses. The harm to the crops and the losses to the farmers can both be significantly reduced if these diseases are quickly and accurately recognized at an early stage. Multiple methods have been proposed to solve this problem using different machine learning and deep Learning techniques. In this paper, we have considered four classes for the classification of the leaf category. We used deep learning techniques to detect the actual disease of affected plants. We implemented three architectures i,e. VGGNet16, RenNet101,& AlexNet. Out of these three, Alexnet has the highest Accuracy. The AlexNet model has achieved training & testing accuracy of 92.35% and 85.27% respectively in our dataset.","PeriodicalId":330870,"journal":{"name":"2023 2nd International Conference on Paradigm Shifts in Communications Embedded Systems, Machine Learning and Signal Processing (PCEMS)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133228348","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}
Machine learning models have been widely adopted in various applications, but their vulnerability to evasion attacks has become a significant concern. Evasion attacks on machine learning models aim to manipulate the test data in a way that causes the model to make incorrect predictions. In this paper, we performed gradient-based attacks on the support vector machine (SVM) model for cyclic alternating patterns (CAP) sleep phase test dataset. Performance of the classifier is evaluated under evasion attacks and detailed analysis on robustness of model has been done.
{"title":"Gradient Descent Adversarial Attacks on SVM for CAP EEG signals","authors":"Bharti Dakhale, Kurasingarapu Satwik, Nallamothu Vinay Kumar, Guttula Bhaskar Narayana, Ankit A. Bhurane, Ashwin Kothari","doi":"10.1109/PCEMS58491.2023.10136092","DOIUrl":"https://doi.org/10.1109/PCEMS58491.2023.10136092","url":null,"abstract":"Machine learning models have been widely adopted in various applications, but their vulnerability to evasion attacks has become a significant concern. Evasion attacks on machine learning models aim to manipulate the test data in a way that causes the model to make incorrect predictions. In this paper, we performed gradient-based attacks on the support vector machine (SVM) model for cyclic alternating patterns (CAP) sleep phase test dataset. Performance of the classifier is evaluated under evasion attacks and detailed analysis on robustness of model has been done.","PeriodicalId":330870,"journal":{"name":"2023 2nd International Conference on Paradigm Shifts in Communications Embedded Systems, Machine Learning and Signal Processing (PCEMS)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127292879","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 this study, we suggested an approximation multiplier that employs an approximate 4-2 compressor and is energy-efficient. When compared to the current designs, the suggested compressor has a small area. The results of simulations reveal that the suggested approximation multipliers display a reasonable decrease in Mean Error Distance, Mean Relative Error Distance, Normalized Mean Error Distance, compared to multiplier that is designed with exact compressors. The Power, Delay and Area of multipliers developed with this approximate compressor is superior to that obtained with previously suggested approximate compressors, according to implementation results in 90nm CMOS technology.
{"title":"Design Of Wallace Multiplier Using Novel Approximate 4:2 Compressors","authors":"Srinivas Pavan Jonnalagadda, Ram Kumar Avutapalli, Venkata Jayasri Pranitha Bobbadi, Keerthi Bagati, G. Kumar","doi":"10.1109/PCEMS58491.2023.10136063","DOIUrl":"https://doi.org/10.1109/PCEMS58491.2023.10136063","url":null,"abstract":"In this study, we suggested an approximation multiplier that employs an approximate 4-2 compressor and is energy-efficient. When compared to the current designs, the suggested compressor has a small area. The results of simulations reveal that the suggested approximation multipliers display a reasonable decrease in Mean Error Distance, Mean Relative Error Distance, Normalized Mean Error Distance, compared to multiplier that is designed with exact compressors. The Power, Delay and Area of multipliers developed with this approximate compressor is superior to that obtained with previously suggested approximate compressors, according to implementation results in 90nm CMOS technology.","PeriodicalId":330870,"journal":{"name":"2023 2nd International Conference on Paradigm Shifts in Communications Embedded Systems, Machine Learning and Signal Processing (PCEMS)","volume":"66 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130584663","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 : 2023-04-05DOI: 10.1109/PCEMS58491.2023.10136058
Anshu Behera, P. Kulkarni
This paper is written with the aim to make an automated temperature-based cooling arrangement for the Solar Panels using Arduino Uno/ Nano. The goal is to lower the operating temperature of PV modules, to increase PV output efficiency due to operation at lower temperatures. This system will shorten the payback period of the investment and increase the longevity of the Solar Panels. The Arduino helps in functioning of the cooling system guided by the code to make it completely automated and hence lead to better energy saving. This system when integrated with IoT helps in better operation management and freedom of control from anywhere. This system is smart” as it operates automatically, managing all year weather variations.
{"title":"Smart Temperature-dependent Cooling of Solar Panel using Arduino","authors":"Anshu Behera, P. Kulkarni","doi":"10.1109/PCEMS58491.2023.10136058","DOIUrl":"https://doi.org/10.1109/PCEMS58491.2023.10136058","url":null,"abstract":"This paper is written with the aim to make an automated temperature-based cooling arrangement for the Solar Panels using Arduino Uno/ Nano. The goal is to lower the operating temperature of PV modules, to increase PV output efficiency due to operation at lower temperatures. This system will shorten the payback period of the investment and increase the longevity of the Solar Panels. The Arduino helps in functioning of the cooling system guided by the code to make it completely automated and hence lead to better energy saving. This system when integrated with IoT helps in better operation management and freedom of control from anywhere. This system is smart” as it operates automatically, managing all year weather variations.","PeriodicalId":330870,"journal":{"name":"2023 2nd International Conference on Paradigm Shifts in Communications Embedded Systems, Machine Learning and Signal Processing (PCEMS)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125578749","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 : 2023-04-05DOI: 10.1109/PCEMS58491.2023.10136046
K. Nithya, Shivam Sharma, R. Sharma
Epilepsy is a neurological disorder characterized by recurrent seizures which are caused by abnormal electrical activity in the brain. The electroencephalogram (EEG) is a commonly used method for detecting and analyzing seizures. Identifying subtle changes in the EEG waveform by visual inspection can be challenging. It has led to a significant domain for researchers to develop intelligent algorithms to detect such subtle changes. Additionally, the EEG signals are non-linear and non-stationary in nature which makes the interpretation and detection of normal and abnormal activity more difficult. This paper proposes an automated method for detection of epilepsy from EEG signals based on the eigenvalues of Hankel matrix. In the proposed method, EEG signals discretely segmented in time domain and each segment is represented by Hankel matrix. Eigenvalues of each Hankel matrix are extracted and considered as features for the detection of epilepsy. All the eigenvalue-based features are ranked using maximum relevanceminimum redundancy (mRMR) algorithm and optimized number of features are calculated for combination of classes in order to achieve best accuracy. Decision tree-based classifier could achieve above 99% of accuracy for classifying normal and seizure patients and and over 98% for normal, seizure-free and seizure affected patients using the proposed method. Obtained results are also compared with recent methods to justify the supremacy of the proposed method over other related methods.
{"title":"Eigenvalues of Hankel Matrix based Epilepsy Detection using EEG Signals","authors":"K. Nithya, Shivam Sharma, R. Sharma","doi":"10.1109/PCEMS58491.2023.10136046","DOIUrl":"https://doi.org/10.1109/PCEMS58491.2023.10136046","url":null,"abstract":"Epilepsy is a neurological disorder characterized by recurrent seizures which are caused by abnormal electrical activity in the brain. The electroencephalogram (EEG) is a commonly used method for detecting and analyzing seizures. Identifying subtle changes in the EEG waveform by visual inspection can be challenging. It has led to a significant domain for researchers to develop intelligent algorithms to detect such subtle changes. Additionally, the EEG signals are non-linear and non-stationary in nature which makes the interpretation and detection of normal and abnormal activity more difficult. This paper proposes an automated method for detection of epilepsy from EEG signals based on the eigenvalues of Hankel matrix. In the proposed method, EEG signals discretely segmented in time domain and each segment is represented by Hankel matrix. Eigenvalues of each Hankel matrix are extracted and considered as features for the detection of epilepsy. All the eigenvalue-based features are ranked using maximum relevanceminimum redundancy (mRMR) algorithm and optimized number of features are calculated for combination of classes in order to achieve best accuracy. Decision tree-based classifier could achieve above 99% of accuracy for classifying normal and seizure patients and and over 98% for normal, seizure-free and seizure affected patients using the proposed method. Obtained results are also compared with recent methods to justify the supremacy of the proposed method over other related methods.","PeriodicalId":330870,"journal":{"name":"2023 2nd International Conference on Paradigm Shifts in Communications Embedded Systems, Machine Learning and Signal Processing (PCEMS)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126575741","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：