Pub Date : 2021-12-01DOI: 10.1109/iSES52644.2021.00023
Shaik Mulla Shabber, Mohan Bansal, P. M. Devi, Prateek Jain
Nowadays, people are looking for methods to improve their lifestyles by utilising the latest technologies accessible. Various home automation system have grown in popularity over the last decade, and it improves comfort and quality of life. The proposed work explores an intelligent home automation system (iHAS) that allows the user to monitor electrical appliances of the home from everywhere in the world. This system can be used to describe how all home appliances function together and control them using the laptop, Android smartphone, or tablet with internet access. The home automation system can be installed in existing home environments without requiring any infrastructure changes. This paper explored the design and implementation of an individual control home automation device utilising Wi-Fi enabled micro-controller unit. The user can have complete control over the home appliances and devices from anywhere using only an Android app and an internet connection.
{"title":"iHAS: An Intelligent Home Automation Based System for Smart City","authors":"Shaik Mulla Shabber, Mohan Bansal, P. M. Devi, Prateek Jain","doi":"10.1109/iSES52644.2021.00023","DOIUrl":"https://doi.org/10.1109/iSES52644.2021.00023","url":null,"abstract":"Nowadays, people are looking for methods to improve their lifestyles by utilising the latest technologies accessible. Various home automation system have grown in popularity over the last decade, and it improves comfort and quality of life. The proposed work explores an intelligent home automation system (iHAS) that allows the user to monitor electrical appliances of the home from everywhere in the world. This system can be used to describe how all home appliances function together and control them using the laptop, Android smartphone, or tablet with internet access. The home automation system can be installed in existing home environments without requiring any infrastructure changes. This paper explored the design and implementation of an individual control home automation device utilising Wi-Fi enabled micro-controller unit. The user can have complete control over the home appliances and devices from anywhere using only an Android app and an internet connection.","PeriodicalId":293167,"journal":{"name":"2021 IEEE International Symposium on Smart Electronic Systems (iSES) (Formerly iNiS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125933632","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 : 2021-12-01DOI: 10.1109/iSES52644.2021.00084
Rashi Kumar, V. Sahula
Natural Language Processing (NLP) is a subfield of semantics, software engineering, and artificial intelligence dealing with the coordination between computers and human language, specifically how to program computers to process and investigate a lot of natural language information. The objective is to program a computer to understand the written texts, including the context of the language inside them. India is a diverse nation and communicates in various dialects. India faces incredible difficulties for research in the field of NLP. In this work we present the various works done in the field of NLP for Indian Languages and also present the various challenges that are faced by the research community working in this field in India. We also discuss our proposed methodology for machine translation from Sanskrit to Hindi.
{"title":"Intelligent Approaches for Natural Language Processing for Indic Languages","authors":"Rashi Kumar, V. Sahula","doi":"10.1109/iSES52644.2021.00084","DOIUrl":"https://doi.org/10.1109/iSES52644.2021.00084","url":null,"abstract":"Natural Language Processing (NLP) is a subfield of semantics, software engineering, and artificial intelligence dealing with the coordination between computers and human language, specifically how to program computers to process and investigate a lot of natural language information. The objective is to program a computer to understand the written texts, including the context of the language inside them. India is a diverse nation and communicates in various dialects. India faces incredible difficulties for research in the field of NLP. In this work we present the various works done in the field of NLP for Indian Languages and also present the various challenges that are faced by the research community working in this field in India. We also discuss our proposed methodology for machine translation from Sanskrit to Hindi.","PeriodicalId":293167,"journal":{"name":"2021 IEEE International Symposium on Smart Electronic Systems (iSES) (Formerly iNiS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129965023","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 : 2021-12-01DOI: 10.1109/iSES52644.2021.00080
Brijraj Singh Solanki, R. Kumawat, S. Srinivasan
Emerging trends, development and growth of industrial-networked control systems (i-NCSs) with real-time communication network drive it more susceptible to malicious intended intrusion and attack. Due to numerous advantages such as reduced maintenance, ease to install, ease of diagnosis and system wiring draws attention to use in various industrial and critical fields. The control performance and robust stability of NCS is directly related to reliable and successful transmission of critical information’s. So in this paper an approach is illustrated to alleviate the effects and avert the unwanted intended intrusive data through the designing of stability conditions and optimized control policies. An unwanted intrusion effects also forced us to design a controlled system, which is hard to be estimated by attackers, through the applications of optimization algorithms.
{"title":"Averting and Mitigating the Effects of Uncertainties with Optimal Control in Industrial Networked Control System","authors":"Brijraj Singh Solanki, R. Kumawat, S. Srinivasan","doi":"10.1109/iSES52644.2021.00080","DOIUrl":"https://doi.org/10.1109/iSES52644.2021.00080","url":null,"abstract":"Emerging trends, development and growth of industrial-networked control systems (i-NCSs) with real-time communication network drive it more susceptible to malicious intended intrusion and attack. Due to numerous advantages such as reduced maintenance, ease to install, ease of diagnosis and system wiring draws attention to use in various industrial and critical fields. The control performance and robust stability of NCS is directly related to reliable and successful transmission of critical information’s. So in this paper an approach is illustrated to alleviate the effects and avert the unwanted intended intrusive data through the designing of stability conditions and optimized control policies. An unwanted intrusion effects also forced us to design a controlled system, which is hard to be estimated by attackers, through the applications of optimization algorithms.","PeriodicalId":293167,"journal":{"name":"2021 IEEE International Symposium on Smart Electronic Systems (iSES) (Formerly iNiS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131051379","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 : 2021-12-01DOI: 10.1109/iSES52644.2021.00049
P. Geetha, S. Nanda, Rajendra Prasad Yadav
Direction of arrival (DOA) estimation in array signal processing has been studied extensively due to its potential applications. One key application is automotive radar, in which a only few snapshots or a single snapshot is applied for DOA estimation. In this paper, DOA estimation with a single snapshot is investigated using a recently reported meta-heuristics sailfish optimization algorithm. The sailfish optimization is influenced by the natural hunting process of sailfish to catch the prey (sardines). The objective is to maximize the maximum likelihood estimator fitness function with the sailfish optimization algorithm. The comparative analysis has been carried out with benchmark algorithms like Genetic Algorithm, Particle Swarm Optimization, and Differential Evolution under identical environments. Superior performance is reported by the sailfish algorithm in terms of convergence curve, box plot of accuracy, RMSE vs SNR plot compared to the other meta-heuristics.
{"title":"Direction of Arrival Estimation in Automotive Radar with Sailfish Optimization Algorithm","authors":"P. Geetha, S. Nanda, Rajendra Prasad Yadav","doi":"10.1109/iSES52644.2021.00049","DOIUrl":"https://doi.org/10.1109/iSES52644.2021.00049","url":null,"abstract":"Direction of arrival (DOA) estimation in array signal processing has been studied extensively due to its potential applications. One key application is automotive radar, in which a only few snapshots or a single snapshot is applied for DOA estimation. In this paper, DOA estimation with a single snapshot is investigated using a recently reported meta-heuristics sailfish optimization algorithm. The sailfish optimization is influenced by the natural hunting process of sailfish to catch the prey (sardines). The objective is to maximize the maximum likelihood estimator fitness function with the sailfish optimization algorithm. The comparative analysis has been carried out with benchmark algorithms like Genetic Algorithm, Particle Swarm Optimization, and Differential Evolution under identical environments. Superior performance is reported by the sailfish algorithm in terms of convergence curve, box plot of accuracy, RMSE vs SNR plot compared to the other meta-heuristics.","PeriodicalId":293167,"journal":{"name":"2021 IEEE International Symposium on Smart Electronic Systems (iSES) (Formerly iNiS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116391078","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 : 2021-12-01DOI: 10.1109/iSES52644.2021.00106
G. Nithin, B. S. Egala, A. K. Pradhan
The COVID-19 outbreak highlighted the smart healthcare infrastructure requirement to speed up vaccination and treatment. Present vaccination supply chain models are fragmented in nature, and they are suitable for a pandemic like COVID-19. Most of these vaccination supply chain models are cloud-centric and depend on humans. Due to this, the transparency in the supply chain and vaccination process is questionable. Moreover, we con’t trace where the vaccination programs are facing issues in real-time. Furthermore, traditional supply chain models are vulnerable to a single point of failure and lack people-centric service capabilities. This paper has proposed a novel supply chain model for COVID-19 using robust technologies such as Blockchain and the Internet of Things. Besides, it automates the entire vaccination supplication chain, and it records management without compromising data integrity. We have evaluated our proposed model using Ethereum based decentralized application (DApp) to showcase its real-time capabilities. The DApp contains two divisions to deal with internal (intra) and worldwide (inter) use cases. From the system analysis, it is clear that it provides digital records integrity, availability, and system scalability by eliminating a single point of failure. Finally, the proposed system eliminates human interference in digital record management, which is prone to errors and alternation.
{"title":"Global Level Smart Vaccination Tracking System using Blockchain and IoT","authors":"G. Nithin, B. S. Egala, A. K. Pradhan","doi":"10.1109/iSES52644.2021.00106","DOIUrl":"https://doi.org/10.1109/iSES52644.2021.00106","url":null,"abstract":"The COVID-19 outbreak highlighted the smart healthcare infrastructure requirement to speed up vaccination and treatment. Present vaccination supply chain models are fragmented in nature, and they are suitable for a pandemic like COVID-19. Most of these vaccination supply chain models are cloud-centric and depend on humans. Due to this, the transparency in the supply chain and vaccination process is questionable. Moreover, we con’t trace where the vaccination programs are facing issues in real-time. Furthermore, traditional supply chain models are vulnerable to a single point of failure and lack people-centric service capabilities. This paper has proposed a novel supply chain model for COVID-19 using robust technologies such as Blockchain and the Internet of Things. Besides, it automates the entire vaccination supplication chain, and it records management without compromising data integrity. We have evaluated our proposed model using Ethereum based decentralized application (DApp) to showcase its real-time capabilities. The DApp contains two divisions to deal with internal (intra) and worldwide (inter) use cases. From the system analysis, it is clear that it provides digital records integrity, availability, and system scalability by eliminating a single point of failure. Finally, the proposed system eliminates human interference in digital record management, which is prone to errors and alternation.","PeriodicalId":293167,"journal":{"name":"2021 IEEE International Symposium on Smart Electronic Systems (iSES) (Formerly iNiS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116741309","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 : 2021-12-01DOI: 10.1109/iSES52644.2021.00036
Binit Kumar Pandit, A. Banerjee
This paper presents a novel VLSI architecture design of the Sigmoid activation function using Chebyshev’s polynomial approximation for efficient hardware realization. The Sigmoid activation function is one of the key components for completing the classification task and provides generality to the deep networks. The complexity of the sigmoid function leads to low accuracy and longer latency in dedicated hardware design. Therefore, an accurate and fast hardware architecture of the sigmoid function is explored. Chebyshev’s polynomial approximation method is capable of reducing the sum of products (SOP) terms leading to optimum utilization of available hardware resources in FPGAs. The availability of a large number of embedded array multipliers in new FPGA families like Zynq, Kintex7, Virtex7, etc., makes hardware realization of non-linear functions like sigmoid easier and robust. The proposed VLSI architecture has been implemented and tested for its correctness on Xilinx’s Zynq UltraScale+ MPSoC ZCU104 Evaluation Kit using Xilinx Vivado 2018.3. software platform. It can be further used for any end-to-end prototyping using FPGAs and deployed for high-performance real-time applications.
{"title":"VLSI Architecture of Sigmoid Activation Function for Rapid Prototyping of Machine Learning Applications.","authors":"Binit Kumar Pandit, A. Banerjee","doi":"10.1109/iSES52644.2021.00036","DOIUrl":"https://doi.org/10.1109/iSES52644.2021.00036","url":null,"abstract":"This paper presents a novel VLSI architecture design of the Sigmoid activation function using Chebyshev’s polynomial approximation for efficient hardware realization. The Sigmoid activation function is one of the key components for completing the classification task and provides generality to the deep networks. The complexity of the sigmoid function leads to low accuracy and longer latency in dedicated hardware design. Therefore, an accurate and fast hardware architecture of the sigmoid function is explored. Chebyshev’s polynomial approximation method is capable of reducing the sum of products (SOP) terms leading to optimum utilization of available hardware resources in FPGAs. The availability of a large number of embedded array multipliers in new FPGA families like Zynq, Kintex7, Virtex7, etc., makes hardware realization of non-linear functions like sigmoid easier and robust. The proposed VLSI architecture has been implemented and tested for its correctness on Xilinx’s Zynq UltraScale+ MPSoC ZCU104 Evaluation Kit using Xilinx Vivado 2018.3. software platform. It can be further used for any end-to-end prototyping using FPGAs and deployed for high-performance real-time applications.","PeriodicalId":293167,"journal":{"name":"2021 IEEE International Symposium on Smart Electronic Systems (iSES) (Formerly iNiS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114987991","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 : 2021-12-01DOI: 10.1109/iSES52644.2021.00068
H. Sarma
Application of Internet of Things (IoT) in agriculture has got attention in recent times. Wireless Sensor Network (WSN) based IoT has been proposed to be deployed in various fields including agriculture. “Routing Protocol for Low Power and Lossy Networks” (RPL) is a standard routing protocol for IoT, proposed in 2012. However, RPL was not designed keeping IoT applications for precision agriculture in mind, and therefore, it needs modification in its design itself, in order to make RPL more suitable for such applications. In this paper, a suitable modification to RPL has been proposed keeping IoT based precision agriculture in mind. The proposed modification suggests a special hierarchical routing structure that leads to energy efficiency. This enhanced form of RPL is scalable and energy efficient. Performance analysis based on analytical model is presented. Future scope of the work is also outlined.
{"title":"Data Aggregation in Internet of Things aiming at Precision Agriculture","authors":"H. Sarma","doi":"10.1109/iSES52644.2021.00068","DOIUrl":"https://doi.org/10.1109/iSES52644.2021.00068","url":null,"abstract":"Application of Internet of Things (IoT) in agriculture has got attention in recent times. Wireless Sensor Network (WSN) based IoT has been proposed to be deployed in various fields including agriculture. “Routing Protocol for Low Power and Lossy Networks” (RPL) is a standard routing protocol for IoT, proposed in 2012. However, RPL was not designed keeping IoT applications for precision agriculture in mind, and therefore, it needs modification in its design itself, in order to make RPL more suitable for such applications. In this paper, a suitable modification to RPL has been proposed keeping IoT based precision agriculture in mind. The proposed modification suggests a special hierarchical routing structure that leads to energy efficiency. This enhanced form of RPL is scalable and energy efficient. Performance analysis based on analytical model is presented. Future scope of the work is also outlined.","PeriodicalId":293167,"journal":{"name":"2021 IEEE International Symposium on Smart Electronic Systems (iSES) (Formerly iNiS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134228935","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 : 2021-12-01DOI: 10.1109/iSES52644.2021.00067
Bhabesh Mali, Santanu Saha, Daimalu Brahma, P. Singh, Sukumar Nandi
In recent years, there has been a lot of utilization of Artificial Intelligence and Machine Learning in the field of agriculture to address various types of challenges faced by this sector. In an agro-based country, the focus of the agricultural sector is to achieve the maximum yield of the crops grown and make profits out of it. There has been a severe loss of crops due to the various climatic variations, pest infestation, improper soil treatment, inadequate rainfall, inadequate nutrients etc. In various research studies, the use of machine learning has been found very helpful in addressing various crop-related problems including crop prediction based on various factors. Motivated from this, we, in this paper conducted a case study in Assam for the prediction of alternate crops using artificial intelligence and with an objective to help out the farmers. With our proposed solution, the farmers will be able to predict a particular crop that will be most suitable to grow according to the season, pH of the soil, temperature, rainfall and type of the soil, keeping an eye to get the maximum yield followed by maximum profit. We have used Artificial Neural Networks (ANN) to predict the right crop to be grown. The proposed model efficiently predicts the alternate crop by preserving the original data distribution with an accuracy of about 90.89% for the test data and by using the k-fold Cross-Validation, the accuracy is about 91.57%.
{"title":"Alternate Crop Prediction using Artificial Intelligence: A Case Study in Assam","authors":"Bhabesh Mali, Santanu Saha, Daimalu Brahma, P. Singh, Sukumar Nandi","doi":"10.1109/iSES52644.2021.00067","DOIUrl":"https://doi.org/10.1109/iSES52644.2021.00067","url":null,"abstract":"In recent years, there has been a lot of utilization of Artificial Intelligence and Machine Learning in the field of agriculture to address various types of challenges faced by this sector. In an agro-based country, the focus of the agricultural sector is to achieve the maximum yield of the crops grown and make profits out of it. There has been a severe loss of crops due to the various climatic variations, pest infestation, improper soil treatment, inadequate rainfall, inadequate nutrients etc. In various research studies, the use of machine learning has been found very helpful in addressing various crop-related problems including crop prediction based on various factors. Motivated from this, we, in this paper conducted a case study in Assam for the prediction of alternate crops using artificial intelligence and with an objective to help out the farmers. With our proposed solution, the farmers will be able to predict a particular crop that will be most suitable to grow according to the season, pH of the soil, temperature, rainfall and type of the soil, keeping an eye to get the maximum yield followed by maximum profit. We have used Artificial Neural Networks (ANN) to predict the right crop to be grown. The proposed model efficiently predicts the alternate crop by preserving the original data distribution with an accuracy of about 90.89% for the test data and by using the k-fold Cross-Validation, the accuracy is about 91.57%.","PeriodicalId":293167,"journal":{"name":"2021 IEEE International Symposium on Smart Electronic Systems (iSES) (Formerly iNiS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133666864","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 : 2021-12-01DOI: 10.1109/iSES52644.2021.00093
Wei Ren, Junhao Pan, Deming Chen
Application-specific acceleration has prevailed in cloud computing and data centers. But the current infrastructure design provides little or no support for security in external accelerators. Existing trusted computing solutions such as Intel SGX or ARM TrustZone only target CPU-only environments, leaving external accelerators and peripheral devices unprotected. This work proposes AccGuard, a new scheme to extend trust computation for remote FPGA accelerators. AccGuard consists of a security manager (SM) with hardware root of trust and remote attestation through standard cryptographic primitives to form an enclave framework for FPGA accelerators. It minimizes the performance overhead (due to the security features) compared to a state-of-the-art CPU-based enclave framework, Intel SGX, while enjoying the benefit of improved performance through hardware acceleration.
{"title":"AccGuard: Secure and Trusted Computation on Remote FPGA Accelerators","authors":"Wei Ren, Junhao Pan, Deming Chen","doi":"10.1109/iSES52644.2021.00093","DOIUrl":"https://doi.org/10.1109/iSES52644.2021.00093","url":null,"abstract":"Application-specific acceleration has prevailed in cloud computing and data centers. But the current infrastructure design provides little or no support for security in external accelerators. Existing trusted computing solutions such as Intel SGX or ARM TrustZone only target CPU-only environments, leaving external accelerators and peripheral devices unprotected. This work proposes AccGuard, a new scheme to extend trust computation for remote FPGA accelerators. AccGuard consists of a security manager (SM) with hardware root of trust and remote attestation through standard cryptographic primitives to form an enclave framework for FPGA accelerators. It minimizes the performance overhead (due to the security features) compared to a state-of-the-art CPU-based enclave framework, Intel SGX, while enjoying the benefit of improved performance through hardware acceleration.","PeriodicalId":293167,"journal":{"name":"2021 IEEE International Symposium on Smart Electronic Systems (iSES) (Formerly iNiS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133093578","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 : 2021-12-01DOI: 10.1109/iSES52644.2021.00019
G. Sharma, A. Joshi, E. Pilli
Electroencephalography (EEG)-based depression detection in the early stage is a very challenging and important research area in artificial intelligence as it can save the lives of several people. This paper presents EEG-based machine learning models involving 30 healthy subjects and 33 major depressive disorder (MDD) subjects to diagnose MDD. The model with the best performance has been evaluated on the Internet of Medical Things (IoMT) framework for smart healthcare. The main idea behind this study is to recognize features and classifiers which can best discriminate the healthy and depressive subjects. This study has three main steps of analysis: 1) Linear, non-linear, fractal dimension, statistical, time, coherence features have been extracted from EEG signals. Their effects are investigated, and quality features are identified. 2) Three feature selection methods, Principle component analysis (PCA), Neighbourhood component analysis (NBA), and Relief-based algorithm (RBA), are utilized for the selection of most relevant features, and their performance is compared. 3) For discriminating normal and depressed subjects, radial-basis function (RBF) based support vector machine (SVM), K- nearest neighbor (KNN), logistic regression (LR), decision tree (DT), naïve Bayes classification (NBC), bagged tree (BT) and linear discriminant analysis (LDA) classifier are used. This paper concludes that non-linear features with an RBF-SVM classifier achieve the best classification accuracy of 98.90%. The findings in this study are utilized to develop a model to detect depression in remote applications and smart healthcare.
{"title":"An Automated MDD Detection System based on Machine Learning Methods in Smart Connected Healthcare","authors":"G. Sharma, A. Joshi, E. Pilli","doi":"10.1109/iSES52644.2021.00019","DOIUrl":"https://doi.org/10.1109/iSES52644.2021.00019","url":null,"abstract":"Electroencephalography (EEG)-based depression detection in the early stage is a very challenging and important research area in artificial intelligence as it can save the lives of several people. This paper presents EEG-based machine learning models involving 30 healthy subjects and 33 major depressive disorder (MDD) subjects to diagnose MDD. The model with the best performance has been evaluated on the Internet of Medical Things (IoMT) framework for smart healthcare. The main idea behind this study is to recognize features and classifiers which can best discriminate the healthy and depressive subjects. This study has three main steps of analysis: 1) Linear, non-linear, fractal dimension, statistical, time, coherence features have been extracted from EEG signals. Their effects are investigated, and quality features are identified. 2) Three feature selection methods, Principle component analysis (PCA), Neighbourhood component analysis (NBA), and Relief-based algorithm (RBA), are utilized for the selection of most relevant features, and their performance is compared. 3) For discriminating normal and depressed subjects, radial-basis function (RBF) based support vector machine (SVM), K- nearest neighbor (KNN), logistic regression (LR), decision tree (DT), naïve Bayes classification (NBC), bagged tree (BT) and linear discriminant analysis (LDA) classifier are used. This paper concludes that non-linear features with an RBF-SVM classifier achieve the best classification accuracy of 98.90%. The findings in this study are utilized to develop a model to detect depression in remote applications and smart healthcare.","PeriodicalId":293167,"journal":{"name":"2021 IEEE International Symposium on Smart Electronic Systems (iSES) (Formerly iNiS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124970930","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：