Pub Date : 2022-05-01DOI: 10.1109/SMARTTECH54121.2022.00057
M. Abdelhafidh, Nadia Charef, A. B. Mnaouer, L. Fourati
Despite the immense use of single Unmanned Aerial Vehicle (UAV) systems in various applications, it is not yet able to cover large areas with optimized energy consumption. Accordingly, Flying Ad-hoc Network (FANET), as a collaborative groups of UAV s, is tremendously employed in recent research works allowing larger coverage and efficient monitoring. To ensure a secure FANET control, Software-Defined Networking (SDN) based solutions are frequently considered. This work presents and compares the recent SDN-based solutions proposed to reinforce FANET security and reduce its attacks. In addition, open research issues are highlighted with respect to SDN-FANET challenges.
{"title":"Software-Defined Networking for Flying Ad-hoc Network Security: A Survey","authors":"M. Abdelhafidh, Nadia Charef, A. B. Mnaouer, L. Fourati","doi":"10.1109/SMARTTECH54121.2022.00057","DOIUrl":"https://doi.org/10.1109/SMARTTECH54121.2022.00057","url":null,"abstract":"Despite the immense use of single Unmanned Aerial Vehicle (UAV) systems in various applications, it is not yet able to cover large areas with optimized energy consumption. Accordingly, Flying Ad-hoc Network (FANET), as a collaborative groups of UAV s, is tremendously employed in recent research works allowing larger coverage and efficient monitoring. To ensure a secure FANET control, Software-Defined Networking (SDN) based solutions are frequently considered. This work presents and compares the recent SDN-based solutions proposed to reinforce FANET security and reduce its attacks. In addition, open research issues are highlighted with respect to SDN-FANET challenges.","PeriodicalId":140094,"journal":{"name":"2022 2nd International Conference of Smart Systems and Emerging Technologies (SMARTTECH)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123809493","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 : 2022-05-01DOI: 10.1109/SMARTTECH54121.2022.00033
Sarah Alhassan, A. Soudani
The affordability and miniaturization of sensors create a revolution in wearable wireless solutions deployed to collect physiological parameters to assist in diseases/disorders diagnosis. Electroencephalography (EEG), a recording of the brain's electrical activity, is a promising physiological measure for autism spectrum disorder detection. It can reveal the irregularity of the neural system that is associated with autism. Wireless sensors represent a suitable infrastructure that can be deployed for signal transmission to the processing center. However, streaming EEG signals remotely for classification could shorten the lifetime of the wireless sensor and might question the viability of the application. Therefore, reducing the data transmission might preserve the sensor's energy and increase the wireless sensor network lifetime. This paper proposes the design of a sensor-based scheme for early-age autism detection in children. The proposed scheme uses low-complexity algorithms for on-node EEG processing, relevant features extraction and classification. The proposed processing scheme of the EEG signal is based on Haar wavelet transform and dynamics features. The experimental results show 93% accuracy, 86% sensitivity, and 100% specificity.
{"title":"Energy-aware EEG-based Scheme for Early-age Autism Detection","authors":"Sarah Alhassan, A. Soudani","doi":"10.1109/SMARTTECH54121.2022.00033","DOIUrl":"https://doi.org/10.1109/SMARTTECH54121.2022.00033","url":null,"abstract":"The affordability and miniaturization of sensors create a revolution in wearable wireless solutions deployed to collect physiological parameters to assist in diseases/disorders diagnosis. Electroencephalography (EEG), a recording of the brain's electrical activity, is a promising physiological measure for autism spectrum disorder detection. It can reveal the irregularity of the neural system that is associated with autism. Wireless sensors represent a suitable infrastructure that can be deployed for signal transmission to the processing center. However, streaming EEG signals remotely for classification could shorten the lifetime of the wireless sensor and might question the viability of the application. Therefore, reducing the data transmission might preserve the sensor's energy and increase the wireless sensor network lifetime. This paper proposes the design of a sensor-based scheme for early-age autism detection in children. The proposed scheme uses low-complexity algorithms for on-node EEG processing, relevant features extraction and classification. The proposed processing scheme of the EEG signal is based on Haar wavelet transform and dynamics features. The experimental results show 93% accuracy, 86% sensitivity, and 100% specificity.","PeriodicalId":140094,"journal":{"name":"2022 2nd International Conference of Smart Systems and Emerging Technologies (SMARTTECH)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129112073","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 : 2022-05-01DOI: 10.1109/SMARTTECH54121.2022.00025
M. Krichen, A. Mihoub, M. Alzahrani, W. Adoni, Tarik Nahhal
Formal approaches can provide strict correctness guarantees for the development of both hardware and software systems. In this work, we examine state-of-the-art formal methods for the verification and validation of machine learning systems in particular. We first provide a brief summary of existing formal approaches in general. After that, we report on formal methods developed for validating data preparation and training phases. Then, we go over the formal methods used for the verification of machine learning systems. At this level, we consider both partial and exhaustive techniques. In addition, we review research works dedicated to the verification of support vector machines and decision tree ensembles. Finally, we propose several potential future directions for formal verification of machine learning systems.
{"title":"Are Formal Methods Applicable To Machine Learning And Artificial Intelligence?","authors":"M. Krichen, A. Mihoub, M. Alzahrani, W. Adoni, Tarik Nahhal","doi":"10.1109/SMARTTECH54121.2022.00025","DOIUrl":"https://doi.org/10.1109/SMARTTECH54121.2022.00025","url":null,"abstract":"Formal approaches can provide strict correctness guarantees for the development of both hardware and software systems. In this work, we examine state-of-the-art formal methods for the verification and validation of machine learning systems in particular. We first provide a brief summary of existing formal approaches in general. After that, we report on formal methods developed for validating data preparation and training phases. Then, we go over the formal methods used for the verification of machine learning systems. At this level, we consider both partial and exhaustive techniques. In addition, we review research works dedicated to the verification of support vector machines and decision tree ensembles. Finally, we propose several potential future directions for formal verification of machine learning systems.","PeriodicalId":140094,"journal":{"name":"2022 2nd International Conference of Smart Systems and Emerging Technologies (SMARTTECH)","volume":"129 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130072332","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 : 2022-05-01DOI: 10.1109/SMARTTECH54121.2022.00050
S. Rashid, M. Khan, U. Akram, A. Saeed
Vehicular Ad-hoc Network (VANET) is a primary part of Intelligent Transportation System (ITS). VANETS provides mechanisms for vehicles to communicate with road side units (RSUs). This information represents past data and predicts upcoming events. The emergence of Neural Networks (NNs) and its variants can simulate learning model for future prediction. Utilizing vehicular network and recognition property of neural network, it is now possible to analyze data of real-time driving and road conditions to predict future traffic condition. This system can be used for traffic monitoring, accident prediction or road hazard detection. In this paper, a detailed survey is provided about use of neural networks for prediction purposes in VANETs.
{"title":"Efficient Future Prediction using Neural Network in Vehicular Ad hoc Networks","authors":"S. Rashid, M. Khan, U. Akram, A. Saeed","doi":"10.1109/SMARTTECH54121.2022.00050","DOIUrl":"https://doi.org/10.1109/SMARTTECH54121.2022.00050","url":null,"abstract":"Vehicular Ad-hoc Network (VANET) is a primary part of Intelligent Transportation System (ITS). VANETS provides mechanisms for vehicles to communicate with road side units (RSUs). This information represents past data and predicts upcoming events. The emergence of Neural Networks (NNs) and its variants can simulate learning model for future prediction. Utilizing vehicular network and recognition property of neural network, it is now possible to analyze data of real-time driving and road conditions to predict future traffic condition. This system can be used for traffic monitoring, accident prediction or road hazard detection. In this paper, a detailed survey is provided about use of neural networks for prediction purposes in VANETs.","PeriodicalId":140094,"journal":{"name":"2022 2nd International Conference of Smart Systems and Emerging Technologies (SMARTTECH)","volume":"373 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134315209","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 : 2022-05-01DOI: 10.1109/SMARTTECH54121.2022.00029
Francesco Nocera, Simone Demilito, Piergiorgio Ladisa, M. Mongiello, A. Shah, Jawad Ahmad, Eugenio Di Sciascio
Distributed denial of service (DDoS) cyber-attack poses a severe threat to the industrial Internet of Things (IIoT) operation due to the security vulnerabilities resulted from increased connectivity and openness, and the large number of deployed low computation power devices. The aim of this paper is to provide a solution to the application-level DDoS attack, which is increasingly difficult to detect because botnets tend to get confused with various legitimate users. The proposed solution aims to study the behavior of users and bots, through a User Behavior Analytics (UBA) solution by using Long Short-Term Memory (LSTM) neural networks to provide a potentially ideal solution to mitigate this type of attack. Accuracy, precision and recall were used to evaluate the model. The values of the three metrics resulting from the training of the model are all very high, which makes us understand that the model reacts well to illicit users but at the same time it does not exchange the licit users for malicious ones.
{"title":"A User Behavior Analytics (UBA)- based solution using LSTM Neural Network to mitigate DDoS Attack in Fog and Cloud Environment","authors":"Francesco Nocera, Simone Demilito, Piergiorgio Ladisa, M. Mongiello, A. Shah, Jawad Ahmad, Eugenio Di Sciascio","doi":"10.1109/SMARTTECH54121.2022.00029","DOIUrl":"https://doi.org/10.1109/SMARTTECH54121.2022.00029","url":null,"abstract":"Distributed denial of service (DDoS) cyber-attack poses a severe threat to the industrial Internet of Things (IIoT) operation due to the security vulnerabilities resulted from increased connectivity and openness, and the large number of deployed low computation power devices. The aim of this paper is to provide a solution to the application-level DDoS attack, which is increasingly difficult to detect because botnets tend to get confused with various legitimate users. The proposed solution aims to study the behavior of users and bots, through a User Behavior Analytics (UBA) solution by using Long Short-Term Memory (LSTM) neural networks to provide a potentially ideal solution to mitigate this type of attack. Accuracy, precision and recall were used to evaluate the model. The values of the three metrics resulting from the training of the model are all very high, which makes us understand that the model reacts well to illicit users but at the same time it does not exchange the licit users for malicious ones.","PeriodicalId":140094,"journal":{"name":"2022 2nd International Conference of Smart Systems and Emerging Technologies (SMARTTECH)","volume":"85 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122559654","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 : 2022-05-01DOI: 10.1109/SMARTTECH54121.2022.00026
Muhammad Arslan Rauf, Muhammad Jehanzeb, Ubaid Ullah, Usman Ali, Muhammad Kashif, Muhammad Abdullah
The fabric pattern recognition and subsequently the classification is an imperative task in textiles. Currently, this is done manually, therefore, the need of the requirement is to develop a system that could recognize and classify the fabric weave patterns for ease of inspection and storage. The classification of woven fabrics in today's textile industry is generally manual, requiring significant human effort and a long time. Automatic and effective approaches for woven fabric classification are desperately required with the rapid development of computer vision. This paper proposes an automated and real-time classification technique to analyze three woven fabrics: plain, twill, and satin weave. To achieve the objective, ResNet pre-trained Convolutional Neural Network architecture is used for classification. To obtain texture characteristics, the gray-level co-occurrence matrix and Gabor wavelet, are included in the technique. To eliminate redundancy and maximize main component feature vectors, Principal component analysis is then used to select feature vectors. The experimental result shows that with quicker training speed, the Deep CNN classifier can reliably and efficiently identify woven fabrics. Deep Convolutional Neural Network provides the best accuracy 96.15%.
{"title":"Fabric Weave Pattern Recognition and Classification by Machine Learning","authors":"Muhammad Arslan Rauf, Muhammad Jehanzeb, Ubaid Ullah, Usman Ali, Muhammad Kashif, Muhammad Abdullah","doi":"10.1109/SMARTTECH54121.2022.00026","DOIUrl":"https://doi.org/10.1109/SMARTTECH54121.2022.00026","url":null,"abstract":"The fabric pattern recognition and subsequently the classification is an imperative task in textiles. Currently, this is done manually, therefore, the need of the requirement is to develop a system that could recognize and classify the fabric weave patterns for ease of inspection and storage. The classification of woven fabrics in today's textile industry is generally manual, requiring significant human effort and a long time. Automatic and effective approaches for woven fabric classification are desperately required with the rapid development of computer vision. This paper proposes an automated and real-time classification technique to analyze three woven fabrics: plain, twill, and satin weave. To achieve the objective, ResNet pre-trained Convolutional Neural Network architecture is used for classification. To obtain texture characteristics, the gray-level co-occurrence matrix and Gabor wavelet, are included in the technique. To eliminate redundancy and maximize main component feature vectors, Principal component analysis is then used to select feature vectors. The experimental result shows that with quicker training speed, the Deep CNN classifier can reliably and efficiently identify woven fabrics. Deep Convolutional Neural Network provides the best accuracy 96.15%.","PeriodicalId":140094,"journal":{"name":"2022 2nd International Conference of Smart Systems and Emerging Technologies (SMARTTECH)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124352170","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 : 2022-05-01DOI: 10.1109/SMARTTECH54121.2022.00043
Mohamed Lamine Hamida, A. Fekik, A. Azar, Nashwa Ahmad Kamal, Aghiles Ardjal, H. Denoun
The multicellular midpoint inverter is an intriguing situation; it is made up of p switching cells isolated by p-1 floating capacitors. This inverter's voltage levels provide frequent advantages and allow it to gain a good current source of excellent quality. This work offers a fuzzy logic - cyclic reports modulation control to improve the output power quality of a one phase series five-cell inverter, which is based on the converter's average model. To keep the capacitor voltages close to their references, the cyclic reports modulation approach is used. Keeping in mind that this command only ensures the regulation of the capacitor voltages, the output current regulation is also ensured in this study by incorporating a fuzzy logic controller. The suggested method is compared to the conventional proportional-integral regulator and the natural balancing strategy. The simulation results demonstrate that the five-cell inverter topology and proposed control result in good performance.
{"title":"Fuzzy Logic Cyclic Reports Modulation Control For a Five-Cell Inverter","authors":"Mohamed Lamine Hamida, A. Fekik, A. Azar, Nashwa Ahmad Kamal, Aghiles Ardjal, H. Denoun","doi":"10.1109/SMARTTECH54121.2022.00043","DOIUrl":"https://doi.org/10.1109/SMARTTECH54121.2022.00043","url":null,"abstract":"The multicellular midpoint inverter is an intriguing situation; it is made up of p switching cells isolated by p-1 floating capacitors. This inverter's voltage levels provide frequent advantages and allow it to gain a good current source of excellent quality. This work offers a fuzzy logic - cyclic reports modulation control to improve the output power quality of a one phase series five-cell inverter, which is based on the converter's average model. To keep the capacitor voltages close to their references, the cyclic reports modulation approach is used. Keeping in mind that this command only ensures the regulation of the capacitor voltages, the output current regulation is also ensured in this study by incorporating a fuzzy logic controller. The suggested method is compared to the conventional proportional-integral regulator and the natural balancing strategy. The simulation results demonstrate that the five-cell inverter topology and proposed control result in good performance.","PeriodicalId":140094,"journal":{"name":"2022 2nd International Conference of Smart Systems and Emerging Technologies (SMARTTECH)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124578769","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 : 2022-05-01DOI: 10.1109/SMARTTECH54121.2022.00045
Muhammad Kazim, A. Azar, Mohamed Abdelkader, A. Koubâa
Unmanned Aerial Vehicles (UAVs) now play critical roles in a wide range of real-world applications and improving their control performance has become an increasingly appealing research topic. The goal of this paper is to solve the problem of controlling UAVs subject to external disturbances to maintain the desired trajectory while ensuring reliable and rapid convergence to the actual values. This paper presents a novel approach for the design and stability analysis of an adaptive trajectory tracking control for a multi-rotor UAV. UA V controllers are divided into two parts: position controllers and attitude controllers. A new Linear Parameter Varying Model Predictive Controller (LPV -MPC) is designed for attitude controller stabilization and quick tracking of the desired values of the Euler angles. The position controller is in charge of the position variables., which are calculated using the adaptive backstepping method and the targeted reference trajectory. The Lyapunov theory is utilized to prove the stability of the UAV's position controller. Finally., simulation results are provided., which demonstrates the effectiveness of the proposed control framework against disturbances.
{"title":"Adaptive Backstepping based Linear Parameter Varying Model Predictive Control Multi-rotor UAVs","authors":"Muhammad Kazim, A. Azar, Mohamed Abdelkader, A. Koubâa","doi":"10.1109/SMARTTECH54121.2022.00045","DOIUrl":"https://doi.org/10.1109/SMARTTECH54121.2022.00045","url":null,"abstract":"Unmanned Aerial Vehicles (UAVs) now play critical roles in a wide range of real-world applications and improving their control performance has become an increasingly appealing research topic. The goal of this paper is to solve the problem of controlling UAVs subject to external disturbances to maintain the desired trajectory while ensuring reliable and rapid convergence to the actual values. This paper presents a novel approach for the design and stability analysis of an adaptive trajectory tracking control for a multi-rotor UAV. UA V controllers are divided into two parts: position controllers and attitude controllers. A new Linear Parameter Varying Model Predictive Controller (LPV -MPC) is designed for attitude controller stabilization and quick tracking of the desired values of the Euler angles. The position controller is in charge of the position variables., which are calculated using the adaptive backstepping method and the targeted reference trajectory. The Lyapunov theory is utilized to prove the stability of the UAV's position controller. Finally., simulation results are provided., which demonstrates the effectiveness of the proposed control framework against disturbances.","PeriodicalId":140094,"journal":{"name":"2022 2nd International Conference of Smart Systems and Emerging Technologies (SMARTTECH)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130076086","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 : 2022-05-01DOI: 10.1109/SMARTTECH54121.2022.00042
A. Fekik, A. Azar, Mohamed Lamine Hamida, Nashwa Ahmad Kamal
Pulse width modulation (PWM) rectifiers are among the best solutions for improving the electrical power transfer quality from a source to a receiver. In fact, some authors have presented several methods for controlling the three-phase PWM rectifier and eliminating total harmonic distortion to achieve an uncontaminated system operating within a unit power factor. This article focuses on the sliding mode method, which is based on data from two or three line current sensors and a DC link voltage sensor, as well as the development of the most modern network voltage controllers, which include a sliding mode regulator for the system. The simulation results demonstrate the viability and reliability of the observer's sliding mode methodology in a transient and stable state with a quasi-sinusoidal low total harmonic distortion (THD) line current source and a good maintenance of the reference voltage on the same day, in the DC side of the PWM rectifier, in accordance with standards.
{"title":"Sliding Mode Control Based on Observation of line side PWM Rectifier Voltage","authors":"A. Fekik, A. Azar, Mohamed Lamine Hamida, Nashwa Ahmad Kamal","doi":"10.1109/SMARTTECH54121.2022.00042","DOIUrl":"https://doi.org/10.1109/SMARTTECH54121.2022.00042","url":null,"abstract":"Pulse width modulation (PWM) rectifiers are among the best solutions for improving the electrical power transfer quality from a source to a receiver. In fact, some authors have presented several methods for controlling the three-phase PWM rectifier and eliminating total harmonic distortion to achieve an uncontaminated system operating within a unit power factor. This article focuses on the sliding mode method, which is based on data from two or three line current sensors and a DC link voltage sensor, as well as the development of the most modern network voltage controllers, which include a sliding mode regulator for the system. The simulation results demonstrate the viability and reliability of the observer's sliding mode methodology in a transient and stable state with a quasi-sinusoidal low total harmonic distortion (THD) line current source and a good maintenance of the reference voltage on the same day, in the DC side of the PWM rectifier, in accordance with standards.","PeriodicalId":140094,"journal":{"name":"2022 2nd International Conference of Smart Systems and Emerging Technologies (SMARTTECH)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125821082","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 : 2022-05-01DOI: 10.1109/SMARTTECH54121.2022.00041
Salim Klibi, M. Vernet, Denis Schwartz, I. Farah
This study aims to improve the automatic detection of epileptic seizures (ESs) using machine learning (ML) algorithms applied to electroencephalography (EEG) brainwave data. Previous studies based on a database published online showed high seizure detection accuracies, but they contrasted seizure activity to all kinds of non-seizure EEG activity, recorded from different populations (healthy and patient) and different types of electrodes (surface and intracranial). Here we decided to focus on detecting seizures from non-seizure activity recorded from the same type of electrodes in the same group of patients. We applied different ML classifiers such as Extreme Gradient Boosting (XgBOOST), Naive Bayes (NB), k-Nearest Neighbor (k-NN), Random Forest (RF), Support Vector Machine (SVM), Linear Regression (LR), and Decision Tree (DT). The best Area Under Curve (AUC) value is given by XgBOOST with 95.84%. This research helps to improve the detection of human ES in EEG signal recordings.
{"title":"Towards a better multivariate time-series detection of epileptic seizures in electroencephalogram (EEG) using Machine Learning algorithms","authors":"Salim Klibi, M. Vernet, Denis Schwartz, I. Farah","doi":"10.1109/SMARTTECH54121.2022.00041","DOIUrl":"https://doi.org/10.1109/SMARTTECH54121.2022.00041","url":null,"abstract":"This study aims to improve the automatic detection of epileptic seizures (ESs) using machine learning (ML) algorithms applied to electroencephalography (EEG) brainwave data. Previous studies based on a database published online showed high seizure detection accuracies, but they contrasted seizure activity to all kinds of non-seizure EEG activity, recorded from different populations (healthy and patient) and different types of electrodes (surface and intracranial). Here we decided to focus on detecting seizures from non-seizure activity recorded from the same type of electrodes in the same group of patients. We applied different ML classifiers such as Extreme Gradient Boosting (XgBOOST), Naive Bayes (NB), k-Nearest Neighbor (k-NN), Random Forest (RF), Support Vector Machine (SVM), Linear Regression (LR), and Decision Tree (DT). The best Area Under Curve (AUC) value is given by XgBOOST with 95.84%. This research helps to improve the detection of human ES in EEG signal recordings.","PeriodicalId":140094,"journal":{"name":"2022 2nd International Conference of Smart Systems and Emerging Technologies (SMARTTECH)","volume":"145 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127598308","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：