Pub Date : 2021-03-22DOI: 10.1109/SSD52085.2021.9429416
Noureddaher Zaidi, A. Khedher, M. Jemli
In this paper, we present a hybrid fault diagnosis approach dedicated for PV generators via current-voltage and power-voltage curves analysis. It is mainly based on two signature generators: a fuzzy logic classifier and a based threshold conventional one. The two classifiers act on the available data by considering three thresholds which are made according to the generator PV typical parameters and with a total conformity with the standards. The proposed fault diagnosis approach requires only the available measured variables and is able to identify the most frequently met faults related to shading, temperature, leakage current and increased series resistance losses. The addressed PV generators are based on one diode model. The overall results have proved the proposed methodology capability in PV faults detection and identification.
{"title":"A Hybrid fault diagnosis approach for PV generators based on I-V and P-V characteristics analysis","authors":"Noureddaher Zaidi, A. Khedher, M. Jemli","doi":"10.1109/SSD52085.2021.9429416","DOIUrl":"https://doi.org/10.1109/SSD52085.2021.9429416","url":null,"abstract":"In this paper, we present a hybrid fault diagnosis approach dedicated for PV generators via current-voltage and power-voltage curves analysis. It is mainly based on two signature generators: a fuzzy logic classifier and a based threshold conventional one. The two classifiers act on the available data by considering three thresholds which are made according to the generator PV typical parameters and with a total conformity with the standards. The proposed fault diagnosis approach requires only the available measured variables and is able to identify the most frequently met faults related to shading, temperature, leakage current and increased series resistance losses. The addressed PV generators are based on one diode model. The overall results have proved the proposed methodology capability in PV faults detection and identification.","PeriodicalId":6799,"journal":{"name":"2021 18th International Multi-Conference on Systems, Signals & Devices (SSD)","volume":"56 1","pages":"97-102"},"PeriodicalIF":0.0,"publicationDate":"2021-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81372101","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 : 2021-03-22DOI: 10.1109/SSD52085.2021.9429298
B. B. Atitallah, J. R. Bautista-Quijano, Haythem Ayari, Ahmed Yahia Kallel, D. Bouchaala, N. Derbel, O. Kanoun
Nowadays, the demand for flexible and wearable measurement systems is significantly increasing. Thereby, sensors based on carbon nanotubes (CNT) materials are gaining importance due to their high flexibility, sensitivity and medical compatibility. Nanocomposite based strain sensors present an interesting potential of movements detection that helps to build the basis for body attached sensor networks, which have the capability for tracking finger movements, gestures and grasping. However, the output of the sensor is noisy and having outliers due to the random deformation of the CNT conductive paths during applied strain, which needs to be filtered. This paper presents S-TPU/C-TPU strain sensors attached to a glove for hand gesture recognition. A filtering study has been conducted of four digital filters for real-time processing of the recorded data (Moving average, Moving median, Savitzky-Golay, and Gaussian), which is required to improve the quality of the data for better gesture identification and classification. The filters are evaluated based on their real-time response and smoothing performance. The Savitzky-Golay filter was found to be the most suitable filter to remove the inherent noises and smooth the baseline and curves of the signal with a fast real-time response equal to 0.072s.
{"title":"Comparative Study of Digital Filters for a Smart Glove Functionalized with Nanocomposite Strain Sensor","authors":"B. B. Atitallah, J. R. Bautista-Quijano, Haythem Ayari, Ahmed Yahia Kallel, D. Bouchaala, N. Derbel, O. Kanoun","doi":"10.1109/SSD52085.2021.9429298","DOIUrl":"https://doi.org/10.1109/SSD52085.2021.9429298","url":null,"abstract":"Nowadays, the demand for flexible and wearable measurement systems is significantly increasing. Thereby, sensors based on carbon nanotubes (CNT) materials are gaining importance due to their high flexibility, sensitivity and medical compatibility. Nanocomposite based strain sensors present an interesting potential of movements detection that helps to build the basis for body attached sensor networks, which have the capability for tracking finger movements, gestures and grasping. However, the output of the sensor is noisy and having outliers due to the random deformation of the CNT conductive paths during applied strain, which needs to be filtered. This paper presents S-TPU/C-TPU strain sensors attached to a glove for hand gesture recognition. A filtering study has been conducted of four digital filters for real-time processing of the recorded data (Moving average, Moving median, Savitzky-Golay, and Gaussian), which is required to improve the quality of the data for better gesture identification and classification. The filters are evaluated based on their real-time response and smoothing performance. The Savitzky-Golay filter was found to be the most suitable filter to remove the inherent noises and smooth the baseline and curves of the signal with a fast real-time response equal to 0.072s.","PeriodicalId":6799,"journal":{"name":"2021 18th International Multi-Conference on Systems, Signals & Devices (SSD)","volume":"5 1","pages":"1366-1371"},"PeriodicalIF":0.0,"publicationDate":"2021-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81987929","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 : 2021-03-22DOI: 10.1109/SSD52085.2021.9429308
B. Bourouis, H. Djeghloud, H. Benalla
This paper concerns the application of a NPC three-level shunt active power filter for damping harmonic disturbances from a three-phase feeder. The main contribution of the article is the elaboration of an algorithm dedicated to manage the energy in the hybrid fuel cell/battery DC bus feeding the SAPF. Design of active and passive components is presented. The control circuit is based on the SRF algorithm for detecting the reference harmonic currents and on the phase-shifted carrier-based PWM technique for gating signals generation. Moreover, dimensioning of the SAPF input DC bus voltage and AC output current PI regulators are provided. The study is validated through computer simulations using MATLAB/Simulink. The checked THDs of the feeder voltage and current, power factor and current unbalance rate, demonstrate a satisfying improvement in the power quality of the feeder.
{"title":"Three-Level NPC Shunt Active Filter Powered by a Hybrid Fuel-Cell/Battery DC Bus Voltage","authors":"B. Bourouis, H. Djeghloud, H. Benalla","doi":"10.1109/SSD52085.2021.9429308","DOIUrl":"https://doi.org/10.1109/SSD52085.2021.9429308","url":null,"abstract":"This paper concerns the application of a NPC three-level shunt active power filter for damping harmonic disturbances from a three-phase feeder. The main contribution of the article is the elaboration of an algorithm dedicated to manage the energy in the hybrid fuel cell/battery DC bus feeding the SAPF. Design of active and passive components is presented. The control circuit is based on the SRF algorithm for detecting the reference harmonic currents and on the phase-shifted carrier-based PWM technique for gating signals generation. Moreover, dimensioning of the SAPF input DC bus voltage and AC output current PI regulators are provided. The study is validated through computer simulations using MATLAB/Simulink. The checked THDs of the feeder voltage and current, power factor and current unbalance rate, demonstrate a satisfying improvement in the power quality of the feeder.","PeriodicalId":6799,"journal":{"name":"2021 18th International Multi-Conference on Systems, Signals & Devices (SSD)","volume":"19 1","pages":"330-339"},"PeriodicalIF":0.0,"publicationDate":"2021-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82359490","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 : 2021-03-22DOI: 10.1109/SSD52085.2021.9429301
K. Aloui, A. Guizani, M. Hammadi, M. Haddar, T. Soriano
Swarm engineering is a systematic application of scientific and technical knowledge to specify requirements, model, design, realize, verify, validate, operate and maintain a swarm intelligence system. In swarm robotics, there is not a well-structured methodology until today for developing robotic swarm systems. Several researchers have developed steps to design swarm robots but these steps are still incomplete. In this paper, we focus on the functional architecture of the swarm robots where we propose a top-down approach to ensure consistency and continuity from requirement level to behavioral level up to the functional and structural levels. This approach is based on the Model-Based Systems Engineering method (MBSE) using the Systems Modeling Language (SysML) where we present the allocations between the functions of each swarm member and the overall swarm behaviors. Then, we will be interested in the architecture of Robot Operating System (ROS) of a swarm behavior where we identify the allocations between the component and the functions of a robot.
{"title":"A Top Down Approach to Ensure the Continuity of the Different Design Levels of Swarm Robots","authors":"K. Aloui, A. Guizani, M. Hammadi, M. Haddar, T. Soriano","doi":"10.1109/SSD52085.2021.9429301","DOIUrl":"https://doi.org/10.1109/SSD52085.2021.9429301","url":null,"abstract":"Swarm engineering is a systematic application of scientific and technical knowledge to specify requirements, model, design, realize, verify, validate, operate and maintain a swarm intelligence system. In swarm robotics, there is not a well-structured methodology until today for developing robotic swarm systems. Several researchers have developed steps to design swarm robots but these steps are still incomplete. In this paper, we focus on the functional architecture of the swarm robots where we propose a top-down approach to ensure consistency and continuity from requirement level to behavioral level up to the functional and structural levels. This approach is based on the Model-Based Systems Engineering method (MBSE) using the Systems Modeling Language (SysML) where we present the allocations between the functions of each swarm member and the overall swarm behaviors. Then, we will be interested in the architecture of Robot Operating System (ROS) of a swarm behavior where we identify the allocations between the component and the functions of a robot.","PeriodicalId":6799,"journal":{"name":"2021 18th International Multi-Conference on Systems, Signals & Devices (SSD)","volume":"38 1","pages":"1438-1445"},"PeriodicalIF":0.0,"publicationDate":"2021-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82931572","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 : 2021-03-22DOI: 10.1109/SSD52085.2021.9429362
Mohamed-hamza Laraki, B. Brahmi, C. El‐Bayeh, M. Rahman
This paper deals with the optimal energy management system (EMS) in wind-based stand-alone microgrid. A new day-ahead integrated control based on dynamic programming (DP) is proposed to optimize the power flow and enhance the battery's lifetime. Defined constraints help to set system limits for safe operation. Finally, the economic model allow us to define the parameters of the system to be optimized. Simulation results using MATLAB/SIMULINK show the effectiveness of the proposed EMS.
{"title":"Energy management system for a Stand-alone Wind/ Diesel/ BESS/ Fuel-cell Using Dynamic Programming","authors":"Mohamed-hamza Laraki, B. Brahmi, C. El‐Bayeh, M. Rahman","doi":"10.1109/SSD52085.2021.9429362","DOIUrl":"https://doi.org/10.1109/SSD52085.2021.9429362","url":null,"abstract":"This paper deals with the optimal energy management system (EMS) in wind-based stand-alone microgrid. A new day-ahead integrated control based on dynamic programming (DP) is proposed to optimize the power flow and enhance the battery's lifetime. Defined constraints help to set system limits for safe operation. Finally, the economic model allow us to define the parameters of the system to be optimized. Simulation results using MATLAB/SIMULINK show the effectiveness of the proposed EMS.","PeriodicalId":6799,"journal":{"name":"2021 18th International Multi-Conference on Systems, Signals & Devices (SSD)","volume":"9 1","pages":"1258-1263"},"PeriodicalIF":0.0,"publicationDate":"2021-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90176523","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 : 2021-03-22DOI: 10.1109/SSD52085.2021.9429430
Israa Y. AbuShawish, S. Mahmoud
This work presents the design of a CMOS bio-medical amplifier using $mathrm{T} Omega$ pseudo-resistor based on MOS transistors operating in the weak inversion region. The pseudo-resistor is utilized as a feedback element in the first and second stage of the two-stages bio-medical amplifiers in the portable bio-detection system. Analytical analysis and simulations in LT-spice using 130 nm CMOS technology are performed to validate the realization of the extremely high resistance which can be reached to over tens of $mathrm{T} Omega$. The simulation of the two-stages bio-medical amplifier based pseudo-resistor are carried out in LT-spice using ± 0.6 V supply. The LT-spice simulation results are confirming with both the results obtained by the MATLAB and the analytical analysis of the pseudo-resistor.
{"title":"CMOS Bio-medical Amplifier based on Tera-Ohm Pseudo-resistor for Bio-detection System","authors":"Israa Y. AbuShawish, S. Mahmoud","doi":"10.1109/SSD52085.2021.9429430","DOIUrl":"https://doi.org/10.1109/SSD52085.2021.9429430","url":null,"abstract":"This work presents the design of a CMOS bio-medical amplifier using $mathrm{T} Omega$ pseudo-resistor based on MOS transistors operating in the weak inversion region. The pseudo-resistor is utilized as a feedback element in the first and second stage of the two-stages bio-medical amplifiers in the portable bio-detection system. Analytical analysis and simulations in LT-spice using 130 nm CMOS technology are performed to validate the realization of the extremely high resistance which can be reached to over tens of $mathrm{T} Omega$. The simulation of the two-stages bio-medical amplifier based pseudo-resistor are carried out in LT-spice using ± 0.6 V supply. The LT-spice simulation results are confirming with both the results obtained by the MATLAB and the analytical analysis of the pseudo-resistor.","PeriodicalId":6799,"journal":{"name":"2021 18th International Multi-Conference on Systems, Signals & Devices (SSD)","volume":"29 1","pages":"403-408"},"PeriodicalIF":0.0,"publicationDate":"2021-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89852235","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 : 2021-03-22DOI: 10.1109/SSD52085.2021.9429412
Noura Ben Moussa, M. Chetoui, M. Amairi
This paper proposes a new multi-input-single-output (MISO) system identification methods with fractional models in the errors-in-variables context. The developed methods are based on the instrumental variables and use the Higher-Order Statistics (HOS), such as the third-order cumulants, to obtain an unbiased estimate. Two different cases are established : the first supposes that the fractional orders of the single input-single-output (SISO) systems decomposing the MISO system are known a priori and only their linear coefficients are estimated. In the second case, the fractional orders are optimized along with linear coefficients. A Monte Carlo simulations are used, in a numerical example, to analyze the consistency of the developed estimators.
{"title":"MISO fractional systems identification with fractional models in the EIV context","authors":"Noura Ben Moussa, M. Chetoui, M. Amairi","doi":"10.1109/SSD52085.2021.9429412","DOIUrl":"https://doi.org/10.1109/SSD52085.2021.9429412","url":null,"abstract":"This paper proposes a new multi-input-single-output (MISO) system identification methods with fractional models in the errors-in-variables context. The developed methods are based on the instrumental variables and use the Higher-Order Statistics (HOS), such as the third-order cumulants, to obtain an unbiased estimate. Two different cases are established : the first supposes that the fractional orders of the single input-single-output (SISO) systems decomposing the MISO system are known a priori and only their linear coefficients are estimated. In the second case, the fractional orders are optimized along with linear coefficients. A Monte Carlo simulations are used, in a numerical example, to analyze the consistency of the developed estimators.","PeriodicalId":6799,"journal":{"name":"2021 18th International Multi-Conference on Systems, Signals & Devices (SSD)","volume":"41 1","pages":"942-947"},"PeriodicalIF":0.0,"publicationDate":"2021-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90154187","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 : 2021-03-22DOI: 10.1109/SSD52085.2021.9429393
Chaima Dhifallah, N. Hamdaoui, S. Ameur, R. Ajjel
The aim of the research is to find the most suitable electrode that can be used to estimate the electrical behavior of cells and biological tissue by measuring the aging of the fish and obtaining results according to physical analysis. For this purpose, the measurements were performed in the frequency range of 1 Hz to 7 MHz, where two areas of dispersion are indicated, $alpha$ dispersion at low frequency and $beta$ dispersion at high frequency. The result shows that the cylindrical electrode is more suitable for measurement because it solves the problem of fiber anisotropy. In addition, the needle electrode has higher resistance values compared to the other electrode.
{"title":"The impact of electrodes on the reduction of anisotropy in biological tissue","authors":"Chaima Dhifallah, N. Hamdaoui, S. Ameur, R. Ajjel","doi":"10.1109/SSD52085.2021.9429393","DOIUrl":"https://doi.org/10.1109/SSD52085.2021.9429393","url":null,"abstract":"The aim of the research is to find the most suitable electrode that can be used to estimate the electrical behavior of cells and biological tissue by measuring the aging of the fish and obtaining results according to physical analysis. For this purpose, the measurements were performed in the frequency range of 1 Hz to 7 MHz, where two areas of dispersion are indicated, $alpha$ dispersion at low frequency and $beta$ dispersion at high frequency. The result shows that the cylindrical electrode is more suitable for measurement because it solves the problem of fiber anisotropy. In addition, the needle electrode has higher resistance values compared to the other electrode.","PeriodicalId":6799,"journal":{"name":"2021 18th International Multi-Conference on Systems, Signals & Devices (SSD)","volume":"12 1","pages":"863-868"},"PeriodicalIF":0.0,"publicationDate":"2021-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84890042","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 : 2021-03-22DOI: 10.1109/SSD52085.2021.9429525
Amal Sellami, Leila Nasraoui, L. N. Atallah
In this paper, we propose a multi-stage localization technique that enables to determine the position of a Target User Equipment (T-UE) with harsh channel conditions through the assistance of neighboring User Equipments (UEs). The proposed approach allows a reduced-complexity localization by minimizing the search space through multistage treatment. A neighbor discovery processing is first performed to identify the two nearest neighboring UEs among a set of UEs in the vicinity. The so selected neighbors are used as anchors (A-UE). Then, based on the signal strength, the distances separating the two A-UEs to the T-UE are determined. The distance estimates are used to plot two potential solutions of the Angle of Arrival (AoA) of T-UE. To distinguish the correct AoA estimate, oriented beamforming is performed around short arcs centered on the two AoA candidates. The user's position is then deduced based on the estimates of the AoA and the distance to the A-UEs. Our approach exploits the capabilities of neighbor discovery and oriented beamforming to provide an accurate position estimate for UEs experiencing harsh channel conditions that render direct localization at the base station difficult.
{"title":"Neighbor-Assisted Localization for Massive MIMO 5G Systems","authors":"Amal Sellami, Leila Nasraoui, L. N. Atallah","doi":"10.1109/SSD52085.2021.9429525","DOIUrl":"https://doi.org/10.1109/SSD52085.2021.9429525","url":null,"abstract":"In this paper, we propose a multi-stage localization technique that enables to determine the position of a Target User Equipment (T-UE) with harsh channel conditions through the assistance of neighboring User Equipments (UEs). The proposed approach allows a reduced-complexity localization by minimizing the search space through multistage treatment. A neighbor discovery processing is first performed to identify the two nearest neighboring UEs among a set of UEs in the vicinity. The so selected neighbors are used as anchors (A-UE). Then, based on the signal strength, the distances separating the two A-UEs to the T-UE are determined. The distance estimates are used to plot two potential solutions of the Angle of Arrival (AoA) of T-UE. To distinguish the correct AoA estimate, oriented beamforming is performed around short arcs centered on the two AoA candidates. The user's position is then deduced based on the estimates of the AoA and the distance to the A-UEs. Our approach exploits the capabilities of neighbor discovery and oriented beamforming to provide an accurate position estimate for UEs experiencing harsh channel conditions that render direct localization at the base station difficult.","PeriodicalId":6799,"journal":{"name":"2021 18th International Multi-Conference on Systems, Signals & Devices (SSD)","volume":"44 1","pages":"503-509"},"PeriodicalIF":0.0,"publicationDate":"2021-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83949585","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 : 2021-03-22DOI: 10.1109/SSD52085.2021.9429511
Hiba Hellara, Rim Barioul, S. Sahnoun, A. Fakhfakh, O. Kanoun
This paper proposes a comparative of binary swarm optimization based wrappers for ElectroMyography (EMG) feature selection. Time-domain and frequency-domain features are extracted from two EMG channels to evaluate the effect of each of them according to the accuracy and computational costs. Six binary algorithms are used in this study namely Grey Wolf Optimizer (GWO), Whale Optimization Algorithm (WOA), Moth-Flame Optimization (MFO), Salp Swarm Algorithm (SSA), Bat Algorithm (BA), and Particle Swarm Optimization (PSO) in the domain of machine learning for feature selection and classification. Results prove that time-domain features are enough to give satisfying classification accuracy, WOA is giving the best average classification accuracy of 80.15% but needs more execution time. Compared with others, SSA is the best algorithm according to the number of selected features, execution time, and fitness function 78.25% as accuracy.
{"title":"Comparative of Swarm Intelligence based Wrappers for sEMG Signals Feature Selection","authors":"Hiba Hellara, Rim Barioul, S. Sahnoun, A. Fakhfakh, O. Kanoun","doi":"10.1109/SSD52085.2021.9429511","DOIUrl":"https://doi.org/10.1109/SSD52085.2021.9429511","url":null,"abstract":"This paper proposes a comparative of binary swarm optimization based wrappers for ElectroMyography (EMG) feature selection. Time-domain and frequency-domain features are extracted from two EMG channels to evaluate the effect of each of them according to the accuracy and computational costs. Six binary algorithms are used in this study namely Grey Wolf Optimizer (GWO), Whale Optimization Algorithm (WOA), Moth-Flame Optimization (MFO), Salp Swarm Algorithm (SSA), Bat Algorithm (BA), and Particle Swarm Optimization (PSO) in the domain of machine learning for feature selection and classification. Results prove that time-domain features are enough to give satisfying classification accuracy, WOA is giving the best average classification accuracy of 80.15% but needs more execution time. Compared with others, SSA is the best algorithm according to the number of selected features, execution time, and fitness function 78.25% as accuracy.","PeriodicalId":6799,"journal":{"name":"2021 18th International Multi-Conference on Systems, Signals & Devices (SSD)","volume":"16 1","pages":"829-834"},"PeriodicalIF":0.0,"publicationDate":"2021-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86152242","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：