Pub Date : 2022-05-17DOI: 10.1109/CoDIT55151.2022.9803951
Abigail Chubwa Ndiku, Randa Ghedira-Chkir, Anouar Ben Khalifa, M. Dogui
The visual analysis of the electroencephalogram (EEG) is an expensive and time-consuming task. It can extract only 5% of the information held in the signal. Computer-assisted diagnosis could offer a way to obtain fast and reliable results and significantly reduce inter-and intra-assessor variability. In this document, we will present a tool for automatic analysis of EEG based on artificial neural networks. The proposed method consists in using signal processing and artificial intelligence algorithms to improve the interpretation of the EEG. For this purpose, we have two databases from the Nihon Kohden and Cadwell systems whose files are encrypted. The first step was to develop an application to decrypt and read the files. Thanks to this, the files could be decrypted in a standard format and the signals could be read. After that, we applied our method of automatic interpretation of the EEG. First, we preprocessed the signals using an Notch filter (50 Hz) and a bandpass filter (1–30Hz). Then, we extracted the features in the time-frequency domain based on three elements: the wavelet transform, its means, and its standard deviations. These features represent what we have used as inputs to our neural networks for classification. Our algorithm efficiently interpreted EEG signals with a correct classification rate of 97.9%, a sensitivity of 96.9%, and a specificity of 98.9%. These results have been deployed in an application that allows not only to visualize automatically the signals and the power spectral densities but also to extract the characteristics while displaying the wavelet transform related to the EEG signals of each chain.
{"title":"Electroencephalography signal classification for automatic interpretation of electroencephalogram based on Artificial Intelligence","authors":"Abigail Chubwa Ndiku, Randa Ghedira-Chkir, Anouar Ben Khalifa, M. Dogui","doi":"10.1109/CoDIT55151.2022.9803951","DOIUrl":"https://doi.org/10.1109/CoDIT55151.2022.9803951","url":null,"abstract":"The visual analysis of the electroencephalogram (EEG) is an expensive and time-consuming task. It can extract only 5% of the information held in the signal. Computer-assisted diagnosis could offer a way to obtain fast and reliable results and significantly reduce inter-and intra-assessor variability. In this document, we will present a tool for automatic analysis of EEG based on artificial neural networks. The proposed method consists in using signal processing and artificial intelligence algorithms to improve the interpretation of the EEG. For this purpose, we have two databases from the Nihon Kohden and Cadwell systems whose files are encrypted. The first step was to develop an application to decrypt and read the files. Thanks to this, the files could be decrypted in a standard format and the signals could be read. After that, we applied our method of automatic interpretation of the EEG. First, we preprocessed the signals using an Notch filter (50 Hz) and a bandpass filter (1–30Hz). Then, we extracted the features in the time-frequency domain based on three elements: the wavelet transform, its means, and its standard deviations. These features represent what we have used as inputs to our neural networks for classification. Our algorithm efficiently interpreted EEG signals with a correct classification rate of 97.9%, a sensitivity of 96.9%, and a specificity of 98.9%. These results have been deployed in an application that allows not only to visualize automatically the signals and the power spectral densities but also to extract the characteristics while displaying the wavelet transform related to the EEG signals of each chain.","PeriodicalId":185510,"journal":{"name":"2022 8th International Conference on Control, Decision and Information Technologies (CoDIT)","volume":"102 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133439947","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 : 2022-05-17DOI: 10.1109/CoDIT55151.2022.9804107
Muhammad Sulaman, Mahmoud Golabi, Mathieu Brévilliers, Julien Lepagnot, L. Idoumghar
As one of the most prominent variants of the facility location problem, the p-median problem aims to determine the best locations for establishing p number of facilities such that the aggregate customers' transportation cost is minimized. Since the p-median problem is classified as NP-hard, the application of metaheuristics to solve it is inevitable. Considering the fast development in metaheuristics, choosing the most appropriate algorithm to solve this problem is a difficult task. Therefore, this work presents a comparative study of several classical and recently developed nature-inspired optimization algorithms to solve the discrete uncapacitated p-median problem on several randomly generated test instances with different sizes and spec-ifications.
{"title":"A comparative study of newly developed metaheuristics for the discrete uncapacitated $p$-median problem","authors":"Muhammad Sulaman, Mahmoud Golabi, Mathieu Brévilliers, Julien Lepagnot, L. Idoumghar","doi":"10.1109/CoDIT55151.2022.9804107","DOIUrl":"https://doi.org/10.1109/CoDIT55151.2022.9804107","url":null,"abstract":"As one of the most prominent variants of the facility location problem, the p-median problem aims to determine the best locations for establishing p number of facilities such that the aggregate customers' transportation cost is minimized. Since the p-median problem is classified as NP-hard, the application of metaheuristics to solve it is inevitable. Considering the fast development in metaheuristics, choosing the most appropriate algorithm to solve this problem is a difficult task. Therefore, this work presents a comparative study of several classical and recently developed nature-inspired optimization algorithms to solve the discrete uncapacitated p-median problem on several randomly generated test instances with different sizes and spec-ifications.","PeriodicalId":185510,"journal":{"name":"2022 8th International Conference on Control, Decision and Information Technologies (CoDIT)","volume":"147 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133038786","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 : 2022-05-17DOI: 10.1109/CoDIT55151.2022.9804095
Rokaya Lassoued, Abdelkarim Elloumi
Over the last few years, the application of operations research techniques to solve various optimization problems has become a very important issue. This paper examines two of the most common problems in maritime logistics, the berth allocation problem and the quay cranes assignment problem, and solves them in a hierarchical integration. Finally, real data from a Tunisian port is used to demonstrate the efficiency of hierarchical optimization.
{"title":"Hierarchical Optimization for Solving the Integrated Berth and Quay Crane Assignment Problem in port terminal","authors":"Rokaya Lassoued, Abdelkarim Elloumi","doi":"10.1109/CoDIT55151.2022.9804095","DOIUrl":"https://doi.org/10.1109/CoDIT55151.2022.9804095","url":null,"abstract":"Over the last few years, the application of operations research techniques to solve various optimization problems has become a very important issue. This paper examines two of the most common problems in maritime logistics, the berth allocation problem and the quay cranes assignment problem, and solves them in a hierarchical integration. Finally, real data from a Tunisian port is used to demonstrate the efficiency of hierarchical optimization.","PeriodicalId":185510,"journal":{"name":"2022 8th International Conference on Control, Decision and Information Technologies (CoDIT)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122227491","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 : 2022-05-17DOI: 10.1109/CoDIT55151.2022.9804010
Zhihao Jiang, O. Bakker, P. Bartolo
This paper is a survey of Industry 4.0 compliant solutions for Occupational Safety and Health (OSH) management. Occupational diseases and accidents in the workplace form a significant drain on human and financial capital. By reviewing the state-of-the-art research on the development and applications of new emerging tools and concepts for OSH management, monitoring and decision- making systems, the potential of the fourth industrial revolution to occupational-related safety and health management issues are reviewed and based on that, the recommended scope of future work is defined.
{"title":"Critical Review of Industry 4.0 Technologies' Applications on Occupational Safety and Health","authors":"Zhihao Jiang, O. Bakker, P. Bartolo","doi":"10.1109/CoDIT55151.2022.9804010","DOIUrl":"https://doi.org/10.1109/CoDIT55151.2022.9804010","url":null,"abstract":"This paper is a survey of Industry 4.0 compliant solutions for Occupational Safety and Health (OSH) management. Occupational diseases and accidents in the workplace form a significant drain on human and financial capital. By reviewing the state-of-the-art research on the development and applications of new emerging tools and concepts for OSH management, monitoring and decision- making systems, the potential of the fourth industrial revolution to occupational-related safety and health management issues are reviewed and based on that, the recommended scope of future work is defined.","PeriodicalId":185510,"journal":{"name":"2022 8th International Conference on Control, Decision and Information Technologies (CoDIT)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122142597","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 : 2022-05-17DOI: 10.1109/CoDIT55151.2022.9804002
A. Davydov, Aleksandr Larionov, N. Nagul
The paper describes a new approach to checking the observability of formal regular languages. As well known, the observability is a crucial property for existence of the supervisory control for partially observed discrete event systems. Our checking procedure is based on the automatic theorem proving in the calculus of positively constructed formulas. The presented technique may be successfully used in various control problems including those appearing in robotics.
{"title":"On Checking Observability of Formal Languages in DES Control Problems","authors":"A. Davydov, Aleksandr Larionov, N. Nagul","doi":"10.1109/CoDIT55151.2022.9804002","DOIUrl":"https://doi.org/10.1109/CoDIT55151.2022.9804002","url":null,"abstract":"The paper describes a new approach to checking the observability of formal regular languages. As well known, the observability is a crucial property for existence of the supervisory control for partially observed discrete event systems. Our checking procedure is based on the automatic theorem proving in the calculus of positively constructed formulas. The presented technique may be successfully used in various control problems including those appearing in robotics.","PeriodicalId":185510,"journal":{"name":"2022 8th International Conference on Control, Decision and Information Technologies (CoDIT)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116005225","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 : 2022-05-17DOI: 10.1109/CoDIT55151.2022.9804090
Sagar Jose, R. H. Ngouna, K. Nguyen, K. Medjaher
In the prognostics and health management (PHM) of industrial systems, prediction of remaining useful life (RUL) is a crucial task. RUL prediction is based on data collected from the industrial system, and involves learning underlying health indicator trends. As industrial systems are complex and can be monitored by different sensors, time alignment of multiple temporal data streams and extraction of their underlying characteristics are essential to perform an accurate prognostics. Hence, this paper aims to develop an efficient method to address the above issue. The proposed method is based on the attention and convolution mechanisms of deep neural networks. Its performance is highlighted when compared to other state of the art models such as RNN and LSTM using the C-MAPSS datasets. Numerous experiments demonstrate that our model provides better results in some situations, as well as an ability to capture both local short term contexts and long term associations.
{"title":"Solving Time Alignment Issue of Multimodal Data for Accurate Prognostics with CNN-Transformer-LSTM Network","authors":"Sagar Jose, R. H. Ngouna, K. Nguyen, K. Medjaher","doi":"10.1109/CoDIT55151.2022.9804090","DOIUrl":"https://doi.org/10.1109/CoDIT55151.2022.9804090","url":null,"abstract":"In the prognostics and health management (PHM) of industrial systems, prediction of remaining useful life (RUL) is a crucial task. RUL prediction is based on data collected from the industrial system, and involves learning underlying health indicator trends. As industrial systems are complex and can be monitored by different sensors, time alignment of multiple temporal data streams and extraction of their underlying characteristics are essential to perform an accurate prognostics. Hence, this paper aims to develop an efficient method to address the above issue. The proposed method is based on the attention and convolution mechanisms of deep neural networks. Its performance is highlighted when compared to other state of the art models such as RNN and LSTM using the C-MAPSS datasets. Numerous experiments demonstrate that our model provides better results in some situations, as well as an ability to capture both local short term contexts and long term associations.","PeriodicalId":185510,"journal":{"name":"2022 8th International Conference on Control, Decision and Information Technologies (CoDIT)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123532629","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 : 2022-05-17DOI: 10.1109/CoDIT55151.2022.9803930
Denis C. Ilie-Ablachim, Bogdan Dumitrescu
In this paper we present new methods of anomaly detection based on Dictionary Learning (DL) and Kernel Dictionary Learning (KDL). The main contribution consists in the adaption of known DL and KDL algorithms in the form of unsupervised methods, used for outlier detection. We propose a reduced kernel version (RKDL), which is useful for problems with large data sets, due to the large kernel matrix. We also improve the DL and RKDL methods by the use of a random selection of signals, which aims to eliminate the outliers from the training procedure. All our algorithms are introduced in an anomaly detection toolbox and are compared to standard benchmark results.
{"title":"Anomaly Detection with Selective Dictionary Learning","authors":"Denis C. Ilie-Ablachim, Bogdan Dumitrescu","doi":"10.1109/CoDIT55151.2022.9803930","DOIUrl":"https://doi.org/10.1109/CoDIT55151.2022.9803930","url":null,"abstract":"In this paper we present new methods of anomaly detection based on Dictionary Learning (DL) and Kernel Dictionary Learning (KDL). The main contribution consists in the adaption of known DL and KDL algorithms in the form of unsupervised methods, used for outlier detection. We propose a reduced kernel version (RKDL), which is useful for problems with large data sets, due to the large kernel matrix. We also improve the DL and RKDL methods by the use of a random selection of signals, which aims to eliminate the outliers from the training procedure. All our algorithms are introduced in an anomaly detection toolbox and are compared to standard benchmark results.","PeriodicalId":185510,"journal":{"name":"2022 8th International Conference on Control, Decision and Information Technologies (CoDIT)","volume":"128 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121524018","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 : 2022-05-17DOI: 10.1109/CoDIT55151.2022.9804021
Mahbouba Brahmi, C. B. Regaya, Hichem Hamdi, A. Zaafouri
The performance of a photovoltaic system is strongly affected by the environmental conditions which it is subjected such as random atmospheric variations. In order to improve the performance of a photovoltaic system, the work of this paper is devoted to the comparative study between the following MPPT algorithms: the perturbation and observation algorithm (P&O) and the particle swarm optimization algorithm PSO. These two algorithms are tested under various atmospheric conditions and evaluated in terms of efficiency, stability, speed, and robustness. The obtained simulation results show the effectiveness of the PSO than the P&O algorithm.
{"title":"Comparative Study of P&O and PSO Particle Swarm Optimization MPPT Controllers for Photovoltaic Systems","authors":"Mahbouba Brahmi, C. B. Regaya, Hichem Hamdi, A. Zaafouri","doi":"10.1109/CoDIT55151.2022.9804021","DOIUrl":"https://doi.org/10.1109/CoDIT55151.2022.9804021","url":null,"abstract":"The performance of a photovoltaic system is strongly affected by the environmental conditions which it is subjected such as random atmospheric variations. In order to improve the performance of a photovoltaic system, the work of this paper is devoted to the comparative study between the following MPPT algorithms: the perturbation and observation algorithm (P&O) and the particle swarm optimization algorithm PSO. These two algorithms are tested under various atmospheric conditions and evaluated in terms of efficiency, stability, speed, and robustness. The obtained simulation results show the effectiveness of the PSO than the P&O algorithm.","PeriodicalId":185510,"journal":{"name":"2022 8th International Conference on Control, Decision and Information Technologies (CoDIT)","volume":"115 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124589888","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 : 2022-05-17DOI: 10.1109/CoDIT55151.2022.9804066
J. P. Vega, E. Sánchez, Larbi Djilali, A. Loukianov
One of the most used electrical machines in the industry and domestic applications are the Single-Phase Induction Motor (SPIM), due to its low cost and low-price regarding maintenance. In this paper the Neural Inverse Optimal Control (NIOC) based Recurrent High Order Neural Network (RHONN) identifier is developed to control the SPIM flux and mechanical speed. The proposed neural identifier is on-line trained using the Extended Kalman Filter (EKF) based algorithm, which helps to obtain adequate SPIM model even in the presence of disturbances. To synthesize the NIOC, a Control Lyapunov Function (CLF) is selected as a cost function to be optimized. To illustrate the effectiveness of the proposed control scheme, simulations results considering time-varying references tracking and robustness in presence of parameter variations are presented and compared with conventional controllers.
{"title":"Neural Inverse Optimal Control of Single-Phase Induction Motors","authors":"J. P. Vega, E. Sánchez, Larbi Djilali, A. Loukianov","doi":"10.1109/CoDIT55151.2022.9804066","DOIUrl":"https://doi.org/10.1109/CoDIT55151.2022.9804066","url":null,"abstract":"One of the most used electrical machines in the industry and domestic applications are the Single-Phase Induction Motor (SPIM), due to its low cost and low-price regarding maintenance. In this paper the Neural Inverse Optimal Control (NIOC) based Recurrent High Order Neural Network (RHONN) identifier is developed to control the SPIM flux and mechanical speed. The proposed neural identifier is on-line trained using the Extended Kalman Filter (EKF) based algorithm, which helps to obtain adequate SPIM model even in the presence of disturbances. To synthesize the NIOC, a Control Lyapunov Function (CLF) is selected as a cost function to be optimized. To illustrate the effectiveness of the proposed control scheme, simulations results considering time-varying references tracking and robustness in presence of parameter variations are presented and compared with conventional controllers.","PeriodicalId":185510,"journal":{"name":"2022 8th International Conference on Control, Decision and Information Technologies (CoDIT)","volume":"18 13","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120894890","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 : 2022-05-17DOI: 10.1109/CoDIT55151.2022.9804027
H. Çelik, L. Dülger, M. Topalbekiroglu
The most important production steps of the handmade carpets produced still by human labor are; knotting (Turkish knot or Persian knot), shedding, picking and tightening of the carpet with a beater (called as beat up operation). Functional requirements during beat up considered. This study is then concentrated on beat up mechanism proposed for handmade carpet looms. A beat-up mechanism model performedvia Matlab/Simulink environment to verify the kinematic objectives assigned. Simulation results are included for the system with further comments on its design and motion control.
{"title":"Design and Simulation of Beat Up Mechanism: Handmade Carpet Looms","authors":"H. Çelik, L. Dülger, M. Topalbekiroglu","doi":"10.1109/CoDIT55151.2022.9804027","DOIUrl":"https://doi.org/10.1109/CoDIT55151.2022.9804027","url":null,"abstract":"The most important production steps of the handmade carpets produced still by human labor are; knotting (Turkish knot or Persian knot), shedding, picking and tightening of the carpet with a beater (called as beat up operation). Functional requirements during beat up considered. This study is then concentrated on beat up mechanism proposed for handmade carpet looms. A beat-up mechanism model performedvia Matlab/Simulink environment to verify the kinematic objectives assigned. Simulation results are included for the system with further comments on its design and motion control.","PeriodicalId":185510,"journal":{"name":"2022 8th International Conference on Control, Decision and Information Technologies (CoDIT)","volume":"108 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115854487","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：