Pub Date : 2023-07-27DOI: 10.1109/ICSSE58758.2023.10227145
Van Thinh Pham, V. Pham, M. Nguyen, Hai-Chau Le
The rise in heart-related diseases has led to a need for proper automatic diagnosis methods to identify irregular heart problems. It has proven to be challenging to promptly and accurately diagnose many complicated and interferential symptom diseases including arrhythmia. Recently, thanks to the evolution of artificial intelligence (AI) and the advance in signal processing, automated arrhythmia detection has become easier and widely applied for physicians and practitioners with machine learning (ML) techniques and the only use of electrocardiograms (ECG). In this paper, we propose an ECG-based machine learning arrhythmia detection approach that exploits R-peak detection and machine learning. Our proposed solution targeting a binary classification of heartbeats employs an efficient R-peak detection that uses a Butterworth bypass filter, Ensemble Empirical Mode Decomposition (EEMD), and Hilbert Transforms (HT) for processing ECG signals, and applies the most effective machine learning algorithm among typical ML algorithms to improve the performance of the arrhythmia diagnosis. In order to select the most suitable one with the highest achievable performance, typical ML algorithms such as BG, BS, KNN, and RF were investigated. A popular public dataset, MIT-BIH Arrhythmia, is used for the numerical experiments. The attained results prove that our developed solution outperforms the notable traditional algorithms and it offers the best performance with an accuracy of 93.4%, a sensitivity of 95.4%, and an F1-score of 96.3%. The high obtained F1-score implies that our solution can overcome the data imbalance to detect arrhythmia correctly and be effective in practical clinical environments.
{"title":"Efficient Electrocardiogram-based Arrhythmia Detection Utilizing R-peaks and Machine Learning","authors":"Van Thinh Pham, V. Pham, M. Nguyen, Hai-Chau Le","doi":"10.1109/ICSSE58758.2023.10227145","DOIUrl":"https://doi.org/10.1109/ICSSE58758.2023.10227145","url":null,"abstract":"The rise in heart-related diseases has led to a need for proper automatic diagnosis methods to identify irregular heart problems. It has proven to be challenging to promptly and accurately diagnose many complicated and interferential symptom diseases including arrhythmia. Recently, thanks to the evolution of artificial intelligence (AI) and the advance in signal processing, automated arrhythmia detection has become easier and widely applied for physicians and practitioners with machine learning (ML) techniques and the only use of electrocardiograms (ECG). In this paper, we propose an ECG-based machine learning arrhythmia detection approach that exploits R-peak detection and machine learning. Our proposed solution targeting a binary classification of heartbeats employs an efficient R-peak detection that uses a Butterworth bypass filter, Ensemble Empirical Mode Decomposition (EEMD), and Hilbert Transforms (HT) for processing ECG signals, and applies the most effective machine learning algorithm among typical ML algorithms to improve the performance of the arrhythmia diagnosis. In order to select the most suitable one with the highest achievable performance, typical ML algorithms such as BG, BS, KNN, and RF were investigated. A popular public dataset, MIT-BIH Arrhythmia, is used for the numerical experiments. The attained results prove that our developed solution outperforms the notable traditional algorithms and it offers the best performance with an accuracy of 93.4%, a sensitivity of 95.4%, and an F1-score of 96.3%. The high obtained F1-score implies that our solution can overcome the data imbalance to detect arrhythmia correctly and be effective in practical clinical environments.","PeriodicalId":280745,"journal":{"name":"2023 International Conference on System Science and Engineering (ICSSE)","volume":"579 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123133316","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-07-27DOI: 10.1109/ICSSE58758.2023.10227193
Thinh Huynh, Cao-Tri Dinh, Young-Bok Kim
This paper investigates the motion control problems of an aerial system powered by water jet propulsion in which the water is conveyed through a flexible hose attached underneath. In this system, the thrust is generated by jetting water out of four nozzles, whose cross-sectional area is much smaller than the inlet, while the necessary torques for fight maneuvers are achieved by rotating these nozzles to direct the respective thrust. The system can be thought of as a tethered drone and its dynamics are described by coupled ordinary–partial differential equations showing the motion interaction of the hose and the system. Based on Lyapunov’s direct method, an observer-based boundary control is designed to achieve the desired flight maneuver of the system while still preserving the stabilization of both the system and the hose. As a result, the uniform ultimate boundedness of the entire control system is achieved, and its performance is verified by simulations.
{"title":"Observer-based Boundary Control of a Water-powered Aerial System","authors":"Thinh Huynh, Cao-Tri Dinh, Young-Bok Kim","doi":"10.1109/ICSSE58758.2023.10227193","DOIUrl":"https://doi.org/10.1109/ICSSE58758.2023.10227193","url":null,"abstract":"This paper investigates the motion control problems of an aerial system powered by water jet propulsion in which the water is conveyed through a flexible hose attached underneath. In this system, the thrust is generated by jetting water out of four nozzles, whose cross-sectional area is much smaller than the inlet, while the necessary torques for fight maneuvers are achieved by rotating these nozzles to direct the respective thrust. The system can be thought of as a tethered drone and its dynamics are described by coupled ordinary–partial differential equations showing the motion interaction of the hose and the system. Based on Lyapunov’s direct method, an observer-based boundary control is designed to achieve the desired flight maneuver of the system while still preserving the stabilization of both the system and the hose. As a result, the uniform ultimate boundedness of the entire control system is achieved, and its performance is verified by simulations.","PeriodicalId":280745,"journal":{"name":"2023 International Conference on System Science and Engineering (ICSSE)","volume":"423 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117350224","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-07-27DOI: 10.1109/ICSSE58758.2023.10227240
Le-Anh Tran, T. Nguyen, Truong-Dong Do, Chung-Nguyen Tran, Daehyun Kwon, Dong-Chul Park
Projection onto Convex Set (POCS) is a powerful signal processing tool for various convex optimization problems. For non-intersecting convex sets, the simultaneous POCS method can result in a minimum mean square error solution. This property of POCS has been applied to clustering analysis and the POCS-based clustering algorithm was proposed earlier. In the POCS-based clustering algorithm, each data point is treated as a convex set, and a parallel projection operation from every cluster prototype to its corresponding data members is carried out in order to minimize the objective function and to update the memberships and prototypes. The algorithm works competitively against conventional clustering methods in terms of execution speed and clustering error on general clustering tasks. In this paper, the performance of the POCS-based clustering algorithm on a more complex task, embedding clustering, is investigated in order to further demonstrate its potential in benefiting other high-level tasks. To this end, an off-the-shelf FaceNet model and an autoencoder network are adopted to synthesize two sets of feature embeddings from the Five Celebrity Faces and MNIST datasets, respectively, for experiments and analyses. The empirical evaluations show that the POCS-based clustering algorithm can yield favorable results when compared with other prevailing clustering schemes such as the K-Means and Fuzzy C-Means algorithms in embedding clustering problems.
{"title":"Embedding Clustering via Autoencoder and Projection onto Convex Set","authors":"Le-Anh Tran, T. Nguyen, Truong-Dong Do, Chung-Nguyen Tran, Daehyun Kwon, Dong-Chul Park","doi":"10.1109/ICSSE58758.2023.10227240","DOIUrl":"https://doi.org/10.1109/ICSSE58758.2023.10227240","url":null,"abstract":"Projection onto Convex Set (POCS) is a powerful signal processing tool for various convex optimization problems. For non-intersecting convex sets, the simultaneous POCS method can result in a minimum mean square error solution. This property of POCS has been applied to clustering analysis and the POCS-based clustering algorithm was proposed earlier. In the POCS-based clustering algorithm, each data point is treated as a convex set, and a parallel projection operation from every cluster prototype to its corresponding data members is carried out in order to minimize the objective function and to update the memberships and prototypes. The algorithm works competitively against conventional clustering methods in terms of execution speed and clustering error on general clustering tasks. In this paper, the performance of the POCS-based clustering algorithm on a more complex task, embedding clustering, is investigated in order to further demonstrate its potential in benefiting other high-level tasks. To this end, an off-the-shelf FaceNet model and an autoencoder network are adopted to synthesize two sets of feature embeddings from the Five Celebrity Faces and MNIST datasets, respectively, for experiments and analyses. The empirical evaluations show that the POCS-based clustering algorithm can yield favorable results when compared with other prevailing clustering schemes such as the K-Means and Fuzzy C-Means algorithms in embedding clustering problems.","PeriodicalId":280745,"journal":{"name":"2023 International Conference on System Science and Engineering (ICSSE)","volume":"256 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121245306","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-07-27DOI: 10.1109/ICSSE58758.2023.10227215
Mayur Hulke, A. Jafari, Appolinaire C. Etoundi
It has been estimated that approximately 7000 people undergo limb amputation in the UK every year [1]. This issue is even more significant in the US, where over 150,000 people undergo lower limb extremity amputations, and this number is predicted to increase by 47% in 2050 [2]. This traumatic and risky procedure leads to lifelong disability that has a direct impacts a patients mobility [4]. As a result, this creates a economic burden on the healthcare system and the economy as a whole [4]. Despite the ever-increasing number of amputees, the fitting of prosthetic sockets remains artisan in nature and often fails to satisfactorily address the stresses experienced between the socket and the RL (RL). This leads to patient discomfort and an average of 25% of users abandoning their prosthesis (Fully Equipped). In this paper, we present a process for monitoring the internal area of a prosthetic socket for above-knee amputees through the use of an electronic circuit incorporating pressure and temperature sensors. This experiment is an extension of the previous experiment where Finite Element Analysis (FEA) has been applied to the same case study and compared with patient experience to analyze the internal socket conditions in the context of discomfort areas. This experiment also demonstrates how commercially available sensors could be integrated within a socket to determine the stresses experienced and hence validate further the FEA studies. Ultimately, the objective of this experiment is to identify the correlation between the collected sensor data from the socket, the discomfort areas, and the verbal feedback on the pain experienced by the amputee. As far as the authors are concerned, this is the first time this type of experiment is being conducted in both outdoor and indoor conditions where real-time sensor data is being collected while an amputee is performing six different activities from high impact level to low impact level.
{"title":"Investigation into the Customization of a Transfemoral Prosthetic Socket to Minimize Discomfort for Residual Limb (RL) Volume Change","authors":"Mayur Hulke, A. Jafari, Appolinaire C. Etoundi","doi":"10.1109/ICSSE58758.2023.10227215","DOIUrl":"https://doi.org/10.1109/ICSSE58758.2023.10227215","url":null,"abstract":"It has been estimated that approximately 7000 people undergo limb amputation in the UK every year [1]. This issue is even more significant in the US, where over 150,000 people undergo lower limb extremity amputations, and this number is predicted to increase by 47% in 2050 [2]. This traumatic and risky procedure leads to lifelong disability that has a direct impacts a patients mobility [4]. As a result, this creates a economic burden on the healthcare system and the economy as a whole [4]. Despite the ever-increasing number of amputees, the fitting of prosthetic sockets remains artisan in nature and often fails to satisfactorily address the stresses experienced between the socket and the RL (RL). This leads to patient discomfort and an average of 25% of users abandoning their prosthesis (Fully Equipped). In this paper, we present a process for monitoring the internal area of a prosthetic socket for above-knee amputees through the use of an electronic circuit incorporating pressure and temperature sensors. This experiment is an extension of the previous experiment where Finite Element Analysis (FEA) has been applied to the same case study and compared with patient experience to analyze the internal socket conditions in the context of discomfort areas. This experiment also demonstrates how commercially available sensors could be integrated within a socket to determine the stresses experienced and hence validate further the FEA studies. Ultimately, the objective of this experiment is to identify the correlation between the collected sensor data from the socket, the discomfort areas, and the verbal feedback on the pain experienced by the amputee. As far as the authors are concerned, this is the first time this type of experiment is being conducted in both outdoor and indoor conditions where real-time sensor data is being collected while an amputee is performing six different activities from high impact level to low impact level.","PeriodicalId":280745,"journal":{"name":"2023 International Conference on System Science and Engineering (ICSSE)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115389002","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-07-27DOI: 10.1109/ICSSE58758.2023.10227192
Van-Dung Hoang, Thanh-an Michel Pham
Over a decade, deep learning methods using convolutional neural network (CNN) architecture have achieved breakthroughs in the precision criterion, which compared to the traditional machine learning methods. However, those approaches still faced some limitations of processing time and precision when they are applied to large samples and hard datasets. Recently, some new methods based on the transformer learning approach have been applied to image processing. This direction approach has illustrated the promising results in the terms of accuracy and computational time. This paper presents a new approach, which combines a pre-processing technique of image filtering and vision transformer (ViT) learning for the problem of plant insect pests and diseases recognition. The proposed solution involves some stages: neural network-based image filtering, then passes results through a ViT module to extract feature map, and then fed to multiple head network for classification. The proposed method applies image filtering pre-processing to highlight features before passing results to the ViT processing stage instead of using ViT from raw input images. Furthermore, element-wise multiplication in the frequency domain reduces processing time instead of using convolutional processing in the spatial domain. Experimental results demonstrate that applying filtering preprocessing does not significantly increase the number of learning parameters and training time compared to using ViT directly and it leverages to improve accuracy to compare to well-known models based on deep CNN. The research results also illustrated that the ViT solution and the proposed method are reached more accurate than CNN-based deep learning methods.
{"title":"Fusion of ViT Technique and Image Filtering in Deep Learning for Plant Pests and Diseases Recognition","authors":"Van-Dung Hoang, Thanh-an Michel Pham","doi":"10.1109/ICSSE58758.2023.10227192","DOIUrl":"https://doi.org/10.1109/ICSSE58758.2023.10227192","url":null,"abstract":"Over a decade, deep learning methods using convolutional neural network (CNN) architecture have achieved breakthroughs in the precision criterion, which compared to the traditional machine learning methods. However, those approaches still faced some limitations of processing time and precision when they are applied to large samples and hard datasets. Recently, some new methods based on the transformer learning approach have been applied to image processing. This direction approach has illustrated the promising results in the terms of accuracy and computational time. This paper presents a new approach, which combines a pre-processing technique of image filtering and vision transformer (ViT) learning for the problem of plant insect pests and diseases recognition. The proposed solution involves some stages: neural network-based image filtering, then passes results through a ViT module to extract feature map, and then fed to multiple head network for classification. The proposed method applies image filtering pre-processing to highlight features before passing results to the ViT processing stage instead of using ViT from raw input images. Furthermore, element-wise multiplication in the frequency domain reduces processing time instead of using convolutional processing in the spatial domain. Experimental results demonstrate that applying filtering preprocessing does not significantly increase the number of learning parameters and training time compared to using ViT directly and it leverages to improve accuracy to compare to well-known models based on deep CNN. The research results also illustrated that the ViT solution and the proposed method are reached more accurate than CNN-based deep learning methods.","PeriodicalId":280745,"journal":{"name":"2023 International Conference on System Science and Engineering (ICSSE)","volume":"193 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116427736","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-07-27DOI: 10.1109/ICSSE58758.2023.10227252
Thanh-Hoan Nguyen, V. Trương, H. Nguyen, D. Truong, Quang-Thai-Dan Nguyen, Thanh-Nhan Nguyen
In the near future, Photovoltaic (PV) network and Electric Vehicle Charging station (EVC) will be deployed in Ho Chi Minh City (HCMC), the use of Cross-phase characteristic will help to reduce the influence of these distributed sources and will improve the imbalance. phase of the current low voltage distribution network. The optimization aims to reduce the loss caused by phase unbalance. Convex optimization model is considered to solve the optimization problem with quadratic constraint and voltage balance equation system (VUF) and phase constraints. Algorithms run according to the above model including OPF, Cross-phase and using unbalanced 3-phase IEEE 33 bus and IEEE 192 bus systems. The results show that using the Cross-phase characteristic significantly reduces phase imbalance.
{"title":"Reduce Phase Unbalance with Cross-phase of PV and EV Chargers, using Convex Optimization on Quadratic Constraint in Distribution Network","authors":"Thanh-Hoan Nguyen, V. Trương, H. Nguyen, D. Truong, Quang-Thai-Dan Nguyen, Thanh-Nhan Nguyen","doi":"10.1109/ICSSE58758.2023.10227252","DOIUrl":"https://doi.org/10.1109/ICSSE58758.2023.10227252","url":null,"abstract":"In the near future, Photovoltaic (PV) network and Electric Vehicle Charging station (EVC) will be deployed in Ho Chi Minh City (HCMC), the use of Cross-phase characteristic will help to reduce the influence of these distributed sources and will improve the imbalance. phase of the current low voltage distribution network. The optimization aims to reduce the loss caused by phase unbalance. Convex optimization model is considered to solve the optimization problem with quadratic constraint and voltage balance equation system (VUF) and phase constraints. Algorithms run according to the above model including OPF, Cross-phase and using unbalanced 3-phase IEEE 33 bus and IEEE 192 bus systems. The results show that using the Cross-phase characteristic significantly reduces phase imbalance.","PeriodicalId":280745,"journal":{"name":"2023 International Conference on System Science and Engineering (ICSSE)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127995665","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-07-27DOI: 10.1109/ICSSE58758.2023.10227238
Cong Minh Ho, Hoang Vu Dao, D. Tran, K. Ahn
This study deals with the fault tolerance problem of an active air suspension system considering parametric uncertainties and sprung mass displacement in the event of sensor fault and unmeasured signals. A pneumatic spring is used to set up a quarter of the car model to investigate the flexible stiffness and provide an active force that can suppress chassis vibrations. To approximate unknown nonlinear parameters of air spring actuator dynamics, fuzzy logic systems (FLSs) are used as function approximators. Sensor failure is considered while all system states are assumed to be unmeasured variables. A fuzzy state observer is then designed to approximate the unknown system states and overcome the effective loss of sensor fault. Adaptive fault-tolerant control based on command filter backstepping technique to solve the problem of exploding complexity. To enhance tracking accuracy, this study involves a prescribed performance technique such that the sprung mass displacement is guaranteed between the predefined boundaries. Finally, the effectiveness of the proposed control is verified by comparative simulation examples under the presence of sensor fault and unknown system states.
{"title":"Design of Observer-Based Adaptive Fuzzy Fault-Tolerant Control for Pneumatic Active Suspension with Displacement Constraint","authors":"Cong Minh Ho, Hoang Vu Dao, D. Tran, K. Ahn","doi":"10.1109/ICSSE58758.2023.10227238","DOIUrl":"https://doi.org/10.1109/ICSSE58758.2023.10227238","url":null,"abstract":"This study deals with the fault tolerance problem of an active air suspension system considering parametric uncertainties and sprung mass displacement in the event of sensor fault and unmeasured signals. A pneumatic spring is used to set up a quarter of the car model to investigate the flexible stiffness and provide an active force that can suppress chassis vibrations. To approximate unknown nonlinear parameters of air spring actuator dynamics, fuzzy logic systems (FLSs) are used as function approximators. Sensor failure is considered while all system states are assumed to be unmeasured variables. A fuzzy state observer is then designed to approximate the unknown system states and overcome the effective loss of sensor fault. Adaptive fault-tolerant control based on command filter backstepping technique to solve the problem of exploding complexity. To enhance tracking accuracy, this study involves a prescribed performance technique such that the sprung mass displacement is guaranteed between the predefined boundaries. Finally, the effectiveness of the proposed control is verified by comparative simulation examples under the presence of sensor fault and unknown system states.","PeriodicalId":280745,"journal":{"name":"2023 International Conference on System Science and Engineering (ICSSE)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124885367","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-07-27DOI: 10.1109/ICSSE58758.2023.10227163
Mahmood Khalsan, Mu Mu, E. Al-Shamery, Lee Machado, Michael Opoku Agyeman, S. Ajit
Machine learning (ML) methods have a plaid an important role in classification and prediction in most fields. However, analyzing gene expression is remain complex in cancer classification because of the high dimensionality of the provided dataset in gene expression. Consequentially, intersection-based three feature selection methods (ITFS) was developed to select optimal features (genes) that would be used as identifiers for classification and reduce the dimensionality of the available data in gene expression. ITFS has employed three feature selection methods (Mutual Information (MI), F-ClassIf, and Minimum Redundancy Maximum Relevance (mRMR)). Therefore, employing intersection concept that leads to select only the genes that have been selected by the three feature selection techniques. These selected genes would be used as identifiers for the training classifier model. Our study applied the proposed ITFS to six gene expression datasets downloaded from (Microarray and RNAseq tools) for validating the effectiveness of ITFS on classifier methods. The highest average accuracy improvement in the six datasets was when Multilayer Perceptron (MLP) and ITFS employed together compared to employing MLP individually. The proposed ITFS-MLP model has produced classification accuracy between (92% to 100%) for the six datasets and the average accuracy is 96%.
{"title":"Intersection Three Feature Selection and Machine Learning Approaches for Cancer Classification","authors":"Mahmood Khalsan, Mu Mu, E. Al-Shamery, Lee Machado, Michael Opoku Agyeman, S. Ajit","doi":"10.1109/ICSSE58758.2023.10227163","DOIUrl":"https://doi.org/10.1109/ICSSE58758.2023.10227163","url":null,"abstract":"Machine learning (ML) methods have a plaid an important role in classification and prediction in most fields. However, analyzing gene expression is remain complex in cancer classification because of the high dimensionality of the provided dataset in gene expression. Consequentially, intersection-based three feature selection methods (ITFS) was developed to select optimal features (genes) that would be used as identifiers for classification and reduce the dimensionality of the available data in gene expression. ITFS has employed three feature selection methods (Mutual Information (MI), F-ClassIf, and Minimum Redundancy Maximum Relevance (mRMR)). Therefore, employing intersection concept that leads to select only the genes that have been selected by the three feature selection techniques. These selected genes would be used as identifiers for the training classifier model. Our study applied the proposed ITFS to six gene expression datasets downloaded from (Microarray and RNAseq tools) for validating the effectiveness of ITFS on classifier methods. The highest average accuracy improvement in the six datasets was when Multilayer Perceptron (MLP) and ITFS employed together compared to employing MLP individually. The proposed ITFS-MLP model has produced classification accuracy between (92% to 100%) for the six datasets and the average accuracy is 96%.","PeriodicalId":280745,"journal":{"name":"2023 International Conference on System Science and Engineering (ICSSE)","volume":"108 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133148071","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-07-27DOI: 10.1109/ICSSE58758.2023.10227235
L. Nguyen, Duy Anh Le, Hoa Phuoc Truong, Viet Chan Nguyen, H. Nguyen, D. Pham
Ensuring seamless transfer between grid-connected and stand-alone modes is crucial for maintaining a reliable power supply. This article presents a technique that allows for a smooth transition from current source control used in grid-connected mode to adopting droop control in stand-alone mode. The distributed generation unit makes use of current-source control during normal grid operation, but in the event of a grid failure, the load voltage is regulated, and load power demand is supported through power and voltage control loops. The proposed method enhances the quality of grid current and ensures consistent power output, even when voltage fluctuations occur in both grid-connected and stand-alone modes. Additionally, the technique includes current control strategies that enhance microgrid reliability during the stand-alone mode. The simulation results in various scenarios prove the efficacy of the suggested control approach.
{"title":"A Smooth Grid Transfer Control Strategy Based on Improved Droop Control","authors":"L. Nguyen, Duy Anh Le, Hoa Phuoc Truong, Viet Chan Nguyen, H. Nguyen, D. Pham","doi":"10.1109/ICSSE58758.2023.10227235","DOIUrl":"https://doi.org/10.1109/ICSSE58758.2023.10227235","url":null,"abstract":"Ensuring seamless transfer between grid-connected and stand-alone modes is crucial for maintaining a reliable power supply. This article presents a technique that allows for a smooth transition from current source control used in grid-connected mode to adopting droop control in stand-alone mode. The distributed generation unit makes use of current-source control during normal grid operation, but in the event of a grid failure, the load voltage is regulated, and load power demand is supported through power and voltage control loops. The proposed method enhances the quality of grid current and ensures consistent power output, even when voltage fluctuations occur in both grid-connected and stand-alone modes. Additionally, the technique includes current control strategies that enhance microgrid reliability during the stand-alone mode. The simulation results in various scenarios prove the efficacy of the suggested control approach.","PeriodicalId":280745,"journal":{"name":"2023 International Conference on System Science and Engineering (ICSSE)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131444406","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-07-27DOI: 10.1109/ICSSE58758.2023.10227224
Simon Peter Khabusi, Yo-Ping Huang, Mong-Fong Lee
Fish is a rich supply of proteins. Due to its high demand, aquaculture has been growing steadily. However, the activity is vulnerable to many diseases. Recent developments in computer vision and internet of things have enabled the automation of aquaculture operations. The lack of public fish disease dataset and complex underwater environments have limited the advancement of automatic fish disease detection and classification. This study proposes attention-based mechanism with background removal for fish disease classification. We focus on using strongly discriminative features of the infected fish regions and weakening regions of low interest using convolutional block attention module (CBAM), which is added to the pretrained classification models to sequentially infer attention maps along the channel and spatial dimensions for every intermediate feature map. The attention maps are then multiplied to the input feature map for adaptive feature refinement. The models are trained, validated and tested on a custom dataset with image samples collected from various internet sources. The performance of the attention-based models is compared with the baseline. The results indicate that ResNet50 with CBAM achieves 89.9% of accuracy, precision of 89.9%, recall of 89.3% and 89.7% of F1-score. Conclusively, attention mechanism improves fish disease classification performance.
{"title":"Attention-Based Mechanism for Fish Disease Classification in Aquaculture","authors":"Simon Peter Khabusi, Yo-Ping Huang, Mong-Fong Lee","doi":"10.1109/ICSSE58758.2023.10227224","DOIUrl":"https://doi.org/10.1109/ICSSE58758.2023.10227224","url":null,"abstract":"Fish is a rich supply of proteins. Due to its high demand, aquaculture has been growing steadily. However, the activity is vulnerable to many diseases. Recent developments in computer vision and internet of things have enabled the automation of aquaculture operations. The lack of public fish disease dataset and complex underwater environments have limited the advancement of automatic fish disease detection and classification. This study proposes attention-based mechanism with background removal for fish disease classification. We focus on using strongly discriminative features of the infected fish regions and weakening regions of low interest using convolutional block attention module (CBAM), which is added to the pretrained classification models to sequentially infer attention maps along the channel and spatial dimensions for every intermediate feature map. The attention maps are then multiplied to the input feature map for adaptive feature refinement. The models are trained, validated and tested on a custom dataset with image samples collected from various internet sources. The performance of the attention-based models is compared with the baseline. The results indicate that ResNet50 with CBAM achieves 89.9% of accuracy, precision of 89.9%, recall of 89.3% and 89.7% of F1-score. Conclusively, attention mechanism improves fish disease classification performance.","PeriodicalId":280745,"journal":{"name":"2023 International Conference on System Science and Engineering (ICSSE)","volume":"73 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131465228","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：