Pub Date : 2023-07-27DOI: 10.1109/ICSSE58758.2023.10227202
Hong Nguyen Thi Khanh, Nam Nguyen Linh
Accomplishing high efficiency solutions in accelerating the power consumption/execution time for implementing the video applications of the Fall Detection System on processors or on FPGA or heterogeneous computing platform, Zynq- 7000 all programmable system-on-chip. In general, the aim of power/execution time estimation methodology mentions about the speed and accuracy. In our work, we target accuracy based modeling style and analysis information collected from measurement on real board to obtain sufficiently accurate power estimation for the Fall Detection System on heterogeneous platform. Therefore, we experiment and verify the model’s accuracy on Zynq-7000 AP SoC platform, to show the applicability of our model.
为实现跌落检测系统在处理器、FPGA或异构计算平台上的视频应用，Zynq- 7000全可编程片上系统，在加速功耗/执行时间方面实现高效率解决方案。一般来说，功率/执行时间估计方法的目标涉及速度和准确性。在我们的工作中，我们以基于精度的建模风格和分析从实际板上测量收集的信息为目标，为异构平台上的跌倒检测系统获得足够准确的功率估计。因此，我们在Zynq-7000 AP SoC平台上实验并验证了模型的准确性，以证明我们模型的适用性。
{"title":"Exploration of Power Consumption/Execution time models for Video Applications","authors":"Hong Nguyen Thi Khanh, Nam Nguyen Linh","doi":"10.1109/ICSSE58758.2023.10227202","DOIUrl":"https://doi.org/10.1109/ICSSE58758.2023.10227202","url":null,"abstract":"Accomplishing high efficiency solutions in accelerating the power consumption/execution time for implementing the video applications of the Fall Detection System on processors or on FPGA or heterogeneous computing platform, Zynq- 7000 all programmable system-on-chip. In general, the aim of power/execution time estimation methodology mentions about the speed and accuracy. In our work, we target accuracy based modeling style and analysis information collected from measurement on real board to obtain sufficiently accurate power estimation for the Fall Detection System on heterogeneous platform. Therefore, we experiment and verify the model’s accuracy on Zynq-7000 AP SoC platform, to show the applicability of our model.","PeriodicalId":280745,"journal":{"name":"2023 International Conference on System Science and Engineering (ICSSE)","volume":"87 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":"127538046","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/ICSSE58758.2023.10227230
T. Nguyen, L. Nguyen, Thanh Pham, Minh Dinh, Ushik Shrestha Khwakhali, Quang Tran
This paper presents a real-life example of successfully applying the Entity-Attribute-Value (EAV) model to build a comprehensive system for managing disabled individuals in Vietnam. By leveraging the EAV model, we address the challenges of collecting and storing extensive disability-related data. Despite concerns about complexity and abstraction, our findings demonstrate that with careful design and architecture, successful implementation is achievable. This system serves as a practical solution for managing disabled individuals, offering insights for policymakers and organizations. The research contributes to innovative approaches in disability systems and provides a blueprint for similar systems in other regions.
{"title":"Big Data for Healthcare: Using Entity-Attribute-Value (EAV) Model to Build a National Platform for Disability Management","authors":"T. Nguyen, L. Nguyen, Thanh Pham, Minh Dinh, Ushik Shrestha Khwakhali, Quang Tran","doi":"10.1109/ICSSE58758.2023.10227230","DOIUrl":"https://doi.org/10.1109/ICSSE58758.2023.10227230","url":null,"abstract":"This paper presents a real-life example of successfully applying the Entity-Attribute-Value (EAV) model to build a comprehensive system for managing disabled individuals in Vietnam. By leveraging the EAV model, we address the challenges of collecting and storing extensive disability-related data. Despite concerns about complexity and abstraction, our findings demonstrate that with careful design and architecture, successful implementation is achievable. This system serves as a practical solution for managing disabled individuals, offering insights for policymakers and organizations. The research contributes to innovative approaches in disability systems and provides a blueprint for similar systems in other regions.","PeriodicalId":280745,"journal":{"name":"2023 International Conference on System Science and Engineering (ICSSE)","volume":"22 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":"116136950","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/ICSSE58758.2023.10227168
Tung-Thanh Vo, Meng-Kun Liu, Chung-Lin Hsieh
Induction motors are prevalent in many industrial applications due to their robustness, efficiency, and reliability. They are used in various applications, such as pumps, fans, compressors, conveyors, and machine tools. However, faults in induction motors can cause operational and financial losses, and in some cases, they can lead to severe accidents. Therefore, timely and accurate detection of faults is crucial for minimizing the negative impact of these faults. The fault detection methods for induction motors can involve the analysis of various signals such as vibration, current, and voltage. Convolutional neural networks (CNNs) have proven highly effective in many applications but have mainly been applied to two-dimensional data. One-dimensional CNNs offer an excellent alternative for analyzing time sequence datasets since they can work directly with raw signal data without requiring pre- or post-processing. However, the main idea behind 1D-CNNs is to extract spatial features, which can result in the loss of critical temporal features related to time distribution. Recurrent neural networks (RNNs) can effectively capture the temporal dependencies and time distribution in sequences data, making them well-suited to fix the issue. In this paper, we propose a method that combines 1D-CNNs and RNNs called Hybrid 1DCNN-RNN network (HCRN) to analyze the voltage and current signals of a three-phase induction motor. It performs accurate and efficient fault diagnosis, ultimately leading to the more efficient maintenance and reduced downtime for industrial processes.
{"title":"Hybrid 1D CNN-RNN Network for Fault Diagnosis in Induction Motors Using Electrical Signals","authors":"Tung-Thanh Vo, Meng-Kun Liu, Chung-Lin Hsieh","doi":"10.1109/ICSSE58758.2023.10227168","DOIUrl":"https://doi.org/10.1109/ICSSE58758.2023.10227168","url":null,"abstract":"Induction motors are prevalent in many industrial applications due to their robustness, efficiency, and reliability. They are used in various applications, such as pumps, fans, compressors, conveyors, and machine tools. However, faults in induction motors can cause operational and financial losses, and in some cases, they can lead to severe accidents. Therefore, timely and accurate detection of faults is crucial for minimizing the negative impact of these faults. The fault detection methods for induction motors can involve the analysis of various signals such as vibration, current, and voltage. Convolutional neural networks (CNNs) have proven highly effective in many applications but have mainly been applied to two-dimensional data. One-dimensional CNNs offer an excellent alternative for analyzing time sequence datasets since they can work directly with raw signal data without requiring pre- or post-processing. However, the main idea behind 1D-CNNs is to extract spatial features, which can result in the loss of critical temporal features related to time distribution. Recurrent neural networks (RNNs) can effectively capture the temporal dependencies and time distribution in sequences data, making them well-suited to fix the issue. In this paper, we propose a method that combines 1D-CNNs and RNNs called Hybrid 1DCNN-RNN network (HCRN) to analyze the voltage and current signals of a three-phase induction motor. It performs accurate and efficient fault diagnosis, ultimately leading to the more efficient maintenance and reduced downtime for industrial processes.","PeriodicalId":280745,"journal":{"name":"2023 International Conference on System Science and Engineering (ICSSE)","volume":"308 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":"116530925","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/icsse58758.2023.10227179
{"title":"ICSSE 2023 Organizing Committee","authors":"","doi":"10.1109/icsse58758.2023.10227179","DOIUrl":"https://doi.org/10.1109/icsse58758.2023.10227179","url":null,"abstract":"","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":"132615017","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/ICSSE58758.2023.10227228
Nguyen Van Toan, Tran Trung Duy, Pham Ngoc Son, Dang The Hung, N. Q. Sang, L. Tu
In this paper, outage performance of hybrid satellite-terrestrial relaying networks using rateless codes (RCs) is evaluated via both simulation and analysis. In the proposed scheme, a satellite (S) transmits encoded packets to a group of terrestrial users (U) with help of a terrestrial station (R). The terrestrial users are suffered from co-channel interference, and they must receive a sufficient number of the encoded packets for the data recovery. This paper analyzes outage probability (OP) at each user and system outage probability (SOP) defined as probability that one of the users cannot collect enough encoded packets after the transmission ends. This paper also investigates impact of number of the users, number of the interference sources, and number of the data transmission of the satellite on the OP and SOP performance.
{"title":"Outage Performance Of Hybrid Satellite-Terrestrial Relaying Networks With Rateless Codes In Co-Channel Interference Environment","authors":"Nguyen Van Toan, Tran Trung Duy, Pham Ngoc Son, Dang The Hung, N. Q. Sang, L. Tu","doi":"10.1109/ICSSE58758.2023.10227228","DOIUrl":"https://doi.org/10.1109/ICSSE58758.2023.10227228","url":null,"abstract":"In this paper, outage performance of hybrid satellite-terrestrial relaying networks using rateless codes (RCs) is evaluated via both simulation and analysis. In the proposed scheme, a satellite (S) transmits encoded packets to a group of terrestrial users (U) with help of a terrestrial station (R). The terrestrial users are suffered from co-channel interference, and they must receive a sufficient number of the encoded packets for the data recovery. This paper analyzes outage probability (OP) at each user and system outage probability (SOP) defined as probability that one of the users cannot collect enough encoded packets after the transmission ends. This paper also investigates impact of number of the users, number of the interference sources, and number of the data transmission of the satellite on the OP and SOP performance.","PeriodicalId":280745,"journal":{"name":"2023 International Conference on System Science and Engineering (ICSSE)","volume":"16 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":"128546775","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/ICSSE58758.2023.10227185
Phuc T Phan, Le An Nhuan, Hoa Truong Phuoc, H. Nguyen, Trong Tai Nguyen, D. M. Pham
The development of an energy-sharing algorithm corresponding to the generating capacity of a parallel generator is a mandatory requirement for overload protection and improving power system reliability. As a consequence, the droop control algorithm is considered a potential algorithm to control the production of distributed generators. However, this conventional method often fails to reach the maximum capacity of sources that vary with environmental conditions such as photovoltaic (PV) systems and wind turbines. To overcome this limitation, this study combines the MPPT algorithm with the droop control algorithm for PV grid-connected systems to improve the system power quality. As a result, the P&O algorithms not only enable grid power sharing but also enable MPPT tracking. The simulation results are analyzed to verify the effectiveness of the combined MPPT method.
{"title":"Modified Droop Control Algorithm for Photovoltaic Solar Energy in Low Voltage DC Microgrid","authors":"Phuc T Phan, Le An Nhuan, Hoa Truong Phuoc, H. Nguyen, Trong Tai Nguyen, D. M. Pham","doi":"10.1109/ICSSE58758.2023.10227185","DOIUrl":"https://doi.org/10.1109/ICSSE58758.2023.10227185","url":null,"abstract":"The development of an energy-sharing algorithm corresponding to the generating capacity of a parallel generator is a mandatory requirement for overload protection and improving power system reliability. As a consequence, the droop control algorithm is considered a potential algorithm to control the production of distributed generators. However, this conventional method often fails to reach the maximum capacity of sources that vary with environmental conditions such as photovoltaic (PV) systems and wind turbines. To overcome this limitation, this study combines the MPPT algorithm with the droop control algorithm for PV grid-connected systems to improve the system power quality. As a result, the P&O algorithms not only enable grid power sharing but also enable MPPT tracking. The simulation results are analyzed to verify the effectiveness of the combined MPPT method.","PeriodicalId":280745,"journal":{"name":"2023 International Conference on System Science and Engineering (ICSSE)","volume":"9 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":"132909736","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/ICSSE58758.2023.10227212
Huu Son Nguyen, Duc Thinh Le, Van Trong Dang, D. H. Nguyen, Le Anh Tuan, T. Nguyen
This paper presents a backstepping sliding mode control with reaching law based on an extended state observer for tracking control of a quadrotor unmanned aerial vehicle (UAV) under external disturbances. Firstly, a six-degree-of-freedom quadrotor UAV model with disturbances is given. Secondly, the cascade control system is proposed with the Backstepping Sliding Mode controller to track the desired trajectory command under parameter uncertainties. Thirdly, the extended state observer is designed to estimate the external disturbances and rate of the states of the quadrotor UAV to reduce the sensor and increase robustness. The stability of the system is demonstrated by Lyapunov theory and the simulation results via Matlab/Simulink environment.
{"title":"Advanced Motion Control of a Quadrotor Unmanned Aerial Vehicle based on Extended State Observer","authors":"Huu Son Nguyen, Duc Thinh Le, Van Trong Dang, D. H. Nguyen, Le Anh Tuan, T. Nguyen","doi":"10.1109/ICSSE58758.2023.10227212","DOIUrl":"https://doi.org/10.1109/ICSSE58758.2023.10227212","url":null,"abstract":"This paper presents a backstepping sliding mode control with reaching law based on an extended state observer for tracking control of a quadrotor unmanned aerial vehicle (UAV) under external disturbances. Firstly, a six-degree-of-freedom quadrotor UAV model with disturbances is given. Secondly, the cascade control system is proposed with the Backstepping Sliding Mode controller to track the desired trajectory command under parameter uncertainties. Thirdly, the extended state observer is designed to estimate the external disturbances and rate of the states of the quadrotor UAV to reduce the sensor and increase robustness. The stability of the system is demonstrated by Lyapunov theory and the simulation results via Matlab/Simulink environment.","PeriodicalId":280745,"journal":{"name":"2023 International Conference on System Science and Engineering (ICSSE)","volume":"55 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":"129749085","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/ICSSE58758.2023.10227143
Gaurav Srivastava, Mahesh Jangid
The complexity of high-dimensional datasets presents significant challenges for machine learning models, including overfitting, computational complexity, and difficulties in interpreting results. To address these challenges, it is essential to identify an informative subset of features that captures the essential structure of the data. In this study, the authors propose Multi-view Sparse Laplacian Eigenmaps (MSLE) for feature selection, which effectively combines multiple views of the data, enforces sparsity constraints, and employs a scalable optimization algorithm to identify a subset of features that capture the fundamental data structure. MSLE is a graph-based approach that leverages multiple views of the data to construct a more robust and informative representation of high-dimensional data. The method applies sparse eigendecomposition to reduce the dimensionality of the data, yielding a reduced feature set. The optimization problem is solved using an iterative algorithm alternating between updating the sparse coefficients and the Laplacian graph matrix. The sparse coefficients are updated using a soft-thresholding operator, while the graph Laplacian matrix is updated using the normalized graph Laplacian. To evaluate the performance of the MSLE technique, the authors conducted experiments on the UCI-HAR dataset, which comprises 561 features, and reduced the feature space by 10-90%. Our results demonstrate that even after reducing the feature space by 90%, the Support Vector Machine (SVM) maintains an error rate of 2.72%. Moreover, the authors observe that the SVM exhibits an accuracy of 96.69% with an 80% reduction in the overall feature space.
{"title":"Multi-view Sparse Laplacian Eigenmaps for nonlinear Spectral Feature Selection","authors":"Gaurav Srivastava, Mahesh Jangid","doi":"10.1109/ICSSE58758.2023.10227143","DOIUrl":"https://doi.org/10.1109/ICSSE58758.2023.10227143","url":null,"abstract":"The complexity of high-dimensional datasets presents significant challenges for machine learning models, including overfitting, computational complexity, and difficulties in interpreting results. To address these challenges, it is essential to identify an informative subset of features that captures the essential structure of the data. In this study, the authors propose Multi-view Sparse Laplacian Eigenmaps (MSLE) for feature selection, which effectively combines multiple views of the data, enforces sparsity constraints, and employs a scalable optimization algorithm to identify a subset of features that capture the fundamental data structure. MSLE is a graph-based approach that leverages multiple views of the data to construct a more robust and informative representation of high-dimensional data. The method applies sparse eigendecomposition to reduce the dimensionality of the data, yielding a reduced feature set. The optimization problem is solved using an iterative algorithm alternating between updating the sparse coefficients and the Laplacian graph matrix. The sparse coefficients are updated using a soft-thresholding operator, while the graph Laplacian matrix is updated using the normalized graph Laplacian. To evaluate the performance of the MSLE technique, the authors conducted experiments on the UCI-HAR dataset, which comprises 561 features, and reduced the feature space by 10-90%. Our results demonstrate that even after reducing the feature space by 90%, the Support Vector Machine (SVM) maintains an error rate of 2.72%. Moreover, the authors observe that the SVM exhibits an accuracy of 96.69% with an 80% reduction in the overall feature space.","PeriodicalId":280745,"journal":{"name":"2023 International Conference on System Science and Engineering (ICSSE)","volume":"41 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":"126300200","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/ICSSE58758.2023.10227229
Thanh Hoang Le Hai, Luan Le Dinh, Dat Ngo Tien, Dat Bui Huu Tien, N. Thoai
Exploiting current High Performance Computing (HPC) systems is a critical task for resolving urgent worldwide problems. However, existing scheduling heuristics such as First Come First Served (FCFS) have limitations in dealing with the increasing complexity of computing systems and the dynamic nature of application workloads. Reinforcement learning (RL) has emerged as a promising approach to designing HPC schedulers that can learn to adapt to dynamic system configurations and workload conditions. However, existing RL-based schedulers often lack the ability to incorporate important identity features of jobs and do not consider user behavior.To address these limitations, we propose an improvement to the latest Deep Reinforcement Learning Agent for Scheduling (DRAS) model, called Improved Reinforcement Learning Scheduler (IRLS). The IRLS model incorporates additional identity features in the state definition to recognize similarities between tasks from the same source and utilizes an empirical approach to perform job runtime prediction. Our experiments demonstrate that by using the IRLS model, we can significantly improve the performance of real-life HPC workloads, with improvements of up to 15.4% compared to the original DRAS model and 35.7% compared to FCFS.
{"title":"IRLS: An Improved Reinforcement Learning Scheduler for High Performance Computing Systems","authors":"Thanh Hoang Le Hai, Luan Le Dinh, Dat Ngo Tien, Dat Bui Huu Tien, N. Thoai","doi":"10.1109/ICSSE58758.2023.10227229","DOIUrl":"https://doi.org/10.1109/ICSSE58758.2023.10227229","url":null,"abstract":"Exploiting current High Performance Computing (HPC) systems is a critical task for resolving urgent worldwide problems. However, existing scheduling heuristics such as First Come First Served (FCFS) have limitations in dealing with the increasing complexity of computing systems and the dynamic nature of application workloads. Reinforcement learning (RL) has emerged as a promising approach to designing HPC schedulers that can learn to adapt to dynamic system configurations and workload conditions. However, existing RL-based schedulers often lack the ability to incorporate important identity features of jobs and do not consider user behavior.To address these limitations, we propose an improvement to the latest Deep Reinforcement Learning Agent for Scheduling (DRAS) model, called Improved Reinforcement Learning Scheduler (IRLS). The IRLS model incorporates additional identity features in the state definition to recognize similarities between tasks from the same source and utilizes an empirical approach to perform job runtime prediction. Our experiments demonstrate that by using the IRLS model, we can significantly improve the performance of real-life HPC workloads, with improvements of up to 15.4% compared to the original DRAS model and 35.7% compared to FCFS.","PeriodicalId":280745,"journal":{"name":"2023 International Conference on System Science and Engineering (ICSSE)","volume":"70 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":"116661452","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/ICSSE58758.2023.10227217
Hai-Binh Le, Thai Dinh Kim, Manh-Hung Ha, Anh Long Quang Tran, Duy-Thuc Nguyen, X. Dinh
Surgica1 tool detection involves identifying the position and type of instruments in an image. This is one of the significant issues in automatic video analysis that can aid in evaluating the surgical skills of doctors or automating the process of controlling the viewing angle of the endoscopic camera. This paper presents a robust method for detecting surgical tools using the YOLOv8 model. We trained four different versions of YOLOv8, evaluated their effectiveness, and compared them with previous models. The experimental results indicate that the YOLOv8 models have an average mAP50 greater than 95.6% across all classes, and are significantly better than some previous research findings.
{"title":"Robust Surgical Tool Detection in Laparoscopic Surgery using YOLOv8 Model","authors":"Hai-Binh Le, Thai Dinh Kim, Manh-Hung Ha, Anh Long Quang Tran, Duy-Thuc Nguyen, X. Dinh","doi":"10.1109/ICSSE58758.2023.10227217","DOIUrl":"https://doi.org/10.1109/ICSSE58758.2023.10227217","url":null,"abstract":"Surgica1 tool detection involves identifying the position and type of instruments in an image. This is one of the significant issues in automatic video analysis that can aid in evaluating the surgical skills of doctors or automating the process of controlling the viewing angle of the endoscopic camera. This paper presents a robust method for detecting surgical tools using the YOLOv8 model. We trained four different versions of YOLOv8, evaluated their effectiveness, and compared them with previous models. The experimental results indicate that the YOLOv8 models have an average mAP50 greater than 95.6% across all classes, and are significantly better than some previous research findings.","PeriodicalId":280745,"journal":{"name":"2023 International Conference on System Science and Engineering (ICSSE)","volume":"1 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":"129521516","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：