Pub Date : 2021-12-03DOI: 10.1109/ICICIP53388.2021.9642158
Huaying Sun, Shujun Wu, Guang-Fu Xue, Kai Zhang, Jian Wang
Broad Learning System (BLS), a newly-developing alternative approach of learning for deep neural network, has attracted much attentions from researchers all over the world due to its straightforward network structure and powerful performance to deal with classification and regression problems. The number of feature nodes and enhancement nodes in classical BLS is determined by grid search method which leads to heavy training burden, while the weights between input data and feature nodes are randomly initialized and fine-tuned taking advantages of sparse autoencoder. Different from that, a new BLS with Particle Swarm optimization (PSO) and Singular Value Decomposition (SVD) is raised in this paper. PSO algorithm is introduced to acquire the optimal number of feature nodes and enhancement nodes, which greatly reduces the search time. In addition, the weights between input data and feature nodes are initialized by SVD method, which avoids using iteration method to optimize them and also reduces computational cost. The experimental results on several regression datasets demonstrate that BLS with PSO and SVD can not only find optimal number of system nodes much faster than classical BLS but also achieve considerable satisfactory accuracy.
{"title":"Broad Learning System with Particle Swarm Optimization and Singular Value Decomposition","authors":"Huaying Sun, Shujun Wu, Guang-Fu Xue, Kai Zhang, Jian Wang","doi":"10.1109/ICICIP53388.2021.9642158","DOIUrl":"https://doi.org/10.1109/ICICIP53388.2021.9642158","url":null,"abstract":"Broad Learning System (BLS), a newly-developing alternative approach of learning for deep neural network, has attracted much attentions from researchers all over the world due to its straightforward network structure and powerful performance to deal with classification and regression problems. The number of feature nodes and enhancement nodes in classical BLS is determined by grid search method which leads to heavy training burden, while the weights between input data and feature nodes are randomly initialized and fine-tuned taking advantages of sparse autoencoder. Different from that, a new BLS with Particle Swarm optimization (PSO) and Singular Value Decomposition (SVD) is raised in this paper. PSO algorithm is introduced to acquire the optimal number of feature nodes and enhancement nodes, which greatly reduces the search time. In addition, the weights between input data and feature nodes are initialized by SVD method, which avoids using iteration method to optimize them and also reduces computational cost. The experimental results on several regression datasets demonstrate that BLS with PSO and SVD can not only find optimal number of system nodes much faster than classical BLS but also achieve considerable satisfactory accuracy.","PeriodicalId":435799,"journal":{"name":"2021 11th International Conference on Intelligent Control and Information Processing (ICICIP)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116858018","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-12-03DOI: 10.1109/ICICIP53388.2021.9642168
F. Farahnakian, J. Heikkonen, S. Björkman
Pose estimation towards providing the assessments of animal health and welfare monitoring has strongly gained interest in the last few years. However, it is a challenging computer vision problem as the frequent interaction causes occlusions the association of detected key-points to the correct individuals. Deep Learning (DL) offers major advances in the field of pose estimation. In this paper, we investigated the possibility of using a famous open-source DL-based toolbox, DeepLabCut [1], for the specific pig pose estimation task. We predicted the body part of each individual pig from only input images or video sequences directly with no adaptations to the application setting. We used a real dataset which contains 2000 annotated images with 24,842 individually annotated pigs from 17 different locations and light conditions. The experimental results demonstrated that we can achieve a small root mean square error between the manual and predicted labels (10.1) when detecting pigs in environments previously seen by a DL model during training. To evaluate the robustness of the trained model, it is also tested on environments and lighting conditions unseen in the training set, where it achieves 12.0 root mean square error.
{"title":"Multi-pig Pose Estimation Using DeepLabCut","authors":"F. Farahnakian, J. Heikkonen, S. Björkman","doi":"10.1109/ICICIP53388.2021.9642168","DOIUrl":"https://doi.org/10.1109/ICICIP53388.2021.9642168","url":null,"abstract":"Pose estimation towards providing the assessments of animal health and welfare monitoring has strongly gained interest in the last few years. However, it is a challenging computer vision problem as the frequent interaction causes occlusions the association of detected key-points to the correct individuals. Deep Learning (DL) offers major advances in the field of pose estimation. In this paper, we investigated the possibility of using a famous open-source DL-based toolbox, DeepLabCut [1], for the specific pig pose estimation task. We predicted the body part of each individual pig from only input images or video sequences directly with no adaptations to the application setting. We used a real dataset which contains 2000 annotated images with 24,842 individually annotated pigs from 17 different locations and light conditions. The experimental results demonstrated that we can achieve a small root mean square error between the manual and predicted labels (10.1) when detecting pigs in environments previously seen by a DL model during training. To evaluate the robustness of the trained model, it is also tested on environments and lighting conditions unseen in the training set, where it achieves 12.0 root mean square error.","PeriodicalId":435799,"journal":{"name":"2021 11th International Conference on Intelligent Control and Information Processing (ICICIP)","volume":"147 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124889193","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-12-03DOI: 10.1109/ICICIP53388.2021.9642156
Guangyang Tian, Cheng Lian, Zhigang Zeng
PCG signal contains important information about heart movement, which is of great significance to the diagnosis and prevention of heart disease. In this paper, we adopt Res2Net which is a multi-scale neural network as the backbone framework to train on PCG dataset. Meanwhile, to address the problem of data imbalance, we utilize Seesaw loss to replace the traditional Cross-entropy loss. Seesaw loss uses mitigation factor and compensation factor to re-balance the gradient of positive and negative samples to reduce the dominance of head classes in the training process. Moreover, we propose an integrated method which is to select three models with the best performance on the test set to integrate to improve the generalizability of Res2Net and the accuracy of PCG classification. Furthermore, we conduct extensive experiments on PCG datasets, and the results show that our method is effective and has strong competitiveness.
{"title":"Integrated Res2Net combined with Seesaw loss for Long-Tailed PCG signal classification","authors":"Guangyang Tian, Cheng Lian, Zhigang Zeng","doi":"10.1109/ICICIP53388.2021.9642156","DOIUrl":"https://doi.org/10.1109/ICICIP53388.2021.9642156","url":null,"abstract":"PCG signal contains important information about heart movement, which is of great significance to the diagnosis and prevention of heart disease. In this paper, we adopt Res2Net which is a multi-scale neural network as the backbone framework to train on PCG dataset. Meanwhile, to address the problem of data imbalance, we utilize Seesaw loss to replace the traditional Cross-entropy loss. Seesaw loss uses mitigation factor and compensation factor to re-balance the gradient of positive and negative samples to reduce the dominance of head classes in the training process. Moreover, we propose an integrated method which is to select three models with the best performance on the test set to integrate to improve the generalizability of Res2Net and the accuracy of PCG classification. Furthermore, we conduct extensive experiments on PCG datasets, and the results show that our method is effective and has strong competitiveness.","PeriodicalId":435799,"journal":{"name":"2021 11th International Conference on Intelligent Control and Information Processing (ICICIP)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114402194","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-12-03DOI: 10.1109/ICICIP53388.2021.9642217
Jiawen Xu, Zhiyuan You, Xinyi Le, Cailian Chen, X. Guan
Intelligent agents utilize various sensors such as LiDAR, cameras to perceive the surroundings. However, the frame rate difference among sensors seriously affects both safety and efficiency of intelligent agents. Recently some research concerning point cloud frame interpolation is conducted to solve the frame rate inconsistency problem by interpolating low frame rate point cloud sequences up to high frame rate ones. To improve the performance of current state-of-the-art method, we come up with a novel Hierarchical Point Cloud Frame Interpolation Network (HINet). By proposed hierarchical warping module, coarse intermediate frames are generated hierarchically to reach closer toward the target position. Besides, we propose spatial aware fusion strategy to hierarchically restore local geometric distribution by attention mechanism and positional offset. Finally, hierarchical supervision module is applied to efficiently train the HINet in two stages, guaranteeing the quality of predicted intermediate frames. We employ HINet in a large outdoor autonomous driving dataset and provide convincing qualitative and quantitative evaluation results.
{"title":"HINet: Hierarchical Point Cloud Frame Interpolation Network","authors":"Jiawen Xu, Zhiyuan You, Xinyi Le, Cailian Chen, X. Guan","doi":"10.1109/ICICIP53388.2021.9642217","DOIUrl":"https://doi.org/10.1109/ICICIP53388.2021.9642217","url":null,"abstract":"Intelligent agents utilize various sensors such as LiDAR, cameras to perceive the surroundings. However, the frame rate difference among sensors seriously affects both safety and efficiency of intelligent agents. Recently some research concerning point cloud frame interpolation is conducted to solve the frame rate inconsistency problem by interpolating low frame rate point cloud sequences up to high frame rate ones. To improve the performance of current state-of-the-art method, we come up with a novel Hierarchical Point Cloud Frame Interpolation Network (HINet). By proposed hierarchical warping module, coarse intermediate frames are generated hierarchically to reach closer toward the target position. Besides, we propose spatial aware fusion strategy to hierarchically restore local geometric distribution by attention mechanism and positional offset. Finally, hierarchical supervision module is applied to efficiently train the HINet in two stages, guaranteeing the quality of predicted intermediate frames. We employ HINet in a large outdoor autonomous driving dataset and provide convincing qualitative and quantitative evaluation results.","PeriodicalId":435799,"journal":{"name":"2021 11th International Conference on Intelligent Control and Information Processing (ICICIP)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129647609","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}
Poor posture and the overuse of electronic devices may lead to an increased incidence of spinal deformity and even scoliosis in students. To investigate the incidence of scoliosis in college students and to explore related risk factors for this problem, a cross-sectional study examining scoliosis was conducted with 318 college students and a cross-sectional survey was delivered to 593 college students on risk factors related to spinal health problems, after all a descriptive analysis and an analytic hierarchy process (AHP) were performed on the collected data. Among 318 college students, 7.23 % of them received a scoliosis diagnosis at greater than seven degrees. The results of the AHP showed that sitting with crossed legs was the most important risk factor for scoliosis. Among the 593 subjects, 35.92% of college students reported always sitting with crossed legs, 33.22% always falling asleep at their desk, and 79.59% seated for more than six hours per day. Spinal health problems, particularly scoliosis, are common among college students. Awareness should be spread for risk factors related to these problems.
{"title":"Epidemiology and Risk Factors of Scoliosis in College Students","authors":"Jia-he Yang, J. Yi, Wenmei Li, Ting Zhang, Wei Liu, Xiaoling Duan","doi":"10.1109/ICICIP53388.2021.9642189","DOIUrl":"https://doi.org/10.1109/ICICIP53388.2021.9642189","url":null,"abstract":"Poor posture and the overuse of electronic devices may lead to an increased incidence of spinal deformity and even scoliosis in students. To investigate the incidence of scoliosis in college students and to explore related risk factors for this problem, a cross-sectional study examining scoliosis was conducted with 318 college students and a cross-sectional survey was delivered to 593 college students on risk factors related to spinal health problems, after all a descriptive analysis and an analytic hierarchy process (AHP) were performed on the collected data. Among 318 college students, 7.23 % of them received a scoliosis diagnosis at greater than seven degrees. The results of the AHP showed that sitting with crossed legs was the most important risk factor for scoliosis. Among the 593 subjects, 35.92% of college students reported always sitting with crossed legs, 33.22% always falling asleep at their desk, and 79.59% seated for more than six hours per day. Spinal health problems, particularly scoliosis, are common among college students. Awareness should be spread for risk factors related to these problems.","PeriodicalId":435799,"journal":{"name":"2021 11th International Conference on Intelligent Control and Information Processing (ICICIP)","volume":"144 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124451279","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-12-03DOI: 10.1109/ICICIP53388.2021.9642170
Pei Zhang, Yinyan Zhang
Intrusion detection is very important to ensure the security of information systems. Neural networks aided by metaheuristic algorithms have been shown to be an alternative for intrusion detection. However, the current methods require much time for the training of the neural networks. In this paper, we propose a beetle antennae search (BAS) algorithm based neural network for efficient intrusion detection. In order to highlight the superiority of the algorithm, we conduct numerical experiments with a simple neural network based on the KDD CUP 99 dataset, which show that the proposed method is effective.
入侵检测是保证信息系统安全的重要手段。神经网络辅助的元启发式算法已被证明是入侵检测的一种替代方案。然而，目前的方法需要大量的时间来训练神经网络。本文提出了一种基于甲虫天线搜索(BAS)算法的神经网络入侵检测方法。为了突出算法的优越性，我们在KDD CUP 99数据集上用一个简单的神经网络进行了数值实验，结果表明该方法是有效的。
{"title":"A BAS Algorithm Based Neural Network for Intrusion Detection","authors":"Pei Zhang, Yinyan Zhang","doi":"10.1109/ICICIP53388.2021.9642170","DOIUrl":"https://doi.org/10.1109/ICICIP53388.2021.9642170","url":null,"abstract":"Intrusion detection is very important to ensure the security of information systems. Neural networks aided by metaheuristic algorithms have been shown to be an alternative for intrusion detection. However, the current methods require much time for the training of the neural networks. In this paper, we propose a beetle antennae search (BAS) algorithm based neural network for efficient intrusion detection. In order to highlight the superiority of the algorithm, we conduct numerical experiments with a simple neural network based on the KDD CUP 99 dataset, which show that the proposed method is effective.","PeriodicalId":435799,"journal":{"name":"2021 11th International Conference on Intelligent Control and Information Processing (ICICIP)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132002750","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-12-03DOI: 10.1109/ICICIP53388.2021.9642161
Hanlin Zhang, Xinming Wang, Weihong Ren, Yuchen Zhao, Qingcai Chen, Jingyong Su, Junjie Chen, Honghai Liu
Autism Spectrum Disorder (ASD), usually discovered in childhood, is a neurodevelopmental disorder with clinical manifestations like social communication disorders, stereotyped behaviors, and narrow interests. Incomplete cognitive ability is one reason that causes social communication disorders among autistic children. Therefore, it is critical to evaluate the cognitive abilities of autistic children and provide guidance for subsequent intervention programs. In this work, we present a gaze-driven interaction system, assessing the cognitive performance of the subject. Based on our paradigms, an interface that contains specific pictures, videos and games creates a bond of interaction between subjects and the system. During the assessment process, the gaze features of subjects will be captured for deducing a cognitive ability index, which is used for judging the degree of cognition. The result shows that our system can evaluate the cognitive ability ranging from colors, shapes, emotions to social relationships, and provide guidance for the formulation of follow-up personalized intervention programs.
{"title":"Gaze-driven Interaction System for Cognitive Ability Assessment","authors":"Hanlin Zhang, Xinming Wang, Weihong Ren, Yuchen Zhao, Qingcai Chen, Jingyong Su, Junjie Chen, Honghai Liu","doi":"10.1109/ICICIP53388.2021.9642161","DOIUrl":"https://doi.org/10.1109/ICICIP53388.2021.9642161","url":null,"abstract":"Autism Spectrum Disorder (ASD), usually discovered in childhood, is a neurodevelopmental disorder with clinical manifestations like social communication disorders, stereotyped behaviors, and narrow interests. Incomplete cognitive ability is one reason that causes social communication disorders among autistic children. Therefore, it is critical to evaluate the cognitive abilities of autistic children and provide guidance for subsequent intervention programs. In this work, we present a gaze-driven interaction system, assessing the cognitive performance of the subject. Based on our paradigms, an interface that contains specific pictures, videos and games creates a bond of interaction between subjects and the system. During the assessment process, the gaze features of subjects will be captured for deducing a cognitive ability index, which is used for judging the degree of cognition. The result shows that our system can evaluate the cognitive ability ranging from colors, shapes, emotions to social relationships, and provide guidance for the formulation of follow-up personalized intervention programs.","PeriodicalId":435799,"journal":{"name":"2021 11th International Conference on Intelligent Control and Information Processing (ICICIP)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131018146","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-12-03DOI: 10.1109/ICICIP53388.2021.9642195
Xin Li
In order to realize the advantages of easy portability,good control,low cost and high reliability of the robot laser ranging controller,we design the robot laser ranging controller based on embedded technology,which consists of two parts:the upper station and the lower station.The upper station displays,analyzes and manages the data from the lower station,which consists of a laser range collector,a direct controller and a display.The lower station collects the status and environmental data of the robot’s laser ranging and consists of an illuminated camera,GT8340 embedded control chip and motor driver.The control process of the GT8340 embedded control chip for the robot laser ranging was analyzed, as well as the connection structure and function of the upper unit,and the software design of the communication interface between the upper unit and the lower unit and the robot was carried out.The experimental results prove that the designed controller has small ranging error and short control delay time.
{"title":"Robot laser range controller design based on embedded technology","authors":"Xin Li","doi":"10.1109/ICICIP53388.2021.9642195","DOIUrl":"https://doi.org/10.1109/ICICIP53388.2021.9642195","url":null,"abstract":"In order to realize the advantages of easy portability,good control,low cost and high reliability of the robot laser ranging controller,we design the robot laser ranging controller based on embedded technology,which consists of two parts:the upper station and the lower station.The upper station displays,analyzes and manages the data from the lower station,which consists of a laser range collector,a direct controller and a display.The lower station collects the status and environmental data of the robot’s laser ranging and consists of an illuminated camera,GT8340 embedded control chip and motor driver.The control process of the GT8340 embedded control chip for the robot laser ranging was analyzed, as well as the connection structure and function of the upper unit,and the software design of the communication interface between the upper unit and the lower unit and the robot was carried out.The experimental results prove that the designed controller has small ranging error and short control delay time.","PeriodicalId":435799,"journal":{"name":"2021 11th International Conference on Intelligent Control and Information Processing (ICICIP)","volume":"121 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133135899","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-12-03DOI: 10.1109/ICICIP53388.2021.9642214
Debiao Li, Cheng Lian, Wei Yao
Time series classification(TSC) is an interesting and worthy research problem in the field of machine learning. Thus, many convolutional neural network(CNN) algorithms have been proposed to improve the classification accuracy. Among these algorithms, most models solve this task by designing different neural network architectures. In addition, we are inspired by the successful application of the attention mechanism in the computer vision field, which can extract critical information that is beneficial to the target task from the input. Therefore, in this article, we apply 5 attention mechanisms to 6 neural networks and construct 30 models to study classification of time series. Specifically, we choose the attention mechanism to focus on the effective information in the time series from the channel dimension or the spatial dimension. We evaluate the performance of our constructed models on the UCR archive [1], and the experimental results show that the model that processes time series from multiple scales obtains the better results.
{"title":"Research on time series classification based on convolutional neural network with attention mechanism","authors":"Debiao Li, Cheng Lian, Wei Yao","doi":"10.1109/ICICIP53388.2021.9642214","DOIUrl":"https://doi.org/10.1109/ICICIP53388.2021.9642214","url":null,"abstract":"Time series classification(TSC) is an interesting and worthy research problem in the field of machine learning. Thus, many convolutional neural network(CNN) algorithms have been proposed to improve the classification accuracy. Among these algorithms, most models solve this task by designing different neural network architectures. In addition, we are inspired by the successful application of the attention mechanism in the computer vision field, which can extract critical information that is beneficial to the target task from the input. Therefore, in this article, we apply 5 attention mechanisms to 6 neural networks and construct 30 models to study classification of time series. Specifically, we choose the attention mechanism to focus on the effective information in the time series from the channel dimension or the spatial dimension. We evaluate the performance of our constructed models on the UCR archive [1], and the experimental results show that the model that processes time series from multiple scales obtains the better results.","PeriodicalId":435799,"journal":{"name":"2021 11th International Conference on Intelligent Control and Information Processing (ICICIP)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130604142","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}
The controller of railway vehicle is the main command control electric appliance which controls the operation of railway vehicle. Any fault of the electronic circuit of the controller will cause the safety accident of railway vehicle. Aiming at the problem of low accuracy in fault diagnosis of controller electronic circuits caused by fuzzy meaning in feature extraction, a fault diagnosis method based on maximum variance rotating principal component analysis and confidence rule base was proposed. Firstly, the dimensionality of the data was reduced by the principal component analysis of the maximum variance rotation to improve the explan ability of the factors after dimensionality reduction. Then the belief rule base reasoning method based on evidence reasoning was used to diagnose the fault, and the CMA-E algorithm was used to optimize the initial parameters of the established model, so as to improve the accuracy of fault diagnosis of electronic circuit of railway vehicle. The effectiveness of the proposed method is verified by simulation and experiment.
{"title":"Diagnose of electronic circuits of the driver controller based on VPCA-BRB model","authors":"Zhi Gao, Siyu Chen, Xinming Zhang, Bangcheng Zhang, Yubo Shao","doi":"10.1109/ICICIP53388.2021.9642221","DOIUrl":"https://doi.org/10.1109/ICICIP53388.2021.9642221","url":null,"abstract":"The controller of railway vehicle is the main command control electric appliance which controls the operation of railway vehicle. Any fault of the electronic circuit of the controller will cause the safety accident of railway vehicle. Aiming at the problem of low accuracy in fault diagnosis of controller electronic circuits caused by fuzzy meaning in feature extraction, a fault diagnosis method based on maximum variance rotating principal component analysis and confidence rule base was proposed. Firstly, the dimensionality of the data was reduced by the principal component analysis of the maximum variance rotation to improve the explan ability of the factors after dimensionality reduction. Then the belief rule base reasoning method based on evidence reasoning was used to diagnose the fault, and the CMA-E algorithm was used to optimize the initial parameters of the established model, so as to improve the accuracy of fault diagnosis of electronic circuit of railway vehicle. The effectiveness of the proposed method is verified by simulation and experiment.","PeriodicalId":435799,"journal":{"name":"2021 11th International Conference on Intelligent Control and Information Processing (ICICIP)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124270737","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：