Pub Date : 2018-10-01DOI: 10.1109/ICCAIS.2018.8570495
Yangyang Zhao, D. Han, Gen Wang, Kun Xiao
In this paper, a new method of modeling a full strap-down laser seeker is proposed for the seeker's characteristics of large field-of-view, small linear area and slight fluctuation in the line-of-sight angle. Moreover, a new switching logic guidance method with pre-estimating function is suggested. Adding pre-estimation and switching correction items to the original, this method is able to switch the line-of-sight angle from the nonlinear to the linear zone quickly and steadily; on the other hand, it also limits the seeker frequent switching between the linear and nonlinear zone caused by the missile's oscillation.
{"title":"A Guidance Method Adapted to the Full Strap-Down Laser Homing System","authors":"Yangyang Zhao, D. Han, Gen Wang, Kun Xiao","doi":"10.1109/ICCAIS.2018.8570495","DOIUrl":"https://doi.org/10.1109/ICCAIS.2018.8570495","url":null,"abstract":"In this paper, a new method of modeling a full strap-down laser seeker is proposed for the seeker's characteristics of large field-of-view, small linear area and slight fluctuation in the line-of-sight angle. Moreover, a new switching logic guidance method with pre-estimating function is suggested. Adding pre-estimation and switching correction items to the original, this method is able to switch the line-of-sight angle from the nonlinear to the linear zone quickly and steadily; on the other hand, it also limits the seeker frequent switching between the linear and nonlinear zone caused by the missile's oscillation.","PeriodicalId":223618,"journal":{"name":"2018 International Conference on Control, Automation and Information Sciences (ICCAIS)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115397460","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 : 2018-10-01DOI: 10.1109/ICCAIS.2018.8570426
Yan Li, Mingyue Yang, Siyu Ji, Jing Zhang, Chenglin Wen
Damage of road surface, e.g., Cracks, is the critical problems in road maintenance. Previous automotive road damage detection methods mainly focus on hand-crafted features and shallow classifier models. Recently, deep learning methods have also been proposed. The deep neural networks consist of dozens of parameters, which is usually optimized by the Mini-batch Stochastic Gradient Descent Algorithm (MB-SGD). However, MB-SGD is awkward for online update when new training samples from a drifting system condition, e.g., illumination, are received. In this paper, we first present an experimental study on how the illumination change affects the generalization of a pre-trained deep convolutional neural networks. Then, we propose a novel Kalman Filter based method for online updating the network parameters. Experimental results convince that the illumination change can affect the performance of a pre-trained CNN using training samples from a fixed illumination condition. By using the proposed method, the CNN can online adapt its parameters in the classifier layer to the received training samples sequentially, which leads to a better classification performance. The proposed method alleviates the need of huge amount of training samples covering all system conditions, which are hard to collect and costly.
{"title":"An Online-Updating Deep CNN Method Based on Kalman Filter for Illumination-Drifting Road Damage Classification","authors":"Yan Li, Mingyue Yang, Siyu Ji, Jing Zhang, Chenglin Wen","doi":"10.1109/ICCAIS.2018.8570426","DOIUrl":"https://doi.org/10.1109/ICCAIS.2018.8570426","url":null,"abstract":"Damage of road surface, e.g., Cracks, is the critical problems in road maintenance. Previous automotive road damage detection methods mainly focus on hand-crafted features and shallow classifier models. Recently, deep learning methods have also been proposed. The deep neural networks consist of dozens of parameters, which is usually optimized by the Mini-batch Stochastic Gradient Descent Algorithm (MB-SGD). However, MB-SGD is awkward for online update when new training samples from a drifting system condition, e.g., illumination, are received. In this paper, we first present an experimental study on how the illumination change affects the generalization of a pre-trained deep convolutional neural networks. Then, we propose a novel Kalman Filter based method for online updating the network parameters. Experimental results convince that the illumination change can affect the performance of a pre-trained CNN using training samples from a fixed illumination condition. By using the proposed method, the CNN can online adapt its parameters in the classifier layer to the received training samples sequentially, which leads to a better classification performance. The proposed method alleviates the need of huge amount of training samples covering all system conditions, which are hard to collect and costly.","PeriodicalId":223618,"journal":{"name":"2018 International Conference on Control, Automation and Information Sciences (ICCAIS)","volume":"236 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116775204","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 : 2018-10-01DOI: 10.1109/ICCAIS.2018.8570336
Xinran Bai, Chen Li, Lihua Tian, Hui Song
Dynamic hand gesture is consisted by hand movement trajectory and the changes of hand shape. However, some existing methods only focus on the trajectory, and those methods can not accurately recognize the gesture that has the similar trajectory but different hand shape changes. For this problem, a dynamic hand gesture recognition method that combines the trajectory with the hand shape is proposed in this paper. First, we use depth images to determine the hand region and extract the location of palm center, avoiding the effect of lighting condition and complex environment. The absolute position and relative position of the palm center is adopted to represent the trajectory. Next, we present a method which combines convex hull with k-curvature to detect the fingertips contour, which can be a better representation of the hand shape change in dynamic gestures. Then we solve the image blurring problem by voting strategy. Besides, the Temporal Pyramid algorithm is applied to process the extracted features, since it can express temporal features more delicately and unify different feature dimensions. Finally, SVM algorithm is utilized to classify the dynamic hand gesture. The experimental results show that our method has higher recognition rate with less time consuming than the compared methods.
{"title":"Dynamic Hand Gesture Recognition Based On Depth Information","authors":"Xinran Bai, Chen Li, Lihua Tian, Hui Song","doi":"10.1109/ICCAIS.2018.8570336","DOIUrl":"https://doi.org/10.1109/ICCAIS.2018.8570336","url":null,"abstract":"Dynamic hand gesture is consisted by hand movement trajectory and the changes of hand shape. However, some existing methods only focus on the trajectory, and those methods can not accurately recognize the gesture that has the similar trajectory but different hand shape changes. For this problem, a dynamic hand gesture recognition method that combines the trajectory with the hand shape is proposed in this paper. First, we use depth images to determine the hand region and extract the location of palm center, avoiding the effect of lighting condition and complex environment. The absolute position and relative position of the palm center is adopted to represent the trajectory. Next, we present a method which combines convex hull with k-curvature to detect the fingertips contour, which can be a better representation of the hand shape change in dynamic gestures. Then we solve the image blurring problem by voting strategy. Besides, the Temporal Pyramid algorithm is applied to process the extracted features, since it can express temporal features more delicately and unify different feature dimensions. Finally, SVM algorithm is utilized to classify the dynamic hand gesture. The experimental results show that our method has higher recognition rate with less time consuming than the compared methods.","PeriodicalId":223618,"journal":{"name":"2018 International Conference on Control, Automation and Information Sciences (ICCAIS)","volume":"271 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120940839","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 : 2018-10-01DOI: 10.1109/ICCAIS.2018.8570461
Zihan Wang, Chenglin Wen, Bingnan Tang, Yi Ren
This paper studies the design method of multiplicative fault diagnosis observer for a class of uncertain discrete-time linear time-varying systems. Compared with the traditional Kalman filter residual fault diagnosis method, it has good fastness and accuracy. Then, for the fault estimation gain in the traditional fault estimator, it is difficult to follow the time-varying of the system state. Using the recursive least squares and Kalman filter combined to estimate the system fault and the system state identification, so that the fault estimation gain can follow the system state change in real time. Improve the accuracy of fault estimation. The simulation results verify the feasibility and effectiveness of the proposed method.
{"title":"Fault Diagnosis and Identification for Discrete-Time Linear Time-Varying Systems Based on Fault Observer and RLSKF","authors":"Zihan Wang, Chenglin Wen, Bingnan Tang, Yi Ren","doi":"10.1109/ICCAIS.2018.8570461","DOIUrl":"https://doi.org/10.1109/ICCAIS.2018.8570461","url":null,"abstract":"This paper studies the design method of multiplicative fault diagnosis observer for a class of uncertain discrete-time linear time-varying systems. Compared with the traditional Kalman filter residual fault diagnosis method, it has good fastness and accuracy. Then, for the fault estimation gain in the traditional fault estimator, it is difficult to follow the time-varying of the system state. Using the recursive least squares and Kalman filter combined to estimate the system fault and the system state identification, so that the fault estimation gain can follow the system state change in real time. Improve the accuracy of fault estimation. The simulation results verify the feasibility and effectiveness of the proposed method.","PeriodicalId":223618,"journal":{"name":"2018 International Conference on Control, Automation and Information Sciences (ICCAIS)","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123254876","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 : 2018-10-01DOI: 10.1109/iccais.2018.8570523
Advanced Biomedical Applications Using Real-time.
使用实时的先进生物医学应用。
{"title":"The 2018 International Conference on Control, Automation and Information Science","authors":"","doi":"10.1109/iccais.2018.8570523","DOIUrl":"https://doi.org/10.1109/iccais.2018.8570523","url":null,"abstract":"Advanced Biomedical Applications Using Real-time.","PeriodicalId":223618,"journal":{"name":"2018 International Conference on Control, Automation and Information Sciences (ICCAIS)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125282089","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 : 2018-10-01DOI: 10.1109/ICCAIS.2018.8570532
Chenyang Zheng, T. Usagawa
This study proposes a rapid eye tracking method, to respond to a situation that require a high processing speed but less accuracy. Unlike other studies, this study uses a webcam with a low resolution of 640 × 480, which decreased the cost of devices considerably. We also developed the corresponding algorithm to suit the low-quality image. We use an efficient algorithm to detect the pupils which is based on color intensity change to decrease the calculation load. The processing speed exceeds the requirement of eye tracking for saccade eyeball movement. The result of experiment shows that the proposed method is a fast and low-cost method for eye tracking.
{"title":"A Rapid Webcam-Based Eye Tracking Method for Human Computer Interaction","authors":"Chenyang Zheng, T. Usagawa","doi":"10.1109/ICCAIS.2018.8570532","DOIUrl":"https://doi.org/10.1109/ICCAIS.2018.8570532","url":null,"abstract":"This study proposes a rapid eye tracking method, to respond to a situation that require a high processing speed but less accuracy. Unlike other studies, this study uses a webcam with a low resolution of 640 × 480, which decreased the cost of devices considerably. We also developed the corresponding algorithm to suit the low-quality image. We use an efficient algorithm to detect the pupils which is based on color intensity change to decrease the calculation load. The processing speed exceeds the requirement of eye tracking for saccade eyeball movement. The result of experiment shows that the proposed method is a fast and low-cost method for eye tracking.","PeriodicalId":223618,"journal":{"name":"2018 International Conference on Control, Automation and Information Sciences (ICCAIS)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129152284","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 : 2018-10-01DOI: 10.1109/ICCAIS.2018.8570332
An‐Min Zou
This paper considers the problem of fixed-time output feedback control for a class of second-order multiple-input multiple-output (MIMO) nonlinear systems. With the help of the homogeneity property, a global observer is first proposed to obtain an accurate estimate of unmeasurable system states within fixed time. Then, with application of the observer derived here, a fixed-time output feedback controller is designed for tracking control of second-order MIMO nonlinear systems. Rigorous analysis is provided to show that the proposed control law can guarantee the system state tracking a time-varying reference within fixed time without using full state measurements. Finally, numerical simulations are presented to demonstrate the effectiveness of the proposed method.
{"title":"Fixed-Time Output Feedback Control for a Class of Second-Order MIMO Nonlinear Systems","authors":"An‐Min Zou","doi":"10.1109/ICCAIS.2018.8570332","DOIUrl":"https://doi.org/10.1109/ICCAIS.2018.8570332","url":null,"abstract":"This paper considers the problem of fixed-time output feedback control for a class of second-order multiple-input multiple-output (MIMO) nonlinear systems. With the help of the homogeneity property, a global observer is first proposed to obtain an accurate estimate of unmeasurable system states within fixed time. Then, with application of the observer derived here, a fixed-time output feedback controller is designed for tracking control of second-order MIMO nonlinear systems. Rigorous analysis is provided to show that the proposed control law can guarantee the system state tracking a time-varying reference within fixed time without using full state measurements. Finally, numerical simulations are presented to demonstrate the effectiveness of the proposed method.","PeriodicalId":223618,"journal":{"name":"2018 International Conference on Control, Automation and Information Sciences (ICCAIS)","volume":"138 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124634125","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 : 2018-10-01DOI: 10.1109/ICCAIS.2018.8570546
Tran Thien Dat Nguyen, D. Kim
In this paper, we propose an algorithm for tracking cells that also provides lineage information. Our approach incorporates cell spawning into the random finite set dynamic model of the cell population, which allows the Bayes multi-object filter to capture information on the cells ancestries. A generalized Labeled Multi-Bernoulli (GLMB) filter (with cell spawning model) is applied to track the cells using detections extracted from time lapse video data. Numerical results on a set of stems cells demonstrate the capability of the proposed solution to track the time-varying number of cells as well as their ancestries.
{"title":"On-line Tracking of Cells and Their Lineage from Time Lapse Video Data","authors":"Tran Thien Dat Nguyen, D. Kim","doi":"10.1109/ICCAIS.2018.8570546","DOIUrl":"https://doi.org/10.1109/ICCAIS.2018.8570546","url":null,"abstract":"In this paper, we propose an algorithm for tracking cells that also provides lineage information. Our approach incorporates cell spawning into the random finite set dynamic model of the cell population, which allows the Bayes multi-object filter to capture information on the cells ancestries. A generalized Labeled Multi-Bernoulli (GLMB) filter (with cell spawning model) is applied to track the cells using detections extracted from time lapse video data. Numerical results on a set of stems cells demonstrate the capability of the proposed solution to track the time-varying number of cells as well as their ancestries.","PeriodicalId":223618,"journal":{"name":"2018 International Conference on Control, Automation and Information Sciences (ICCAIS)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123891336","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 : 2018-10-01DOI: 10.1109/ICCAIS.2018.8570670
Huilin Wang, Chunxiao Liu, Yanfeng Wang, Dawei Sun
In view of the negative influence of selfish nodes in Mobile Crowd Sensing, this paper proposes an incentive mechanism based on Reputation and Trust (RTM). Firstly, this paper analyzes the reputation incentive mechanism and trust incentive mechanism. Secondly, this paper constructs an incentive model, which is divided into user selection module and reward implementation module, and defines the service quality factor, link reliability factor and time heat factor as the pricing factors to calculate comprehensive pricing to reward service providers. Finally, the experimental results show that with successful package delivery rate, average delay and energy consumption as evaluation parameters, in terms of motivating nodes to participate in network cooperation and suppressing the selfish behavior of selfish nodes, it is proved that RTM has better effect and feasibility than reputation incentive mechanism and trust incentive mechanism.
{"title":"A Novel Incentive Mechanism Based on Reputation and Trust for Mobile Crowd Sensing Network","authors":"Huilin Wang, Chunxiao Liu, Yanfeng Wang, Dawei Sun","doi":"10.1109/ICCAIS.2018.8570670","DOIUrl":"https://doi.org/10.1109/ICCAIS.2018.8570670","url":null,"abstract":"In view of the negative influence of selfish nodes in Mobile Crowd Sensing, this paper proposes an incentive mechanism based on Reputation and Trust (RTM). Firstly, this paper analyzes the reputation incentive mechanism and trust incentive mechanism. Secondly, this paper constructs an incentive model, which is divided into user selection module and reward implementation module, and defines the service quality factor, link reliability factor and time heat factor as the pricing factors to calculate comprehensive pricing to reward service providers. Finally, the experimental results show that with successful package delivery rate, average delay and energy consumption as evaluation parameters, in terms of motivating nodes to participate in network cooperation and suppressing the selfish behavior of selfish nodes, it is proved that RTM has better effect and feasibility than reputation incentive mechanism and trust incentive mechanism.","PeriodicalId":223618,"journal":{"name":"2018 International Conference on Control, Automation and Information Sciences (ICCAIS)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124020164","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 : 2018-10-01DOI: 10.1109/ICCAIS.2018.8570625
Wei Yu, C. Wen
Permanent magnet synchronous motor is a kind of typical nonlinear complex system. With its excellent performance such as high torque density, high efficiency and high reliability, it becomes the mainstream motor in the fields of active aircraft, electric vehicles and industrial servo drives. However, the existing fault diagnosis based on integer order model does not consider the fractional-order characteristics contained in the electromagnetic coupling and friction in the motor system, then it is difficult to effectively diagnose minor faults of the current with the residual error signal. In this paper, based on the traditional method, the state space representation based on fractional order model and the fault detection method of Kalman filter algorithm are introduced, and the secondary detection is adopted to calculate the relative change rate of typical fault feature quantity, and the experiment is verified.
{"title":"Minor Fault Detection for Permanent Magnet Synchronous Motor Based on Fractional Order Model and Relative Rate of Change","authors":"Wei Yu, C. Wen","doi":"10.1109/ICCAIS.2018.8570625","DOIUrl":"https://doi.org/10.1109/ICCAIS.2018.8570625","url":null,"abstract":"Permanent magnet synchronous motor is a kind of typical nonlinear complex system. With its excellent performance such as high torque density, high efficiency and high reliability, it becomes the mainstream motor in the fields of active aircraft, electric vehicles and industrial servo drives. However, the existing fault diagnosis based on integer order model does not consider the fractional-order characteristics contained in the electromagnetic coupling and friction in the motor system, then it is difficult to effectively diagnose minor faults of the current with the residual error signal. In this paper, based on the traditional method, the state space representation based on fractional order model and the fault detection method of Kalman filter algorithm are introduced, and the secondary detection is adopted to calculate the relative change rate of typical fault feature quantity, and the experiment is verified.","PeriodicalId":223618,"journal":{"name":"2018 International Conference on Control, Automation and Information Sciences (ICCAIS)","volume":"113 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124525731","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：