Heartbeat segmentation in Seism cardiogram (SCG) provides the fundamentals for automated SCG analysis. Traditionally, waveform detection of each cardiac cycle in SCG was depended on the reference QRS complex in Electrocardiogram (ECG). The dominant wave in SCG, namely W complex, could be used as the feature wave for heartbeat segmentation. In this paper, matched-filtering approach was developed and evaluated for W complex detection in SCG without noise suppression stage. Firstly, the template of W complex was selected automatically by the triangle character in SCG and then was used as the coefficients of the finite impulse response (FIR), which greatly enhanced W complexes and attenuated other regions. Subsequently, W complex was detected using the triangle structure, and cardiac cycles and triangle structures were further analyzed for the reduction of false-positive and false-negative detections. The performance of the proposed algorithm was tested on 20 records (each record lasted 50 min) of the combined measurement of ECG, Breathing and Seism cardiograms Database (CEBSDB). The detection rate of 98.74%, the sensitivity of 99.33% and the positive prediction of 99.41 % was achieved on the CEBSDB, respectively. In conclusion, matched-filtering is reliable for the heartbeat segmentation of Seism cardiogram.
地震心电图(SCG)中的心跳分割为自动分析SCG提供了基础。传统上，SCG各心动周期的波形检测依赖于心电图(ECG)的参考QRS复合体。SCG中的优势波即W复合体可以作为心跳分割的特征波。本文提出并评价了匹配滤波方法在无噪声抑制阶段的SCG W复合体检测中的应用。首先，利用SCG中的三角形特征自动选择W配合物模板，然后将其作为有限脉冲响应(FIR)的系数，极大地增强了W配合物，减弱了其他区域。随后，利用三角结构检测W复合物，并进一步分析心周期和三角结构，以减少假阳性和假阴性检测。在CEBSDB (ECG, Breathing and Seism cardiogram Database，简称CEBSDB)联合测量的20条记录(每条记录持续50 min)上测试了算法的性能。CEBSDB的检出率为98.74%，灵敏度为99.33%，阳性预测率为99.41%。综上所述，匹配滤波对地震心电图的心跳分割是可靠的。
{"title":"An Approach of Heartbeat Segmentation in Seismocardiogram by Matched-Filtering","authors":"Yanjun Li, Xiaoying Tang, Zhi Xu","doi":"10.1109/IHMSC.2015.157","DOIUrl":"https://doi.org/10.1109/IHMSC.2015.157","url":null,"abstract":"Heartbeat segmentation in Seism cardiogram (SCG) provides the fundamentals for automated SCG analysis. Traditionally, waveform detection of each cardiac cycle in SCG was depended on the reference QRS complex in Electrocardiogram (ECG). The dominant wave in SCG, namely W complex, could be used as the feature wave for heartbeat segmentation. In this paper, matched-filtering approach was developed and evaluated for W complex detection in SCG without noise suppression stage. Firstly, the template of W complex was selected automatically by the triangle character in SCG and then was used as the coefficients of the finite impulse response (FIR), which greatly enhanced W complexes and attenuated other regions. Subsequently, W complex was detected using the triangle structure, and cardiac cycles and triangle structures were further analyzed for the reduction of false-positive and false-negative detections. The performance of the proposed algorithm was tested on 20 records (each record lasted 50 min) of the combined measurement of ECG, Breathing and Seism cardiograms Database (CEBSDB). The detection rate of 98.74%, the sensitivity of 99.33% and the positive prediction of 99.41 % was achieved on the CEBSDB, respectively. In conclusion, matched-filtering is reliable for the heartbeat segmentation of Seism cardiogram.","PeriodicalId":6592,"journal":{"name":"2015 7th International Conference on Intelligent Human-Machine Systems and Cybernetics","volume":"49 1","pages":"47-51"},"PeriodicalIF":0.0,"publicationDate":"2015-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83606375","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 traditional vision based hand gesture recognition technology requires a lot of light environment and backgrounds. Focused on these above problems, this paper presents a new hand gesture recognition model, in which, the unsupervised sparse auto-encoder neural network model is applied to train the image patches, in order to extract the edge feature that is the weight, and the pooled features are used as the input of the classifier for classification. The fine turning for the parameter of the entire net is to improve the classification accuracy finally.
{"title":"A Hand Gesture Recognition Model Based on Semi-supervised Learning","authors":"Meiping Tao, Li Ma","doi":"10.1109/IHMSC.2015.230","DOIUrl":"https://doi.org/10.1109/IHMSC.2015.230","url":null,"abstract":"The traditional vision based hand gesture recognition technology requires a lot of light environment and backgrounds. Focused on these above problems, this paper presents a new hand gesture recognition model, in which, the unsupervised sparse auto-encoder neural network model is applied to train the image patches, in order to extract the edge feature that is the weight, and the pooled features are used as the input of the classifier for classification. The fine turning for the parameter of the entire net is to improve the classification accuracy finally.","PeriodicalId":6592,"journal":{"name":"2015 7th International Conference on Intelligent Human-Machine Systems and Cybernetics","volume":"41 1","pages":"43-46"},"PeriodicalIF":0.0,"publicationDate":"2015-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88492987","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}
According to the need from the security and monitoring management, the paper proposes a new type of access control and positioning security management system based on RFID techniques. Combining with non-barrier access control subsystem and regional positioning subsystem, the system uses a small amount of passive and active RFID devices and monitoring management subsystem to make up the complex area of internal security management loopholes. In addition, an improved RF packet loss rate localization algorithm is presented to trace the exact location of the crews. The application result shows that the system can realize personnel identify, personnel fixed position and personnel track record etc, the system runs stability with a low fail rate and a quickly warned response.
{"title":"An Access Control and Positioning Security Management System Based on RFID","authors":"Anchan Mai, Zongtian Wei, Mengji Gao","doi":"10.1109/IHMSC.2015.227","DOIUrl":"https://doi.org/10.1109/IHMSC.2015.227","url":null,"abstract":"According to the need from the security and monitoring management, the paper proposes a new type of access control and positioning security management system based on RFID techniques. Combining with non-barrier access control subsystem and regional positioning subsystem, the system uses a small amount of passive and active RFID devices and monitoring management subsystem to make up the complex area of internal security management loopholes. In addition, an improved RF packet loss rate localization algorithm is presented to trace the exact location of the crews. The application result shows that the system can realize personnel identify, personnel fixed position and personnel track record etc, the system runs stability with a low fail rate and a quickly warned response.","PeriodicalId":6592,"journal":{"name":"2015 7th International Conference on Intelligent Human-Machine Systems and Cybernetics","volume":"39 1","pages":"537-540"},"PeriodicalIF":0.0,"publicationDate":"2015-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84599095","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}
UUVs adopt different fins/rudders layout and propellers arrangement, for achieving underwater hovering, in situ rotation, lateral translation, vertical translation, for having a good adaptation of ocean current disturbances and wave disturbances, for improving the capabilities of sailing stability, speed performance, maneuverability and seaworthiness in low speed cruising. There is not a uniform standard over the fins/rudders layout and propulsion types of UUV. This paper concludes the partition in way of fins/rudders layout + main thruster + assistant thruster. And various characteristics of fins/rudders layout and propulsion types are summarized.
{"title":"The Partition to Fins/Rudders Layout and Propulsion Types for UUV","authors":"Yutian Li","doi":"10.1109/IHMSC.2015.44","DOIUrl":"https://doi.org/10.1109/IHMSC.2015.44","url":null,"abstract":"UUVs adopt different fins/rudders layout and propellers arrangement, for achieving underwater hovering, in situ rotation, lateral translation, vertical translation, for having a good adaptation of ocean current disturbances and wave disturbances, for improving the capabilities of sailing stability, speed performance, maneuverability and seaworthiness in low speed cruising. There is not a uniform standard over the fins/rudders layout and propulsion types of UUV. This paper concludes the partition in way of fins/rudders layout + main thruster + assistant thruster. And various characteristics of fins/rudders layout and propulsion types are summarized.","PeriodicalId":6592,"journal":{"name":"2015 7th International Conference on Intelligent Human-Machine Systems and Cybernetics","volume":"162 1","pages":"366-369"},"PeriodicalIF":0.0,"publicationDate":"2015-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73802750","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}
Earth observation satellites provide important information security for modern military activities. In the future war, who achieves the initiative of space battlefield will directly affects the process and outcome of the war. By analyzing the development and application of typical plans and tests of the Operationally Responsive Space (ORS) such as the TacSat plan, System F6 Program and "100-Satellite Constellation", and its content, key technology and expected target of ORS can be organized and extracted. Through comparing the experimental results for several generations of test products, it demonstrates that the idea of ORS will influence the development of the theory and practice on space operations and joint operations in the future, which will play a decisive role in the future war and put forward new ideas for the development of satellite system.
{"title":"Review on the Development and Technology of Operationally Responsive Space","authors":"Yongming He, Lining Xing, Yingwu Chen","doi":"10.1109/IHMSC.2015.262","DOIUrl":"https://doi.org/10.1109/IHMSC.2015.262","url":null,"abstract":"Earth observation satellites provide important information security for modern military activities. In the future war, who achieves the initiative of space battlefield will directly affects the process and outcome of the war. By analyzing the development and application of typical plans and tests of the Operationally Responsive Space (ORS) such as the TacSat plan, System F6 Program and \"100-Satellite Constellation\", and its content, key technology and expected target of ORS can be organized and extracted. Through comparing the experimental results for several generations of test products, it demonstrates that the idea of ORS will influence the development of the theory and practice on space operations and joint operations in the future, which will play a decisive role in the future war and put forward new ideas for the development of satellite system.","PeriodicalId":6592,"journal":{"name":"2015 7th International Conference on Intelligent Human-Machine Systems and Cybernetics","volume":"6 1 1","pages":"548-553"},"PeriodicalIF":0.0,"publicationDate":"2015-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72778986","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}
In order to reduce the standard particle swarm algorithm trapped in local optimal value, guarantee the convergence speed of the particle swarm optimization algorithm and improve the quality of the solution and robustness in the vehicle scheduling problem, based on the standard particle swarm optimization (PSO) algorithm, this paper proposes a new improved standard particle swarm algorithm namely global-local optimal information ratio PSO (GLIR-PSO), and the algorithm using the particle's global-local optimal information ratio weighs the particles of particle's global optimal and local optimal information and it is applied to the vehicle scheduling problem, the model of particle swarm optimization for vehicle scheduling problem is established, and compared with standard particle swarm optimization algorithm and the new particle swarm optimization algorithm with global-local best minimum. The results of simulation demonstrate that the algorithm shows a better performance in convergence speed, so it is an effective method for solving the vehicle scheduling problem.
{"title":"Research on Global-Local Optimal Information Ratio Particle Swarm Optimization for Vehicle Scheduling Problem","authors":"Zhuangkuo Li, Tingting Zhu","doi":"10.1109/IHMSC.2015.59","DOIUrl":"https://doi.org/10.1109/IHMSC.2015.59","url":null,"abstract":"In order to reduce the standard particle swarm algorithm trapped in local optimal value, guarantee the convergence speed of the particle swarm optimization algorithm and improve the quality of the solution and robustness in the vehicle scheduling problem, based on the standard particle swarm optimization (PSO) algorithm, this paper proposes a new improved standard particle swarm algorithm namely global-local optimal information ratio PSO (GLIR-PSO), and the algorithm using the particle's global-local optimal information ratio weighs the particles of particle's global optimal and local optimal information and it is applied to the vehicle scheduling problem, the model of particle swarm optimization for vehicle scheduling problem is established, and compared with standard particle swarm optimization algorithm and the new particle swarm optimization algorithm with global-local best minimum. The results of simulation demonstrate that the algorithm shows a better performance in convergence speed, so it is an effective method for solving the vehicle scheduling problem.","PeriodicalId":6592,"journal":{"name":"2015 7th International Conference on Intelligent Human-Machine Systems and Cybernetics","volume":"118 1","pages":"92-96"},"PeriodicalIF":0.0,"publicationDate":"2015-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75952587","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}
Yujie Wang, Xiaoping Hu, Jun-xiang Lian, Lilian Zhang, Xianglong Kong
Place recognition plays an important role in long term navigation in challenging environment and Seq SLAM has achieved quite remarkable results. In this paper, we mainly adopt three strategies to improve the original Seq SLAM algorithm: integrating Seq SLAM with odometry, optimizing sequence searching strategy and multi-scale sequence matching. The improved algorithm is evaluated using the KITTI dataset. The template library is created online using navigation information from the sliding-window visual-inertial odometer. When a place is recognized, the corresponding information is used as observation of the filter. The result shows the superiority of the proposed method in real-time place recognition. The optimized sequence searching strategy performs much better in minor deviations. Meanwhile, the advantages of longer sequence match (higher recall rate) and short sequence match (precise location) are combined together. At last, the navigation errors are greatly reduced by close-loop detection. The overall position error of odometer with Seq SLAM is 20.3m (0.55% of the trajectory), which is much smaller than the navigation errors of the single odometer (32.0m, 0.86%).
{"title":"Improved Seq SLAM for Real-Time Place Recognition and Navigation Error Correction","authors":"Yujie Wang, Xiaoping Hu, Jun-xiang Lian, Lilian Zhang, Xianglong Kong","doi":"10.1109/IHMSC.2015.23","DOIUrl":"https://doi.org/10.1109/IHMSC.2015.23","url":null,"abstract":"Place recognition plays an important role in long term navigation in challenging environment and Seq SLAM has achieved quite remarkable results. In this paper, we mainly adopt three strategies to improve the original Seq SLAM algorithm: integrating Seq SLAM with odometry, optimizing sequence searching strategy and multi-scale sequence matching. The improved algorithm is evaluated using the KITTI dataset. The template library is created online using navigation information from the sliding-window visual-inertial odometer. When a place is recognized, the corresponding information is used as observation of the filter. The result shows the superiority of the proposed method in real-time place recognition. The optimized sequence searching strategy performs much better in minor deviations. Meanwhile, the advantages of longer sequence match (higher recall rate) and short sequence match (precise location) are combined together. At last, the navigation errors are greatly reduced by close-loop detection. The overall position error of odometer with Seq SLAM is 20.3m (0.55% of the trajectory), which is much smaller than the navigation errors of the single odometer (32.0m, 0.86%).","PeriodicalId":6592,"journal":{"name":"2015 7th International Conference on Intelligent Human-Machine Systems and Cybernetics","volume":"66 1","pages":"260-264"},"PeriodicalIF":0.0,"publicationDate":"2015-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81574247","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}
Assimilation, Accommodation and Equilibration are three important concepts in the description of the developmental process of human cognition in schema theory. Based on comparing some relative ideas in adaptive resonance theory and schema theory, a self-adjusting method to the vigilance value of ART2 network is proposed. It constructs the basis of supervised ART2 network, which make the computer simulation of the developmental process of human cognition feasible. In the recognition trial of circle, triangle and quadrangle, the stable schemata are formed in the Long-Term Memory of ART2 through the process of assimilation, accommodation and equilibration. The realization of these basic processes of human cognition by artificial neural network will benefit the development of artificial intelligent agent.
{"title":"Simulation of the Concepts of Assimilation, Accommodation and Equilibration in Schema Theory Based on ART2 Network","authors":"Chen Zhong, Xu Songxiang, Li Lin","doi":"10.1109/IHMSC.2015.274","DOIUrl":"https://doi.org/10.1109/IHMSC.2015.274","url":null,"abstract":"Assimilation, Accommodation and Equilibration are three important concepts in the description of the developmental process of human cognition in schema theory. Based on comparing some relative ideas in adaptive resonance theory and schema theory, a self-adjusting method to the vigilance value of ART2 network is proposed. It constructs the basis of supervised ART2 network, which make the computer simulation of the developmental process of human cognition feasible. In the recognition trial of circle, triangle and quadrangle, the stable schemata are formed in the Long-Term Memory of ART2 through the process of assimilation, accommodation and equilibration. The realization of these basic processes of human cognition by artificial neural network will benefit the development of artificial intelligent agent.","PeriodicalId":6592,"journal":{"name":"2015 7th International Conference on Intelligent Human-Machine Systems and Cybernetics","volume":"50 1","pages":"16-20"},"PeriodicalIF":0.0,"publicationDate":"2015-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80888406","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}
In this paper, a new predictive control scheme named model-free adaptive PI predictive control (MFAPIPC) is proposed for a class of an adaptive PI control algorithm and the model-free adaptive control (MFAC). In this work, the model-free is designed by pseudo-partial-derivatives (PPD) which is predicted using the multi-level recursive prediction algorithm, and PI control algorithm is extended by using general predictive control. The results of the simulation show that MFAPIPC is an excellent control scheme.
{"title":"Model-Free Adaptive PI Predictive Control for a Class of Nonlinear SISO Systems","authors":"Xiaoke Li, Hongxin Li, Yao-Bing Wei","doi":"10.1109/IHMSC.2015.145","DOIUrl":"https://doi.org/10.1109/IHMSC.2015.145","url":null,"abstract":"In this paper, a new predictive control scheme named model-free adaptive PI predictive control (MFAPIPC) is proposed for a class of an adaptive PI control algorithm and the model-free adaptive control (MFAC). In this work, the model-free is designed by pseudo-partial-derivatives (PPD) which is predicted using the multi-level recursive prediction algorithm, and PI control algorithm is extended by using general predictive control. The results of the simulation show that MFAPIPC is an excellent control scheme.","PeriodicalId":6592,"journal":{"name":"2015 7th International Conference on Intelligent Human-Machine Systems and Cybernetics","volume":"22 1","pages":"101-104"},"PeriodicalIF":0.0,"publicationDate":"2015-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78673007","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}
Path optimization, which can improve the travel efficiency of vehicle, has significances to time and cost saving. Path optimization mentioned in this article aims for optimizing total length and converts it into classical TSP to solve optimization problems and establish path optimization model. Based on this model, the improved adaptive genetic algorithm is put forward. This algorithm improves the population fitness sorting, adaptive crossover probability and mutation probability, etc. The comparison of simulation experiments shows that the improved adaptive genetic algorithm (AGA) has better global optimization ability and faster convergence speed than Simple Genetic Algorithm (SGA), which is the effective method to improve path optimization.
{"title":"Research on Path Optimization Based on Improved Adaptive Genetic Algorithm","authors":"Ziqian Xiao, Jingyou Chen","doi":"10.1109/IHMSC.2015.188","DOIUrl":"https://doi.org/10.1109/IHMSC.2015.188","url":null,"abstract":"Path optimization, which can improve the travel efficiency of vehicle, has significances to time and cost saving. Path optimization mentioned in this article aims for optimizing total length and converts it into classical TSP to solve optimization problems and establish path optimization model. Based on this model, the improved adaptive genetic algorithm is put forward. This algorithm improves the population fitness sorting, adaptive crossover probability and mutation probability, etc. The comparison of simulation experiments shows that the improved adaptive genetic algorithm (AGA) has better global optimization ability and faster convergence speed than Simple Genetic Algorithm (SGA), which is the effective method to improve path optimization.","PeriodicalId":6592,"journal":{"name":"2015 7th International Conference on Intelligent Human-Machine Systems and Cybernetics","volume":"33 1","pages":"207-209"},"PeriodicalIF":0.0,"publicationDate":"2015-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86242056","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：