Pub Date : 2015-10-01DOI: 10.1109/ICINFA.2015.7279466
Qingyang Xu, Chengjin Zhang, Li Zhang
Convolutional Neural Network (CNN) is a kind of deep artificial neural network. CNN has kinds of merits, such as multidimensional data input, and fewer parameters. However, the network always has the problem of overfitting due to lots of connection in the full connection layer. In order to overcome the overfitting problem, the denoising method is used to corrupt input data and hidden unit output which will enforce the network learning a better feature representations of the sample data. In the simulation, some situations are considered, such as input data corruption and hidden unit output corruption, and a comparison is exhibited.
{"title":"Denoising Convolutional Neural Network","authors":"Qingyang Xu, Chengjin Zhang, Li Zhang","doi":"10.1109/ICINFA.2015.7279466","DOIUrl":"https://doi.org/10.1109/ICINFA.2015.7279466","url":null,"abstract":"Convolutional Neural Network (CNN) is a kind of deep artificial neural network. CNN has kinds of merits, such as multidimensional data input, and fewer parameters. However, the network always has the problem of overfitting due to lots of connection in the full connection layer. In order to overcome the overfitting problem, the denoising method is used to corrupt input data and hidden unit output which will enforce the network learning a better feature representations of the sample data. In the simulation, some situations are considered, such as input data corruption and hidden unit output corruption, and a comparison is exhibited.","PeriodicalId":186975,"journal":{"name":"2015 IEEE International Conference on Information and Automation","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125911056","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 : 2015-10-01DOI: 10.1109/ICINFA.2015.7279479
Jianxin Huang, Ji Sun
Optimal control problems for nonlinear neutral systems are considered for nonlinear state-delay system. Using measures theory, the optimal control problem is modified into one consisting of the minimization of a linear form over a set of positive measures satisfying linear constraints; the minimization in the new problem can be approximated by a finite dimensional linear programming problem. The solution of this linear programming can be used to construct an optimal control. A numerical example is given to illustrate the procedure.
{"title":"The piecewise-constant optimal control of nonlinear neutral system with control constraints","authors":"Jianxin Huang, Ji Sun","doi":"10.1109/ICINFA.2015.7279479","DOIUrl":"https://doi.org/10.1109/ICINFA.2015.7279479","url":null,"abstract":"Optimal control problems for nonlinear neutral systems are considered for nonlinear state-delay system. Using measures theory, the optimal control problem is modified into one consisting of the minimization of a linear form over a set of positive measures satisfying linear constraints; the minimization in the new problem can be approximated by a finite dimensional linear programming problem. The solution of this linear programming can be used to construct an optimal control. A numerical example is given to illustrate the procedure.","PeriodicalId":186975,"journal":{"name":"2015 IEEE International Conference on Information and Automation","volume":"81 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116540423","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 : 2015-10-01DOI: 10.1109/ICINFA.2015.7279354
Chen Wei, Pu Yue
Power curve provided by wind generator manufacturer, which characterizes the steady-state operation condition of wind generating set, has deviation when it is used to analyze the real operating condition of wind generation set. This paper conducts the calibration of power curve of wind-driven generator and builds the forecasting model of wind power based on least squares support vector machine (LS-SVM). Simulation results have verified the efficacy of the proposed prediction model.
{"title":"Calibration power curve of wind generator and forecasting model of wind power unit","authors":"Chen Wei, Pu Yue","doi":"10.1109/ICINFA.2015.7279354","DOIUrl":"https://doi.org/10.1109/ICINFA.2015.7279354","url":null,"abstract":"Power curve provided by wind generator manufacturer, which characterizes the steady-state operation condition of wind generating set, has deviation when it is used to analyze the real operating condition of wind generation set. This paper conducts the calibration of power curve of wind-driven generator and builds the forecasting model of wind power based on least squares support vector machine (LS-SVM). Simulation results have verified the efficacy of the proposed prediction model.","PeriodicalId":186975,"journal":{"name":"2015 IEEE International Conference on Information and Automation","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116726041","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 : 2015-10-01DOI: 10.1109/ICINFA.2015.7279369
Yu-Kumg Chen, Kuan-Jung Chen
Recognition of driving-view image is the most important future issue in a smart tachograph. The intersection imaging recognition is one of the important issues in driving-view image recognition. In addition to using in the GPS satellite positioning correction in the metropolitan area, it can also be applied to the traffic lights imaging recognition in an intersection. With some samples analyzing, the color ranges of pavement in the YCbCr color space is developed in this paper. Therefore, pavement and markings on the road can be separated. By using this color separation and calculating the ratio of markings and pavement, it can be applied to intersection imaging recognition of driving-view image. Experiments are carried out for some VEDR's videos to demonstration the computational advantage of the proposed method.
{"title":"Pavement detection in YCbCr color space and its application","authors":"Yu-Kumg Chen, Kuan-Jung Chen","doi":"10.1109/ICINFA.2015.7279369","DOIUrl":"https://doi.org/10.1109/ICINFA.2015.7279369","url":null,"abstract":"Recognition of driving-view image is the most important future issue in a smart tachograph. The intersection imaging recognition is one of the important issues in driving-view image recognition. In addition to using in the GPS satellite positioning correction in the metropolitan area, it can also be applied to the traffic lights imaging recognition in an intersection. With some samples analyzing, the color ranges of pavement in the YCbCr color space is developed in this paper. Therefore, pavement and markings on the road can be separated. By using this color separation and calculating the ratio of markings and pavement, it can be applied to intersection imaging recognition of driving-view image. Experiments are carried out for some VEDR's videos to demonstration the computational advantage of the proposed method.","PeriodicalId":186975,"journal":{"name":"2015 IEEE International Conference on Information and Automation","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122445864","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 : 2015-10-01DOI: 10.1109/ICINFA.2015.7279332
H. Zhang, Lei Zhang, Zheng Fang, H. Trannois, M. Huchard, R. Zapata
Cloud robotic system is a mono- or multi- robot system that profits one or more services of Cloud Computing. In a few short years, Cloud robotics as a newly emerged field has already received much research and industrial attention. The use of the Cloud for robotics and automation brings some potential benefits largely ameliorating the performance of robotic systems. However, there are also some challenges. First of all, from the viewpoint of architecture, how to model and describe the architectures of Cloud robotic systems? How to deploy these architectures in Clouds? Merely a language could explicitly describe or model the architecture of Cloud robotic systems. In this paper, we present an architecture approach to support design and implementation of Cloud robotic system.
{"title":"CRALA: Towards a domain specific language of architecture-centric Cloud robotics","authors":"H. Zhang, Lei Zhang, Zheng Fang, H. Trannois, M. Huchard, R. Zapata","doi":"10.1109/ICINFA.2015.7279332","DOIUrl":"https://doi.org/10.1109/ICINFA.2015.7279332","url":null,"abstract":"Cloud robotic system is a mono- or multi- robot system that profits one or more services of Cloud Computing. In a few short years, Cloud robotics as a newly emerged field has already received much research and industrial attention. The use of the Cloud for robotics and automation brings some potential benefits largely ameliorating the performance of robotic systems. However, there are also some challenges. First of all, from the viewpoint of architecture, how to model and describe the architectures of Cloud robotic systems? How to deploy these architectures in Clouds? Merely a language could explicitly describe or model the architecture of Cloud robotic systems. In this paper, we present an architecture approach to support design and implementation of Cloud robotic system.","PeriodicalId":186975,"journal":{"name":"2015 IEEE International Conference on Information and Automation","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122470134","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 : 2015-10-01DOI: 10.1109/ICINFA.2015.7279605
Zhiqiang Jiao, Weihua Li, Qian Zhang, Peng Wang
This paper considers the tracking problem for the maneuvering target with the motion subject to some known physical constrains. For the target tracking problem, the moving horizon estimation (MHE) approach is firstly introduced, by which we can treat the physical constraints on the target motion as some useful knowledge. Under the MHE framework, we then adopt the multiple model (MM) method to describe different behaviours for the maneuvering target. To incorporate the MM method into MHE framework, we derive an estimation evolution formula and modify the weighting matrix update formula with considering the multiple model, then the physical constraint can be directly handled based on the evolved estimation. Based on the above procedures, the MM-MHE optimization and algorithm are finally presented for the tracking problem. Comparing with the adaptive Kalman filter (AKF) and the interacting multiple model (IMM) approaches, a better tracking performance can be achieved by applying our algorithm (especially for the physically constrained motion condition), which is demonstrated by a simple simulation example.
{"title":"Tracking for the maneuvering target based on multiple model and moving horizon estimation","authors":"Zhiqiang Jiao, Weihua Li, Qian Zhang, Peng Wang","doi":"10.1109/ICINFA.2015.7279605","DOIUrl":"https://doi.org/10.1109/ICINFA.2015.7279605","url":null,"abstract":"This paper considers the tracking problem for the maneuvering target with the motion subject to some known physical constrains. For the target tracking problem, the moving horizon estimation (MHE) approach is firstly introduced, by which we can treat the physical constraints on the target motion as some useful knowledge. Under the MHE framework, we then adopt the multiple model (MM) method to describe different behaviours for the maneuvering target. To incorporate the MM method into MHE framework, we derive an estimation evolution formula and modify the weighting matrix update formula with considering the multiple model, then the physical constraint can be directly handled based on the evolved estimation. Based on the above procedures, the MM-MHE optimization and algorithm are finally presented for the tracking problem. Comparing with the adaptive Kalman filter (AKF) and the interacting multiple model (IMM) approaches, a better tracking performance can be achieved by applying our algorithm (especially for the physically constrained motion condition), which is demonstrated by a simple simulation example.","PeriodicalId":186975,"journal":{"name":"2015 IEEE International Conference on Information and Automation","volume":"95 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122488950","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 : 2015-10-01DOI: 10.1109/ICINFA.2015.7279394
S. Sun, Changwei Zhao, Zhiyong Zhang
Considering the complexity of trust among users, we presented a new trust factor model. In this model, trust relationships among users are represented as an adjacent matrix, and trust matrix can be decomposed into two low rank dimensionality matrixes, which are trust factor matrix of users and trusted factor matrix by users, through matrix factorization in this model. User-to-user trust values are computed as inner products of corresponding vectors., Trust users can be identified according sorts of trust values. The model can give consideration to the global structure and finer-grained characteristics of trust. The experimental results show that this model has higher accuracy of trust identification and efficiency in prediction stage. The Trust factors model not only reflect users' characteristics of trust and trusted, but also can be used to explain trust propagation in trust chain.
{"title":"A matrix factorization based trust factors model","authors":"S. Sun, Changwei Zhao, Zhiyong Zhang","doi":"10.1109/ICINFA.2015.7279394","DOIUrl":"https://doi.org/10.1109/ICINFA.2015.7279394","url":null,"abstract":"Considering the complexity of trust among users, we presented a new trust factor model. In this model, trust relationships among users are represented as an adjacent matrix, and trust matrix can be decomposed into two low rank dimensionality matrixes, which are trust factor matrix of users and trusted factor matrix by users, through matrix factorization in this model. User-to-user trust values are computed as inner products of corresponding vectors., Trust users can be identified according sorts of trust values. The model can give consideration to the global structure and finer-grained characteristics of trust. The experimental results show that this model has higher accuracy of trust identification and efficiency in prediction stage. The Trust factors model not only reflect users' characteristics of trust and trusted, but also can be used to explain trust propagation in trust chain.","PeriodicalId":186975,"journal":{"name":"2015 IEEE International Conference on Information and Automation","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131602788","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 underwater video coding has relative high demand of Underwater Acoustic Channel and the underwater video scenes are complex and instable. To deal with these problems, this paper presents a reconstruction algorithm based on three dimension (3D) tree-structure Bayesian compressive sensing for underwater videos. On the encoder side, analog color coded aperture compressive temporal imaging system (CACTI) encodes the video signal. On the decoder end, based on the model of Bayesian compressive sensing, by exploiting the 3D tree structure of the wavelet and Discrete Cosine Transformation(DCT) coefficients, a Bayesian compressive sensing inverse transform algorithm is derived to reconstruct color video frames from single-channel compression measurements. The experimental results show that the algorithm is able to reconstruct complex video scenes more accurately.
{"title":"A reconstruction algorithm based on 3D tree-structure Bayesian compressive sensing for underwater videos","authors":"Xianjian Xiao, Yanbin Zhuang, Zunzhi Wang, Xuewu Zhang","doi":"10.1109/ICINFA.2015.7279411","DOIUrl":"https://doi.org/10.1109/ICINFA.2015.7279411","url":null,"abstract":"The traditional underwater video coding has relative high demand of Underwater Acoustic Channel and the underwater video scenes are complex and instable. To deal with these problems, this paper presents a reconstruction algorithm based on three dimension (3D) tree-structure Bayesian compressive sensing for underwater videos. On the encoder side, analog color coded aperture compressive temporal imaging system (CACTI) encodes the video signal. On the decoder end, based on the model of Bayesian compressive sensing, by exploiting the 3D tree structure of the wavelet and Discrete Cosine Transformation(DCT) coefficients, a Bayesian compressive sensing inverse transform algorithm is derived to reconstruct color video frames from single-channel compression measurements. The experimental results show that the algorithm is able to reconstruct complex video scenes more accurately.","PeriodicalId":186975,"journal":{"name":"2015 IEEE International Conference on Information and Automation","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116499880","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 : 2015-10-01DOI: 10.1109/ICINFA.2015.7279559
Jong-doo Park, Bo-mu Cheoun, J. Jeon
The existing in-vehicle networks are not capable of accommodating increased data in vehicle and the demand of bandwidth. Next generation networks require higher bandwidth and shorter latency. Therefore, inexpensive and high bandwidth ethernet have be studied. IEEE802.1 Audio Video Bridging (AVB) is the standard used to transmit Audio and Video streaming data with guaranteed Quality of Service (QoS). AVB can reserve network resources using IEEE 802.1 Qat protocol with low latency and periodic messages using traffic shaping. In addition, it can transmit streaming data with Credit based Shaping (CBS) algorithms. In this paper, we analyzed CBS algorithms. In addition, we measured the worst case in embedded system.
{"title":"Worst-case analysis of ethernet AVB in automotive system","authors":"Jong-doo Park, Bo-mu Cheoun, J. Jeon","doi":"10.1109/ICINFA.2015.7279559","DOIUrl":"https://doi.org/10.1109/ICINFA.2015.7279559","url":null,"abstract":"The existing in-vehicle networks are not capable of accommodating increased data in vehicle and the demand of bandwidth. Next generation networks require higher bandwidth and shorter latency. Therefore, inexpensive and high bandwidth ethernet have be studied. IEEE802.1 Audio Video Bridging (AVB) is the standard used to transmit Audio and Video streaming data with guaranteed Quality of Service (QoS). AVB can reserve network resources using IEEE 802.1 Qat protocol with low latency and periodic messages using traffic shaping. In addition, it can transmit streaming data with Credit based Shaping (CBS) algorithms. In this paper, we analyzed CBS algorithms. In addition, we measured the worst case in embedded system.","PeriodicalId":186975,"journal":{"name":"2015 IEEE International Conference on Information and Automation","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127695607","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 the following paper, L1 adaptive control theory is used to design a controller for longitudinal short-period aircraft pitch. This controller accounts for the uncertainties of the aircraft model and the lack of robustness of existing methods. The aircraft handling qualities of six groups of different flight cases were used to build this model, regarding the uncertainties of the aircraft model as time-varying parameters. Our simulation results show that the controller can ensure that the system output asymptotically tracks the output of an ideal system with quantifiable transient and steady-state performance bounds.
{"title":"Longitudinal inner loop flight controller design by using L1 adaptive control theory","authors":"Ya-yun Yan, Wen-han Dong, Q. Zou, Wu-jie Xie, Hui Yin","doi":"10.1109/ICINFA.2015.7279796","DOIUrl":"https://doi.org/10.1109/ICINFA.2015.7279796","url":null,"abstract":"In the following paper, L1 adaptive control theory is used to design a controller for longitudinal short-period aircraft pitch. This controller accounts for the uncertainties of the aircraft model and the lack of robustness of existing methods. The aircraft handling qualities of six groups of different flight cases were used to build this model, regarding the uncertainties of the aircraft model as time-varying parameters. Our simulation results show that the controller can ensure that the system output asymptotically tracks the output of an ideal system with quantifiable transient and steady-state performance bounds.","PeriodicalId":186975,"journal":{"name":"2015 IEEE International Conference on Information and Automation","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132732383","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：