Pub Date : 2011-09-01DOI: 10.1109/ICAWST.2011.6163132
Gang Yang, D. Wang, Yutao Wang, Zunyi Wang
Robust tracking is a challenging problem, due to intrinsic appearance variability of objects caused by in-plane or out-plane rotation and extrinsic factors change such as illumination, occlusion, background clutter and local blur. A tracker based on a single cue may be robust to certain distractions but vulnerable to some others. Therefore, it is appealing to fuse multiple cues into one tracker. In this paper, we propose an adaptive models combination framework for visual tracking. The color cue, texture cue and global representation of object are fused into one tracker by combination of three individual models. Then a simple yet effective adaptive weights strategy is proposed for evaluating weights of different models based on their performance. Experiments are performed on some changeling video sequences, both public and our own, show that our proposed framework achieve good performance.
{"title":"Robust object tracking by adaptive models combination","authors":"Gang Yang, D. Wang, Yutao Wang, Zunyi Wang","doi":"10.1109/ICAWST.2011.6163132","DOIUrl":"https://doi.org/10.1109/ICAWST.2011.6163132","url":null,"abstract":"Robust tracking is a challenging problem, due to intrinsic appearance variability of objects caused by in-plane or out-plane rotation and extrinsic factors change such as illumination, occlusion, background clutter and local blur. A tracker based on a single cue may be robust to certain distractions but vulnerable to some others. Therefore, it is appealing to fuse multiple cues into one tracker. In this paper, we propose an adaptive models combination framework for visual tracking. The color cue, texture cue and global representation of object are fused into one tracker by combination of three individual models. Then a simple yet effective adaptive weights strategy is proposed for evaluating weights of different models based on their performance. Experiments are performed on some changeling video sequences, both public and our own, show that our proposed framework achieve good performance.","PeriodicalId":126169,"journal":{"name":"2011 3rd International Conference on Awareness Science and Technology (iCAST)","volume":"73 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121679742","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 : 2011-09-01DOI: 10.1109/ICAWST.2011.6163098
Wei Cheng, Xuemin Li, Pengcheng Du
For the characters of the City of Kunming' trunk road, this paper proposed a model of one-way green wave coordination control based on fuzzy neural network, from the optimization of the cycle, offset and split of intersections. At last the simulation shows the proposed method can reduce the queue length and vehicle delay very well.
{"title":"Kunming city mainline one-way green wave coordinated control technology","authors":"Wei Cheng, Xuemin Li, Pengcheng Du","doi":"10.1109/ICAWST.2011.6163098","DOIUrl":"https://doi.org/10.1109/ICAWST.2011.6163098","url":null,"abstract":"For the characters of the City of Kunming' trunk road, this paper proposed a model of one-way green wave coordination control based on fuzzy neural network, from the optimization of the cycle, offset and split of intersections. At last the simulation shows the proposed method can reduce the queue length and vehicle delay very well.","PeriodicalId":126169,"journal":{"name":"2011 3rd International Conference on Awareness Science and Technology (iCAST)","volume":"147 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124265515","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 : 2011-09-01DOI: 10.1109/ICAWST.2011.6163113
Xiaoli Mi, Shijie Jia
In this paper, a novel compressed-domain watermarking approach based on motion velocity is proposed. Here the motion velocity is defined as the ration of motion vector and time interval of adjacent frames. An asymmetry watermark detecting algorithm is proposed, where input watermark is a two-value sequence and output watermark is a three-value sequence. The experiment result shows that this watermarking approach has great robustness, especially to video format transformation and bit rate change. This approach can apply to the copyright protection of digital video products in network environment.
{"title":"An asymmetric watermarking algorithm based on motion velocity","authors":"Xiaoli Mi, Shijie Jia","doi":"10.1109/ICAWST.2011.6163113","DOIUrl":"https://doi.org/10.1109/ICAWST.2011.6163113","url":null,"abstract":"In this paper, a novel compressed-domain watermarking approach based on motion velocity is proposed. Here the motion velocity is defined as the ration of motion vector and time interval of adjacent frames. An asymmetry watermark detecting algorithm is proposed, where input watermark is a two-value sequence and output watermark is a three-value sequence. The experiment result shows that this watermarking approach has great robustness, especially to video format transformation and bit rate change. This approach can apply to the copyright protection of digital video products in network environment.","PeriodicalId":126169,"journal":{"name":"2011 3rd International Conference on Awareness Science and Technology (iCAST)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129513032","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 : 2011-09-01DOI: 10.1109/ICAWST.2011.6163133
Y. Liu
In the balanced ensemble learning for a two-class classification problem, the target values are shifted between [1 ∶ 0.5) or (0.5 ∶ 0] instead of 1 and 0 in the learned error function. Such shifted error function could let the ensemble avoid from unnecessary further learning on the well-learned data points. Therefore, the learning direction could be shifted away from the well-learned data points, and turned to the other not-yet-learned data points. By shifting away from well-learned data and focusing on not-yet-learned data, a good balanced learning could be achieved in the ensemble. Through examining both individual learners and the combined ensembles, this paper is to explore how the target shift awareness could help to decide a decision boundary that is neither too close nor too further to all training samples.
{"title":"Target shift awareness in balanced ensemble learning","authors":"Y. Liu","doi":"10.1109/ICAWST.2011.6163133","DOIUrl":"https://doi.org/10.1109/ICAWST.2011.6163133","url":null,"abstract":"In the balanced ensemble learning for a two-class classification problem, the target values are shifted between [1 ∶ 0.5) or (0.5 ∶ 0] instead of 1 and 0 in the learned error function. Such shifted error function could let the ensemble avoid from unnecessary further learning on the well-learned data points. Therefore, the learning direction could be shifted away from the well-learned data points, and turned to the other not-yet-learned data points. By shifting away from well-learned data and focusing on not-yet-learned data, a good balanced learning could be achieved in the ensemble. Through examining both individual learners and the combined ensembles, this paper is to explore how the target shift awareness could help to decide a decision boundary that is neither too close nor too further to all training samples.","PeriodicalId":126169,"journal":{"name":"2011 3rd International Conference on Awareness Science and Technology (iCAST)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115915414","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 : 2011-09-01DOI: 10.1109/ICAWST.2011.6163191
Xin Zhu, Wenxi Chen, T. Nemoto, K. Kitamura
We proposed an adaptive pulse template method for accurate detection of heart beat from pressure signals measured during sleep. 13 subjects' pressure and photoplethysmography signals were measured during sleep for evaluation. Compared with our previous heart beat detection method based on differential filtering, the adaptive pulse template method has a higher positive predictivity 94.46% and a satisfying sensitivity 94.08% for the detection of heart beat in the pulse waveform extracted from pressure signals. The accurate detection of heart beat can improve the estimation accuracy of pulse rate variability analysis.
{"title":"Adaptive pulse template method for accurate detection of heart beat from pressure signals measured during sleep","authors":"Xin Zhu, Wenxi Chen, T. Nemoto, K. Kitamura","doi":"10.1109/ICAWST.2011.6163191","DOIUrl":"https://doi.org/10.1109/ICAWST.2011.6163191","url":null,"abstract":"We proposed an adaptive pulse template method for accurate detection of heart beat from pressure signals measured during sleep. 13 subjects' pressure and photoplethysmography signals were measured during sleep for evaluation. Compared with our previous heart beat detection method based on differential filtering, the adaptive pulse template method has a higher positive predictivity 94.46% and a satisfying sensitivity 94.08% for the detection of heart beat in the pulse waveform extracted from pressure signals. The accurate detection of heart beat can improve the estimation accuracy of pulse rate variability analysis.","PeriodicalId":126169,"journal":{"name":"2011 3rd International Conference on Awareness Science and Technology (iCAST)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128471092","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 : 2011-09-01DOI: 10.1109/ICAWST.2011.6163182
Mi-Yeong Hwang, C. Jin, Y. Lee, Kwang Deuk Kim, Jungpil Shin, K. Ryu
The use of fossil fuel in the world has been increasing and it generates lots of greenhouse gases. As a result, environmental pollution brought us a serious weather change. In order to reduce the environmental pollution, we should use renewable energy that does not produce any pollution such as wind data. However, wind data can change much in a short time, which is called ramp event. It can make the demand and response imbalance and also cause damages to the wind turbines. Therefore, we should predict the power generation and power ramp rate (PRR) to avoid these problems. In this paper, we predicted the wind power generation and PRR with exponential smoothing method and ARIMA. The prediction method predict wind power generation and PRR after 1 minute using data measured 1 hour ago at 10 intervals. We got forecasting error rate such as Mean Absolute Error (MAE) and Root Mean Square Error (RMSE), and then we compared two results of ARIMA and exponential smoothing method. The comparison results showed that exponential smoothing method gets better prediction accuracy than ARIMA.
{"title":"Prediction of wind power generation and power ramp rate with time series analysis","authors":"Mi-Yeong Hwang, C. Jin, Y. Lee, Kwang Deuk Kim, Jungpil Shin, K. Ryu","doi":"10.1109/ICAWST.2011.6163182","DOIUrl":"https://doi.org/10.1109/ICAWST.2011.6163182","url":null,"abstract":"The use of fossil fuel in the world has been increasing and it generates lots of greenhouse gases. As a result, environmental pollution brought us a serious weather change. In order to reduce the environmental pollution, we should use renewable energy that does not produce any pollution such as wind data. However, wind data can change much in a short time, which is called ramp event. It can make the demand and response imbalance and also cause damages to the wind turbines. Therefore, we should predict the power generation and power ramp rate (PRR) to avoid these problems. In this paper, we predicted the wind power generation and PRR with exponential smoothing method and ARIMA. The prediction method predict wind power generation and PRR after 1 minute using data measured 1 hour ago at 10 intervals. We got forecasting error rate such as Mean Absolute Error (MAE) and Root Mean Square Error (RMSE), and then we compared two results of ARIMA and exponential smoothing method. The comparison results showed that exponential smoothing method gets better prediction accuracy than ARIMA.","PeriodicalId":126169,"journal":{"name":"2011 3rd International Conference on Awareness Science and Technology (iCAST)","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122869225","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 : 2011-09-01DOI: 10.1109/ICAWST.2011.6163154
Kiyota Hashimoto, K. Takeuchi
Various kinds of learner support systems have been proposed and employed, and their evaluation, whether it is at a developmental stage or at the employing stage, depends on learners, which is inevitable but which failure must be avoided as much as possible. For that purpose, it is desirable to employ a computer simulation, but the body of relevant knowledge, the model representing learning stages, and learner data are necessary. In this prototypical study, we propose a novel method to employ a multi-layered multi-agent simulation.
{"title":"Multi-layered learner knowledge model for evaluative multi-agent simulation","authors":"Kiyota Hashimoto, K. Takeuchi","doi":"10.1109/ICAWST.2011.6163154","DOIUrl":"https://doi.org/10.1109/ICAWST.2011.6163154","url":null,"abstract":"Various kinds of learner support systems have been proposed and employed, and their evaluation, whether it is at a developmental stage or at the employing stage, depends on learners, which is inevitable but which failure must be avoided as much as possible. For that purpose, it is desirable to employ a computer simulation, but the body of relevant knowledge, the model representing learning stages, and learner data are necessary. In this prototypical study, we propose a novel method to employ a multi-layered multi-agent simulation.","PeriodicalId":126169,"journal":{"name":"2011 3rd International Conference on Awareness Science and Technology (iCAST)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125940838","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 : 2011-09-01DOI: 10.1109/ICAWST.2011.6163165
Jun Zeng, S. Hirokawa
The existing search engines return the whole web pages as the search results, which make user spend extra time to read the useless information before finding the information they really want. We propose a novel search engine model called “Component Search Engine”, which can return the contents satisfying user's query rather than the whole pages. For achieving the purpose, we adopt a Tree-View interface to display the results. Through usability study, we determinate that Component Search Engine using Tree-View interface can improve user's searching experience and efficiency.
{"title":"Component search engine using tree-view interface for tourist blogs","authors":"Jun Zeng, S. Hirokawa","doi":"10.1109/ICAWST.2011.6163165","DOIUrl":"https://doi.org/10.1109/ICAWST.2011.6163165","url":null,"abstract":"The existing search engines return the whole web pages as the search results, which make user spend extra time to read the useless information before finding the information they really want. We propose a novel search engine model called “Component Search Engine”, which can return the contents satisfying user's query rather than the whole pages. For achieving the purpose, we adopt a Tree-View interface to display the results. Through usability study, we determinate that Component Search Engine using Tree-View interface can improve user's searching experience and efficiency.","PeriodicalId":126169,"journal":{"name":"2011 3rd International Conference on Awareness Science and Technology (iCAST)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129942791","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 : 2011-09-01DOI: 10.1109/ICAWST.2011.6163138
F. Cong, T. Ristaniemi
This study addresses an empirical study for data model conversion when using independent component analysis (ICA) to extract brain event-related potentials (ERPs). We firstly prove that in theory there is no difference to perform ICA on the concatenated EEG recordings of a number of single trials and the averaged EEG recordings over those single trials. The general assumption for such conclusion is that mixing models of linear transformations do not change along single trials. Furthermore, we explicitly illustrate that an optimal wavelet filter based on properties of an ERP can convert the underdetermined model of EEG to at least quasi-determined one, but the optimal digital filter based on that ERP cannot make it, through empirical studies. Hence, we suggest combining an optimal wavelet filter and ICA together to extract desired brain signal from the averaged EEG recordings in the ERP study.
{"title":"Data model conversion for independent component analysis to extract brain signals","authors":"F. Cong, T. Ristaniemi","doi":"10.1109/ICAWST.2011.6163138","DOIUrl":"https://doi.org/10.1109/ICAWST.2011.6163138","url":null,"abstract":"This study addresses an empirical study for data model conversion when using independent component analysis (ICA) to extract brain event-related potentials (ERPs). We firstly prove that in theory there is no difference to perform ICA on the concatenated EEG recordings of a number of single trials and the averaged EEG recordings over those single trials. The general assumption for such conclusion is that mixing models of linear transformations do not change along single trials. Furthermore, we explicitly illustrate that an optimal wavelet filter based on properties of an ERP can convert the underdetermined model of EEG to at least quasi-determined one, but the optimal digital filter based on that ERP cannot make it, through empirical studies. Hence, we suggest combining an optimal wavelet filter and ICA together to extract desired brain signal from the averaged EEG recordings in the ERP study.","PeriodicalId":126169,"journal":{"name":"2011 3rd International Conference on Awareness Science and Technology (iCAST)","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131721672","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 : 2011-09-01DOI: 10.1109/ICAWST.2011.6163126
Shuangwu Li, Jinqing Qi
In this paper, a new digital image stabilization (DIS) algorithm base on gray scale projection algorithm (PA) and representative point matching (RPM) is proposed to stabilize videos. First, the gray-projection algorithm is used to estimate the global motion vectors (GMV). Second, we choose a block from the center of image, and estimate the local motion vectors (LMV) by use of RPM algorithm. Finally, we combine the two groups of vectors and calculate the final global motion vectors. The experimental results show that the proposed algorithm is better than traditional gray scale projection algorithm in accuracy, especially for the video sequences which contained interior moved objects. The algorithm can achieve good stabilizing accuracy with processing speed of 24 fps for 240×320 video sequences, it can meet the real-time processing requirement.
{"title":"Image stabilization by combining gray-scale projection and representative point matching algorithms","authors":"Shuangwu Li, Jinqing Qi","doi":"10.1109/ICAWST.2011.6163126","DOIUrl":"https://doi.org/10.1109/ICAWST.2011.6163126","url":null,"abstract":"In this paper, a new digital image stabilization (DIS) algorithm base on gray scale projection algorithm (PA) and representative point matching (RPM) is proposed to stabilize videos. First, the gray-projection algorithm is used to estimate the global motion vectors (GMV). Second, we choose a block from the center of image, and estimate the local motion vectors (LMV) by use of RPM algorithm. Finally, we combine the two groups of vectors and calculate the final global motion vectors. The experimental results show that the proposed algorithm is better than traditional gray scale projection algorithm in accuracy, especially for the video sequences which contained interior moved objects. The algorithm can achieve good stabilizing accuracy with processing speed of 24 fps for 240×320 video sequences, it can meet the real-time processing requirement.","PeriodicalId":126169,"journal":{"name":"2011 3rd International Conference on Awareness Science and Technology (iCAST)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131192891","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：