Pub Date : 2011-09-01DOI: 10.1109/ICAWST.2011.6163158
Kefeng Wang, Xu Xu, Chonghui Guo
Independent Component Analysis (ICA) is an effective method to solve the problem of Blind Source Separation (BSS). In this paper, a new algorithm is proposed to separate signals mixtured by sub-Gaussian, super-Gaussian, symmetric and asymmetric sources. Alternative score functions in the algorithm are derived by using exponent density model and Gaussian parametric density mixture model. The score functions are selfadaptive through estimating the high-order moments of original signals. Moreover, a stability condition for the proposed algorithm is given to guarantee separating the true solution. Simulations are presented to illustrate the performance and effectiveness of the proposed algorithm.
{"title":"A stable ICA algorithm based on exponent density and Gaussian parametric density mixture models","authors":"Kefeng Wang, Xu Xu, Chonghui Guo","doi":"10.1109/ICAWST.2011.6163158","DOIUrl":"https://doi.org/10.1109/ICAWST.2011.6163158","url":null,"abstract":"Independent Component Analysis (ICA) is an effective method to solve the problem of Blind Source Separation (BSS). In this paper, a new algorithm is proposed to separate signals mixtured by sub-Gaussian, super-Gaussian, symmetric and asymmetric sources. Alternative score functions in the algorithm are derived by using exponent density model and Gaussian parametric density mixture model. The score functions are selfadaptive through estimating the high-order moments of original signals. Moreover, a stability condition for the proposed algorithm is given to guarantee separating the true solution. Simulations are presented to illustrate the performance and effectiveness of the proposed algorithm.","PeriodicalId":126169,"journal":{"name":"2011 3rd International Conference on Awareness Science and Technology (iCAST)","volume":"47 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":"124742351","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.2011.6163180
Deze Zeng, Song Guo, Zixue Cheng, A. Pham
With the advent of Internet of Things (IoT), more and more smart things automatically engage in people's daily life by various means as they are becoming capable of computation and communication. Both challenges and opportunities are posed. To exploit the potential of IoT, different concepts from various points of view have been explored. One of the IoT developing trend is so-called Ambient Intelligence (AI), which refers to things that are sensitive and responsive to the presence of other things and people. The things shall be aware of ambient environments (e.g., other things or people) and take actions accordingly. However, complicated configuration of AI hinders the popularity of IoT. To tackle this problem, we advocate applying the highly abstract concept of “IF-THEN” as the front-end of AI in IoT. To realize such a concept, we present a preliminary design in this paper, including issues of the architecture design, the uniformly understandable language and function assembly.
{"title":"IF-THEN in the Internet of Things","authors":"Deze Zeng, Song Guo, Zixue Cheng, A. Pham","doi":"10.1109/ICAWST.2011.6163180","DOIUrl":"https://doi.org/10.1109/ICAWST.2011.6163180","url":null,"abstract":"With the advent of Internet of Things (IoT), more and more smart things automatically engage in people's daily life by various means as they are becoming capable of computation and communication. Both challenges and opportunities are posed. To exploit the potential of IoT, different concepts from various points of view have been explored. One of the IoT developing trend is so-called Ambient Intelligence (AI), which refers to things that are sensitive and responsive to the presence of other things and people. The things shall be aware of ambient environments (e.g., other things or people) and take actions accordingly. However, complicated configuration of AI hinders the popularity of IoT. To tackle this problem, we advocate applying the highly abstract concept of “IF-THEN” as the front-end of AI in IoT. To realize such a concept, we present a preliminary design in this paper, including issues of the architecture design, the uniformly understandable language and function assembly.","PeriodicalId":126169,"journal":{"name":"2011 3rd International Conference on Awareness Science and Technology (iCAST)","volume":"1 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":"129074479","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.2011.6163175
Kazuhisa Seta, M. Ikeda
It is difficult to generalize and accumulate experiences of system development as methodologies for building meta-learning support systems because the meaning of “meta-cognition” is vague. Therefore, the importance of a model oriented system development approach has been recognized. It contributes to systematic refinement of each learning system by iterating a loop that building a model that can clarify design rationale of the system, developing and evaluating each learning system according to the model, and revising the model based on it. Moreover we can accumulate knowledge on meta-learning system development based on it. Thus, we adopt a model-oriented approach: (i) we adopt Kayashima's computational model as a basis to build a meta-learning task model and we add two factors of difficulties in performing meta-learning activities, (ii) we conceptualize five concepts for building meta-learning scheme that clarifies means to remove/ eliminate the factors of difficulties; then (iii) we embed support functions to facilitate meta-learning processes based on the model. This constitutes a promising approach not only for building learning support systems but also for accumulating/ revising knowledge on the system development. In this paper, we firstly describe the philosophy of our research to elucidate our model-oriented approach. Secondly, we present a meta-learning process model as a basis for understanding meta-learning tasks and what factors of difficulty exist in performing meta-learning activities. Thirdly, we explain our conceptualizations as a basis to design sophisticated meta-learning scheme to prompt learners' meta-learning processes. Fourthly, we integrate a meta-learning process model and conceptualizations so that we design our meta-learning scheme based on the deep understanding of meta-learning processes. Then, we present our presentation-based meta-learning scheme designed based on the model and clarify the design rationale of our system based on the model. Finally, we describe the usefulness of the model by characterizing other meta-cognition support schemes.
{"title":"Model based development of a meta-leraning support system to prompt self-awareness through presenation for meta-learning","authors":"Kazuhisa Seta, M. Ikeda","doi":"10.1109/ICAWST.2011.6163175","DOIUrl":"https://doi.org/10.1109/ICAWST.2011.6163175","url":null,"abstract":"It is difficult to generalize and accumulate experiences of system development as methodologies for building meta-learning support systems because the meaning of “meta-cognition” is vague. Therefore, the importance of a model oriented system development approach has been recognized. It contributes to systematic refinement of each learning system by iterating a loop that building a model that can clarify design rationale of the system, developing and evaluating each learning system according to the model, and revising the model based on it. Moreover we can accumulate knowledge on meta-learning system development based on it. Thus, we adopt a model-oriented approach: (i) we adopt Kayashima's computational model as a basis to build a meta-learning task model and we add two factors of difficulties in performing meta-learning activities, (ii) we conceptualize five concepts for building meta-learning scheme that clarifies means to remove/ eliminate the factors of difficulties; then (iii) we embed support functions to facilitate meta-learning processes based on the model. This constitutes a promising approach not only for building learning support systems but also for accumulating/ revising knowledge on the system development. In this paper, we firstly describe the philosophy of our research to elucidate our model-oriented approach. Secondly, we present a meta-learning process model as a basis for understanding meta-learning tasks and what factors of difficulty exist in performing meta-learning activities. Thirdly, we explain our conceptualizations as a basis to design sophisticated meta-learning scheme to prompt learners' meta-learning processes. Fourthly, we integrate a meta-learning process model and conceptualizations so that we design our meta-learning scheme based on the deep understanding of meta-learning processes. Then, we present our presentation-based meta-learning scheme designed based on the model and clarify the design rationale of our system based on the model. Finally, we describe the usefulness of the model by characterizing other meta-cognition support schemes.","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":"117255116","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.2011.6163192
A. Doi, H. Takahashi, T. Mawatari, S. Mega
In this paper, we present the development of a high-speed volume rendering system that combines 3D texture compression and parallel programming techniques for rendering multiple high-resolution 3D images obtained with medical or industrial CT. The 3D texture compression algorithm (DXT5) provides extremely high efficiency since it reduces the memory consumption to 1/4 of the original without having a negative impact on the image quality or display speed. By using this approach, it is possible to use personal computers with general-purpose graphics capabilities to display high-resolution 3D images or groups of multiple 3D images obtained with medical or industrial CT in real time.
{"title":"Development of a volume rendering system using 3D texture compression techniques on general-purpose personal computers","authors":"A. Doi, H. Takahashi, T. Mawatari, S. Mega","doi":"10.1109/ICAWST.2011.6163192","DOIUrl":"https://doi.org/10.1109/ICAWST.2011.6163192","url":null,"abstract":"In this paper, we present the development of a high-speed volume rendering system that combines 3D texture compression and parallel programming techniques for rendering multiple high-resolution 3D images obtained with medical or industrial CT. The 3D texture compression algorithm (DXT5) provides extremely high efficiency since it reduces the memory consumption to 1/4 of the original without having a negative impact on the image quality or display speed. By using this approach, it is possible to use personal computers with general-purpose graphics capabilities to display high-resolution 3D images or groups of multiple 3D images obtained with medical or industrial CT in real time.","PeriodicalId":126169,"journal":{"name":"2011 3rd International Conference on Awareness Science and Technology (iCAST)","volume":"68 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":"117322510","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.2011.6163091
Meng Yao, Huchuan Lu
In this work, we propose a new method for human body accurate detection in a static image with multiscale superpixels. The main contribution of this work is as follows: (1) A new framework for human body accurate detection using multiscale superpixels and classifier with autothreshold is proposed. (2) Some effective constraints for human body detection are given. Experimental results show the framework can accurately detect the human body in most situations. The dataset we use is a collection of photos of humans, varying in pose and clothing with complex backgrounds.
{"title":"Human body segmentation in a static image with multiscale superpixels","authors":"Meng Yao, Huchuan Lu","doi":"10.1109/ICAWST.2011.6163091","DOIUrl":"https://doi.org/10.1109/ICAWST.2011.6163091","url":null,"abstract":"In this work, we propose a new method for human body accurate detection in a static image with multiscale superpixels. The main contribution of this work is as follows: (1) A new framework for human body accurate detection using multiscale superpixels and classifier with autothreshold is proposed. (2) Some effective constraints for human body detection are given. Experimental results show the framework can accurately detect the human body in most situations. The dataset we use is a collection of photos of humans, varying in pose and clothing with complex backgrounds.","PeriodicalId":126169,"journal":{"name":"2011 3rd International Conference on Awareness Science and Technology (iCAST)","volume":"36 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":"132818508","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.2011.6163163
Masafumi Matsuhara, Satoshi Suzuki
Opportunities and needs are increasing to input Japanese sentences on mobile phones since performance of mobile phones is improving. Applications like E-mail, Web search and so on are widely used on mobile phones now. We need to input Japanese sentences using only 12 keys on mobile phones. We have proposed a method to input Japanese sentences on mobile phones quickly and easily. We call this method Number-Kanji translation method. The number-string inputted by a user is translated into string to Kana-string is a one-to-many mapping. Therefore, it is difficult to translate a number-string into the correct sentence intended by the user. The proposed context-aware mapping method is able to disambiguate a number-string by artificial neural network (ANN). The system is able to translate number-segments into the intended words because the system becomes aware of the correspondence of number-segments with Japanese words through learning by ANN. The system does not need a dictionary. We also show the effectiveness of our proposed method by the result of the evaluation experiment.
{"title":"An efficient context-aware character input algorithm for mobile phone based on artificial neural network","authors":"Masafumi Matsuhara, Satoshi Suzuki","doi":"10.1109/ICAWST.2011.6163163","DOIUrl":"https://doi.org/10.1109/ICAWST.2011.6163163","url":null,"abstract":"Opportunities and needs are increasing to input Japanese sentences on mobile phones since performance of mobile phones is improving. Applications like E-mail, Web search and so on are widely used on mobile phones now. We need to input Japanese sentences using only 12 keys on mobile phones. We have proposed a method to input Japanese sentences on mobile phones quickly and easily. We call this method Number-Kanji translation method. The number-string inputted by a user is translated into string to Kana-string is a one-to-many mapping. Therefore, it is difficult to translate a number-string into the correct sentence intended by the user. The proposed context-aware mapping method is able to disambiguate a number-string by artificial neural network (ANN). The system is able to translate number-segments into the intended words because the system becomes aware of the correspondence of number-segments with Japanese words through learning by ANN. The system does not need a dictionary. We also show the effectiveness of our proposed method by the result of the evaluation experiment.","PeriodicalId":126169,"journal":{"name":"2011 3rd International Conference on Awareness Science and Technology (iCAST)","volume":"36 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":"132858016","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.2011.6163150
Qun Wang, Zhiwen Liu
This paper presents a novel iterative greedy algorithm for Distributed Compressed Sensing (DCS) scenario based on backtracking technique, which is denoted by DCS-SAMP. The algorithm can reconstruct several input signals simultaneously, even when the measurements are contaminated with noise and without any prior information of their sparseness. It can provide a fast runtime while also offers comparably theoretical guarantees as the best optimization-based approach. This makes it as a promising candidate for many practical applications,such as Tele-Health or Telemedicine. Numerical experiments are performed to demonstrate the validity and high performance of the proposed DCS-SAMP algorithm for multichannel biomedical signals.
{"title":"Distributed Compressed Sensing for biomedical signals","authors":"Qun Wang, Zhiwen Liu","doi":"10.1109/ICAWST.2011.6163150","DOIUrl":"https://doi.org/10.1109/ICAWST.2011.6163150","url":null,"abstract":"This paper presents a novel iterative greedy algorithm for Distributed Compressed Sensing (DCS) scenario based on backtracking technique, which is denoted by DCS-SAMP. The algorithm can reconstruct several input signals simultaneously, even when the measurements are contaminated with noise and without any prior information of their sparseness. It can provide a fast runtime while also offers comparably theoretical guarantees as the best optimization-based approach. This makes it as a promising candidate for many practical applications,such as Tele-Health or Telemedicine. Numerical experiments are performed to demonstrate the validity and high performance of the proposed DCS-SAMP algorithm for multichannel biomedical signals.","PeriodicalId":126169,"journal":{"name":"2011 3rd International Conference on Awareness Science and Technology (iCAST)","volume":"1 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":"130482426","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.2011.6163179
Van Tam Nguyen, F. Villain, Y. L. Guillou
Cognitive radio system (CRS) is a disruptive technology targeting very high spectral efficiency. This paper presents an overview of CRS and summarizes the related regulation and standardization status. We point out some key research challenges, especially implementation challenges of cognitive radio and deduce research directions in CRS. Despite numerous challenges, the timeframe for the success of CRS is more linked to the economical and business model than real technological issues.
{"title":"Cognitive radio systems: Overview and challenges","authors":"Van Tam Nguyen, F. Villain, Y. L. Guillou","doi":"10.1109/ICAWST.2011.6163179","DOIUrl":"https://doi.org/10.1109/ICAWST.2011.6163179","url":null,"abstract":"Cognitive radio system (CRS) is a disruptive technology targeting very high spectral efficiency. This paper presents an overview of CRS and summarizes the related regulation and standardization status. We point out some key research challenges, especially implementation challenges of cognitive radio and deduce research directions in CRS. Despite numerous challenges, the timeframe for the success of CRS is more linked to the economical and business model than real technological issues.","PeriodicalId":126169,"journal":{"name":"2011 3rd International Conference on Awareness Science and Technology (iCAST)","volume":"923 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":"123288302","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.2011.6163160
Kazuma Suzuki, K. Naruse
Passive Dynamic Walker can descend a shallow slope only using an initial velocity and the gravity. It has good energy efficiency because it does not require any actuator. However, it has been known that it cannot walk on a steep slope. Controlled walking models, called “semi-passive dynamic walkers” are considered in this research to accomplish stable walking on the steep slope. The experimental model is defined as the compass shaped model which has control to the hip joint and ankle joint. Three different controlled models are tested to investigate the characteristics of walking. As the result the controlled model accomplishes steep slope walking and it has some robustness to the angle of the slope if sufficient torque is added.
{"title":"Robustness of semi-passive dynamic walking models for steep slopes","authors":"Kazuma Suzuki, K. Naruse","doi":"10.1109/ICAWST.2011.6163160","DOIUrl":"https://doi.org/10.1109/ICAWST.2011.6163160","url":null,"abstract":"Passive Dynamic Walker can descend a shallow slope only using an initial velocity and the gravity. It has good energy efficiency because it does not require any actuator. However, it has been known that it cannot walk on a steep slope. Controlled walking models, called “semi-passive dynamic walkers” are considered in this research to accomplish stable walking on the steep slope. The experimental model is defined as the compass shaped model which has control to the hip joint and ankle joint. Three different controlled models are tested to investigate the characteristics of walking. As the result the controlled model accomplishes steep slope walking and it has some robustness to the angle of the slope if sufficient torque is added.","PeriodicalId":126169,"journal":{"name":"2011 3rd International Conference on Awareness Science and Technology (iCAST)","volume":"18 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":"123633227","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.2011.6163097
Mingxin Jiang, Fangshun Mu, Hongyu Wang
This work presents a method for height measurements of moving objects based on rubust tracking. At first, we compute vanishing line of the ground plane and the vertical vanishing point using three vertical poles. Secondly, tracking of multiple people is performed by graph cuts. Then, the head feature points and the feet feature points are extracted in each frame of video sequences, and obtain height measurements of multiple objects according to the projective geometric constraint. Finally, the multiframe measurements are optimized using RANSAC algorithm. The experimental results demonstrate that our method is effective and also achieves real-time performance.
{"title":"Height measurements of moving people based on single camera","authors":"Mingxin Jiang, Fangshun Mu, Hongyu Wang","doi":"10.1109/ICAWST.2011.6163097","DOIUrl":"https://doi.org/10.1109/ICAWST.2011.6163097","url":null,"abstract":"This work presents a method for height measurements of moving objects based on rubust tracking. At first, we compute vanishing line of the ground plane and the vertical vanishing point using three vertical poles. Secondly, tracking of multiple people is performed by graph cuts. Then, the head feature points and the feet feature points are extracted in each frame of video sequences, and obtain height measurements of multiple objects according to the projective geometric constraint. Finally, the multiframe measurements are optimized using RANSAC algorithm. The experimental results demonstrate that our method is effective and also achieves real-time performance.","PeriodicalId":126169,"journal":{"name":"2011 3rd International Conference on Awareness Science and Technology (iCAST)","volume":"1 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":"123732310","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：