Pub Date : 2013-11-01DOI: 10.1109/ICAWST.2013.6765423
Jun Li, Zhutian Chen, Yu Liu, Y. Cai, Huaqing Min, Qing Li
Distributed coordination is critical for a multi-robot system in collective cleanup task under a dynamic environment. In traditional methods, robots easily drop into premature convergence. In this paper, we propose a swarm-intelligence based algorithm to reduce the expectation time for searching targets and removing. We modify the traditional PSO algorithm with a random factor to tackle premature convergence problem, and it can achieve a significant improvement in multi-robot system. The proposed method has been implemented on self-developed simulator for searching task. The simulation results demonstrate the feasibility, robustness, and scalability of our proposed method than previous methods.
{"title":"A modified particle swarm optimization algorithm for distributed search and collective cleanup","authors":"Jun Li, Zhutian Chen, Yu Liu, Y. Cai, Huaqing Min, Qing Li","doi":"10.1109/ICAWST.2013.6765423","DOIUrl":"https://doi.org/10.1109/ICAWST.2013.6765423","url":null,"abstract":"Distributed coordination is critical for a multi-robot system in collective cleanup task under a dynamic environment. In traditional methods, robots easily drop into premature convergence. In this paper, we propose a swarm-intelligence based algorithm to reduce the expectation time for searching targets and removing. We modify the traditional PSO algorithm with a random factor to tackle premature convergence problem, and it can achieve a significant improvement in multi-robot system. The proposed method has been implemented on self-developed simulator for searching task. The simulation results demonstrate the feasibility, robustness, and scalability of our proposed method than previous methods.","PeriodicalId":68697,"journal":{"name":"炎黄地理","volume":"29 1","pages":"137-143"},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78213226","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 : 2013-11-01DOI: 10.1109/ICAWST.2013.6765439
Ivan Khozyainov, Evgeny Pyshkin, V. Klyuev
In recent years there is growing interest to the opinion mining applications in numerous areas of information and social science. In this paper we investigate main problems in opinion mining and sentiment analysis systems development. We review examples of difficulties in process of opinion extraction and introduce essential multidimensionality of opinion mining. We carried out a series of experiments with different sentiment analyzers and classified main reasons of incorrect sentiment recognition.
{"title":"Spelling out opinions: Difficult cases of sentiment analysis","authors":"Ivan Khozyainov, Evgeny Pyshkin, V. Klyuev","doi":"10.1109/ICAWST.2013.6765439","DOIUrl":"https://doi.org/10.1109/ICAWST.2013.6765439","url":null,"abstract":"In recent years there is growing interest to the opinion mining applications in numerous areas of information and social science. In this paper we investigate main problems in opinion mining and sentiment analysis systems development. We review examples of difficulties in process of opinion extraction and introduce essential multidimensionality of opinion mining. We carried out a series of experiments with different sentiment analyzers and classified main reasons of incorrect sentiment recognition.","PeriodicalId":68697,"journal":{"name":"炎黄地理","volume":"56 1","pages":"231-237"},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84516678","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 : 2013-11-01DOI: 10.1109/ICAWST.2013.6765467
M. Yokota
This paper considers human intuition in association with mental images and proposes a functional model of human intuition where it is defined as a set of procedural functions specialized for facilitating cognition of significant matters in perception of external stimuli, for example, instinctive detection of dangerously keen objects. Here is proposed a multilayered model of human cognition of the external world. The model consists of three main processing components, namely, Perception, Intuition and Reason. At the first layer, Perception produces vague and unarticulated images (i.e., perceptive images) from external stimuli. At the second layer, Intuition translates perceptive images into articulated ones (i.e., intuitive images) with direct knowledge but any mediate knowledge yielded by reasoning. Finally, Reason calibrates intuitive images into rational images, so called, by inference employing various kinds of knowledge.
{"title":"Intuition as mental image processing: Some psycholinguistic considerations on intuitive sensory data structuring and processing based on mental image directed semantic theory","authors":"M. Yokota","doi":"10.1109/ICAWST.2013.6765467","DOIUrl":"https://doi.org/10.1109/ICAWST.2013.6765467","url":null,"abstract":"This paper considers human intuition in association with mental images and proposes a functional model of human intuition where it is defined as a set of procedural functions specialized for facilitating cognition of significant matters in perception of external stimuli, for example, instinctive detection of dangerously keen objects. Here is proposed a multilayered model of human cognition of the external world. The model consists of three main processing components, namely, Perception, Intuition and Reason. At the first layer, Perception produces vague and unarticulated images (i.e., perceptive images) from external stimuli. At the second layer, Intuition translates perceptive images into articulated ones (i.e., intuitive images) with direct knowledge but any mediate knowledge yielded by reasoning. Finally, Reason calibrates intuitive images into rational images, so called, by inference employing various kinds of knowledge.","PeriodicalId":68697,"journal":{"name":"炎黄地理","volume":"485 1","pages":"365-371"},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77450238","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 : 2013-11-01DOI: 10.1109/ICAWST.2013.6765443
Chi-Chih Yu, Toru Yamaguchi, Y. Takama
A decade ago, an increasing number of people are accustomed to utilize the social media for sharing their impressions, experiences, information, and resources. A social media website does not only provide the information sharing functions for the users but also has the capability to match users' similar interesting preferences. Therefore, a recommender that can recommend highly interesting information to the users will make the users easy to gain new information they want, suggest implicit friends who have same hobbies, and increase the interactions with others. In this paper, we proposed a weight based recommendation method for social media, which usually has only the personal items uploaded by the users. Our evaluation results show this recommendation approach is feasible and flexible. Furthermore, we applied the proposed recommendation method into our information sharing system and look forward it can raise the interactions with the users in order to improve the quality of community.
{"title":"A hybrid recommender system based non-common items in social media","authors":"Chi-Chih Yu, Toru Yamaguchi, Y. Takama","doi":"10.1109/ICAWST.2013.6765443","DOIUrl":"https://doi.org/10.1109/ICAWST.2013.6765443","url":null,"abstract":"A decade ago, an increasing number of people are accustomed to utilize the social media for sharing their impressions, experiences, information, and resources. A social media website does not only provide the information sharing functions for the users but also has the capability to match users' similar interesting preferences. Therefore, a recommender that can recommend highly interesting information to the users will make the users easy to gain new information they want, suggest implicit friends who have same hobbies, and increase the interactions with others. In this paper, we proposed a weight based recommendation method for social media, which usually has only the personal items uploaded by the users. Our evaluation results show this recommendation approach is feasible and flexible. Furthermore, we applied the proposed recommendation method into our information sharing system and look forward it can raise the interactions with the users in order to improve the quality of community.","PeriodicalId":68697,"journal":{"name":"炎黄地理","volume":"93 1","pages":"255-261"},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72909708","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 : 2013-11-01DOI: 10.1109/ICAWST.2013.6765449
H. Iwata, S. Tsumoto, S. Hirano
This paper proposes a temporal data mining method to construct a clinical pathway for nurses by using the following four steps: first, histories of nursing orders are extracted from hospital information system. Second, orders are classified into several groups by using clustering. Third, by using the labels obtained, rule induction is applied to the data and important features for classification are extracted. Finally, an original temporal dataset is split into several subtables, and the first step will be recursively applied to each table until no split is needed. The method was applied to datasets of several diseases extracted from a hospital information system. The results show that the reuse of stored data will give a powerful tool for maintenance of clinical pathway, which can be viewed as data-oriented management of nursing schedule.
{"title":"Data mining based clinical care plan construction","authors":"H. Iwata, S. Tsumoto, S. Hirano","doi":"10.1109/ICAWST.2013.6765449","DOIUrl":"https://doi.org/10.1109/ICAWST.2013.6765449","url":null,"abstract":"This paper proposes a temporal data mining method to construct a clinical pathway for nurses by using the following four steps: first, histories of nursing orders are extracted from hospital information system. Second, orders are classified into several groups by using clustering. Third, by using the labels obtained, rule induction is applied to the data and important features for classification are extracted. Finally, an original temporal dataset is split into several subtables, and the first step will be recursively applied to each table until no split is needed. The method was applied to datasets of several diseases extracted from a hospital information system. The results show that the reuse of stored data will give a powerful tool for maintenance of clinical pathway, which can be viewed as data-oriented management of nursing schedule.","PeriodicalId":68697,"journal":{"name":"炎黄地理","volume":"7 1","pages":"286-292"},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78837189","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 : 2013-11-01DOI: 10.1109/icawst.2013.6765455
F. Ishida, Y. Sawada
Anticipatory activity arising from characteristic predictive mechanisms is observed in human and animal sensory-motor control systems. The quantitative features of anticipatory activity have been reported in terms of the amount of hand precedence from the target with various conditions in tasks that involve tracking and synchronizing a visual and auditory target. However, the mechanism of anticipatory activity has not been investigated in detail. In the present study, numerical simulations were performed with a hand-tracking model that exhibited anticipatory activity with a focus on the relationship between feedforward and feedback control elements. Rhythmic components and an on-off mechanism were introduced to the feedforward control element and the feedback control element, respectively, depending on whether or not the visual target was displayed. Anticipatory activity of hand-motion was observed when feedback control was activated with weaker operation of feedforward control. In addition, hand motion was delayed when feedback control was activated with stronger operation of feedforward control. This suggests that in sensory-motor control systems, feedforward and feedback control work complementarity rather than simultaneously.
{"title":"Complementarity between the feedforward and feedback mechanisms is necessary for anticipatory activity in hand tracking","authors":"F. Ishida, Y. Sawada","doi":"10.1109/icawst.2013.6765455","DOIUrl":"https://doi.org/10.1109/icawst.2013.6765455","url":null,"abstract":"Anticipatory activity arising from characteristic predictive mechanisms is observed in human and animal sensory-motor control systems. The quantitative features of anticipatory activity have been reported in terms of the amount of hand precedence from the target with various conditions in tasks that involve tracking and synchronizing a visual and auditory target. However, the mechanism of anticipatory activity has not been investigated in detail. In the present study, numerical simulations were performed with a hand-tracking model that exhibited anticipatory activity with a focus on the relationship between feedforward and feedback control elements. Rhythmic components and an on-off mechanism were introduced to the feedforward control element and the feedback control element, respectively, depending on whether or not the visual target was displayed. Anticipatory activity of hand-motion was observed when feedback control was activated with weaker operation of feedforward control. In addition, hand motion was delayed when feedback control was activated with stronger operation of feedforward control. This suggests that in sensory-motor control systems, feedforward and feedback control work complementarity rather than simultaneously.","PeriodicalId":68697,"journal":{"name":"炎黄地理","volume":"106 1","pages":"310-316"},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76101621","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 : 2013-11-01DOI: 10.1109/ICAWST.2013.6765522
Fenglin Han, P. Herrmann
The development and analysis of embedded real-time system is complex due to its platform and application dependencies. To tackle this complexity, we amended the model-based engineering method SPACE to enable also the modeling, simulation and verification of real-time properties of reactive systems. In this paper, we present a further extension making performance estimations and schedulability analysis of reactive real-time building blocks possible. First, a performance profile for evaluating real-time tasks of a building block is outlined. Second, we present the schedulability analysis of a high level real-time system which is carried out by transforming real-time interface descriptions to timed automata that are composed with automata simulating hardware and scheduling policies.
{"title":"Modeling real-time system performance with respect to scheduling analysis","authors":"Fenglin Han, P. Herrmann","doi":"10.1109/ICAWST.2013.6765522","DOIUrl":"https://doi.org/10.1109/ICAWST.2013.6765522","url":null,"abstract":"The development and analysis of embedded real-time system is complex due to its platform and application dependencies. To tackle this complexity, we amended the model-based engineering method SPACE to enable also the modeling, simulation and verification of real-time properties of reactive systems. In this paper, we present a further extension making performance estimations and schedulability analysis of reactive real-time building blocks possible. First, a performance profile for evaluating real-time tasks of a building block is outlined. Second, we present the schedulability analysis of a high level real-time system which is carried out by transforming real-time interface descriptions to timed automata that are composed with automata simulating hardware and scheduling policies.","PeriodicalId":68697,"journal":{"name":"炎黄地理","volume":"2 1","pages":"663-671"},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87921121","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}
This paper aims to customer classification age groups by walking data using pressure sensor array. Techniques of the age groups estimation in many retail businesses (for example, convenience stores, supermarkets, shopping malls, etc.) are marketable. Because those techniques are applicable for market research and customer analysis. There are many researches of the age estimation using face images, walking silhouette data, etc. However, there are some problems too. One of problem is that the estimation classes are a few. Moreover, many age estimation systems use some video cameras. Therefore, these systems may invade surveyed person's privacy by taking one's face images. Obviously the pressure sensor does not record one's face images. In this study, this fact is one of merit in using the pressure sensors. The pressure sensor array gets feature quantity including center of gravity, pressure value, area of foot, etc. In this study, our system classifies surveyed persons to 6 age groups as each decade. Here, surveyed persons are 20s-70s. Average estimation accuracy of all age groups is 82.67%. The highest estimation accuracy is 89.33% at 20s and 60s.
{"title":"Customer classification method for multiple pedestrians using pressure sensors","authors":"Junjirou Hasegawa, Takuya Tajima, Takehiko Abe, Haruhiko Kimura","doi":"10.1109/ICAWST.2013.6765464","DOIUrl":"https://doi.org/10.1109/ICAWST.2013.6765464","url":null,"abstract":"This paper aims to customer classification age groups by walking data using pressure sensor array. Techniques of the age groups estimation in many retail businesses (for example, convenience stores, supermarkets, shopping malls, etc.) are marketable. Because those techniques are applicable for market research and customer analysis. There are many researches of the age estimation using face images, walking silhouette data, etc. However, there are some problems too. One of problem is that the estimation classes are a few. Moreover, many age estimation systems use some video cameras. Therefore, these systems may invade surveyed person's privacy by taking one's face images. Obviously the pressure sensor does not record one's face images. In this study, this fact is one of merit in using the pressure sensors. The pressure sensor array gets feature quantity including center of gravity, pressure value, area of foot, etc. In this study, our system classifies surveyed persons to 6 age groups as each decade. Here, surveyed persons are 20s-70s. Average estimation accuracy of all age groups is 82.67%. The highest estimation accuracy is 89.33% at 20s and 60s.","PeriodicalId":68697,"journal":{"name":"炎黄地理","volume":"81 1","pages":"350-354"},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86325843","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 : 2013-11-01DOI: 10.1109/ICAWST.2013.6765463
Hirotsugu Matsukida, H. Fujioka
In this paper, we consider the problem of modeling and reshaping handwritten character fonts. From a set of measured data of human handwriting, characters are modeled by employing the so-called dynamic font model and a theory of smoothing splines. Then, using the dynamic programming and the nonlinear transformation based on Yasumoto's work [1], we then develop a scheme for reshaping the typeface of modeled characters based on some model writings. The effectiveness and usefulness are demonstrated by some experiments.
{"title":"Modeling and reshaping handwritten characters based on dynamic font model","authors":"Hirotsugu Matsukida, H. Fujioka","doi":"10.1109/ICAWST.2013.6765463","DOIUrl":"https://doi.org/10.1109/ICAWST.2013.6765463","url":null,"abstract":"In this paper, we consider the problem of modeling and reshaping handwritten character fonts. From a set of measured data of human handwriting, characters are modeled by employing the so-called dynamic font model and a theory of smoothing splines. Then, using the dynamic programming and the nonlinear transformation based on Yasumoto's work [1], we then develop a scheme for reshaping the typeface of modeled characters based on some model writings. The effectiveness and usefulness are demonstrated by some experiments.","PeriodicalId":68697,"journal":{"name":"炎黄地理","volume":"1 1","pages":"344-350"},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86561675","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 : 2013-11-01DOI: 10.1109/ICAWST.2013.6765500
Yuan Tian, Junjie Lai, Lei Yang, Ji Qi, Qingguo Zhou
To calculate the large number of particles in discrete elements simulation, a heterogeneous CPU-GPU implementation with multiple GPUs is developed. The implementation is achieved by combining two different parallel programming languages so that it can be assigned to a CPU-GPU cluster. The communication between nodes uses Massage Passing Interface (MPI) implementation for dynamic domain decomposition, particles re-mapping and data copying of overlapping areas. Other works are assigned to GPUs to obtain a high computational speed. The results of strong and weak scalability tests are analyzed for different number of GPUs. Last, the LAMMPS is used as CPU platform to compare with multi-GPU application for reflecting the superiority of using heterogeneous implementation.
{"title":"A heterogeneous CPU-GPU implementation for discrete elements simulation with multiple GPUs","authors":"Yuan Tian, Junjie Lai, Lei Yang, Ji Qi, Qingguo Zhou","doi":"10.1109/ICAWST.2013.6765500","DOIUrl":"https://doi.org/10.1109/ICAWST.2013.6765500","url":null,"abstract":"To calculate the large number of particles in discrete elements simulation, a heterogeneous CPU-GPU implementation with multiple GPUs is developed. The implementation is achieved by combining two different parallel programming languages so that it can be assigned to a CPU-GPU cluster. The communication between nodes uses Massage Passing Interface (MPI) implementation for dynamic domain decomposition, particles re-mapping and data copying of overlapping areas. Other works are assigned to GPUs to obtain a high computational speed. The results of strong and weak scalability tests are analyzed for different number of GPUs. Last, the LAMMPS is used as CPU platform to compare with multi-GPU application for reflecting the superiority of using heterogeneous implementation.","PeriodicalId":68697,"journal":{"name":"炎黄地理","volume":"71 1","pages":"547-552"},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83235096","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：