Pub Date : 2014-12-01DOI: 10.1109/IIAI-AAI.2014.174
Tatsuya Sakato, Motoyuki Ozeki, N. Oka
Learning is essential for an autonomous agent to adapt to an environment. One method of learning is through trial and error, however, this method is impractical in a complex environment because of the long learning time required by the agent. Therefore, guidelines are necessary in order to expedite the learning process in such environments, and imitation is one such guideline. Sakato, Ozeki, and Oka (2012-2013) recently proposed a computational model of imitation and autonomous behavior by which an agent can reduce its learning time through imitation. They evaluate the model in discrete and continuous spaces, and apply the model to a real robot in order to acquire painting skills. Their experimental results indicate that the model adapted to the experimental environment by imitation. In this paper, we introduce the model and discuss what are needed to improve the model.
{"title":"Learning through Imitation and Reinforcement Learning: Toward the Acquisition of Painting Motions","authors":"Tatsuya Sakato, Motoyuki Ozeki, N. Oka","doi":"10.1109/IIAI-AAI.2014.174","DOIUrl":"https://doi.org/10.1109/IIAI-AAI.2014.174","url":null,"abstract":"Learning is essential for an autonomous agent to adapt to an environment. One method of learning is through trial and error, however, this method is impractical in a complex environment because of the long learning time required by the agent. Therefore, guidelines are necessary in order to expedite the learning process in such environments, and imitation is one such guideline. Sakato, Ozeki, and Oka (2012-2013) recently proposed a computational model of imitation and autonomous behavior by which an agent can reduce its learning time through imitation. They evaluate the model in discrete and continuous spaces, and apply the model to a real robot in order to acquire painting skills. Their experimental results indicate that the model adapted to the experimental environment by imitation. In this paper, we introduce the model and discuss what are needed to improve the model.","PeriodicalId":432222,"journal":{"name":"2014 IIAI 3rd International Conference on Advanced Applied Informatics","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116510019","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 : 2014-12-01DOI: 10.1109/IIAI-AAI.2014.105
Qingzhong Liu, B. Ribeiro, A. Sung, Divya Suryakumar
In mining massive datasets, often two of the most important and immediate problems are sampling and feature selection. Proper sampling and feature selection contributes to reducing the size of the dataset while obtaining satisfactory results in model building. Theoretically, therefore, it is interesting to investigate whether a given dataset possesses a critical feature dimension, or the minimum number of features that is required for a given learning machine to achieve "satisfactory" performance. (Likewise, the critical sampling size problem concerns whether, for a given dataset, there is a minimum number of data points that must be included in any sample for a learning machine to achieve satisfactory performance.) Here the specific meaning of "satisfactory" performance is to be defined by the user. This paper addresses the complexity of both problems in one general theoretical setting and shows that they have the same complexity and are highly intractable. Next, an empirical method is applied in an attempt to find the approximate critical feature dimension of datasets. It is demonstrated that, under generally reasonable assumptions pertaining to feature ranking algorithms, the critical feature dimension are successfully discovered by the empirical method for a number of datasets of various sizes. The results are encouraging in achieving significant feature size reduction and point to a promising way in dealing with big data. The significance of the existence of crucial dimension in datasets is also explained.
{"title":"Mining the Big Data: The Critical Feature Dimension Problem","authors":"Qingzhong Liu, B. Ribeiro, A. Sung, Divya Suryakumar","doi":"10.1109/IIAI-AAI.2014.105","DOIUrl":"https://doi.org/10.1109/IIAI-AAI.2014.105","url":null,"abstract":"In mining massive datasets, often two of the most important and immediate problems are sampling and feature selection. Proper sampling and feature selection contributes to reducing the size of the dataset while obtaining satisfactory results in model building. Theoretically, therefore, it is interesting to investigate whether a given dataset possesses a critical feature dimension, or the minimum number of features that is required for a given learning machine to achieve \"satisfactory\" performance. (Likewise, the critical sampling size problem concerns whether, for a given dataset, there is a minimum number of data points that must be included in any sample for a learning machine to achieve satisfactory performance.) Here the specific meaning of \"satisfactory\" performance is to be defined by the user. This paper addresses the complexity of both problems in one general theoretical setting and shows that they have the same complexity and are highly intractable. Next, an empirical method is applied in an attempt to find the approximate critical feature dimension of datasets. It is demonstrated that, under generally reasonable assumptions pertaining to feature ranking algorithms, the critical feature dimension are successfully discovered by the empirical method for a number of datasets of various sizes. The results are encouraging in achieving significant feature size reduction and point to a promising way in dealing with big data. The significance of the existence of crucial dimension in datasets is also explained.","PeriodicalId":432222,"journal":{"name":"2014 IIAI 3rd International Conference on Advanced Applied Informatics","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133100446","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 : 2014-12-01DOI: 10.1109/IIAI-AAI.2014.41
Hungming Hung, J. Watada
After obtaining search results through web search engine, classifying into clusters enables us to quickly browse them. Currently, famous search engines like Google, Bing and Baidu always return a long list of web pages which can be more than a hundred million that are ranked by their relevancies to the search key words. Users are forced to examine the results to look for their required information. This consumes a lot of time when the results come into so huge a number that consisting various kinds. Traditional clustering techniques are inadequate for readable descriptions. In this research, we first build a local semantic thesaurus (L.S.T) to transform natural language into two dimensional numerical points. Second, we analyze and gather different attributes of the search results so as to cluster them through on density analysis based K-Medoids method. Without defining categories in advance, K-Medoids method generates clusters with less susceptibility to noise. Experimental results verify our method's feasibility and effectiveness.
{"title":"Search Result Clustering through Density Analysis Based K-Medoids Method","authors":"Hungming Hung, J. Watada","doi":"10.1109/IIAI-AAI.2014.41","DOIUrl":"https://doi.org/10.1109/IIAI-AAI.2014.41","url":null,"abstract":"After obtaining search results through web search engine, classifying into clusters enables us to quickly browse them. Currently, famous search engines like Google, Bing and Baidu always return a long list of web pages which can be more than a hundred million that are ranked by their relevancies to the search key words. Users are forced to examine the results to look for their required information. This consumes a lot of time when the results come into so huge a number that consisting various kinds. Traditional clustering techniques are inadequate for readable descriptions. In this research, we first build a local semantic thesaurus (L.S.T) to transform natural language into two dimensional numerical points. Second, we analyze and gather different attributes of the search results so as to cluster them through on density analysis based K-Medoids method. Without defining categories in advance, K-Medoids method generates clusters with less susceptibility to noise. Experimental results verify our method's feasibility and effectiveness.","PeriodicalId":432222,"journal":{"name":"2014 IIAI 3rd International Conference on Advanced Applied Informatics","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125999018","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 : 2014-12-01DOI: 10.1109/IIAI-AAI.2014.70
Chung-Hsien Tsai, Jiung-yao Huang
Mobile learning provides learners with the capability to assimilate courses anywhere in any time. However, most of the existing Mobile learning systems only allows learners to passively receive knowledge without considering the temporal and spatial information of the learners. The paper proposed a context-aware mobile augmented reality learning platform, called Historical Time Tunnel (HTT), as scaffolding platform for outdoor field learning. The location-based nature of Augmented Reality (AR) technology, AR-based Mobile learning systems could enable learners to acquire the historical interactive knowledge that are related to the specific geographical location. Through such direct interaction with location-based information provided by AR-based M-learning technology, the knowledge acquisition efficiency can be significantly boosted. The designed HTT system not only focuses on student learning management module but also provides teaching material management module for teachers. The conducted experiments on the elementary school student successfully prove that HTT system is an effective scaffolding tool for the novice teachers as well as a helpful assistant to the experienced teachers.
移动学习为学习者提供了随时随地吸收课程的能力。然而，现有的大多数移动学习系统只允许学习者被动地接受知识，而不考虑学习者的时空信息。本文提出了一种情境感知的移动增强现实学习平台——历史时间隧道(Historical Time Tunnel, HTT)，作为户外现场学习的脚手架平台。增强现实(AR)技术基于位置的特性，基于AR的移动学习系统可以使学习者获得与特定地理位置相关的历史交互式知识。通过这种与基于ar的移动学习技术提供的基于位置信息的直接交互，可以显著提高知识获取效率。设计的HTT系统不仅注重学生学习管理模块，还为教师提供了教材管理模块。在小学生身上进行的实验成功地证明了HTT系统是新手教师有效的脚手架工具，也是经验丰富的教师的得力助手。
{"title":"A Mobile Augmented Reality Based Scaffolding Platform for Outdoor Fieldtrip Learning","authors":"Chung-Hsien Tsai, Jiung-yao Huang","doi":"10.1109/IIAI-AAI.2014.70","DOIUrl":"https://doi.org/10.1109/IIAI-AAI.2014.70","url":null,"abstract":"Mobile learning provides learners with the capability to assimilate courses anywhere in any time. However, most of the existing Mobile learning systems only allows learners to passively receive knowledge without considering the temporal and spatial information of the learners. The paper proposed a context-aware mobile augmented reality learning platform, called Historical Time Tunnel (HTT), as scaffolding platform for outdoor field learning. The location-based nature of Augmented Reality (AR) technology, AR-based Mobile learning systems could enable learners to acquire the historical interactive knowledge that are related to the specific geographical location. Through such direct interaction with location-based information provided by AR-based M-learning technology, the knowledge acquisition efficiency can be significantly boosted. The designed HTT system not only focuses on student learning management module but also provides teaching material management module for teachers. The conducted experiments on the elementary school student successfully prove that HTT system is an effective scaffolding tool for the novice teachers as well as a helpful assistant to the experienced teachers.","PeriodicalId":432222,"journal":{"name":"2014 IIAI 3rd International Conference on Advanced Applied Informatics","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123535475","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 : 2014-12-01DOI: 10.1109/IIAI-AAI.2014.133
K. Funaki, T. Hochin, Hiroki Nomiya, H. Nakanishi, M. Kojima
This paper proposes a parallel indexing scheme of a large amount of data in order to resolve the issues about time limitation. Three kinds of computing-nodes are introduced. These are reception-nodes, representative-nodes, and normalnodes. A reception-node receives data for insertion. A representative-node receives queries. Normal-nodes retrieve data from indexes. Here, three kinds of indexes are introduced. These are a whole-index, a partial-index, and a reception-index. In a partial-index, data are stored. In a whole-index, partial-indexes are stored as its data. In a reception-index, additional data are stored. The reception-index is moved to a normal-node, and becomes a partial-index. The proposed scheme is also a data distribution scheme for shortening the insertion time. A reception-node accepts additional data even if the index is already built.
{"title":"Parallel Indexing Scheme for Data Intensive Applications","authors":"K. Funaki, T. Hochin, Hiroki Nomiya, H. Nakanishi, M. Kojima","doi":"10.1109/IIAI-AAI.2014.133","DOIUrl":"https://doi.org/10.1109/IIAI-AAI.2014.133","url":null,"abstract":"This paper proposes a parallel indexing scheme of a large amount of data in order to resolve the issues about time limitation. Three kinds of computing-nodes are introduced. These are reception-nodes, representative-nodes, and normalnodes. A reception-node receives data for insertion. A representative-node receives queries. Normal-nodes retrieve data from indexes. Here, three kinds of indexes are introduced. These are a whole-index, a partial-index, and a reception-index. In a partial-index, data are stored. In a whole-index, partial-indexes are stored as its data. In a reception-index, additional data are stored. The reception-index is moved to a normal-node, and becomes a partial-index. The proposed scheme is also a data distribution scheme for shortening the insertion time. A reception-node accepts additional data even if the index is already built.","PeriodicalId":432222,"journal":{"name":"2014 IIAI 3rd International Conference on Advanced Applied Informatics","volume":"2150 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130030851","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 : 2014-12-01DOI: 10.1109/IIAI-AAI.2014.52
Y. Yamashita, Yuuki Shiiba, Noriko Horibe, S. Aoqui
Since a number of farmers has been decreasing in recent years, shortage of work force became one of the most serious problems for many farmhouses. In order to solve this problem, it is important to develop an effective system to support farmer's works. Thus, in this research, we construct a base system for realizing an automatic control of environment of farmlands. In our experiment, crops are cultivated in plastic greenhouse equipped with some sensors for observation about the environmental data. The environmental data is continuously stored to a server system, and the data is analyzed in order to extract environmental features of farmland by using a Web system which was constructed by our research.
{"title":"Development of Web System for Estimating Environmental Features of Farmland","authors":"Y. Yamashita, Yuuki Shiiba, Noriko Horibe, S. Aoqui","doi":"10.1109/IIAI-AAI.2014.52","DOIUrl":"https://doi.org/10.1109/IIAI-AAI.2014.52","url":null,"abstract":"Since a number of farmers has been decreasing in recent years, shortage of work force became one of the most serious problems for many farmhouses. In order to solve this problem, it is important to develop an effective system to support farmer's works. Thus, in this research, we construct a base system for realizing an automatic control of environment of farmlands. In our experiment, crops are cultivated in plastic greenhouse equipped with some sensors for observation about the environmental data. The environmental data is continuously stored to a server system, and the data is analyzed in order to extract environmental features of farmland by using a Web system which was constructed by our research.","PeriodicalId":432222,"journal":{"name":"2014 IIAI 3rd International Conference on Advanced Applied Informatics","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127777976","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 : 2014-12-01DOI: 10.1109/IIAI-AAI.2014.177
Shota Murayama, Ippei Torii, N. Ishii
Recently, Projection Mapping is attracting attention as a new approach for visual expression method. In order to perform large-scale Projection Mapping, multiple projectors are required. In this paper, we propose a new representation technique by various attempts. To determine more impressive visual expression, we have developed Projection Mapping and devised Prodigious Mapping. We have set the projector not to project from many directions, but from one direction. We have been pursuing the possibility that we could use Projection Mapping not only as one of the movie technique but also as a practical approach into a wide range of fields, such as coordination of the shopping mall as regional contribution, transmission of academic contents in the science museum, projection to the historic building to inform the history and culture and so on. We developed the new projection method, "Gem Mapping", specializing for indoor settings. In this method, we make objections made with white boards and set them on a wall inside of a building. We create big gems on the wall by projecting video to the objects. Gem Mapping can set inside the building permanently and reduce the costs. We use touch sensor to detect the motions of people and change images to create interactive Projection Mapping. Gem Mapping is a new advertising media to be used in a lot of commercial facilities as digital signage.
{"title":"Development of Projection Mapping with Utility of Digital Signage","authors":"Shota Murayama, Ippei Torii, N. Ishii","doi":"10.1109/IIAI-AAI.2014.177","DOIUrl":"https://doi.org/10.1109/IIAI-AAI.2014.177","url":null,"abstract":"Recently, Projection Mapping is attracting attention as a new approach for visual expression method. In order to perform large-scale Projection Mapping, multiple projectors are required. In this paper, we propose a new representation technique by various attempts. To determine more impressive visual expression, we have developed Projection Mapping and devised Prodigious Mapping. We have set the projector not to project from many directions, but from one direction. We have been pursuing the possibility that we could use Projection Mapping not only as one of the movie technique but also as a practical approach into a wide range of fields, such as coordination of the shopping mall as regional contribution, transmission of academic contents in the science museum, projection to the historic building to inform the history and culture and so on. We developed the new projection method, \"Gem Mapping\", specializing for indoor settings. In this method, we make objections made with white boards and set them on a wall inside of a building. We create big gems on the wall by projecting video to the objects. Gem Mapping can set inside the building permanently and reduce the costs. We use touch sensor to detect the motions of people and change images to create interactive Projection Mapping. Gem Mapping is a new advertising media to be used in a lot of commercial facilities as digital signage.","PeriodicalId":432222,"journal":{"name":"2014 IIAI 3rd International Conference on Advanced Applied Informatics","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121060827","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 : 2014-12-01DOI: 10.1109/IIAI-AAI.2014.93
A. Bossard
Being located on the Pacific Ring of Fire, Japan has an important seismic activity. Earthquake forecasting is thus a critical topic for the archipelago, and it is actively researched. Although the long-term objective remains seismic prediction accuracy, in this study, rather than focusing directly on prediction, we shall review and analyse recent past seismic data aiming at deducing patterns depending on, for instance, seismic intensities and geographical locations. In practice, we shall investigate several parameters for the application of the Poisson distribution and measure their impact on seismic probabilities and correspondence with past data.
{"title":"Analysis of the Poisson Distribution Applicability to the Japanese Seismic Activity","authors":"A. Bossard","doi":"10.1109/IIAI-AAI.2014.93","DOIUrl":"https://doi.org/10.1109/IIAI-AAI.2014.93","url":null,"abstract":"Being located on the Pacific Ring of Fire, Japan has an important seismic activity. Earthquake forecasting is thus a critical topic for the archipelago, and it is actively researched. Although the long-term objective remains seismic prediction accuracy, in this study, rather than focusing directly on prediction, we shall review and analyse recent past seismic data aiming at deducing patterns depending on, for instance, seismic intensities and geographical locations. In practice, we shall investigate several parameters for the application of the Poisson distribution and measure their impact on seismic probabilities and correspondence with past data.","PeriodicalId":432222,"journal":{"name":"2014 IIAI 3rd International Conference on Advanced Applied Informatics","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121071941","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 : 2014-12-01DOI: 10.1109/IIAI-AAI.2014.171
Takeshi Yonesaka, N. Kuwahara, K. Morimoto
In this study we propose the system for searching scenes from the video recorded by the wearable camera when people leave their valuable objects. Our proposed system analyses the movement of the hands by using various parameters in order to identify the actions that the patient hides the object and extracts scenes when the patient hides the object. By using this system the dementia patient and the caregiver can easily find the object that the dementia patient hides without a doubt the people around them when he/she develops delusion of being stolen.
{"title":"A Supporting System for Finding Lost Objects for Dementia Patient and Caregiver by Image Recognition","authors":"Takeshi Yonesaka, N. Kuwahara, K. Morimoto","doi":"10.1109/IIAI-AAI.2014.171","DOIUrl":"https://doi.org/10.1109/IIAI-AAI.2014.171","url":null,"abstract":"In this study we propose the system for searching scenes from the video recorded by the wearable camera when people leave their valuable objects. Our proposed system analyses the movement of the hands by using various parameters in order to identify the actions that the patient hides the object and extracts scenes when the patient hides the object. By using this system the dementia patient and the caregiver can easily find the object that the dementia patient hides without a doubt the people around them when he/she develops delusion of being stolen.","PeriodicalId":432222,"journal":{"name":"2014 IIAI 3rd International Conference on Advanced Applied Informatics","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114769071","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 : 2014-12-01DOI: 10.1109/IIAI-AAI.2014.104
Zeng Kai, Yue-jiao Gong, Jun Zhang
Nowadays real-time traffic signal control is a crucial issue with potential benefits in the fields of traffic control, environmental pollution, and energy utilization. In the literature, few related studies have been done with dynamic evolutionary algorithms. In this paper, we proposed a strategy using Collaborative Evolutionary-Swarm Optimization (CESO), which is able to track time-varying optimal solutions effectively. We use the simulator of urban mobility (SUMO), a popular traffic simulator to generate traffic flows. A grid traffic network is designed with several scenarios to simulate changes of traffic flows captured by traffic monitors. We test different traffic changes in the network using the proposed strategy and compare its performance with a traditional evolutionary algorithm. Experimental results show that our algorithm can obtain promising configuration of traffic light cycles and reduce the average delay time of all vehicles in various scenarios.
{"title":"Real-Time Traffic Signal Control with Dynamic Evolutionary Computation","authors":"Zeng Kai, Yue-jiao Gong, Jun Zhang","doi":"10.1109/IIAI-AAI.2014.104","DOIUrl":"https://doi.org/10.1109/IIAI-AAI.2014.104","url":null,"abstract":"Nowadays real-time traffic signal control is a crucial issue with potential benefits in the fields of traffic control, environmental pollution, and energy utilization. In the literature, few related studies have been done with dynamic evolutionary algorithms. In this paper, we proposed a strategy using Collaborative Evolutionary-Swarm Optimization (CESO), which is able to track time-varying optimal solutions effectively. We use the simulator of urban mobility (SUMO), a popular traffic simulator to generate traffic flows. A grid traffic network is designed with several scenarios to simulate changes of traffic flows captured by traffic monitors. We test different traffic changes in the network using the proposed strategy and compare its performance with a traditional evolutionary algorithm. Experimental results show that our algorithm can obtain promising configuration of traffic light cycles and reduce the average delay time of all vehicles in various scenarios.","PeriodicalId":432222,"journal":{"name":"2014 IIAI 3rd International Conference on Advanced Applied Informatics","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130178887","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：