Green-waved traffic control, which coordinates intersections to allow continuous traffic flow from major directions without unnecessary stops, is one of the most efficient strategies to improve the efficiency of urban transportation. However, in large-scale urban transportation systems, traditional centralized coordination methods suffer bottlenecks in both communication and computation. It is hard to make decentralized control with very limited observation to the whole network or avoid conflict traffic flows within a complex intersection. In this paper, we proposed a novel decentralized, multi-agent based schema for massive traffic lights coordination to promote the green-waved effect. In additional, we use constraint optimization agents within a local intersection to efficiently search for joint activities of the lights. This paper also builds a heuristic algorithm to solve the scalable coordination problem and with our massive urban transportation simulator, we have proved the feasibility of our approach.
{"title":"Green-Waved Cooperative Coordination Algorithm for Decentralized Traffic Control","authors":"Yulin Zhang, Yang Xu, Tingting Sun, Pengfei Liu","doi":"10.1109/WI-IAT.2012.141","DOIUrl":"https://doi.org/10.1109/WI-IAT.2012.141","url":null,"abstract":"Green-waved traffic control, which coordinates intersections to allow continuous traffic flow from major directions without unnecessary stops, is one of the most efficient strategies to improve the efficiency of urban transportation. However, in large-scale urban transportation systems, traditional centralized coordination methods suffer bottlenecks in both communication and computation. It is hard to make decentralized control with very limited observation to the whole network or avoid conflict traffic flows within a complex intersection. In this paper, we proposed a novel decentralized, multi-agent based schema for massive traffic lights coordination to promote the green-waved effect. In additional, we use constraint optimization agents within a local intersection to efficiently search for joint activities of the lights. This paper also builds a heuristic algorithm to solve the scalable coordination problem and with our massive urban transportation simulator, we have proved the feasibility of our approach.","PeriodicalId":220218,"journal":{"name":"2012 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126932332","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}
Qing Cheng, Zhong Liu, Jincai Huang, Cheng Zhu, Yanjun Liu
Community structure is very important for many real-world networks. It has been shown that communities are overlapping and hierarchical. However, most previous methods, based on the graph model, can't investigate these two properties of community structure simultaneously. Moreover, in some cases the use of simple graphs does not provide a complete description of the real-world network. After introducing hyper graphs to describe real-world networks and defining hyper-edge similarity measurement, we propose a Hierarchical Clustering method based on Hyper-edge Similarity (HCHS) to simultaneously detect both the overlapping and hierarchical properties of complex community structure, as well as using the newly introduced community density to evaluate the goodness of a community. The examples of application to real-world networks give excellent results.
{"title":"Hierarchical Clustering Based on Hyper-edge Similarity for Community Detection","authors":"Qing Cheng, Zhong Liu, Jincai Huang, Cheng Zhu, Yanjun Liu","doi":"10.1109/WI-IAT.2012.9","DOIUrl":"https://doi.org/10.1109/WI-IAT.2012.9","url":null,"abstract":"Community structure is very important for many real-world networks. It has been shown that communities are overlapping and hierarchical. However, most previous methods, based on the graph model, can't investigate these two properties of community structure simultaneously. Moreover, in some cases the use of simple graphs does not provide a complete description of the real-world network. After introducing hyper graphs to describe real-world networks and defining hyper-edge similarity measurement, we propose a Hierarchical Clustering method based on Hyper-edge Similarity (HCHS) to simultaneously detect both the overlapping and hierarchical properties of complex community structure, as well as using the newly introduced community density to evaluate the goodness of a community. The examples of application to real-world networks give excellent results.","PeriodicalId":220218,"journal":{"name":"2012 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126791049","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 introduces MinCor (Minimum of Correlations), a decentralized simulated annealing algorithm designed for the data placement in peer-to-peer networks. Its goal is to reduce the correlated failures impact in such data storage systems. This data placement is realized using a multi-agent system which turns the documents into mobile agents flocks. After a network clustering step where highly correlated peers are regrouped together, the flocks executing MinCor are able to find a placement minimizing the number of agents on the same clusters. This placement is obtained in a decentralized way thanks to the environment exploration capabilities of the flocks. A set of experiments are performed on this system in presence of correlated failures. They show that, in practice, the expected placement is well obtained. They also show that, flocks using the MinCor algorithm suffer less simultaneous losses in presence of correlated failures than a mere random placement.
本文介绍了一种用于点对点网络中数据放置的去中心化模拟退火算法MinCor (Minimum of correlation)。其目标是减少此类数据存储系统中相关故障的影响。这种数据放置是使用多代理系统实现的，该系统将文档转换为移动代理群。在将高度相关的节点重新组合在一起的网络聚类步骤之后，执行MinCor的群能够找到最小化同一集群上代理数量的放置。由于羊群的环境探索能力，这种安置是以分散的方式获得的。在存在相关故障的情况下，对该系统进行了一组实验。它们表明，在实践中，预期的安置是很好的。他们还表明，与随机放置相比，使用MinCor算法的鸟群在存在相关故障时遭受的同时损失更少。
{"title":"Reducing Correlated Failures Impact in Peer-to-Peer Storage Systems Using Mobile Agents Flocks","authors":"Benoît Romito, F. Bourdon","doi":"10.1109/WI-IAT.2012.17","DOIUrl":"https://doi.org/10.1109/WI-IAT.2012.17","url":null,"abstract":"This paper introduces MinCor (Minimum of Correlations), a decentralized simulated annealing algorithm designed for the data placement in peer-to-peer networks. Its goal is to reduce the correlated failures impact in such data storage systems. This data placement is realized using a multi-agent system which turns the documents into mobile agents flocks. After a network clustering step where highly correlated peers are regrouped together, the flocks executing MinCor are able to find a placement minimizing the number of agents on the same clusters. This placement is obtained in a decentralized way thanks to the environment exploration capabilities of the flocks. A set of experiments are performed on this system in presence of correlated failures. They show that, in practice, the expected placement is well obtained. They also show that, flocks using the MinCor algorithm suffer less simultaneous losses in presence of correlated failures than a mere random placement.","PeriodicalId":220218,"journal":{"name":"2012 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology","volume":"323 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123649559","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}
Virtual learning environments (VLEs) are online learning systems that are used to enhance a student's learning experience by providing a set of teaching, learning and communication tools. The current VLEs, however, are not fully utilised or exploited to support effective collaborative learning. This paper investigates how to build effective online collaborative virtual learning environments, by exploring the requirements of VLEs from personal users. A prototype is then created to show how the designs of current VLEs can be improved to provide the essential functionalities and ease of use.
{"title":"Investigation and Prototype Design of Collaborative Virtual Learning Enivronments","authors":"M. Darwaish, Fang Wang","doi":"10.1109/WI-IAT.2012.176","DOIUrl":"https://doi.org/10.1109/WI-IAT.2012.176","url":null,"abstract":"Virtual learning environments (VLEs) are online learning systems that are used to enhance a student's learning experience by providing a set of teaching, learning and communication tools. The current VLEs, however, are not fully utilised or exploited to support effective collaborative learning. This paper investigates how to build effective online collaborative virtual learning environments, by exploring the requirements of VLEs from personal users. A prototype is then created to show how the designs of current VLEs can be improved to provide the essential functionalities and ease of use.","PeriodicalId":220218,"journal":{"name":"2012 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129835820","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}
We present a description of our multi-agent system where computational intelligence methods are embodied as software agents. This system is designed in order to allow easy experiments with learning, meta learning, gathering experience based on previous computations, and recommending suitable methods for particular data. The architecture of the system is presented and its meta learning abilities are demonstrated on a set of experiments with neural network models and both evolutionary and local search heuristics.
{"title":"A Novel Meta Learning System and Its Application to Optimization of Computing Agents' Results","authors":"O. Kazík, K. Pesková, M. Pilát, Roman Neruda","doi":"10.1109/WI-IAT.2012.250","DOIUrl":"https://doi.org/10.1109/WI-IAT.2012.250","url":null,"abstract":"We present a description of our multi-agent system where computational intelligence methods are embodied as software agents. This system is designed in order to allow easy experiments with learning, meta learning, gathering experience based on previous computations, and recommending suitable methods for particular data. The architecture of the system is presented and its meta learning abilities are demonstrated on a set of experiments with neural network models and both evolutionary and local search heuristics.","PeriodicalId":220218,"journal":{"name":"2012 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123017160","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 introduces the utilization of data originated in the web user ocular movement to improve the methodology for identifying Website Key objects that was designed by Velasquez and Dujovne through the use of eye tracking tools. Given a website, this methodology takes as input the request register (Web log) of the website, the pages that compose it and the interest of users in the web objects of each page, which is quantified using a survey. Subsequently, the data is transformed and preprocessed before finally applying Web mining algorithms that allow the extraction of the Website Key objects. In this paper, a novel application of the eye tracking technology is proposed, in order to dispense with the survey, that is to say, using a more precise tool to achieve an improvement in the classification of the Website Key objects. It was concluded that eye tracking technology is useful and accurate when it comes to knowing what a user looks at and therefore, what attracts their attention the most. Finally, it was established that there is an improvement of between 15% and 16% when using the information generated by the eye tracker.
{"title":"Improvement of a Methodology for Website Keyobject Identification through the Application of Eye-Tracking Technologies","authors":"Juan Domingo Velásquez-Silva","doi":"10.1109/WI-IAT.2012.182","DOIUrl":"https://doi.org/10.1109/WI-IAT.2012.182","url":null,"abstract":"This paper introduces the utilization of data originated in the web user ocular movement to improve the methodology for identifying Website Key objects that was designed by Velasquez and Dujovne through the use of eye tracking tools. Given a website, this methodology takes as input the request register (Web log) of the website, the pages that compose it and the interest of users in the web objects of each page, which is quantified using a survey. Subsequently, the data is transformed and preprocessed before finally applying Web mining algorithms that allow the extraction of the Website Key objects. In this paper, a novel application of the eye tracking technology is proposed, in order to dispense with the survey, that is to say, using a more precise tool to achieve an improvement in the classification of the Website Key objects. It was concluded that eye tracking technology is useful and accurate when it comes to knowing what a user looks at and therefore, what attracts their attention the most. Finally, it was established that there is an improvement of between 15% and 16% when using the information generated by the eye tracker.","PeriodicalId":220218,"journal":{"name":"2012 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124169364","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}
Since around 2000, many companies have worked to create interorganizational cooperation, which can solve the problem of a lack of resources when creating new business. In the real world, many companies cannot find the holder of necessary resources, and they cannot conduct proper interor-ganizational cooperation. To solve these problems, we propose a business process visualization tool.
{"title":"Prototype of New Business Process Visualization Tool","authors":"A. Nagai, T. Tsuboi, Takayuki Ito","doi":"10.1109/WI-IAT.2012.118","DOIUrl":"https://doi.org/10.1109/WI-IAT.2012.118","url":null,"abstract":"Since around 2000, many companies have worked to create interorganizational cooperation, which can solve the problem of a lack of resources when creating new business. In the real world, many companies cannot find the holder of necessary resources, and they cannot conduct proper interor-ganizational cooperation. To solve these problems, we propose a business process visualization tool.","PeriodicalId":220218,"journal":{"name":"2012 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology","volume":"292 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121478773","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}
Co-Space refers to interactive virtual environment modelled after the real world in terms of look-and-feel, functionalities and services. We have developed a 3D virtual world named Nan yang Technological University (NTU) Co-Space populated with virtual human characters. Three key requirements of realistic virtual humans in the virtual world have been identified, namely (1) autonomy: agents can function on their own, (2) interactivity: agents can interact naturally with players, and (3) personality: agents can exhibit human traits and characteristics. Working towards these challenges, we propose a brain-inspired agent architecture that integrates goal-directed autonomy, natural language interaction and human-like personality. We conducted an evaluative study involving human subjects to assess how virtual characters may enhance user experience in the virtual world. The results show that the fusion ART-based virtual humans receive significantly higher ratings in various performance measures related to user experience, especially Telepresence, Perceived Interactivity and Flow.
{"title":"Agent-Based Virtual Humans in Co-Space: An Evaluative Study","authors":"Yilin Kang, A. Tan, F. Nah","doi":"10.1109/WI-IAT.2012.130","DOIUrl":"https://doi.org/10.1109/WI-IAT.2012.130","url":null,"abstract":"Co-Space refers to interactive virtual environment modelled after the real world in terms of look-and-feel, functionalities and services. We have developed a 3D virtual world named Nan yang Technological University (NTU) Co-Space populated with virtual human characters. Three key requirements of realistic virtual humans in the virtual world have been identified, namely (1) autonomy: agents can function on their own, (2) interactivity: agents can interact naturally with players, and (3) personality: agents can exhibit human traits and characteristics. Working towards these challenges, we propose a brain-inspired agent architecture that integrates goal-directed autonomy, natural language interaction and human-like personality. We conducted an evaluative study involving human subjects to assess how virtual characters may enhance user experience in the virtual world. The results show that the fusion ART-based virtual humans receive significantly higher ratings in various performance measures related to user experience, especially Telepresence, Perceived Interactivity and Flow.","PeriodicalId":220218,"journal":{"name":"2012 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128488105","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}
Yi-feng Zeng, Hua Mao, Prashant Doshi, Yinghui Pan, Jian Luo
Communication is one of central activities in multiagent systems. It enables the knowledge sharing among multiple agents and improves the planning quality in a long run. In this paper, we study communication decision problems in the framework of interactive dynamic influence diagrams~(I-DIDs). I-DIDs are recognized probabilistic graphical models for sequential decision making in uncertain multiagent settings. We extend the representation to explicitly model communication actions as well as their relations to other variables in the domain. The challenging work is on developing an incentive mechanism that drives level 0 agents to learn communication while they act alone in a dynamic environment. We present solutions to the new model and show meaningful communication strategies in a multiagent problem domain.
{"title":"Learning Communication in Interactive Dynamic Influence Diagrams","authors":"Yi-feng Zeng, Hua Mao, Prashant Doshi, Yinghui Pan, Jian Luo","doi":"10.1109/WI-IAT.2012.180","DOIUrl":"https://doi.org/10.1109/WI-IAT.2012.180","url":null,"abstract":"Communication is one of central activities in multiagent systems. It enables the knowledge sharing among multiple agents and improves the planning quality in a long run. In this paper, we study communication decision problems in the framework of interactive dynamic influence diagrams~(I-DIDs). I-DIDs are recognized probabilistic graphical models for sequential decision making in uncertain multiagent settings. We extend the representation to explicitly model communication actions as well as their relations to other variables in the domain. The challenging work is on developing an incentive mechanism that drives level 0 agents to learn communication while they act alone in a dynamic environment. We present solutions to the new model and show meaningful communication strategies in a multiagent problem domain.","PeriodicalId":220218,"journal":{"name":"2012 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology","volume":"4 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125344439","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}
A. T. Mors, C. Witteveen, Charlotte Ipema, F. D. Nijs, Theodor Tsiourakis
In multi-agent route planning, there is a set of autonomous vehicles (agents), each with their own start and destination locations. Agents want to reach their destinations as quickly as possible while avoiding conflicts with other agents. We present a single-agent route planning algorithm that finds an optimal conflict-free route plan given a set of reservations from higher-priority agents. We also present an approach that constructs a conflict-free schedule along a fixed path. In order to obtain low-cost multi-agent plans, the fixed paths must provide the agents with sufficiently different alternatives in case certain parts of the infrastructure are more congested than others. We tried both a k shortest paths algorithm, and an algorithm for node-disjoint paths, and compared both approaches to the routing algorithm, and investigated how performances depend on characteristics of the infrastructure.
{"title":"Empirical Evaluation of Multi-Agent Routing Approaches","authors":"A. T. Mors, C. Witteveen, Charlotte Ipema, F. D. Nijs, Theodor Tsiourakis","doi":"10.1109/WI-IAT.2012.198","DOIUrl":"https://doi.org/10.1109/WI-IAT.2012.198","url":null,"abstract":"In multi-agent route planning, there is a set of autonomous vehicles (agents), each with their own start and destination locations. Agents want to reach their destinations as quickly as possible while avoiding conflicts with other agents. We present a single-agent route planning algorithm that finds an optimal conflict-free route plan given a set of reservations from higher-priority agents. We also present an approach that constructs a conflict-free schedule along a fixed path. In order to obtain low-cost multi-agent plans, the fixed paths must provide the agents with sufficiently different alternatives in case certain parts of the infrastructure are more congested than others. We tried both a k shortest paths algorithm, and an algorithm for node-disjoint paths, and compared both approaches to the routing algorithm, and investigated how performances depend on characteristics of the infrastructure.","PeriodicalId":220218,"journal":{"name":"2012 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126114627","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：