P. V. Maanen, Francien Wisse, J. Diggelen, R. Beun
Problems with estimating trust in information sources are common in time constraining and ambiguous situations and often lead to a decrease of team performance. Humans lack the resources to track the integrity of information and thus tend to over- or under-rely on advice from support systems. Two types of adaptive team support have been developed and evaluated that are intended to support human-computer teams in estimating trust appropriately and making appropriate reliance decisions thereof. The first adaptive system (graphical support) supports by communicating the estimated degree of over- or under-trust. The second system (adaptive autonomy) takes over a reliance decision when this estimation exceeds a certain threshold. The two types of support were implemented in a multi-agent environment where human operators and Unmanned Aerial Vehicles (UAVs) work together on a target classification task. We evaluated the two support types in terms of team performance, satisfaction and effectiveness and obtained promising results.
{"title":"Effects of Reliance Support on Team Performance by Advising and Adaptive Autonomy","authors":"P. V. Maanen, Francien Wisse, J. Diggelen, R. Beun","doi":"10.1109/WI-IAT.2011.117","DOIUrl":"https://doi.org/10.1109/WI-IAT.2011.117","url":null,"abstract":"Problems with estimating trust in information sources are common in time constraining and ambiguous situations and often lead to a decrease of team performance. Humans lack the resources to track the integrity of information and thus tend to over- or under-rely on advice from support systems. Two types of adaptive team support have been developed and evaluated that are intended to support human-computer teams in estimating trust appropriately and making appropriate reliance decisions thereof. The first adaptive system (graphical support) supports by communicating the estimated degree of over- or under-trust. The second system (adaptive autonomy) takes over a reliance decision when this estimation exceeds a certain threshold. The two types of support were implemented in a multi-agent environment where human operators and Unmanned Aerial Vehicles (UAVs) work together on a target classification task. We evaluated the two support types in terms of team performance, satisfaction and effectiveness and obtained promising results.","PeriodicalId":128421,"journal":{"name":"2011 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130236147","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}
Qiuyan Zhong, Xiaonan Zhang, Jiangnan Qiu, Gang Qu
How to enhance technological capability of the software outsourcing enterprise is a focal issue in theory study and practice. According to the different executives of enterprise R & D investment, the paper builds the dynamics model of technological capability of software outsourcing enterprise, and verifies the rationality of the model by using vensim software with neusoft group data. Developing scenarios of enterprise technological capabilities of in-house research and technological cooperation research are discussed. The influence of R&D efficiency and government's indirect support on technological capability is analyzed. The research shows that the expansion of R&D investment, improving R & D efficiency and strengthening the intensity of tax incentives have a greater role in developing technological capability.
{"title":"Technological Capability Enhancement Mechanism of Software Outsourcing Enterprises","authors":"Qiuyan Zhong, Xiaonan Zhang, Jiangnan Qiu, Gang Qu","doi":"10.1109/WI-IAT.2011.100","DOIUrl":"https://doi.org/10.1109/WI-IAT.2011.100","url":null,"abstract":"How to enhance technological capability of the software outsourcing enterprise is a focal issue in theory study and practice. According to the different executives of enterprise R & D investment, the paper builds the dynamics model of technological capability of software outsourcing enterprise, and verifies the rationality of the model by using vensim software with neusoft group data. Developing scenarios of enterprise technological capabilities of in-house research and technological cooperation research are discussed. The influence of R&D efficiency and government's indirect support on technological capability is analyzed. The research shows that the expansion of R&D investment, improving R & D efficiency and strengthening the intensity of tax incentives have a greater role in developing technological capability.","PeriodicalId":128421,"journal":{"name":"2011 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125530030","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 article proposes a MAS architecture for network diagnosis under uncertainty. Network diagnosis is divided into two inference processes: hypothesis generation and hypothesis confirmation. The first process is distributed among several agents based on a MSBN, while the second one is carried out by agents using semantic reasoning. A diagnosis ontology has been defined in order to combine both inference processes. To drive the deliberation process, dynamic data about the influence of observations are taken during diagnosis process. In order to achieve quick and reliable diagnoses, this influence is used to choose the best action to perform. This approach has been evaluated in a P2P video streaming scenario. Computational and time improvements are highlight as conclusions.
{"title":"Multi-agent Architecture for Heterogeneous Reasoning under Uncertainty Combining MSBN and Ontologies in Distributed Network Diagnosis","authors":"Álvaro Carrera, C. Iglesias","doi":"10.1109/WI-IAT.2011.106","DOIUrl":"https://doi.org/10.1109/WI-IAT.2011.106","url":null,"abstract":"This article proposes a MAS architecture for network diagnosis under uncertainty. Network diagnosis is divided into two inference processes: hypothesis generation and hypothesis confirmation. The first process is distributed among several agents based on a MSBN, while the second one is carried out by agents using semantic reasoning. A diagnosis ontology has been defined in order to combine both inference processes. To drive the deliberation process, dynamic data about the influence of observations are taken during diagnosis process. In order to achieve quick and reliable diagnoses, this influence is used to choose the best action to perform. This approach has been evaluated in a P2P video streaming scenario. Computational and time improvements are highlight as conclusions.","PeriodicalId":128421,"journal":{"name":"2011 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127174273","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 presents the community set space canvas, a triangular canvas where the results of community finding algorithms can be plotted for comparison. The points of the triangle represent trivial sets, such as the set of one large community, and the edges are populated by well known set types, such as disjoint communities.
{"title":"Exploring the Community Set Space","authors":"J. Scripps","doi":"10.1109/WI-IAT.2011.75","DOIUrl":"https://doi.org/10.1109/WI-IAT.2011.75","url":null,"abstract":"This paper presents the community set space canvas, a triangular canvas where the results of community finding algorithms can be plotted for comparison. The points of the triangle represent trivial sets, such as the set of one large community, and the edges are populated by well known set types, such as disjoint communities.","PeriodicalId":128421,"journal":{"name":"2011 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114402654","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}
Cross-lingual projection encounters two major challenges, the noise from word-alignment error and the syntactic divergences between two languages. To solve these two problems, a semi-supervised learning framework of cross-lingual projection is proposed to get better annotations using parallel data. Moreover, a projection model is introduced to model the projection process of labeling from the resource-rich language to the resource-scarce language. The projection model, together with the traditional target model of cross-lingual projection, can be seen as two views of parallel data. Utilizing these two views, an extension of co-training algorithm to structured predictions is designed to boost the result of the two models. Experiments show that the proposed cross-lingual projection method improves the accuracy in the task of POS-tagging projection. And using only one-to-one alignments proves to lead to more accurate results than using all kinds of alignment information.
{"title":"Semi-supervised Learning Framework for Cross-Lingual Projection","authors":"PengLong Hu, Mo Yu, Jing Li, Conghui Zhu, T. Zhao","doi":"10.1109/WI-IAT.2011.58","DOIUrl":"https://doi.org/10.1109/WI-IAT.2011.58","url":null,"abstract":"Cross-lingual projection encounters two major challenges, the noise from word-alignment error and the syntactic divergences between two languages. To solve these two problems, a semi-supervised learning framework of cross-lingual projection is proposed to get better annotations using parallel data. Moreover, a projection model is introduced to model the projection process of labeling from the resource-rich language to the resource-scarce language. The projection model, together with the traditional target model of cross-lingual projection, can be seen as two views of parallel data. Utilizing these two views, an extension of co-training algorithm to structured predictions is designed to boost the result of the two models. Experiments show that the proposed cross-lingual projection method improves the accuracy in the task of POS-tagging projection. And using only one-to-one alignments proves to lead to more accurate results than using all kinds of alignment information.","PeriodicalId":128421,"journal":{"name":"2011 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125995203","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 article addresses the coalition formation problem in a multi-agent context where agents plan their activities dynamically and use these plans to coordinate their actions and form suitable coalitions. In most coalition formation methods, when negotiating their coalitions the agents focus mainly on the immediate tasks to be executed, in order to decide which coalitions to form. Agents relegate the negotiations of the coalitions for their subsequent tasks to later stages of the coordination process. This paper deals with this issue and proposes a new coalition formation model which is based on two principles:1) it uses the plans of the agents to guide the search for the coalitions to be formed and shows the significance of not only taking into account the immediate actions of the agents in the coalition formation process, 2) it analyzes the coalition proposals already suggested by other agents in order to derive their intentions and thus facilitate the negotiations fort he coalitions. First we analyse and develop the constraints that should be enforced on self-interested agents, in order to form suitable coalitions which guarantee significant solution concepts. Then we detail our coalition formation mechanism.
{"title":"A Plan Based Coalition Formation Model for Multi-agent Systems","authors":"Souhila Arib, S. Aknine","doi":"10.1109/WI-IAT.2011.222","DOIUrl":"https://doi.org/10.1109/WI-IAT.2011.222","url":null,"abstract":"This article addresses the coalition formation problem in a multi-agent context where agents plan their activities dynamically and use these plans to coordinate their actions and form suitable coalitions. In most coalition formation methods, when negotiating their coalitions the agents focus mainly on the immediate tasks to be executed, in order to decide which coalitions to form. Agents relegate the negotiations of the coalitions for their subsequent tasks to later stages of the coordination process. This paper deals with this issue and proposes a new coalition formation model which is based on two principles:1) it uses the plans of the agents to guide the search for the coalitions to be formed and shows the significance of not only taking into account the immediate actions of the agents in the coalition formation process, 2) it analyzes the coalition proposals already suggested by other agents in order to derive their intentions and thus facilitate the negotiations fort he coalitions. First we analyse and develop the constraints that should be enforced on self-interested agents, in order to form suitable coalitions which guarantee significant solution concepts. Then we detail our coalition formation mechanism.","PeriodicalId":128421,"journal":{"name":"2011 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126330773","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 major potential of agent technologies is the ability to support personalized learning. This is a trend where students are taking more control of their learning in the form of personal choice over topics, activities and tools. In this context, in previous work we presented a multiagent system based on an iterative voting protocol where student agents could vote to decide which courses the university would be running, those courses with little to no interest would be cancelled. This work assumed that the preferences for different courses were independent, which is not always realistic. In this paper, we extend this work and consider complex preferences. In particular, we assume substitutable and complementary preferences between courses. We show that, by using an intelligent voting strategy which tries to predict the voting result, and takes into account the interdependencies between the courses can outperform more naive strategies.
{"title":"An Agent Based Voting System for E-Learning Course Selection Involving Complex Preferences","authors":"A. Aseere, D. Millard, E. Gerding","doi":"10.1109/WI-IAT.2011.238","DOIUrl":"https://doi.org/10.1109/WI-IAT.2011.238","url":null,"abstract":"A major potential of agent technologies is the ability to support personalized learning. This is a trend where students are taking more control of their learning in the form of personal choice over topics, activities and tools. In this context, in previous work we presented a multiagent system based on an iterative voting protocol where student agents could vote to decide which courses the university would be running, those courses with little to no interest would be cancelled. This work assumed that the preferences for different courses were independent, which is not always realistic. In this paper, we extend this work and consider complex preferences. In particular, we assume substitutable and complementary preferences between courses. We show that, by using an intelligent voting strategy which tries to predict the voting result, and takes into account the interdependencies between the courses can outperform more naive strategies.","PeriodicalId":128421,"journal":{"name":"2011 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology","volume":"27 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123077670","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}
Large distributed systems often require intelligent behavior. Although multiagent reinforcement learning can be applied to such systems, several yet unsolved challenges arise due to the large number of simultaneous learners. Among others, these include exponential growth of state-action spaces and coordination. In this work, we deal with these two issues. Therefore, we consider a subclass of stochastic games called cooperative sequential stage games. With the help of a stateless distributed learning algorithm we solve the problem of growing state-action spaces. Then, we present six different techniques to coordinate action selection during the learning process. We prove a property of the learning algorithm that helps to reduce computational costs of one technique. An experimental analysis in a distributed agent partitioning problem with hundreds of agents reveals that the proposed techniques can lead to higher quality solutions and increase convergence speed compared to the basic approach. Some techniques even outperform a state-of-the-art special purpose approach.
{"title":"Coordination in Large Multiagent Reinforcement Learning Problems","authors":"Thomas Kemmerich, H. K. Büning","doi":"10.1109/WI-IAT.2011.44","DOIUrl":"https://doi.org/10.1109/WI-IAT.2011.44","url":null,"abstract":"Large distributed systems often require intelligent behavior. Although multiagent reinforcement learning can be applied to such systems, several yet unsolved challenges arise due to the large number of simultaneous learners. Among others, these include exponential growth of state-action spaces and coordination. In this work, we deal with these two issues. Therefore, we consider a subclass of stochastic games called cooperative sequential stage games. With the help of a stateless distributed learning algorithm we solve the problem of growing state-action spaces. Then, we present six different techniques to coordinate action selection during the learning process. We prove a property of the learning algorithm that helps to reduce computational costs of one technique. An experimental analysis in a distributed agent partitioning problem with hundreds of agents reveals that the proposed techniques can lead to higher quality solutions and increase convergence speed compared to the basic approach. Some techniques even outperform a state-of-the-art special purpose approach.","PeriodicalId":128421,"journal":{"name":"2011 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129503844","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 presents a meaning-based method to distinguish text without or with little semantic content from text that has meaning which can be processed. The basic method assumes that a semantic analyzer will be able to produce less output from semantically less grammatical input text. The method was pilot-tested on a corpus of blog spam. Future improvements, including a method to distinguish semantically unified from semantically disparate text are sketched. The tested method, but even more the projected improvements, open up the way to taking the spam filtering arms race to a new level that is very costly to spam producers.
{"title":"Baseline Semantic Spam Filtering","authors":"Christian F. Hempelmann, Vikas Mehra","doi":"10.1109/WI-IAT.2011.133","DOIUrl":"https://doi.org/10.1109/WI-IAT.2011.133","url":null,"abstract":"This paper presents a meaning-based method to distinguish text without or with little semantic content from text that has meaning which can be processed. The basic method assumes that a semantic analyzer will be able to produce less output from semantically less grammatical input text. The method was pilot-tested on a corpus of blog spam. Future improvements, including a method to distinguish semantically unified from semantically disparate text are sketched. The tested method, but even more the projected improvements, open up the way to taking the spam filtering arms race to a new level that is very costly to spam producers.","PeriodicalId":128421,"journal":{"name":"2011 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology","volume":"818 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132794601","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}
Norms are a way to specify acceptable behaviour in a context. In literature there is a lot of work on norm theories, models and specifications on how agents might take norms into account when reasoning but few practical implementations. In this paper we present a framework and an implementation for norm-oriented planning. Unlike most frameworks, our approach takes into consideration the operationalisation of norms during the plan generation phase. In our framework norms can be obligations or prohibitions which can be violated, and are accompanied by repair norms in case they are breached. Norm operational semantics is expressed as an extension/on top of STRIPS semantics, acting as a form of temporal restrictions over the trajectories (plans) computed by the planner. In combination with the agent's utility functions over the actions, the norm-aware planner computes the most profitable trajectory concluding to a state of the world where no pending obligations exist and any (obligation/prohibition) violation has been handled. An implementation of the framework in PDDL is provided.
{"title":"Norm-Aware Planning: Semantics and Implementation","authors":"Sofia Panagiotidi, Javier Vázquez-Salceda","doi":"10.1109/WI-IAT.2011.249","DOIUrl":"https://doi.org/10.1109/WI-IAT.2011.249","url":null,"abstract":"Norms are a way to specify acceptable behaviour in a context. In literature there is a lot of work on norm theories, models and specifications on how agents might take norms into account when reasoning but few practical implementations. In this paper we present a framework and an implementation for norm-oriented planning. Unlike most frameworks, our approach takes into consideration the operationalisation of norms during the plan generation phase. In our framework norms can be obligations or prohibitions which can be violated, and are accompanied by repair norms in case they are breached. Norm operational semantics is expressed as an extension/on top of STRIPS semantics, acting as a form of temporal restrictions over the trajectories (plans) computed by the planner. In combination with the agent's utility functions over the actions, the norm-aware planner computes the most profitable trajectory concluding to a state of the world where no pending obligations exist and any (obligation/prohibition) violation has been handled. An implementation of the framework in PDDL is provided.","PeriodicalId":128421,"journal":{"name":"2011 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133071332","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：