Pub Date : 2002-11-04DOI: 10.1109/TAI.2002.1180815
E. Petrov, É. Monfroy
Cooperative constraint solving is an area of constraint programming which develops and studies methods for organizing interaction between constraint solvers. The goal of research in cooperative constraint solving is to discover the interaction patterns which amplify the positive qualities of individual constraint solvers. Analysis of composite solvers is a theoretically and practically important issue in cooperative constraint solving. In this paper we present an analysis by means of set constraints which allows one to reason about the behaviour of composite solvers in terms of pre- and post-conditions.
{"title":"Automatic analysis of composite solvers","authors":"E. Petrov, É. Monfroy","doi":"10.1109/TAI.2002.1180815","DOIUrl":"https://doi.org/10.1109/TAI.2002.1180815","url":null,"abstract":"Cooperative constraint solving is an area of constraint programming which develops and studies methods for organizing interaction between constraint solvers. The goal of research in cooperative constraint solving is to discover the interaction patterns which amplify the positive qualities of individual constraint solvers. Analysis of composite solvers is a theoretically and practically important issue in cooperative constraint solving. In this paper we present an analysis by means of set constraints which allows one to reason about the behaviour of composite solvers in terms of pre- and post-conditions.","PeriodicalId":197064,"journal":{"name":"14th IEEE International Conference on Tools with Artificial Intelligence, 2002. (ICTAI 2002). Proceedings.","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2002-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117146255","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 : 2002-11-04DOI: 10.1109/TAI.2002.1180786
S. Shekhar, Chang-Tien Lu, Pusheng Zhang, Rulin Liu
Data mining is the process of extracting implicit, valuable, and interesting information from large sets of data. Visualization is the process of visually exploring data for pattern and trend analysis, and it is a common method of browsing spatial datasets to look for patterns. However the growing volume of spatial datasets make it difficult for humans to browse such datasets in their entirety, and data mining algorithms are needed to filter out large uninteresting parts of spatial datasets. We construct a web-based visualization software package for observing the summarization of spatial patterns and temporal trends. We also present data mining algorithms for filtering out vast parts of datasets for spatial outlier patterns. The algorithms were implemented and tested with a real-world set of Minneapolis-St. Paul (Twin Cities) traffic data.
{"title":"Data mining for selective visualization of large spatial datasets","authors":"S. Shekhar, Chang-Tien Lu, Pusheng Zhang, Rulin Liu","doi":"10.1109/TAI.2002.1180786","DOIUrl":"https://doi.org/10.1109/TAI.2002.1180786","url":null,"abstract":"Data mining is the process of extracting implicit, valuable, and interesting information from large sets of data. Visualization is the process of visually exploring data for pattern and trend analysis, and it is a common method of browsing spatial datasets to look for patterns. However the growing volume of spatial datasets make it difficult for humans to browse such datasets in their entirety, and data mining algorithms are needed to filter out large uninteresting parts of spatial datasets. We construct a web-based visualization software package for observing the summarization of spatial patterns and temporal trends. We also present data mining algorithms for filtering out vast parts of datasets for spatial outlier patterns. The algorithms were implemented and tested with a real-world set of Minneapolis-St. Paul (Twin Cities) traffic data.","PeriodicalId":197064,"journal":{"name":"14th IEEE International Conference on Tools with Artificial Intelligence, 2002. (ICTAI 2002). Proceedings.","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2002-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116500865","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 : 2002-11-04DOI: 10.1109/TAI.2002.1180845
D. Goldman, Ming Yang, N. Bourbakis
The paper focuses on the development of an efficient and accurate tool for segmenting color images. The segmentation is a problem that has been widely studied since machine vision first evolved as a research area. The neural network segmentation tools and technology developed and presented in this paper show great potential in application where the accuracy is the major factor. Similar requirements exist in the area of medical imaging where segmentation must provide the highest possible precision. The feasibility of the work presented shows a promising future by using a cluster-based approach to training very large feedforward neural networks.
{"title":"A neural network-based segmentation tool for color images","authors":"D. Goldman, Ming Yang, N. Bourbakis","doi":"10.1109/TAI.2002.1180845","DOIUrl":"https://doi.org/10.1109/TAI.2002.1180845","url":null,"abstract":"The paper focuses on the development of an efficient and accurate tool for segmenting color images. The segmentation is a problem that has been widely studied since machine vision first evolved as a research area. The neural network segmentation tools and technology developed and presented in this paper show great potential in application where the accuracy is the major factor. Similar requirements exist in the area of medical imaging where segmentation must provide the highest possible precision. The feasibility of the work presented shows a promising future by using a cluster-based approach to training very large feedforward neural networks.","PeriodicalId":197064,"journal":{"name":"14th IEEE International Conference on Tools with Artificial Intelligence, 2002. (ICTAI 2002). Proceedings.","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2002-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122818692","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 : 2002-11-04DOI: 10.1109/TAI.2002.1180834
Dimitris Kalles, Eirini Ntoutsi
Reinforcement learning is considered as one of the most suitable and prominent methods for solving game problems due to its capability to discover good strategies by extended se self-training and limited initial knowledge. In this paper we elaborate on using reinforcement learning for verifying game designs and playing strategies. Specifically, we examine a new strategy game that has been trained on self-playing games and analyze the game performance after human interaction. We demonstrate, through selected game instances, the impact of human interference to the learning process, and eventually the game design.
{"title":"Interactive verification of game design and playing strategies","authors":"Dimitris Kalles, Eirini Ntoutsi","doi":"10.1109/TAI.2002.1180834","DOIUrl":"https://doi.org/10.1109/TAI.2002.1180834","url":null,"abstract":"Reinforcement learning is considered as one of the most suitable and prominent methods for solving game problems due to its capability to discover good strategies by extended se self-training and limited initial knowledge. In this paper we elaborate on using reinforcement learning for verifying game designs and playing strategies. Specifically, we examine a new strategy game that has been trained on self-playing games and analyze the game performance after human interaction. We demonstrate, through selected game instances, the impact of human interference to the learning process, and eventually the game design.","PeriodicalId":197064,"journal":{"name":"14th IEEE International Conference on Tools with Artificial Intelligence, 2002. (ICTAI 2002). Proceedings.","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2002-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130332580","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 : 2002-11-04DOI: 10.1109/TAI.2002.1180781
R. Brause
The early prediction of mortality is one of the unresolved tasks in intensive care medicine. This paper models medical symptoms as observations cased by transitions between hidden Markov states. Learning the underlying state transition probabilities results in a prediction probability success of about 91%. The results are discussed and put in relation to the model used. Finally, the rationales for using the model are reflected: Are there states in the septic shock data?.
{"title":"About adaptive state knowledge extraction for septic shock mortality prediction","authors":"R. Brause","doi":"10.1109/TAI.2002.1180781","DOIUrl":"https://doi.org/10.1109/TAI.2002.1180781","url":null,"abstract":"The early prediction of mortality is one of the unresolved tasks in intensive care medicine. This paper models medical symptoms as observations cased by transitions between hidden Markov states. Learning the underlying state transition probabilities results in a prediction probability success of about 91%. The results are discussed and put in relation to the model used. Finally, the rationales for using the model are reflected: Are there states in the septic shock data?.","PeriodicalId":197064,"journal":{"name":"14th IEEE International Conference on Tools with Artificial Intelligence, 2002. (ICTAI 2002). Proceedings.","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2002-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124525892","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 : 2002-11-04DOI: 10.1109/TAI.2002.1180783
Yan Liu, T. Menzies, B. Cukic
Adaptive systems are systems whose function evolves while adapting to current environmental conditions, Due to the real-time adaptation, newly learned data have a significant impact on system behavior When online adaptation is included in system control, anomalies could cause abrupt loss of system functionality and possibly result in a failure. In this paper we present a framework for reasoning about the online adaptation problem. We describe a machine learning tool that sniffs data and detects anomalies before they are passed to the adaptive components for learning. Anomaly detection is based on distance computation. An algorithm for framework evaluation as well as sample implementation and empirical results are discussed. The method we propose is simple and reasonably effective, thus it can be easily adopted for testing.
{"title":"Data sniffing - monitoring of machine learning for online adaptive systems","authors":"Yan Liu, T. Menzies, B. Cukic","doi":"10.1109/TAI.2002.1180783","DOIUrl":"https://doi.org/10.1109/TAI.2002.1180783","url":null,"abstract":"Adaptive systems are systems whose function evolves while adapting to current environmental conditions, Due to the real-time adaptation, newly learned data have a significant impact on system behavior When online adaptation is included in system control, anomalies could cause abrupt loss of system functionality and possibly result in a failure. In this paper we present a framework for reasoning about the online adaptation problem. We describe a machine learning tool that sniffs data and detects anomalies before they are passed to the adaptive components for learning. Anomaly detection is based on distance computation. An algorithm for framework evaluation as well as sample implementation and empirical results are discussed. The method we propose is simple and reasonably effective, thus it can be easily adopted for testing.","PeriodicalId":197064,"journal":{"name":"14th IEEE International Conference on Tools with Artificial Intelligence, 2002. (ICTAI 2002). Proceedings.","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2002-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126223135","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 : 2002-11-04DOI: 10.1109/TAI.2002.1180846
Chi-Hung Chi, Chen Ding, Kwok-Yan Lam
The relevance of a Web document could be measured not only by its text content, but also by some other factors such as the link connectivity and usage patterns. In previous data fusion researches, the text is the only source to determine the relevance, and only the different runs (e.g. by different retrieval models, different query or document representations) on this same source are combined. It is the purpose of this paper to investigate whether the different sources can be combined to determine the relevance with a better accuracy than any single source. We conducted a preliminary experiment to test its feasibility and effectiveness and a positive result was obtained.
{"title":"Study for fusion of different sources to determine relevance","authors":"Chi-Hung Chi, Chen Ding, Kwok-Yan Lam","doi":"10.1109/TAI.2002.1180846","DOIUrl":"https://doi.org/10.1109/TAI.2002.1180846","url":null,"abstract":"The relevance of a Web document could be measured not only by its text content, but also by some other factors such as the link connectivity and usage patterns. In previous data fusion researches, the text is the only source to determine the relevance, and only the different runs (e.g. by different retrieval models, different query or document representations) on this same source are combined. It is the purpose of this paper to investigate whether the different sources can be combined to determine the relevance with a better accuracy than any single source. We conducted a preliminary experiment to test its feasibility and effectiveness and a positive result was obtained.","PeriodicalId":197064,"journal":{"name":"14th IEEE International Conference on Tools with Artificial Intelligence, 2002. (ICTAI 2002). Proceedings.","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2002-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126383381","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 : 2002-11-04DOI: 10.1109/TAI.2002.1180838
Chi-Hung Chi, John Sim, Kwok-Yan Lam
This paper describes a novel concept of agent warehouse. Non-mobile Web agents typically operate from their users' computer and make request for data possibly from a very far location. In addition, much of this data will be irrelevant to the user, thus aggravating the bandwidth scarcity problem of the Internet. With current mobile agent paradigm, many of these problems such as bandwidth reduction and off-line autonomous negotiation are solved. However, this paradigm does have some significant limitations in its common deployment scenarios; system resource consumption, server collaboration, and accumulated agent size along the travelling path, etc. are some typical ones. These limitations are becoming more important when multiple visits to the same server host are required: updating time of host information is nondeterministic and the decision of negotiation is also not simultaneous. In this paper, the intermediate "proxy-like" agent warehouse is proposed to address these issues. The agent warehouse locates near the data sources and supports agent execution, thus allowing agents to operate much closer to these data sources and minimising the effect of discarded search results. In addition, it is able to provide more resources than a normal Web server host does as it is dedicated to cater for agents. More importantly, even if the remote site does not support agent execution, the agent will still be able to complete its task through the warehouse. This changes the typical approach of how agents can be deployed by providing a more generic, flexible system environment for agents to execute.
{"title":"Agent warehouse: a new paradigm for mobile agent deployment","authors":"Chi-Hung Chi, John Sim, Kwok-Yan Lam","doi":"10.1109/TAI.2002.1180838","DOIUrl":"https://doi.org/10.1109/TAI.2002.1180838","url":null,"abstract":"This paper describes a novel concept of agent warehouse. Non-mobile Web agents typically operate from their users' computer and make request for data possibly from a very far location. In addition, much of this data will be irrelevant to the user, thus aggravating the bandwidth scarcity problem of the Internet. With current mobile agent paradigm, many of these problems such as bandwidth reduction and off-line autonomous negotiation are solved. However, this paradigm does have some significant limitations in its common deployment scenarios; system resource consumption, server collaboration, and accumulated agent size along the travelling path, etc. are some typical ones. These limitations are becoming more important when multiple visits to the same server host are required: updating time of host information is nondeterministic and the decision of negotiation is also not simultaneous. In this paper, the intermediate \"proxy-like\" agent warehouse is proposed to address these issues. The agent warehouse locates near the data sources and supports agent execution, thus allowing agents to operate much closer to these data sources and minimising the effect of discarded search results. In addition, it is able to provide more resources than a normal Web server host does as it is dedicated to cater for agents. More importantly, even if the remote site does not support agent execution, the agent will still be able to complete its task through the warehouse. This changes the typical approach of how agents can be deployed by providing a more generic, flexible system environment for agents to execute.","PeriodicalId":197064,"journal":{"name":"14th IEEE International Conference on Tools with Artificial Intelligence, 2002. (ICTAI 2002). Proceedings.","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2002-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130140137","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：