the Robot World Cup is the largest mobile robot event and the most important internationalconference on AI and robotics at present. RoboCup is an attempt to promote AI and robotics research by providing a common task...
详细信息
the Robot World Cup is the largest mobile robot event and the most important internationalconference on AI and robotics at present. RoboCup is an attempt to promote AI and robotics research by providing a common task for evaluation of various theories, algorithms, and agent architectures. this paper studies the theoretical and technical issues of the application of the expert system for robot planning theory to RoboCup. this paper gives a primary introduction of the expert system and the robot planning, the content includes the theory of the robot planning based on expert system and the framework of the system that based on the theory. Finally, its application of the framework to RoboCup and how machinelearning can be integrated in the system are also studied in this paper.
In this paper, the development and evaluation of a computer based multimedia learning environment capable of supporting group working is reported. the application developed in this study was used in a Further Educatio...
详细信息
ISBN:
(纸本)3540424067
In this paper, the development and evaluation of a computer based multimedia learning environment capable of supporting group working is reported. the application developed in this study was used in a Further Education (FE) college by tutors and students following a catering course, Learners engaged in the application, performing a range of tasks, based on group working and role playing both on and off-computer. Although no significant difference was found between performance in individual and group work it was found that learners and teachers valued the approach used and performed at least as well on the course than in previous years.
Defining adequate similarity measures is one of the most difficult tasks when developing CBR applications. Unfortunately, only a limited number of techniques for supporting this task by using machinelearning techniqu...
详细信息
ISBN:
(纸本)3540423583
Defining adequate similarity measures is one of the most difficult tasks when developing CBR applications. Unfortunately, only a limited number of techniques for supporting this task by using machinelearning techniques have been developed up to now. In this paper, a new framework for learning similarity measures is presented. the main advantage of this approach is its generality, because its application is not restricted to classification tasks in contrast to other already known algorithms. A first refinement of the introduced framework for learning feature weights is described and finally some preliminary experimental results are presented.
In this paper, methods of choosing a vehicle out of an image are explored. Digital images are taken from a monocular camera. Image processing techniques are applied to each single frame picture to create the feature v...
详细信息
ISBN:
(纸本)0819441937
In this paper, methods of choosing a vehicle out of an image are explored. Digital images are taken from a monocular camera. Image processing techniques are applied to each single frame picture to create the feature vector. Finally the resulting features are used to classify whether there is a car in the picture or not using support vector machines. the result are compared to those obtained using a neural network. A discussion on techniques to enhance the feature vector and th results from bothlearningmachines will be included.
First, the paper investigates incremental knowledge discovery(IKD) in which the knowledge obtained is reapplied in the discovery process. then we realize the algorithm application in color matching method (CMM), findi...
详细信息
ISBN:
(纸本)3540427325
First, the paper investigates incremental knowledge discovery(IKD) in which the knowledge obtained is reapplied in the discovery process. then we realize the algorithm application in color matching method (CMM), finding some laws in secondary colors data and their relations with pure color data. Finally, the experiment result that is fairly satisfying is given.
the proceedings contain 53 papers. the special focus in this conference is on Case-Based Reasoning. the topics include: Highlights of the european INRECA projects;a challenging CBR application;similarity assessment fo...
ISBN:
(纸本)3540423583
the proceedings contain 53 papers. the special focus in this conference is on Case-Based Reasoning. the topics include: Highlights of the european INRECA projects;a challenging CBR application;similarity assessment for relational CBR;acquiring customer preferences from return-set selections;the role of information extraction for textual CBR;an attribute graph approach;ranking algorithms for costly similarity measures;a fuzzy-rough approach for case base maintenance;learning and applying case-based adaptation knowledge;case representation issues for case-based reasoning from ensemble research;a declarative similarity framework for knowledge intensive CBR;classification based retrieval using formal concept analysis;conversational case-based planning for agent team coordination;a hybrid approach for the management of FAQ documents in latin languages;taxonomic conversational case-based reasoning;a case-based reasoning view of automated collaborative filtering;a case-based approach to tailoring software processes;the conflict graph for maintaining case-based reasoning systems;issues on the effective use of CBR technology for software project prediction;incremental case-based plan recognition using state indices;a similarity-based approach to attribute selection in user-adaptive sales dialogs;exploiting multiple case bases.
Adaptation is an important step in CBR when applied to design tasks. However adaptation knowledge can be difficult to acquire directly from an expert. Nevertheless, CBR tools provide few facilities to assist withthe ...
详细信息
ISBN:
(纸本)3540423583
Adaptation is an important step in CBR when applied to design tasks. However adaptation knowledge can be difficult to acquire directly from an expert. Nevertheless, CBR tools provide few facilities to assist withthe acquisition of adaptation knowledge. this paper considers a special class of design task, where a component-based solution can be developed in stages, and suggests adaptation knowledge that is suited tu CBR systems for component-based design. A case-based adaptation is proposed where the adaptation cases are generated from the original problem-solving case-base, and so knowledge acquisition is automated. Both numeric and nominal targets are adapted, although a different case-based adaptation is applied for each. the gains of adaptation are presented for a tablet formulation application, although the approach is suited for other formulation and configuration tasks that apply a component-based approach to design. the learned adaptation knowledge is understandable to the expert, withthe effect that he can criticise the content and refine the knowledge if necessary. Results are promising but the case-based adaptation systems offer many opportunities for optimisation and further learning.
We develop novel algorithmic ideas for building a natural language parser grounded upon the hypothesis of incrementality, which is widely supported by experimental data as a model of human parsing. Our proposal relies...
详细信息
We develop novel algorithmic ideas for building a natural language parser grounded upon the hypothesis of incrementality, which is widely supported by experimental data as a model of human parsing. Our proposal relies on a machinelearning technique for predicting the correctness of partial syntactic structures that are built during the parsing process. A recursive neural network architecture is employed for computing predictions after a training phase on examples drawn from a corpus of parsed sentences, the Penn Treebank. Our results indicate the viability of the approach and lay out the premises for a novel generation of algorithms for natural language processing which more closely model human parsing. these algorithms may prove very useful in the development of efficient parsers and have an immediate application in the construction of semiautomatic annotation tools.
We develop novel algorithmic ideas for building a natural language parser grounded upon the hypothesis of incrementality, which is widely supported by experimental data as a model of human parsing. Our proposal relies...
详细信息
the proceedings contain 47 papers. the special focus in this conference is on Image Information Systems and Video Information Systems. the topics include: the sentient map and its application to the macro-university e...
ISBN:
(纸本)3540411771
the proceedings contain 47 papers. the special focus in this conference is on Image Information Systems and Video Information Systems. the topics include: the sentient map and its application to the macro-university e-learning environment;interaction in content-based image retrieval;automatic video summary and description;relevance ranking of video data using hidden markov model distances and polygon simplification;video clustering using superhistograms in large archives;3D camera movements tracking and indexing based on 2D hints extraction;main mobile object detection and localization in video sequences;statistical motion-based retrieval with partial query;experiments in using visual and textual clues for image hunting on the web;spatial/temporal query processing for information fusion applications;metaphors for visual querying spatio-temporal databases;about ambiguities in visual GIS query languages;visualization of dynamic spatial data and query results over time in a GIS using animation;upgrading color distributions for image retrieval;color normalization for digital video processing;multimedia content filtering, browsing, and matching using MPEG-7 compact color descriptors;shape description for content-based image retrieval;applications to image retrieval using color and texture features;matching shapes with self-intersections;a novel approach for accessing partially indexed image corpora;scale summarized and focused browsing of primitive visual content;integrated browsing and searching of large image collections;a rich get richer strategy for content-based image retrieval;a communication protocol for content-based image retrieval and an integrated multimedia system withlearning capabilities.
暂无评论