By Topic

2004 International Conference on Machine Learning and Applications, 2004. Proceedings.

16-18 Dec. 2004

Filter Results

Displaying Results 1 - 25 of 74
  • Proceedings of the 2004 International Conference on Machine Learning and Applications

    Publication Year: 2004, Page(s):i - ii
    Request permission for commercial reuse | PDF file iconPDF (59 KB)
    Freely Available from IEEE
  • Foreward

    Publication Year: 2004, Page(s):iii - iv
    Request permission for commercial reuse | PDF file iconPDF (39 KB) | HTML iconHTML
    Freely Available from IEEE
  • Conference organization

    Publication Year: 2004, Page(s):v - viii
    Request permission for commercial reuse | PDF file iconPDF (49 KB)
    Freely Available from IEEE
  • Table of contents

    Publication Year: 2004, Page(s):ix - xiv
    Request permission for commercial reuse | PDF file iconPDF (91 KB)
    Freely Available from IEEE
  • Unsupervised machine learning and cognitive systems in learning user state for context-aware computing

    Publication Year: 2004, Page(s):1 - 2
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (44 KB)

    We at Carnegie Mellon University have pioneered context-aware mobile computing and built their first prototypes, including context-aware mobile phones and a context-aware personal communicator. These prototypes use machine learning and cognitive modeling techniques to derive user state and intent from the devices sensors. Context-aware computing describes the situation where a mobile computer is a... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Data mining for security applications

    Publication Year: 2004, Page(s):3 - 4
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (56 KB) | HTML iconHTML

    Data mining is the process of posing queries and extracting patterns, often previously unknown from large quantities of data using pattern matching or other reasoning techniques. Cyber security is the area that deals with cyber terrorism. We are hearing that cyber attacks will cause corporations billions of dollars. For example, one could masquerade as a legitimate user and swindle say a bank of b... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Identifying word boundaries in handwrittem text

    Publication Year: 2004, Page(s):5 - 9
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (216 KB) | HTML iconHTML

    Recent work on extracting features of gaps in handwritten text allows a classification of these gaps into inter-word and intra-word classes using suitable classification techniques. In the previous work, we apply 5 different supervised classification algorithms from the machine learning field on both the original gap dataset and the gap dataset with the best features selected using mutual informat... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • LASSO: a learning architecture for semantic web ontologies

    Publication Year: 2004, Page(s):10 - 17
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (296 KB) | HTML iconHTML

    Expressing web page content in a way that computers can understand is the key to a semantic web. Generating ontological information from the web automatically using machine learning shows great promise towards this goal. We present LASSO, an architecture that combines distributed components for training web page classifiers via machine learning and information extraction, and then labels new pages... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A naiive bayes learning based website reconfiguration system

    Publication Year: 2004, Page(s):18 - 25
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (289 KB) | HTML iconHTML

    The continuous and sharp growth of web sites in terms of size and complexity has made improving the website organization to facilitate users' navigation something of an emergency. To address this problem, in this paper we propose a website reconfiguration system using the machine learning approach. First, a Naive Bayes Classifier is trained and then applied to identify each page in a web site as i... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A minimum classification error (MCE) framework for generalized linear classifier in machine learning for text categorization/retrieval

    Publication Year: 2004, Page(s):26 - 33
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (287 KB) | HTML iconHTML

    In this paper, we present the theoretical framework of minimum classification error (MCE) training of generalized linear classifiers for text classification. We show that many important text classifiers, either probabilistic or non-probabilistic, can be unified under this framework, and the proposed MCE classifier training approach can be applied to improve the classifier performance. In addition,... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Multi-dimensional sequential web mining by utilizing fuzzy interferencing

    Publication Year: 2004, Page(s):34 - 40
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (265 KB) | HTML iconHTML

    There are several applications of sequential web mining, which is used to find the frequent subsequences in a web log in the World Wide Web (the web). We implemented a tool to analyze the sequential behavior of web log access patterns in multiple-dimensions. Sequences of frequent access patterns may change temporally and spatially. Based on the specified criteria like year, month, day, hours and l... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Two new regularized AdaBoost algorithms

    Publication Year: 2004, Page(s):41 - 48
    Cited by:  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (265 KB) | HTML iconHTML

    AdaBoost rarely suffers from overfitting problems in low noise data cases. However, recent studies with highly noisy patterns clearly showed that overfitting can occur. A natural strategy to alleviate the problem is to penalize the distribution skewness in the learning process to prevent several hardest examples from spoiling decision boundaries. In this paper, we describe in detail how a penalty ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Bayesian technique for task localization in multiple goal Markov decision processes

    Publication Year: 2004, Page(s):49 - 56
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (252 KB) | HTML iconHTML

    In a reinforcement learning task library system for Multiple Goal Markov Decision Process (MGMDP), localization in the task space allows the agent to determine whether a given task is already in its library in order to exploit previously learned experience. Task localization in MGMDPs can be accomplished through a Bayesian approach, however a trivial approach fails when the rewards are not distrib... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Matching an opponent's performance in a real-time, dynamic environment

    Publication Year: 2004, Page(s):57 - 64
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (282 KB) | HTML iconHTML

    In this paper, we explore high-level, strategic learning in a real-time environment. Our long-term goal is to create a computer game that provides a continuous challenge without ever being too difficult that discourages players or too easy that it bores players. Towards this goal, we propose an agent that is able to observe its environment, measure its performance against the human player(s), and ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Satisficing Q-learning: efficient learning in problems with dichotomous attributes

    Publication Year: 2004, Page(s):65 - 72
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (278 KB) | HTML iconHTML

    In some environments, a learning agent must learn to balance competing objectives. For example, a Q-learner agent may need to learn which choices expose the agent to risk and which choices lead to a goal. In this paper, we present a variant of Q-learning that learns a pair of utilities for worlds with dichotomous attributes and show that this algorithm properly balances the competing objectives an... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Learning hidden Markov models from the state distribution oracle

    Publication Year: 2004, Page(s):73 - 80
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (380 KB) | HTML iconHTML

    A Hidden Markov Model (HMM) is a probabilistic model that has been widely applied to a number of fields since its inception over 30 years ago. Computational Biology, Speech Recognition, and Image Processing are but a few of the application areas of HMMs. We propose an efficient algorithm for learning the parameters of a first order HMM from a state distribution (SD) oracle. The SD oracle provides ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Decision-tree learning in dwell point policies in autonomous vehicle storage and retrieval systems (AVSRS)

    Publication Year: 2004, Page(s):81 - 84
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (157 KB) | HTML iconHTML

    Autonomous vehicle storage and retrieval system (A VSRS) is a new material handling technology for unit load storage and retrieval. The dwell point issue is one of important aspects to increase the throughput. We examine two dwell point policies of an IO point policy and a last transaction floor policy. We combine two policies from findings in a decision tree. The result indicates significant impr... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Mobile data mining for radio resource management in wireless mobile networks

    Publication Year: 2004, Page(s):85 - 92
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (267 KB) | HTML iconHTML

    We have introduced in [15] a predictive call admission control and resource reservation (PCAC-RR) technique for wireless mobile networks. In this technique, the behavior of the user is recorded over a period of time and analyzed to generate the mobility models (profiles) of the users. The generated mobility models are used to predict the future movement of the users in order to perform the call ad... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A new cluster-based feature extraction method for surface defect detection

    Publication Year: 2004, Page(s):93 - 98
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (256 KB) | HTML iconHTML

    In this paper, a new cluster-based approach is proposed for feature extraction from the coefficients of two-dimensional discrete wavelet transform. The proposed method divides the matrices of wavelet coefficients into clusters by identifying regions with no holes. The features that contain the informative attributes of the images are computed from the energy content of so obtained clusters. Images... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Solving an inverse partial differential equation for a two dimensional heat conduction problem with oscillating boundary conditions using an artificial immune system

    Publication Year: 2004, Page(s):99 - 106
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (198 KB) | HTML iconHTML

    Increases in computing power have brought a renewed interest in solving inverse initial-value, boundary-value (inverse IVBV) problems, and in the development of robust, computationally efficient methods suitable for their solution. Inverse IVBV problems are prominent in science and engineering problems governed by partial differential equations where often an effect is measured and the cause is no... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Feature fusion and degradation using self-organizing map

    Publication Year: 2004, Page(s):107 - 114
    Cited by:  Papers (1)  |  Patents (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (269 KB) | HTML iconHTML

    Successful prognostics is based on effective feature exaction and correct feature selection processes. Feature map is one of the widely used performance assessment and degradation detection methods. By continuously tracking the trajectories, degradation detection and prognostics in feature space can be conducted. The challenge is how to construct a feature space that can consistently exemplify the... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A game theory approach to pairwise classification with support vector machines

    Publication Year: 2004, Page(s):115 - 122
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (286 KB) | HTML iconHTML

    Support Vector Machines (SVM) for pattern recognition are discriminant binary classifiers. One of the approaches to extend them to multi-class case is pairwise classification. Pairwise comparisons for each pair of classes are combined together to predict the class or to estimate class probabilities. This paper presents a novel approach, which considers the pairwise S VM classification as a decisio... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Multiple instance learning using simple classifiers

    Publication Year: 2004, Page(s):123 - 128
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (216 KB) | HTML iconHTML

    In this paper we study Multiple Instance Learning, a variant of the standard classification problem. We demonstrate the utility of an empirical risk minimization approach allowing for a straightforward classification treatment of the problem. In addition we consider simple data dependent hypothesis classes that allow efficient minimization of the empirical loss function and the development of boun... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Sparse representations and performances in support vector machines

    Publication Year: 2004, Page(s):129 - 136
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (303 KB) | HTML iconHTML

    This paper focuses on the problem of how data representation influences the generalization error of kernel based learning machines like Support Vector Machines (SVM) for classification. Frame theory provides a well founded mathematical framework for representing data in many different ways. We analyze the effects of sparse and dense data representations on the generalization error of such learning... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Scoring systems, classifiers, default probabilities, and kernel methods

    Publication Year: 2004, Page(s):137 - 142
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (179 KB) | HTML iconHTML

    Perceptron learning is discussed in the context of so-called scoring systems. It is argued that in conjunction with maximum likelihood methods this is particularly suitable for such a banking application. Several practical reasons are given why in this context it should be preferred to support vector machines. The interpretation of the perceptron output as a posteriori probability using a prior fr... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.