Meta-learning is currently a hot research topic in machinelearning, which has emerged from the need to support datamining automation in issues related to algorithm and parameter selection. Finding the best learning ...
详细信息
ISBN:
(纸本)9781424450077
Meta-learning is currently a hot research topic in machinelearning, which has emerged from the need to support datamining automation in issues related to algorithm and parameter selection. Finding the best learning strategy for a new domain/problem can prove to be an expensive and time-consuming process even for the experienced analysts. this paper presents a new meta-learning system, designed to automatically discover the most reliable learning schemes for a particular dataset, based on the knowledge the system acquired about similar datasets. the novelty of the approach consists in combining dataset characterization with landmarking to increase the accuracy of the predictions. the proposed architecture is aiming to resolve the problem of selecting the best classifier for a dataset while minimizing the work done by the user but still offering flexibility.
Prior knowledge about it problem domain can be utilized to bias Support Vector machines (SVMs) towards learning better hypothesis functions. To this end, a number of methods have been proposed that demonstrate improve...
详细信息
ISBN:
(纸本)9783642030697
Prior knowledge about it problem domain can be utilized to bias Support Vector machines (SVMs) towards learning better hypothesis functions. To this end, a number of methods have been proposed that demonstrate improved generalization performance after the application of domain knowledge;especially in the case of scarce training data. In this paper, we propose an extension to the Virtual Support vectors (VSVs) technique where only a subset of the Support vectors (SVs) is Utilized. Unlike previous methods, the Purpose here is to compensate for noise and uncertainty in the training data. Furthermore, we investigate the effect of domain knowledge not only oil the quality of the SVM model, but also Oil rules extracted from it: hence the learned pattern by the SVM. Results on five benchmark and one real life data sets show that domain knowledge can significantly improve boththe quality Of the SVM and the rules extracted from it.
In this paper we present a comparative analysis of two types of remote sensing satellite data by using the wavelet-based datamining techniques. the analyzed results reveal that the anomalous variations exist related ...
详细信息
ISBN:
(纸本)9783642030697
In this paper we present a comparative analysis of two types of remote sensing satellite data by using the wavelet-based datamining techniques. the analyzed results reveal that the anomalous variations exist related to the earthquakes. the methods studied in this work include wavelet transformations and spatial/temporal continuity analysis of wavelet maxima. these methods have been used to analyze the singularities of seismic anomalies in remote sensing satellite data, which are associated with file two earthquakes of Wenchuan and Pure recently occurred in China.
We face the problem of novelty detection from stream data, that is, the identification of new or unknown situations in an ordered sequence of objects which arrive on-line, at consecutive time points. We extend previou...
详细信息
ISBN:
(纸本)9783642030697
We face the problem of novelty detection from stream data, that is, the identification of new or unknown situations in an ordered sequence of objects which arrive on-line, at consecutive time points. We extend previous solutions by considering the case of objects modeled by multiple database relations. Frequent relational patterns are efficiently extracted at each time point, and a time window is used to filter out novelty patterns. An application of the proposed algorithm to the problem of detecting anomalies in network traffic is described and quantitative and qualitative results obtained by analyzing real stream of data collected from the firewall logs are reported.
datamining is the process of extracting interesting information from large sets of data. Outliers are defined as events that occur very infrequently. Detecting outliers before they escalate with potentially catastrop...
详细信息
ISBN:
(纸本)9783642030697
datamining is the process of extracting interesting information from large sets of data. Outliers are defined as events that occur very infrequently. Detecting outliers before they escalate with potentially catastrophic consequences is very important for various real life applications such as in the field of fraud detection, network robustness analysis, and intrusion detection. this paper presents a comprehensive analysis of three Outlier detection methods Extensible Markov Model (EMM), Local Outlier Factor (LOF) and LCS-Mine, where algorithm analysis shows the time complexity analysis and outlier detection accuracy. the experiments conducted with Ozone level Detection, IR video trajectories, and 1999 and 2000 DARPA DDoS datasets demonstrate that EMM outperforms both LOF and LSC-Mine in both time and outlier detection accuracy.
Many applications require predictions with confidence. We are interested in Confidence machines which are algorithms that call provide some measure oil how confident they are that their Output is correct. Confidence M...
详细信息
ISBN:
(纸本)9783642030697
Many applications require predictions with confidence. We are interested in Confidence machines which are algorithms that call provide some measure oil how confident they are that their Output is correct. Confidence machines are quite general and there are many algorithms solving the problem of prediction with confidence. As predictors we consider Venn Probability machines and Conformal Predictors. Both of these algorithms rely oil all underlying algorithm for prediction and in this paper We use two simple algorithms, namely the Nearest Neighbours and Nearest Centroid algorithms. Our aim is to provide some guidelines on how to choose the Most Suitable algorithm for a practical application where confidence is needed.
the new approach of relevant feature selection in machinelearning is proposed for the case of ordered features. Feature selection and regularization of decision rule are combined in a single procedure. the selection ...
详细信息
ISBN:
(纸本)9783642030697
the new approach of relevant feature selection in machinelearning is proposed for the case of ordered features. Feature selection and regularization of decision rule are combined in a single procedure. the selection of features is realized by introducing weight coefficients, characterizing degree of relevance of respective feature. A priori information about feature ordering is taken into account in the form of quadratic penalty or in the form of absolute Value penalty on the difference of weight coefficients of neighboring features. Study of a penalty function in the form of absolute value shows computational complexity Of Such formulation. the effective method of solution is proposed. the brief survey of authors early papers. the mathematical frameworks, and experimental results are provided.
Many data sets derived from the web are large, high-dimensional, sparse and have a Zipfian distribution of both classes and features. On such data sets, current scalable clustering methods such as streaming clustering...
详细信息
ISBN:
(纸本)9783642030697
Many data sets derived from the web are large, high-dimensional, sparse and have a Zipfian distribution of both classes and features. On such data sets, current scalable clustering methods such as streaming clustering suffer from fragmentation. where large classes are incorrectly divided into many smaller clusters. and computational efficiency drops significantly. We present a new clustering algorithm based on connected components that addresses these issues and so works well oil web-type data.
patternmining derives from the need of discovering hidden knowledge in very large amounts of data, regardless form in which it is presented. When it;comes to Natural Language, Processing (NLP), it arose along the hum...
详细信息
ISBN:
(纸本)9783642030697
patternmining derives from the need of discovering hidden knowledge in very large amounts of data, regardless form in which it is presented. When it;comes to Natural Language, Processing (NLP), it arose along the humans necessity of being understood by computers. In this paper we present, an exploratory approach that aims at bringing together the best of both worlds. Our goal is to patterns in linguistically processed texts, through the usage of NLP state-of-the-art tools and traditional patternmining algorithms. Articles from a Portuguese newspaper are the input of a series of tests described in this paper. First, they are processed by an NLP chain which performs a (feel) linguistic analysis of text: afterwards patternmining algorithms Apriori and GenPrefixSpan, are used. Results showed the applicability of sequential patternmining techniques in textual structured data and also provided Several evidence's about the structure of the language.
this paper addresses the problem of automatically learningthe title metadata from HTML documents. the objective, is to help indexing Web resources that are poorly annotated. Other works proposed similar objectives, b...
详细信息
ISBN:
(纸本)9783642030697
this paper addresses the problem of automatically learningthe title metadata from HTML documents. the objective, is to help indexing Web resources that are poorly annotated. Other works proposed similar objectives, but they considered only titles in text format . In this paper we propose a general learning schema that allows learning textual titles based on style information and image format titles based on image properties. We construct features from automatically annotated pages harvested from the Web;this paper details the corpus creation method as well as the information extraction techniques. Based oil these features. learning algorithms, such as Decision Trees and Random Forest algorithms are applied achieving good results despite the heterogeneity of our corpus, we also show that, combining both methods can induce better performance.
暂无评论