The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Traditional domain adaptation methods attempted to learn the shared representation for distribution matching between source domain and target domain where the individual information in both domains was not characterized. Such a solution suffers from the mixing problem of individual information with the shared features which considerably constrains the performance for domain adaptation. To relax this...
In order to extract effective audio feature using autoencoder, different from traditional bottle-neck autoencoder, bottle-body autoencoder is presented in this paper, which is constructed using restricted Boltzmann machine with the same neurons at every layer. Bottle-body feature, which is obtained by using pseudo-inverse method to initialize weights, is applied to audio signal classification. The...
Symbolic time series analysis (STSA) is built upon the concept of symbolic dynamics that deals with discretization of dynamical systems in both space and time. The notion of STSA has led to the development of a pattern recognition tool in the paradigm of dynamic data-driven application systems (DDDAS), where a time series of sensor signals is partitioned to obtain a symbol sequence that, in turn,...
The proposed research focuses on designing a low-cost electromyogram (EMG) data acquisition system (DAQ). The developed system acquires EMG signals from the sub-vocal region and suitable features are extracted using time-frequency transform such as Wavelet Transform. Once the features are extracted, the final classification is carried out using ensemble decision trees called Random Forests (RF). Giving...
The extraction of urban patterns from Very High Spatial Resolution (VHSR) images presents several challenges related to the size, the accuracy and the complexity of the considered data. In order to assist the end-user to efficiently carry out this task, a new approach is proposed for hierarchically extracting segments of interest from lower resolution data and finally determining urban patterns in...
The scarcity of fault samples often occurs in the fault diagnosis of Chongqing light-rail's cast steel pedestal system. In the case of this situation, this paper first puts forward a fault diagnosis method based on One-class Support Vector Machine (One-class SVM). This method can build up one-class classifier to distinguish between normal condition and abnormal condition as long as the normal data...
Knowledge discovery from the Web is a cyclic process. In this paper we focus on the important part of transforming unstructured information from Web pages into structured relations. Relation extraction systems capture information from natural language text on Web pages, called Web text. However, extraction is quite costly and time consuming. Worse, many Web pages may not contain a textual representation...
A classifier model for satellite image data by using Partitioned-Feature based Classifier (PFC)is proposed in this paper. The PFC does not use concatenated feature vectors extracted from the original data at once to classify each datum, but uses extracted feature vectors to classify data separately. In the training stage, the contribution rate calculated from each feature vector group is drawn throughout...
Although data mining techniques are made tremendous progress, "knowledge-poor" is still a large gap of the current data mining systems. Few researches notice the fact that useful knowledge not only is the final results of an intelligent classification, clustering or prediction algorithm, but also runs through the whole process of data mining in which much potential useful information is...
This article proposes such a question classification approach that integrates multiple semantic features. It is aimed at these two questions in Chinese question classification models: inaccurate semantic information extraction and too slow processing speed caused by too high Eigenvector dimension. With the help of HowNet and the support vector machine and syntactic and semantic information of question...
Base on RS and GIS, 1993, 2000, 2007 and 2009 TM images of Tangshan Nanhu Wetland are taken as the data source, Landscape characteristics and change are studied. The knowledge discovery and feature extraction on the basis of traditional classification method of the remote sensing pictures are discussed. Multi-level classification method is used in monitoring of Tangshan Nanhu Wetland area land cover...
The latest statistics of WHO show that approximately 500, 000 women die worldwide every year - the majority of them residing in developing countries - due to pregnancy related complications. The situation is so grave that UN has set a target of reducing Maternal Mortality Rate (MMR) by 75% till the year 2015 in its millennium development goals (MDGs). Therefore, the current focus of health care researchers...
The effect of the training set on supervised classifier performance has always been overlooked. This paper provides a new approach for training set cleaning based on the concept of outlier detection to help build sound class models during the training of supervised classifiers. Outliers in a training set result in classifier performance deterioration and slow convergence. For training set cleaning,...
To extract implicit knowledge and data relationships from the audio and audio similarity measure, this paper uses the audio mining techniques. A model for audio clustering and classification technique is proposed. Neural networks are used for classifying the data. The working prototype of the Music classification system has been developed and tested in MATLAB 6.5 using the signal Processing Toolbox...
This paper presents concepts, ecosystem, research challenges and directions of Social Services Computing. Social Services Computing is an emerging computing paradigm which sweeps through Social Computing, Internet of Things, Services Computing, and Cloud Computing. Physical things, computer systems and social individuals are connected together through dedicate and complex communication and control...
Classifier selection aims to reduce the size of an ensemble of classifiers in order to improve its efficiency and classification accuracy. Recently an information-theoretic view was presented for feature selection. It derives a space of possible selection criteria and show that several feature selection criteria in the literature are points within this continuous space. The contribution of this paper...
Classification, or supervised learning, is one of the major data mining processes. Protein classification focuses on predicting the function or the structure of new proteins. This can be done by classifying a new protein to a given family with previously known characteristics. There are many approaches available for classification tasks, such as statistical techniques, decision trees and the neural...
This paper proposes a new approach to data selection, a key issue in classification problems. This approach, which is based on a feature selection algorithm and one instance selection algorithm, reduces the original dataset in two dimensions, selecting relevant features and retaining important instances simultaneously. The search processes for the best feature and instance subsets occur separately...
Development of a feature ranking method based upon the discriminative power of features and unbiased towards classifiers is of interest. We have studied a consensus feature ranking method, based on multiple classifiers, and have shown its superiority to well known statistical ranking methods. In a target environment such as a medical dataset, missing values and an unbalanced distribution of data must...
Worms are self-contained programs that spread over the Internet. Worms cause problems such as lost of information, information theft and denial-of-service attacks. The first part of the paper evaluates the detection of worms based on content classification by using all machine learning techniques available in WEKA data mining tools. Four most accurate and quite fast classifiers are identified for...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.