Minimal Enclosing Ball (MEB) has a limitation for dealing with a large dataset in which computational load drastically increases as training data size becomes large. To handle this problem in huge dataset used for speaker recognition and identification system, we propose two algorithms using Fuzzy C-Mean clustering method. Our method uses divide-and-conquer strategy; trains each decomposed sub-problems to get support vectors and retrains with the support vectors to find a global data description of a whole target class. Our study is experimented on Universal Background Model (UBM) architectures in speech recognition and identification system to eliminate all noise features and reducing time training. For this, the training data, learned by Support Vector Machines (SVMs), is partitioned among several data sources. Computation of such SVMs can be efficiently achieved by finding a core-set for the image of the data.
Abstract-Generating electrical power from wind energy is becoming increasingly important throughout the world. This fast development has attracted many researchers and electrical engineers to work on this field. The authors develop a dynamic model of the squirrel cage induction generator exists usually on wind energy systems, for the diagnosis of broken rotor bars defects from an approach of magnetically coupled multiple circuits. The generalized model is established on the base of mathematical recurrences. The winding function theory is used for determining the rotor resistances and the inductances in the case of n-broken bars. Simulation results, in Part. II of this paper, confirm the validity of the proposed model.
While Modern Standard Arabic is the formal spoken and written language of the Arab world; dialects are the major communication mode for everyday life. Therefore, identifying a speaker's dialect is critical in the Arabic-speaking world for speech processing tasks, such as automatic speech recognition or identification. In this paper, we examine two approaches that reduce the Universal Background Model (UBM) in the automatic dialect identification system across the five following Arabic Maghreb dialects: Moroccan, Tunisian, and 3 dialects of the western (Oranian), central (Algiersian), and eastern (Constantinian) regions of Algeria. We applied our approaches to the Maghreb dialect detection domain that contains a collection of 10-second utterances and we compared the performance precision gained against the dialect samples from a baseline GMM-UBM system and the ones from our own improved GMM-UBM system that uses a Reduced UBM algorithm. Our experiments show that our approaches significantly improve identification performance over purely acoustic features with an identification rate of 80.49%.
In this paper, the ability to detect broken rotor bar (BRB) defects in a small renewable energy system (based on a squirrel cage induction generator (SCIG)) by the digital signal processing of captured phase currents, is presented. The new approach proposed in this study is a combination of two techniques. The first technique is a discrete wavelet transform (DWT) by the decomposition of the phase current signal in multilevel frequency bands. This is performed with the analysis of some selected approximations and/or details, which contain both the lower and upper sideband components presenting the characteristic frequency of the BRB fault. The second technique is power spectral density (PSD) analysis. This approach provides the ability to optimize the diagnosis of rotor defects in electrical generators. The results obtained by the proposed DWT-PSD approach are proved and improved by comparing them with the results of the PSD analysis, obtained from the original phase current signal delivered by the 5.7-kW squirrel cage induction generator, based on a small wind energy conversion system.
The main goal of this paper is to develop a method permitting to determine the nature of the rotor defects thanks to the spectral analysis. The development growing that the equipment of measurement (spectral analyzer) and the software of digital signal processing had made possible the diagnosis of the electric machine defects. Motor current signature analysis (MCSA) is used for the detection of the electrical and the mechanical faults of an induction machine to identify rotor bar faults. Also, the calculation of machine inductances (with and without rotor defects) is carried out by the tools of software MATLAB before the beginning of simulation under Software SIMULINK. Simulation and experimental results are presented to confirm the validity of proposed approach.
The recent progress in speech and vision has issued from the increased use of machine learning. Not only does the machine learning provides many useful tools, it also help us to understand existing algorithms and their connections in a new light. As a powerful tool in machine learning, support vector machine (SVM) leads to an expensive computational cost in the training phase due to the large number of original training samples, while minimal enclosing ball (MEB) presents limitations dealing with a large dataset. The training computation increases as data size becomes large, hence in this paper, we propose two improved approaches that handle this problem in huge dataset used in different domains. These approaches, based on L2-SVMs reduced to MEB problems result in a reduced data optimally matched to the input demands of different background of systems such as Universal Background Model architectures in language recognition and identification systems. We experiment on speech information based on acoustic shifted delta coefficient feature vectors applied in GMM-based dialect identification system where all data outer the ball defined by MEB are eliminated and the training time is reduced. Further numerical experiments on some real-world datasets show proof of the usefulness of our approaches in the field of data mining.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.