107 articles for “training methods”

Research ArticleOpen accessIn the abstractContent Based Image Retrieval using Novel Gaussian Fuzzy Feed Forward-Neural NetworkC. Ramesh Babu Durai, V. DuraisamyProblem statement: With extensive digitization of images, diagrams and paintings, traditional keyword based search has been found to be inefficient for retrieval of the required data. Content-Based Image Retrieval (CBIR) system responds to image queries as input and relies on image content, using techniques from computer vision and image processing to interpret and understand it, while using techniques from information … …Journal of Computer Science, Vol. 7, Issue 7 · 28 Jun 2011 · 7,326 accessesView PDF Cite

Research ArticleOpen accessIn the abstractA New Speaker Recognition System with Combined Feature Extraction TechniquesM. G. Sumithra, K. Thanuskodi, A. Helen Jenifer ArchanaProblem statement: This study introduces a new method for speaker verification system by fusing two different feature extraction methods to improve the recognition accuracy and security. Approach: The proposed system uses Mel frequency cepstral coefficients for speaker identification and Modified MFCC for verification. For speaker modeling vector quantization is used. Results: The proposed system was investigated the effect of the … …Journal of Computer Science, Vol. 7, Issue 4 · 4 Apr 2011 · 7,424 accessesView PDF Cite

Research ArticleOpen accessIn the abstractWaste Disposal and Pollution Management in Urban Areas: A Workable Remedy for the Environment in Developing CountriesJ. A. Awomeso, A. M. Taiwo, A. M. Gbadebo, A. O. ArimoroProblem statement: Both wastes and the crude disposal techniques have created subtle and yet serious environmental pollution havoc in many developing countries. This has lead to the degradation of abiotic and biotic components of these nations’ ecological systems. Poor industrial waste disposal systems as well as the indiscriminate and inappropriate domestic litter disposal habit have been identified and proved to … …American Journal of Environmental Sciences, Vol. 6, Issue 1 · 28 Feb 2010 · 9,108 accessesView PDF Cite

Research ArticleOpen accessIn the abstractFLANN Detector Based Filtering of Images Corrupted by Impulse NoiseBanshidhar Majhi, Mowafak FathiWe present a novel non-linear scheme for image restoration based on neuro-detector using Functional Link Artificial Neural Network (FLANN) followed by an improved spatial filter. The method is applied to images corrupted by impulse noise with varying strengths and different noise probability. The neural detector is based on the concept of training or learning by examples. When trained properly, the … …Journal of Computer Science, Vol. 1, Issue 3 · 30 Sep 2005 · 7,237 accessesView PDF Cite

Research ArticleOpen accessAll words, across the recordPreparation of a Measure of Kinetic Analysis using Artificial Intelligence Methods for Volleyball CoachesMarwa Ahmed FadlCoaches need tool codified, modern and fast determine their ability to quantitative analysis using modern techniques to improve the performance and scalability while conducting education and training through the use of analytical skills ByumKaniki modern techniques with coaches some sports selected, as the researcher used the descriptive style screening for suitability and nature of the research, random sample was selected … …American Journal of Biochemistry and Biotechnology, Vol. 16, Issue 2 · 15 May 2020 · 6,835 accessesView PDF Cite

Research ArticleOpen accessAll words, across the recordOn the Front Lines: Educating Teachers about Bullying and Prevention MethodsAviva Twersky GlasnerProblem statement: Bullying is a serious problem in American schools and is characterized by aggressive behavior distinguished by unequal power and the intention to cause physical, social, or emotional harm to others Bullying is evolving from the classic image of a big schoolyard bully picking on smaller kids to a more technologically, sophisticated model of kids using cyber technology to … …Journal of Social Sciences, Vol. 6, Issue 4 · 23 Oct 2010 · 9,281 accessesView PDF Cite

Research ArticleOpen accessAll words, across the recordIMPROVING INDEPENDENT COMPONENT ANALYSIS USING SUPPORT VECTOR MACHINES FOR MULTIMODAL IMAGE FUSIOND. Egfin Nirmala, A. Bibin Sam Paul, V. VaidehiThe objective of this study is to combine multiple images of a scene acquired by different sensors to create a new image with all important information from the input images. Recent studies show that bases trained using Independent Component Analysis (ICA) is effective in multisensor fusion and has improved performance over traditional wavelet approaches. In the ICA based fusion, the … …Journal of Computer Science, Vol. 9, Issue 9 · 6 Aug 2013 · 7,272 accessesView PDF Cite