A pattern recognition system for environmental sound classification based on MFCCs and neural networks

2008 ◽  
Author(s):  
F. Beritelli ◽  
R. Grasso
Keyword(s):  
Neural Networks ◽  
Pattern Recognition ◽  
Recognition System ◽  
Environmental Sound ◽  
Pattern Recognition System ◽  
Sound Classification

EMG Pattern Recognition System Based on Neural Networks

2012 ◽  
Author(s):  
Juan Carlos Gonzalez-Ibarra ◽  
Carlos Soubervielle-Montalvo ◽  
Omar Vital-Ochoa ◽  
Hector Gerardo Perez-Gonzalez
Keyword(s):  
Neural Networks ◽  
Pattern Recognition ◽  
Recognition System ◽  
Pattern Recognition System ◽  
Emg Pattern Recognition

scholarly journals Environment Sound Classification System Based on Hybrid Feature and Convolutional Neural Network

2020 ◽  
Vol 38 (1) ◽  
pp. 162-169
Author(s):  
Ke Zhang ◽  
Yu Su ◽  
Jingyu Wang ◽  
Sanyu Wang ◽  
Yanhua Zhang
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Convolutional Neural Network ◽  
Deep Neural Networks ◽  
Recognition System ◽  
Sound Recognition ◽  
Environmental Sound ◽  
Sound Classification ◽  
Proposed Model ◽  
Auditory Features

At present, the environment sound recognition system mainly identifies environment sounds with deep neural networks and a wide variety of auditory features. Therefore, it is necessary to analyze which auditory features are more suitable for deep neural networks based ESCR systems. In this paper, we chose three sound features which based on two widely used filters:the Mel and Gammatone filter banks. Subsequently, the hybrid feature MGCC is presented. Finally, a deep convolutional neural network is proposed to verify which features are more suitable for environment sound classification and recognition tasks. The experimental results show that the signal processing features are better than the spectrogram features in the deep neural network based environmental sound recognition system. Among all the acoustic features, the MGCC feature achieves the best performance than other features. Finally, the MGCC-CNN model proposed in this paper is compared with the state-of-the-art environmental sound classification models on the UrbanSound 8K dataset. The results show that the proposed model has the best classification accuracy.

Discrimination of Two-Mixture Fragrances Odor Using Artificial Odor Recognition System with Ensemble Backpropagation Neural Networks

2013 ◽  
Vol 303-306 ◽  
pp. 1514-1518
Author(s):  
Benyamin Kusumoputro ◽  
Li Na
Keyword(s):  
Neural Networks ◽  
Pattern Recognition ◽  
Recognition Rate ◽  
Recognition System ◽  
Quartz Resonator ◽  
Learning Mechanisms ◽  
Odor Recognition ◽  
Pattern Recognition System ◽  
Backpropagation Neural Networks ◽  
Ensemble Neural Networks

The human sensory test is often used to obtain the sensory quantities of odors, however, the fluctuation of results due to the experts condition can cause discrepancies among panelists. We have developed an artificial odor recognition system using a quartz resonator sensor and backpropagation neural networks as the pattern recognition system in order to eliminate the disadvantage of human panelist system. The backpropagation neural networks shows high recognition rate for single component odor, however, become very low when it is used to discriminate mixture fragrances odor. In this paper we have proposed an ensemble of backpropagation neural networks as the pattern recognition system, and by using the ensemble learning mechanisms, the recognition rate is significantly increased, especially when using ensemble neural networks with five components.

A test of a pattern recognition system for identification of spiders

1999 ◽  
Vol 89 (3) ◽  
pp. 217-224 ◽  
Author(s):  
M.T. Do ◽  
J.M. Harp ◽  
K.C. Norris
Keyword(s):  
Neural Networks ◽  
Pattern Recognition ◽  
Artificial Neural Networks ◽  
Recognition System ◽  
Test System ◽  
Shape Information ◽  
Pattern Recognition System ◽  
Taxonomic Research ◽  
Automated Pattern Recognition ◽  
Artificial Neural

AbstractGrowing interest in biodiversity and conservation has increased the demand for accurate and consistent identification of arthropods. Unfortunately, professional taxonomists are already overburdened and underfunded and their numbers are not increasing with significant speed to meet the demand. In an effort to bridge the gap between professional taxonomists and non-specialists by making the results of taxonomic research more accessible, we present a partially automated pattern recognition system utilizing artificial neural networks (ANNs). Various artificial neural networks were trained to identify spider species using only digital images of female genitalia, from which key shape information had been extracted by wavelet transform. Three different sized networks were evaluated based on their ability to discriminate a test set of six species to either the genus or the species level. The species represented three genera of the wolf spiders (Araneae: Lycosidae). The largest network achieved the highest accuracy, identifying specimens to the correct genus 100% of the time and to the correct species an average of 81% of the time. In addition, the networks were most accurate when identifying specimens in a hierarchical system, first to genus and then to species. This test system was surprisingly accurate considering the small size of our training set.

Sign in / Sign up

Export Citation Format

Share Document