Gaussian Mixture Model Classification of Frogs
Journal Title: International Journal of engineering Research and Applications - Year 2018, Vol 8, Issue 4
Abstract
This Work Deals With Automatic Call-Independent Frog Species Identification. An Algorithm Is Designed To Process Field Recordings And Perform Automatic Identification Of 10 Species Of Anurans Inhabiting The Yasuní National Park In The Ecuadorian Amazon Region. First, End-Point Detection Using Short-Term-Energy (STE) With A Moving-Average Filter Is Applied To Isolate Frog Calls Over An SNR > 15 Db Threshold. Audio Segments With Background Noise And Silence Are Discarded. Isolated Segments Are Then Parametrized Using Cepstral Feature Vectors That Represent The Frog Acoustic Phenomenon. The Data Is Divided Into Two Groups From Which One Is Used To Train Gaussian Mixture Models And The Others Are Used For Testing Classification Accuracy For Each Species. GMM Models With Different Mixture Weights (Components) Are Generated In Order To Determine The Best Model Order. The Classification Task Is Based On The Maximum-Likelihood (ML) Rule Achieving The Maximum Average Success Rate Of 97.24% With GMM Models Of 64 Components.
Authors and Affiliations
Damián A. Nicolalde Rodríguez, Andrés E. Terneux, Daniel P. Nicolalde Rodríguez
Keywords
Related Articles
- EP ID EP393947
- DOI 10.9790/9622-0804014249.
- Views 132
- Downloads 0
Microstructural Analysis of the Influence of Ecap on the Pure Nb Rolling Plane
Starting From a sample of pure and pre-deformed niobium by cold rolling a severe plastic deformation process was performed using ECAP (equal channel angular pressing) in order to verify the evolution and distibution of t...
Efficient Data Integrity Algorithm for Outsourced Data in Cloud Environment
With The Rapid Advances In Communication Services And Increasing Growth In Outsourcing Of Data To Cloud Environment; Concerns Of Data Integrity Of Outsourced Data Is On The Rise. The Evidence Of Data Integrity Being Tamp...
Antibacterial properties of Unripened Fruits of Trapa natans, Annona squamosa, Ficus carica and Anthocephalus cadamba against Pathogenic Gram Positive and Negative Bacteria.
4 gm. of the unripened ground fruits of Ficus carica, Trapa natans, Annona squamosa and Anthocephalus cadamba were weighed and homogenized with 40 ml of acetone, 70% ethanol, 80% methanol, and ethyl acetate separately in...
Development of a Simulation and Analysis Tool for Chemical Reactors
A reactor analysis and simulation tool (ASchem) for the design and performance analysis of batch, continuous stirred-tank and plug-flow reactors has been developed. The simulation tool is robust, allows for choice of rea...
Performance Levels of RC Structures by Non-Linear Pushover Analysis
In the recent earthquakes in which many concrete structures have been severely damaged or collapsed, have indicated the need for evaluating the seismic adequacy of existing buildings. About 60% of the land area of our co...