Insect species identification by means of optical sensor using music and speech signals classification techniques

• Grant number: 12/18985-0
• Support type: Scholarships abroad - Research Internship - Master's degree
• Effective date (Start): February 01, 2013
• Effective date (End): July 31, 2013
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computer Systems
• Principal researcher: Gustavo Enrique de Almeida Prado Alves Batista
• Grantee: Diego Furtado Silva
• Supervisor abroad: Daniel P. W. Ellis
• Home Institution: Instituto de Ciências Matemáticas e de Computação (ICMC). Universidade de São Paulo (USP). São Carlos , SP, Brazil
• Research place: Columbia University in the City of New York, United States
• Associated to the scholarship: 11/04054-2 - Time series classification by similarity and extraction of intrinsic attributes with application to insect species identification, BP.MS

Abstract

Applications that involve signals interpretation are ubiquitous in human life. A common task in this type of application is the classification. This task involves a mapping f:X->Y where X is the space of complex objects, in this case digital signals, and Y represents the space of possible categories or classes for which each signal can be associated. In this project, we are interested in classifying species of diseases vector mosquitoes from signals collected by an optical sensor. The classification by similarity and attribute extraction in various signal representations are possible approaches to be used to accomplish this task. In this project, we propose the insect classification from optical sensor signals based on representations proposed to speech and music signals analysis. (AU)