Kernel-based learning algorithms applied to human behaviour analysis: exploring dynamic patterns

• Grant number: 11/04608-8
• Support Opportunities: Scholarships in Brazil - Master
• Start date: August 01, 2011
• End date: April 30, 2013
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computing Methodologies and Techniques
• Principal Investigator: Sarajane Marques Peres
• Grantee: Renata Cristina Barros Madeo
• Host Institution: Escola de Artes, Ciências e Humanidades (EACH). Universidade de São Paulo (USP). São Paulo , SP, Brazil

Abstract

Recently, Kernel-based learning algorithms have been applied to complex pattern recognition problems, presenting good results. In several works, these algorithms are applied to spatiotemporal pattern recognition problems, such as gesture and movement recognition. However, most of these works only extract spatiotemporal features and include them in a vector representation of the data, instead of incorporating the temporal information treatment to the recognition model construction process. This research project at Masters level aims to explore the area of Kernel-based Learning algorithms applied to human behavior analysis problems, initially focusing on the study of human movements and gestures as dynamic patterns. And, to better match the kernel-based methods to dynamic pattern recognition problem, this project intends to investigate approaches that insert characteristics of recurrent learning algorithms and/or time-delay learning algorithms. (AU)

Scientific publications

(The scientific publications listed on this page originate from the Web of Science or SciELO databases. Their authors have cited FAPESP grant or fellowship project numbers awarded to Principal Investigators or Fellowship Recipients, whether or not they are among the authors. This information is collected automatically and retrieved directly from those bibliometric databases.)

MADEO, RENATA C. B.; LIMA, CLODOALDO A. M.; PERES, SARAJANE M.. Studies in automated hand gesture analysis: an overview of functional types and gesture phases. Language Resources and Evaluation, v. 51, n. 2, p. 547-579, JUN 2017. (11/04608-8)

LIMA, CLODOALDO A. M.; COELHO, ANDRE L. V.; MADEO, RENATA C. B.; PERES, SARAJANE M.. Classification of electromyography signals using relevance vector machines and fractal dimension. NEURAL COMPUTING & APPLICATIONS, v. 27, n. 3, p. 791-804, APR 2016. (11/04608-8)

MADEO, RENATA C. B.; PERES, SARAJANE M.; LIMA, CLODOALDO A. M.; BOSCARIOLI, CLODIS; IEEE. Hybrid Architecture for Gesture Recognition: Integrating Fuzzy-Connectionist and Heuristic Classifiers using Fuzzy Syntactical Strategy. 2012 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), v. N/A, p. 8-pg., 2012-01-01. (11/04608-8)

Academic Publications

(References retrieved automatically from State of São Paulo Research Institutions)

MADEO, Renata Cristina Barros. Support Vector Machines and Gesture Analysis: incorporating temporal aspects. 2013. Master's Dissertation - Universidade de São Paulo (USP). Escola de Artes, Ciências e Humanidades (EACH) São Paulo.