Documentação de convênios
URI permanente desta comunidadehttps://rigalileo.itegam.org.br/handle/123456789/173
Trabalhos ténico-científico oriundos de convênios com universidades para oferta de turmas de mestrado e doutorados no Estado do Amazonas
Navegar
3 resultados
Resultados da Pesquisa
Item Motion for a product to collect a sample of human stool and/or urine – KITLAB(INSTITUTO DE TECNOLOGIA, 2015) MELO, Cláudio Márcio Bizantino de; LEITE, Jandecy Cabral; Prof. Dr. Carlos Tavares da Costa JúniorThis paper presents an innovative product proposal for collecting stool and/or urine samples using the KITLAB device. It is a detachable container that can be installed directly on toilet bowls, enabling hygienic, practical, and hands-free collection. The design addresses contamination and discomfort issues associated with traditional sample collection methods, improving health service practices. Market research results showed broad public acceptance and commercial viability of the product.Item Two solutions for the processing of ambulatory electrocardiogram(INSTITUTO DE TECNOLOGIA, 2015) SEISDEDOS, Carlos R. Vázquez; NETO, João Evangelista; LEÓN, Alexander A. Suárez; OLIVEIRA, Roberto C. Limão de.; Jandecy Cabral LeiteThe paper addresses two challenges in ambulatory electrocardiogram (ECG) processing: identifying valid heartbeats for heart rate variability (HRV) analysis and robust detection of the T-wave end (Te point) under noisy conditions. Proposed methods include computational intelligence techniques (KPCA + MLP) and a trapezoidal area-based algorithm (TRA). Results show superior accuracy and noise resilience compared to conventional approaches.Item Métodos de extracción de características en el ECG(INSTITUTO DE TECNOLOGIA, 2011) NETO, João Evangelista; SUAREZ-LEON, A. A.; VÁZQUEZ-SEISDEDOS, C. R; LÓPEZ-MORA, N. A; LEITE, J. C; OLIVEIRA, R. C. L.; Rui Nelson Otoni MagnoThe article compares three ECG feature extraction methods (Discrete Cosine Transform - DCT, Principal Component Analysis - PCA, and Kernel PCA) for heartbeat classification using an MLP neural network. Results indicate that Kernel PCA achieves the highest accuracy (98.7%) but with longer execution times, while linear PCA is the fastest but less accurate (93%). The study uses data from the MIT-BIH Arrhythmia Database.