Método não invasivo utilizando acelerômetro para classificar movimentos normais e anormais de humanos

• Ano de defesa: 2011
• Autor(a) principal: Giacomossi, Luiz Carlos
• Tipo de documento: Dissertação
• Tipo de acesso: Acesso aberto
• Idioma: por
• Instituição de defesa: Universidade Tecnológica Federal do Paraná; Curitiba; Programa de Pós-Graduação em Engenharia Elétrica e Informática Industrial
• Palavras-chave em Português: Mecânica humana - Classificação; Redes neurais (Computação); Detectores; Engenharia elétrica; Human mechanics - Classification; Neural networks (Computer science); Detectors; Electric engineering
• Link de acesso: http://repositorio.utfpr.edu.br/jspui/handle/1/913

The aim of this research is the capture, detection and classification of abnormal human movements (tremors, vibrations, spasms and muscle contractions) and normal movements of everyday life. A non-invasive device, developed by undergraduate students of UTFPR, based on integrated electronic accelerometer, was placed on the wrist of volunteers to capture the movements. All experiments were performed in the laboratory Biota of CPGEI-UTFPR. The movement of walking, running, waving a goodbye, clapping and shaking, were captured in 5 adult volunteers. A pre-processing was done off-line by a program developed using Matlab 6.5, which extracts key features that should reflect the breadth, intensity and frequency of each movement and provide a file containing the standard supervised. We used a fuzzy neural network-type FAN (Free Associative Neuron) and a neural network MLP (Multi-Layer Perceptron) to classify a database containing a total of 375 patterns, of which 250 patterns (50 of each movement) for the training phase and 125 patterns (25 of each movement) to data validation. The average percentage of correct classification of data obtained from 5 individuals, were captured from 81.6% for the neural network FAN and 72.6% for MLP. Another experiment was conducted to capture the same movements in the previous study from a single individual. From a total of 2100 patterns, 1500 were used for training (300 for each movement) and 600 patterns (120 for each movement) for validation. The average percentage of correct classification of the data were 98.2% for the neural network FAN, 96.7% for MLP neural network, observing a significant improvement in the results. A final experiment was performed adding to the database some more movements performed by a single individual: combing, bolting, circles, punching the air and scratching his leg. The average percentage of correct classification of the data obtained were 99.3% for the neural network FAN and 99.1% for MLP neural network. The results of the classification of data for a total of 10 movements and elaborate patterns with 13 features were obtained based on a database containing a total of 4200 patterns, of which 3000 patterns (300 for each movement) for the training and 1200 patterns (120 for each movement) to data validation. In this experiment there was a further improvement in data classification, considering the addition of three new features to the training patterns, postural values (offset) extracted from the signals related to the axes x, y and z of the accelerometer.