1. PAVITHRA D S - Research Scholar, Visvesvaraya Technological University, Belgaum, Karnataka, India.
2. SHRISHAIL MATH - Professor, Computer Science and Engineering, Visvesvaraya Technological University, Belgaum, Karnataka, India.
Ataxic gait monitoring and assessment of neurological disorders belong to important multidisciplinary areas that are supported by digital Image processing methods and machine learning tools. This paper presents the possibility of using image sensor data to optimize deep learning convolutional neural network systems to distinguish between ataxic and normal gait. The experimental dataset includes 4800 Images segments of 10 ataxic patients and 4 individuals from the control set with the mean age of 30 and 60 year, respectively. The proposed methodology is based upon the analysis of human gait images. The deep learning system uses all the Image components to extract the features using resent and to perform feature optimization. After selecting optimal features, classification of the ataxic or normal gait are done and then compared with standard methods, which include the MLP machine, Convolution neural network with features estimated as such as speed, step length, foot angle. Proposed result shows that the appropriate classification including increase in accuracy from 80% to 91.5% for the spine position. Combining the input data and the deep learning methodology with five layers the accuracy increases to 97.5%. Proposed methodology suggests that artificial intelligence methods and deep learning are efficient methods in the assessment of motion disorders, and they have a wide range of further applications.
Accelerometric signal analysis, computational intelligence, deep learning, classification, motion monitoring.