This paper proposes a method to quantitatively measure and evaluate finger tapping movements for the assessment of motor function using log-linearized Gaussian mixture networks (LLGMNs). First, finger tapping movements are measured using magnetic sensors, and eleven indices are computed for evaluation. After standardizing these indices based on those of normal subjects, they are input to LLGMNs to assess motor function. Then, motor ability is probabilistically discriminated to determine whether it is normal or not using a classifier combined with the output of multiple LLGMNs based on bagging and entropy. This paper reports on evaluation and discrimination experiments performed on finger tapping movements in 33 Parkinson’s disease (PD) patients and 32 normal elderly subjects. The results showed that the patients could be classified correctly in terms of their impairment status with a high degree of accuracy (average rate: 93:1 § 3:69%) using 12 LLGMNs, which was about 5% higher than the results obtained using a single LLGMN.
31 March 2016 in Medical & Biological Engineering & Computing
This paper proposes a quantitative measurement and evaluation method of finger tapping movements for diagnosis support and assessment of motor function. In this method, a magnetic sensor consisting of two coils is used to measure movement. The coil voltage induced by the electromagnetic induction law changes depending on the distance between the two coils; this enables estimation of the distance between two coil-bearing fingertips from the voltage measured by the nonlinear modeling relationships between the voltages and distances. Further, the finger movements measured are evaluated by computing ten indices such as the finger tapping interval, and radar charts of the evaluation indices and phase-plane trajectories of the finger movements are then displayed in real time on a monitor. Evaluation experiments were performed on finger movement in 16 Parkinson's disease patients and 32 normal elderly subjects, with the results showing that all evaluation indices differ significantly for each subject (p < 0.05).
7 October 2017 in Journal of Autism and Developmental Disorders
This paper proposes a probabilistic neural network (NN) developed on the basis of time-series discriminant component analysis (TSDCA) that can be used to classify high-dimensional time-series patterns. TSDCA involves the compression of high-dimensional time series into a lower dimensional space using a set of orthogonal transformations and the calculation of posterior probabilities based on a continuous-density hidden Markov model with a Gaussian mixture model expressed in the reduced-dimensional space. The analysis can be incorporated into an NN, which is named a time-series discriminant component network (TSDCN), so that parameters of dimensionality reduction and classification can be obtained simultaneously as network coefficients according to a backpropagation through time-based learning algorithm with the Lagrange multiplier method. The TSDCN is considered to enable high-accuracy classification of high-dimensional time-series patterns and to reduce the computation time taken for network training. The validity of the TSDCN is demonstrated for high-dimensional artificial data and electroencephalogram signals in the experiments conducted during the study.
8 June 2012 in IEEE Transactions on Neural Systems and Rehabilitation Engineering
This paper proposes the cybernetic rehabilitation aid (CRA) based on the concept of direct teaching using tactile feedback with electromyography (EMG)-based motor skill evaluation. Evaluation and teaching of motor skills are two important aspects of rehabilitation training, and the CRA provides novel and effective solutions to potentially solve the difficulties inherent in these two processes within a single system. In order to evaluate motor skills, EMG signals measured from a patient are analyzed using a log-linearized Gaussian mixture network that can classify motion patterns and compute the degree of similarity between the patient's measured EMG patterns and the desired pattern provided by the therapist. Tactile stimulators are used to convey motion instructions from the therapist or the system to the patient, and a rehabilitation robot can also be integrated into the developed prototype to increase its rehabilitation capacity. A series of experiments performed using the developed prototype demonstrated that the CRA can work as a human-human, human-computer and human-machine system. The experimental results indicated that the healthy (able-bodied) subjects were able to follow the desired muscular contraction levels instructed by the therapist or the system and perform proper joint motion without relying on visual feedback.