Low limb rehabilitation training is recognized as a very effective technique to facilitate body recovery. To make rehabilitation more efficient, we need to monitor the whole progress and detect how well the patient improves. The physician could make an optimal treatment plan according to the patient's improvement only when the patient's condition is correctly evaluated. Also, it is essential to provide a rehabilitation assessment system which would enable more accurate tracking of patient's status and minimize the requirement of time-consuming manual evaluations conducted by skilled person. Traditionally, clinical rehabilitation assessment is performed manually, which is not only coarse but also time-consuming. In this paper, we propose an objective, quantitative and manual-independent assessment system for lower extremity rehabilitation. Four predictive variables, i.e. rang of motion (ROM), movement smoothness, trajectory error, and improved L-Z complexity of electromyographic signal (EMG), are explored besides conventional clinical assessment scales. A cost-effective and wearable human-independent device which mainly consists of two sensors (MPU6050 and HMC5883L), is developed to measure the ROM, movement smoothness and trajectory error. What's more, a 3D leg model is employed to visualize the leg motion in real-time on PC screen to increase the entertainment. Those physical quantities are more sensitive at the early stage of rehabilitation. And when the basic body function is recovered, the subtle rehabilitation improvement can only be detected by the intrinsic EMG signal. Therefore an improved L-Z complexity of EMG is applied to combine with physical assessment metrics. Compared with traditional L-Z complexity, the improved one proposed in this paper could reflect more precisely the underlying property of EMG signal. The future work is to integrate all the evaluation metrics, thus we introduce a BP network to quantize a final assessment outcome.

The state of health and remaining useful life of lithium-ion batteries are key indicators for the normal operation of electrical devices. To address the problem of the capacity of lithium-ion batteries being difficult to measure online, in this paper, we propose an online method based on particle swarm optimization and support vector regression to estimation the state of health and remaining useful life. First, a novel health indicator is extracted from the discharge voltage to characterize the capacity of lithium-ion batteries. Then, based on the capacity degradation characteristics, support vector regression is used to predict the remaining useful life of these batteries, and particle swarm optimization is selected to optimize the parameters of the support vector regression, which effectively enhances the predictive performance of the model. Validated for the NASA battery aging dataset, when training with the first 40% of the dataset, the maximum error of the predicted remaining useful life was four cycles, and when training with the first 50% of the dataset, the maximum error of the predicted remaining useful life was only one cycle. When comparing to a deep neural network, support vector regression, long short-term memory algorithms and existing similar methods in the literature, the particle swarm optimization and support vector regression method can obtain more accurate prediction results.

No abstract

No abstract

No abstract