Stroke is one of the leading causes of death and disability in the world. The rehabilitation of Patients' limb functions has great medical value, for example, the therapy of functional electrical stimulation (FES) systems, but suffers from effective rehabilitation evaluation. In this paper, six gestures of upper limb rehabilitation were monitored and collected using microelectromechanical systems sensors, where data stability was guaranteed using data preprocessing methods, that is, deweighting, interpolation, and feature extraction. A fully connected neural network has been proposed investigating the effects of different hidden layers, and determining its activation functions and optimizers. Experiments have depicted that a three-hidden-layer model with a softmax function and an adaptive gradient descent optimizer can reach an average gesture recognition rate of 97.19%. A stop mechanism has been used via recognition of dangerous gesture to ensure the safety of the system, and the lightweight cryptography has been used via hash to ensure the security of the system. Comparison to the classification models, for example, k-nearest neighbor, logistic regression, and other random gradient descent algorithms, was conducted to verify the outperformance in recognition of upper limb gesture data. This study also provides an approach to creating health profiles based on large-scale rehabilitation data and therefore consequent diagnosis of the effects of FES rehabilitation.
Blood cell images are difficult for segmentation because of their intrinsic characteristics. We proposed a dual-layer structure to solve the problem: the 1st layer introduces and simplifies pulse coupled neural network to split the images based on traditional Split-Merge method, and Mumford-Shah model was utilized to merge the split areas. The output of the first layer is a coarse segmented image. The second layer extracts the edges via LoG operator with considering the edges whose length are larger than given threshold as cell edge while the opposite as false-edges caused by noises. The output is a non-continuous edge. To obtain the final labeling results, we combined the two layers together with skeleton extraction and thinning from mathematical morphology. Experiments suggested the superiority of proposed method.