Muqing Deng

TL;DR: A new method based on deterministic learning and knowledge fusion is proposed to eliminate the effect of view angle for efficient view-invariant gait recognition and shows that promising recognition accuracy can be achieved.

TL;DR: Wang et al. as discussed by the authors proposed a gait recognition algorithm by combining shallow and deep features through multiple walking views, where the binary silhouettes are characterized with width features as shallow parameters, including arm silhouette width and leg silhouette widths, which implicitly reflect the temporal changes of silhouette shape.

TL;DR: In this article, a risk stratification method for myocardial ischemia based on deterministic learning and deep learning is proposed, which includes the steps that conventional 12-lead electrocardiogram signals are collected, and the deep neural network can learn data features independently without further data characterization.

TL;DR: In this article, a heart sound signal classification method based on a convolutional recurrent neural network (RNN) was proposed, which consists of the following steps: performing noise processing on heart sound data; extracting heart sound characteristics of the heart sound signals; standardizing the data; constructing a CNN model; training the constructed neural network by using the training sample data characteristics; storing the trained network structure and parameters; and testing the test sample data by using trained model parameters to obtain a final classification and identification result.