Machine learning includes deep learning (supervised and unsupervised deep learning) and traditional machine learning methods (such as support vector machine, random forest, decision tree et al.) have been consistently playing a significant role in the field of biomedical engineering research. Deep learning can help to analyze physiological data at a large scale, and traditional machine learning are suitable for small-scale data. Traditional machine learning based on prior knowledge may sever as a useful complement to deep learning.

Thus, this Special Issue will focus on the use and elaboration of the latest techniques, like deep learning including supervised and unsupervised methods, traditional machine learning, novel prior features extracted from physiological signals, and so on, to analyze physiological data relevant for understanding healthcare. More specifically, the advanced techniques are applied to ECG, EEG, heart sounds, blood pressure, pulse, and so on.

The purpose of this Special Issue is to publish high-quality research papers and reviews from researchers working in the fields of machine learning techniques in healthcare, with focus on theory, applications, physiological data mining, and biomedical engineering, with special emphasis on the following research topics.

Potential topics include but are not limited to the following:

• Data mining in biomedical applications
• Deep learning in physiological signals and images
• Iterative and non-iterative machine learning algorithms for physiological data
• Pattern recognition in biomedical applications
• Unsupervised deep learning model for clinical big data analytics
• Application of nonlinear features of physiological data
• Multi-feature fusion
• Analysis of physiological signals with low signal-to-noise ratio