Special Issue "Deep Learning Soft Computing for Physiological Signals"

Submission Deadline: 30 June 2020 (closed)
Guest Editors
Dr. N. Arunkumar, Rathinam Technical Campus, India
Prof. Joel J. P. C. Rodrigues, Federal University of Piauí, Brazil

Summary

Any ailment in our organs can be identified by using different modality signals such as EEG, ECG, EOG, ERG, EMG etc., belonging to various body parts to obtain useful information. Hence, there is massive influx of huge multimodality patient data to be analyzed quickly and accurately. Many machine learning (ML) algorithms have been developed to automatically detect the diseases using various feature extraction methods from the images. Extracting the proper features from the medical signals using advanced signal processing methods is a challenging task. Hence, nowadays deep learning (DL) the state-of-art artificial intelligence technique is widely used for automated diagnosis without performing feature extraction.

The DL techniques like convolution neural networks (CNN), long short- term memory (LSTM), autoencoder, deep generative models and deep belief networks have been applied for big data efficiently. Application of such novel methods to the medical signals can aid the clinicians to make accurate and fast diagnosis. Thus, this special issue, entitled "Deep learning soft computing for physiological signals", focuses on application of new deep learning techniques that can be used to improve healthcare using big data.


Keywords
• Deep learning for ECG, EEG signals
• Advanced machine learning for Epilepsy prediction
• Deep Neural networks for ERG and EOG
• Nature based deep learning methods for biomedical signal processing
• Deep learning vs traditional machine learning comparative analysis of bio signals
• Reviews on various deep learning soft computing architectures for biomedical signals