A review of Hidden Markov models and Recurrent Neural Networks for event detection and localization in biomedical signals

Abstract

Biomedical signals carry signature rhythms of complex physiological processes that control our daily bodily activity. The properties of these rhythms indicate the nature of interaction dynamics among physiological processes that maintain a homeostasis. Abnormalities associated with diseases or disorders usually appear as disruptions in the structure of the rhythms which makes isolating these rhythms and the ability to differentiate between them, indispensable. Computer aided diagnosis systems are ubiquitous nowadays in almost every medical facility and more closely in wearable technology, and rhythm or event detection is the first of many intelligent steps that they perform. How these rhythms are isolated? How to develop a model that can describe the transition between processes in time? Many methods exist in the literature that address these questions and perform the decoding of biomedical signals into separate rhythms. In here, we demystify the most effective methods that are used for detection and isolation of rhythms or events in time series and highlight the way in which they were applied to different biomedical signals and how they contribute to information fusion. The key strengths and limitations of these methods are also discussed as well as the challenges encountered with application in biomedical signals.

An overview of deep learning techniques for epileptic seizures detection and prediction based on neuroimaging modalities: Methods, challenges, and future works

“…Few variants of these networks, such as LSTM (long short term memory) and GRU, are created to find local and global patterns efficiently (Li et al, 2018;Hsu et al, 1990). The standard type of these networks is usually used as a baseline for creating models on signal processing and time-dependent datasets (Khalifa et al, 2020;Zihlmann et al, 2017). However, a combination of these networks with convolutional layers is popular among researchers aiming to reach high performances with more complex models.…”

Classification System of National Music Rhythm Spectrogram Based on Biological Neural Network

“…Finally, according to the classification results of the two-level classifiers and the weights of each level of classifiers, the final classification results are obtained by matching and accumulating. Literature [ 5 ] attributes the spectrum classification of music to the problem of regression. According to quality, melody, and rhythm characteristics of music, SVR regression algorithm is used to calculate the arousal and value values of each song and locate them in the emotion plane proposed by Thayer.…”

Markov Chain: A Novel Tool for Electronic Ripple Analysis

“…Markov chain model is widely used in different fields of science, technology and social science. It finds several biomedical applications like the estimation of event detection and localization of biomedical signals like EEG and lung sounds (10,11) . It is also employed in laser-based applications to understand the system entropy in thermal lens signals and beam quality analysis (12,13) .…”