Convolutional Neural Network Application in Biomedical Signals

Abstract

Recent improvements in big data and machine learning have enhanced the importance of biomedical signal and image-processing research. One part of machine learning evolution is deep learning networks. Deep learning networks are designed for the task of exploiting compositional structure in data. The golden age of the deep learning network in particular convolutional neural networks (CNNs) began in 2012. CNNs have rapidly become a methodology of optimal choice for analysing biomedical signals. CNNs have been successful in detecting and diagnosing an abnormality in biomedical signals. This paper has three distinct aims. The key primary aim is to provide state of the art knowledge about how deep learning evolved and revolutionized machine learning in the past few years. Second, to critically review the application of deep learning for different biomedical signals analysis and provide a holistic overview of current works of literature. Finally, to discuss the research opportunities with deep learning algorithms in the field of study that can serve as a starting point for new researchers to identify the future research direction in a concise manner.

Convolutional Neural Network for Drowsiness Detection Using EEG Signals

“…Simple CNN, ResNet, WaveNet, and Inception are among the best CNNs networks widely used in biomedical signals analysis studies. Based on recent works [ 42 , 83 , 84 , 85 , 86 , 87 , 88 , 89 , 90 , 91 , 92 , 93 , 94 , 95 , 96 , 97 ], a comparative analysis is provided in the following using various performance criteria as complexity , 1D-dimension , performance and time-consumption . In this regard, specific three tests (2, 3 and 4 states) with various values are given for each criterion as following.…”

“…Various DL models have been applied to biomedical signal analysis [ 36 ] particularly for recurrent neural networks (RNNs) [ 37 ], long short-term memory (LSTM) [ 38 ], auto-encoder (AE) [ 39 ], convolutional neural networks (CNNs) [ 40 ], deep stacking networks (DSNs) [ 41 ], etc. Among them, CNNs models [ 42 ] are the most frequently used in biomedical signals classification for anomaly detection due to its high classification accuracy. In this sense, several biomedical signals-based CNNs studies [ 43 , 44 , 45 ] have been suggested for anomaly detection tasks using various architectures such as CNN, visual geometry group network (VGGNet), Residual Network (ResNet), Dense Net, Inception Net, etc.…”

Deep Conviction Systems for Biomedical Applications Using Intuiting Procedures With Cross Point Approach

“…The operating frequencies of various signals are not determined due to the presence of diverse designs, resulting in a miscount of separate integration gates. As a starting point, neural networks are useful for processing crucial signals because they take advantage of a variety of compositional properties of biological points of representation ( 10 ). Furthermore, if any problems are found in a large structure, ECG and EEG data will be isolated, allowing for future orientations and change.…”

Deep learning in systems medicine

“…electroencephalogram, electromyography and so forth [104,105]. As illustrated in Figure 5, this method transforms a time series into polar coordinates and then into Gramian Angular Fields (GAF) images [105], i.e., the visual representation of the Gramian matrix, a linear algebra structure used to compute linear independence.…”

“…Inspired by recent successes of DL in computer vision and speech recognition, a promising relatively recent methodology has been proposed to encode time series data as images and to classify them using techniques from computer vision, which can be used to apply DL models to analyze various physiological signals such as heart rate, electrocardiogram, electroencephalogram, electromyography and so forth [ 103 , 104 ]. As illustrated in Figure 5 , this method transforms a time series into polar coordinates and then into Gramian Angular Fields (GAF) images [ 104 ], i.e.…”