Cloud‐aided online EEG classification system for brain healthcare: A case study of depression evaluation with a lightweight CNN

Abstract

Summary Brain healthcare, when supported by Internet of Things, can perform online and accurate analysis of brain big data for the classification of multivariate Electroencephalogram (EEG), which is a prerequisite for the recent boom in neurofeedback applications and clinical practices. However, it remains a grand research challenge due to (1) the embedded intensive noises and the intrinsic nonstationarity determined by the evolution of brain states; and (2) the lack of a user‐friendly computing platform to sustain the complicated analytics. This study presents the design of an online EEG classification system aided by Cloud centering on a lightweight Convolutional Neural Network (CNN). The system incrementally trains the CNN on Cloud and enables hot deployment of the trained classifier without the need to restart the gateway to adapt to the users' needs. The classifier maintains a High Convolutional Layer to gain the ability of processing high‐dimensional EEG segments. The number of hidden layers is minimized to ensure the efficiency of training. The lightweight CNN adopts an “hourglass” block of fully connected layers to reduce the number of neurons quickly toward the output end. A case study of depression evaluation has been performed against raw EEG datasets to distinguish between (1) Healthy and Major Depression Disorder with an accuracy, sensitivity, and specificity of [98.59% ± 0.28%], [97.77% ± 0.63%], and [99.51% ± 0.19%], respectively; and (2) Effective and Noneffective treatment outcome with an accuracy, sensitivity, and specificity of [99.53% ± 0.002%], [99.50% ± 0.01%], and [99.58% ± 0.02%], respectively. The results show that the classification can be completed several magnitudes faster when EEG is collected on the gateway (several milliseconds vs. 4 seconds).

Unsupervised Classifications of Depression Levels Based on Machine Learning Algorithms Perform Well as Compared to Traditional Norm-Based Classifications

“…In addition, Figure 2 illustrated the accuracy metrics for the training and testing processes. Obviously, the classifier had a good generalization ability and the over-fitting or less-fitting did not occur in this case as (1) training accuracy and testing accuracy were high at the same time, and (2) there was no exist significant difference between training accuracy and testing accuracy in all iterations (48).…”

A Unified Framework for Depth Prediction from a Single Image and Binocular Stereo Matching

“…Deep learning methods have helped reduce the heavy work of feature engineering [31,32]. In the context of deep learning methods, depth prediction from a single image often uses an encoder-like network to extract a feature map for a single image.…”

Geometric Accuracy Improvement Method for High-Resolution Optical Satellite Remote Sensing Imagery Combining Multi-Temporal SAR Imagery and GLAS Data

“…Cheng et al analyzed the influences of the number of SAR images, orbit direction of the SAR satellite, and the distribution of SAR images on geometric accuracy using the RFM model [14]. The first Earth observation laser altimetry satellite, Ice Cloud and Land Elevation Satellite (ICESat-1), carrying the GLAS, was launched in 2003 [15][16][17][18]. With the advantages of high altitude accuracy, global distribution, and a large number of collected footprints, GLAS footprints are widely used for height reference in the calibration and validation of digital elevation models (DEMs) [19].…”