Classification of the Central Effects of Transcutaneous Electroacupuncture Stimulation (TEAS) at Different Frequencies: A Deep Learning Approach Using Wavelet Packet Decomposition with an Entropy Estimator

Abstract

The field of signal processing using machine and deep learning algorithms has undergone significant growth in the last few years, with a wide scope of practical applications for electroencephalography (EEG). Transcutaneous electroacupuncture stimulation (TEAS) is a well-established variant of the traditional method of acupuncture that is also receiving increasing research attention. This paper presents the results of using deep learning algorithms on EEG data to investigate the effects on the brain of different frequencies of TEAS when applied to the hands in 66 participants, before, during and immediately after 20 min of stimulation. Wavelet packet decomposition (WPD) and a hybrid Convolutional Neural Network Long Short-Term Memory (CNN-LSTM) model were used to examine the central effects of this peripheral stimulation. The classification results were analysed using confusion matrices, with kappa as a metric. Contrary to expectation, the greatest differences in EEG from baseline occurred during TEAS at 80 pulses per second (pps) or in the ‘sham’ (160 pps, zero amplitude), while the smallest differences occurred during 2.5 or 10 pps stimulation (mean kappa 0.414). The mean and CV for kappa were considerably higher for the CNN-LSTM than for the Multilayer Perceptron Neural Network (MLP-NN) model. As far as we are aware, from the published literature, no prior artificial intelligence (AI) research appears to have been conducted into the effects on EEG of different frequencies of electroacupuncture-type stimulation (whether EA or TEAS). This ground-breaking study thus offers a significant contribution to the literature. However, as with all (unsupervised) DL methods, a particular challenge is that the results are not easy to interpret, due to the complexity of the algorithms and the lack of a clear understanding of the underlying mechanisms. There is therefore scope for further research that explores the effects of the frequency of TEAS on EEG using AI methods, with the most obvious place to start being a hybrid CNN-LSTM model. This would allow for better extraction of information to understand the central effects of peripheral stimulation.

Architectural Neuroimmunology: A Pilot Study Examining the Impact of Biophilic Architectural Design on Neuroinflammation

“…Following the data collection process, a custom EEGLab protocol established by Uyulan et al (2023) was applied to process the raw EEG data [62]. High-and low-pass filters were applied to the data in the EEGLab to remove environmental noise.…”

“…Following the artifact rejection process, the EEGLab trimOutlier (version 0.17) script [68] was used to eliminate compromised channels and data. Once a "clean" dataset was produced, the LaplaciancleanData.m tool created by Uyulan et al (2023) was selected to transform the data into a Laplacian montage [62]. A Laplacian montage was selected for this study based on a literature review of appropriate methodologies that assessed localised neurological activity in architectural contexts [8].…”

Voiceprint Recognition under Cross-Scenario Conditions Using Perceptual Wavelet Packet Entropy-Guided Efficient-Channel-Attention–Res2Net–Time-Delay-Neural-Network Model

“…Cross-environment recognition is likely to be the most prevalent form of recognition in practical systems, as users tend to register their voiceprints in quiet environments where they can produce relatively stable and clear pronunciations, while, during verification, they may encounter various complex environments where environmental noises interfere with the recognition effectiveness. Most studies adopt scenarios that are overly simplistic, such as HI-MIA, which categorizes scenarios based on the distance between the recording device and the speaker [7][8][9]. These excessively idealistic research findings fail to reflect the true level of complexity involved in cross-environment recognition [10].…”