Search citation statements
Paper Sections
Citation Types
Year Published
Publication Types
Relationship
Authors
Journals
Electroencephalography (EEG) signals provide information about the brain activities, this study bridges neuroscience and machine learning by introducing an astronomy-inspired feature extraction model. In this work, we developed a novel feature extraction function, black-white hole pattern (BWHPat) which dynamically selects the most suitable pattern from 14 options. We developed BWHPat in a four-phase feature engineering model, involving multileveled feature extraction, feature selection, classification, and cortex map generation. Textural and statistical features are extracted in the first phase, while tunable q-factor wavelet transform (TQWT) aids in multileveled feature extraction. The second phase employs iterative neighborhood component analysis (INCA) for feature selection, and the k-nearest neighbors (kNN) classifier is applied for classification, yielding channel-specific results. A new cortex map generation model highlights the most active channels using median and intersection functions. Our BWHPat-driven model consistently achieved over 99% classification accuracy across three scenarios using the publicly available EEG pain dataset. Furthermore, a semantic cortex map precisely identifies pain-affected brain regions. This study signifies the contribution to EEG signal classification and neuroscience. The BWHPat pattern establishes a unique link between astronomy and feature extraction, enhancing the understanding of brain activities.
Electroencephalography (EEG) signals provide information about the brain activities, this study bridges neuroscience and machine learning by introducing an astronomy-inspired feature extraction model. In this work, we developed a novel feature extraction function, black-white hole pattern (BWHPat) which dynamically selects the most suitable pattern from 14 options. We developed BWHPat in a four-phase feature engineering model, involving multileveled feature extraction, feature selection, classification, and cortex map generation. Textural and statistical features are extracted in the first phase, while tunable q-factor wavelet transform (TQWT) aids in multileveled feature extraction. The second phase employs iterative neighborhood component analysis (INCA) for feature selection, and the k-nearest neighbors (kNN) classifier is applied for classification, yielding channel-specific results. A new cortex map generation model highlights the most active channels using median and intersection functions. Our BWHPat-driven model consistently achieved over 99% classification accuracy across three scenarios using the publicly available EEG pain dataset. Furthermore, a semantic cortex map precisely identifies pain-affected brain regions. This study signifies the contribution to EEG signal classification and neuroscience. The BWHPat pattern establishes a unique link between astronomy and feature extraction, enhancing the understanding of brain activities.
Chronic neuropathic pain (CNP) remains a significant clinical challenge, with complex neurophysiological underpinnings that are not fully understood. Identifying specific neural oscillatory patterns related to pain perception and interference can enhance our understanding and management of CNP. The present study aimed to analyze resting electroencephalography data from individuals with CNP to explore potential neural signatures associated with pain intensity, pain interference, and specific characteristics of neuropathic pain. This was achieved through a secondary analysis of electroencephalography data and Brief Pain Inventory responses from 36 patients with CNP, originally collected in a previous cross-sectional study. For statistical analysis, we modeled a linear or logistic regression by dependent variable for each model. As independent variables, we used electroencephalography data with such brain oscillations: as delta, theta, alpha, and beta, as well as the oscillations low alpha, high alpha, low beta, and high beta, for the central, frontal, and parietal regions. All models were tested for confounding factors, such as age and medication. There were no significant models for pain interference in general activity, walking, work, relationships, sleep, and enjoyment of life. However, the model for pain intensity during the past 4 weeks showed decreased alpha oscillations, and increased delta and theta oscillations were associated with decreased levels of pain, especially in the central area. In terms of pain interference in mood, the model showed high oscillatory alpha signals in the frontal and central regions correlated with mood impairment due to pain. Our models confirm recent findings proposing that lower oscillatory frequencies, likely related to subcortical pain sources, may be associated with brain compensatory mechanisms and thus may be associated with decreased pain levels. On the other hand, higher frequencies, including alpha oscillations, may disrupt top-down compensatory mechanisms.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.