Abstract
Human stress analysis using electroencephalogram (EEG) signals requires a detailed and domain-specific information pool to develop an effective machine learning model. In this study, a multi-domain hybrid feature pool is designed to identify most of the important information from the signal. The hybrid feature pool contains features from two types of analysis: (a) statistical parametric analysis from the time domain, and (b) wavelet-based bandwidth specific feature analysis from the time-frequency domain. Then, a wrapper-based feature selector, Boruta, is applied for ranking all the relevant features from that feature pool instead of considering only the non-redundant features. Finally, the k-nearest neighbor (k-NN) algorithm is used for final classification. The proposed model yields an overall accuracy of 73.38% for the total considered dataset. To validate the performance of the proposed model and highlight the necessity of designing a hybrid feature pool, the model was compared to non-linear dimensionality reduction techniques, as well as those without feature ranking.
Highlights
For industrial safety, identifying risks from human error is necessary because unsafe and reckless behaviors of industrial workers and lack of precautions are directly responsible for human-caused problems
Techniques including functional magnetic resonance imaging, near-infrared spectroscopy (NIRS), electrocorticography (ECoG), and, electroencephalogram (EEG) signals have been used to detect and analyze emotional states [5,6]. fMRI and NIRS measure brain activations using brain blood. fMRI has the benefit of determining signals inside the brain with an exceptional altitudinal resolution, but the measurements are deferred until the state of the brain changes
The main purpose of this paper is to identify the mental state of a person by analyzing the EEG signals
Summary
For industrial safety, identifying risks from human error is necessary because unsafe and reckless behaviors of industrial workers and lack of precautions are directly responsible for human-caused problems. Some of the key factors of these unsafe and reckless behaviors include lack of proper sleep, lack of a proper diet, physical defects, and fatigue, which can lead a person into a stressful situation. This situation causes discomfort, anxiety, depression, cardiovascular disease, high heart rate, and several other harmful effects [1,2]. EEG uses a procedure that requires wearing a helmet [7], and EEG can be measured non-invasively It measures signals from the scalp rather than the brain itself [8]. The main purpose of this paper is to identify the mental state of a person by analyzing the EEG signals
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
