Real-Time Stress Assessment Using Sliding Window Based Convolutional Neural Network

Abstract

Mental stress has been identified as a significant cause of several bodily disorders, such as depression, hypertension, neural and cardiovascular abnormalities. Conventional stress assessment methods are highly subjective and tedious and tend to lack accuracy. Machine-learning (ML)-based computer-aided diagnosis systems can be used to assess the mental state with reasonable accuracy, but they require offline processing and feature extraction, rendering them unsuitable for real-time applications. This paper presents a real-time mental stress assessment approach based on convolutional neural networks (CNNs). The CNN-based approach afforded real-time mental stress assessment with an accuracy as high as 96%, the sensitivity of 95%, and specificity of 97%. The proposed approach is compared with state-of-the-art ML techniques in terms of accuracy, time utilisation, and quality of features.

Workplace Mental State Monitoring during VR-Based Training for Offshore Environment

“…Reduction in alpha activity is a strong indicator of stress as brain activity in this frequency band reflects relaxed state of consciousness [ 48 , 61 ]. Higher relative power in the alpha band compared to theta and beta bands during resting reflects its dominant role during relaxed consciousness [ 62 ], and has commonly been used as the neuromarker for stress response state [ 6 , 8 , 23 , 25 ]. Change in the alpha activity from high to low indicates increasing alertness and attention to external stimuli, as observed during the VR trials.…”

“…The electroencephalography (EEG) is the most used brain-monitoring method for mental stress because of its portability, high temporal resolution, non-invasive, and low cost advantages [ 5 ]. The EEG brain waves (0.5–45 Hz) are strongly associated with different brain responses towards stress and have been used to detect stress [ 6 , 7 , 8 ].…”

Exploration of EEG-Based Depression Biomarkers Identification Techniques and Their Applications: A Systematic Review

“…[51] Visual [52] N/A [53], [54], [55], [56], [57], [58], [59], [60], [61], [45], [33], [62], [63], [64], [65], [66] Depression both mild and severe stages Emotional Note reading [67] Audio [68] Emotional Picture [69], [70], [71], [72] Distractor and target [73] N/A [74], [75], [76], [77], [78], [79], [80], [81], [82], [83], [84], [85], [86], [87], [88] Depression for other reasons (stress/ epilepsy) Audio [89], [90] N/A [91], [92], [93] This…”

“…Research Articles 100-90 [89], [74], [51], [53], [64], [101], [66], [54], [2], [56], [57], [77], [70], [75], [58], [80], [81], [44], [52], [45], [93], [65], [34], [62], [63], [86], [99], [87], [88] 89.9-80 [49], [68], [102], [69], [47], [59], [78], [92], [48], [43], [50], [72] 79.9-70 [67], [82], [100], [90], [61], [85], [73], [71] 69.9-60 [79], [91] In 2017, Cai et al presented a journal where he showed a depression identification model comparison between five classifiers on 265 participants where the control participants were 113 and depressed subjects were 152. Among five classifiers (SVM, KNN, DT, LR, R...…”

“…[89], [74], [68], [53], [102], [69], [101], [66], [54], [76], [2], [56], [57], [82], [47], [100], [90], [70], [75], [78], [79], [81], [91], [92], [52], [48], [61], [85], [43], [93], [71], [34], [62], [50], [72] [74], [69], [101], [76], [75], [78], [52], [43] Beta 12-35 Hz Observable for alertness and nervous behavior, increment of beta oscillation in-phase synchronization has been found in the frontalparietal region for MDD [158].…”