Bio-signal Analysis for StressDetection Using Machine Learning Methods: A Review

R, Sohara Banu A; Nagaveni,

doi:10.1109/icstcee49637.2020.9277314

Cited by 3 publications

(2 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Biosignals are time-dependent measures of biological processes occurring in the human body, and can be utilized to infer a person's state of health. Biosignals have been shown to be efficient as indicators of stress [28,29]. Their reliability is based on the fact that they are not subject to intentional or even partial conscious control, unlike the more manipulable behavioral and psychological components of stress.…”

Section: Biosignalsmentioning

confidence: 99%

AI-Enabled Smart Wristband Providing Real-Time Vital Signs and Stress Monitoring

Mitro,Nikos

Argyri

Pavlopoulos

et al. 2023

Sensors

View full text Add to dashboard Cite

This work introduces the design, architecture, implementation, and testing of a low-cost and machine-learning-enabled device to be worn on the wrist. The suggested wearable device has been developed for use during emergency incidents of large passenger ship evacuations, and enables the real-time monitoring of the passengers’ physiological state, and stress detection. Based on a properly preprocessed PPG signal, the device provides essential biometric data (pulse rate and oxygen saturation level) and an efficient unimodal machine learning pipeline. The stress detecting machine learning pipeline is based on ultra-short-term pulse rate variability, and has been successfully integrated into the microcontroller of the developed embedded device. As a result, the presented smart wristband is able to provide real-time stress detection. The stress detection system has been trained with the use of the publicly available WESAD dataset, and its performance has been tested through a two-stage process. Initially, evaluation of the lightweight machine learning pipeline on a previously unseen subset of the WESAD dataset was performed, reaching an accuracy score equal to 91%. Subsequently, external validation was conducted, through a dedicated laboratory study of 15 volunteers subjected to well-acknowledged cognitive stressors while wearing the smart wristband, which yielded an accuracy score equal to 76%.

show abstract

Section: Biosignalsmentioning

confidence: 99%

AI-Enabled Smart Wristband Providing Real-Time Vital Signs and Stress Monitoring

Mitro,Nikos

Argyri

Pavlopoulos

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…Most of the existing work implementing machine learning algorithms for the detection and prediction of stress use HRV or EDA/GSR signal as their collection does not demand intrusive methods and they provide relatively solid information about stress levels [62]. Shatte et al (2019) [63] provide in their review an extensive list of machine learning techniques used for stress detection, prediction or assessment.…”

Section: Machine Learning (Ml) Techniquesmentioning

confidence: 99%

Overview of Biosignal Analysis Methods for the Assessment of Stress

Ladakis

Chouvarda

2021

Emerg Sci J

View full text Add to dashboard Cite

Objectives: Stress is a normal reaction of the human organism induced in situations that demand a level of activation. This reaction has both positive and negative impact on the life of each individual. Thus, the problem of stress management is vital for the maintenance of a person’s psychological balance. This paper aims at the brief presentation of stress definition and various factors that can lead to augmented stress levels. Moreover, a brief synopsis of biosignals that are used for the detection and categorization of stress and their analysis is presented. Methods: Several studies, articles and reviews were included after literature research. The main questions of the research were: the most important and widely used physiological signals for stress detection/assessment, the analysis methods for their manipulation and the implementation of signal analysis for stress detection/assessment in various developed systems. Findings: The main conclusion is that current researching approaches lead to more sophisticated methods of analysis and more accurate systems of stress detection and assessment. However, the lack of a concrete framework towards stress detection and assessment remains a great challenge for the research community. Doi: 10.28991/esj-2021-01267 Full Text: PDF

show abstract

Analysis of EEG Signals Using Machine Learning for Prediction and Detection of Stress

Kotkar¹,

Nagpure²,

Phadke³

et al. 2022

IOT With Smart Systems

View full text Add to dashboard Cite

Bio-signal Analysis for StressDetection Using Machine Learning Methods: A Review

Cited by 3 publications

References 2 publications

AI-Enabled Smart Wristband Providing Real-Time Vital Signs and Stress Monitoring

AI-Enabled Smart Wristband Providing Real-Time Vital Signs and Stress Monitoring

Overview of Biosignal Analysis Methods for the Assessment of Stress

Analysis of EEG Signals Using Machine Learning for Prediction and Detection of Stress

Contact Info

Product

Resources

About