Galvanic Skin Response and Photoplethysmography for Stress Recognition Using Machine Learning and Wearable Sensors

被引:0
作者
Nechyporenko, Alina [1 ,2 ]
Frohme, Marcus [1 ]
Strelchuk, Yaroslav [1 ]
Omelchenko, Vladyslav [1 ,2 ]
Gargin, Vitaliy [3 ,4 ]
Ishchenko, Liudmyla [1 ]
Alekseeva, Victoriia [1 ,3 ,4 ]
机构
[1] Tech Univ Appl Sci Wildau, Div Mol Biotechnol & Funct Genom, 1 Hochschulring, D-15745 Wildau, Germany
[2] Kharkiv Natl Univ Radio Elect, Syst Engn Dept, 14 Nauky ave, UA-61166 Kharkiv, Ukraine
[3] Kharkiv Natl Med Univ, Dept Otorhinolaryngol, Dept Pathol Anat, 4 Nauky Ave, UA-61000 Kharkiv, Ukraine
[4] Kharkiv Int Med Univ, Dept Professionally Oriented Disciplines, 38 Molochna Str, UA-61001 Kharkiv, Ukraine
来源
APPLIED SCIENCES-BASEL | 2024年 / 14卷 / 24期
关键词
galvanic skin response; photoplethysmography; stress; machine learning; PSYCHOLOGICAL STRESS; CONDUCTANCE; SYSTEM;
D O I
10.3390/app142411997
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
This study investigates stress recognition using galvanic skin response (GSR) and photoplethysmography (PPG) data and machine learning, with a new focus on air raid sirens as a stressor. It bridges laboratory and real-world conditions and highlights the reliability of wearable sensors in dynamic, high-stress environments such as war and conflict zones. The study involves 37 participants (20 men, 17 women), aged 20-30, who had not previously heard an air raid siren. A 70 dB "S-40 electric siren" (400-450 Hz) was delivered via headphones. The protocol included a 5 min resting period, followed by 3 min "no-stress" phase, followed by 3 min "stress" phase, and finally a 3 min recovery phase. GSR and PPG signals were recorded using Shimmer 3 GSR+ sensors on the fingers and earlobes. A single session was conducted to avoid sensitization. The workflow includes signal preprocessing to remove artifacts, feature extraction, feature selection, and application of different machine learning models to classify the "stress "and "no-stress" states. As a result, the best classification performance was shown by the k-Nearest Neighbors model, achieving 0.833 accuracy. This was achieved by using a particular combination of heart rate variability (HRV) and GSR features, which can be considered as new indicators of siren-induced stress.
引用
收藏
页数:20
相关论文
共 50 条
  • [21] Fall Detection with Supervised Machine Learning using Wearable Sensors
    Giuffrida, Davide
    Benetti, Guido
    De Martini, Daniele
    Facchinetti, Tullio
    2019 IEEE 17TH INTERNATIONAL CONFERENCE ON INDUSTRIAL INFORMATICS (INDIN), 2019, : 253 - 259
  • [22] Detecting Falls with Wearable Sensors Using Machine Learning Techniques
    Ozdemir, Ahmet Turan
    Barshan, Billur
    SENSORS, 2014, 14 (06) : 10691 - 10708
  • [23] Determination of Stress using Blood Pressure and Galvanic Skin Response
    Fernandes, Atlee
    Helawar, Rakesh
    Lokesh, R.
    Tari, Tushar
    Shahapurkar, Ashwini V.
    2014 INTERNATIONAL CONFERENCE ON COMMUNICATION AND NETWORK TECHNOLOGIES (ICCNT), 2014, : 165 - 168
  • [24] User Stress Modeling through Galvanic Skin Response
    Satti, Fahad Ahmed
    Hussain, Musarrat
    Hussain, Jamil
    Kim, Tae-Seong
    Lee, Sungyoung
    Chung, TaeChoong
    PROCEEDINGS OF THE 2021 15TH INTERNATIONAL CONFERENCE ON UBIQUITOUS INFORMATION MANAGEMENT AND COMMUNICATION (IMCOM 2021), 2021,
  • [25] Fabrication of a portable device for stress monitoring using wearable sensors and soft computing algorithms
    Alireza Golgouneh
    Bahram Tarvirdizadeh
    Neural Computing and Applications, 2020, 32 : 7515 - 7537
  • [26] Fall Recognition using Wearable Technologies and Machine Learning Algorithms
    Harris, Austin
    True, Hanna
    Hu, Zhen
    Cho, Jin
    Fell, Nancy
    Sartipi, Mina
    2016 IEEE INTERNATIONAL CONFERENCE ON BIG DATA (BIG DATA), 2016, : 3974 - 3976
  • [27] A machine-learning approach for stress detection using wearable sensors in free-living environments
    Abd Al-Alim M.
    Mubarak R.
    M. Salem N.
    Sadek I.
    Computers in Biology and Medicine, 2024, 179
  • [28] Analysis of Galvanic Skin Response to Acoustic Stimuli by Wearable Devices
    Iadarola, Grazia
    Poli, Angelica
    Spinsante, Susanna
    2021 IEEE INTERNATIONAL SYMPOSIUM ON MEDICAL MEASUREMENTS AND APPLICATIONS (IEEE MEMEA 2021), 2021,
  • [29] Automatic recognition of labor activity: a machine learning approach to capture activity physiological patterns using wearable sensors
    Al Jassmi, Hamad
    Al Ahmad, Mahmoud
    Ahmed, Soha
    CONSTRUCTION INNOVATION-ENGLAND, 2021, 21 (04): : 555 - 575
  • [30] Sequential Human Activity Recognition Based on Deep Convolutional Network and Extreme Learning Machine Using Wearable Sensors
    Sun, Jian
    Fu, Yongling
    Li, Shengguang
    He, Jie
    Xu, Cheng
    Tan, Lin
    JOURNAL OF SENSORS, 2018, 2018