Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2020 Aug 1:2020:8860841.
doi: 10.1155/2020/8860841. eCollection 2020.

Modified Support Vector Machine for Detecting Stress Level Using EEG Signals

Richa Gupta  1 , M Afshar Alam  1 , Parul Agarwal  1
Affiliations

Modified Support Vector Machine for Detecting Stress Level Using EEG Signals

Richa Gupta et al. Comput Intell Neurosci. .

Abstract

Stress is categorized as a condition of mental strain or pressure approaches because of upsetting or requesting conditions. There are various sources of stress initiation. Researchers consider human cerebrum as the primary wellspring of stress. To study how each individual encounters stress in different forms, researchers conduct surveys and monitor it. The paper presents the fusion of 5 algorithms to enhance the accuracy for detection of mental stress using EEG signals. The Whale Optimization Algorithm has been modified to select the optimal kernel in the SVM classifier for stress detection. An integrated set of algorithms (NLM, DCT, and MBPSO) has been used for preprocessing, feature extraction, and selection. The proposed algorithm has been tested on EEG signals collected from 14 subjects to identify the stress level. The proposed approach was validated using accuracy, sensitivity, specificity, and F1 score with values of 96.36%, 96.84%, 90.8%, and 97.96% and was found to be better than the existing ones. The algorithm may be useful to psychiatrists and health consultants for diagnosing the stress level.

PubMed Disclaimer

Conflict of interest statement

The authors declare that there are no conflicts of interest among authors. Also, the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.

Figures

Figure 1
Figure 1
Block diagram of EEG data processing algorithms.
Figure 2
Figure 2
The 32-electrode location map used in the data acquisition step as per 10–20 international system.
Figure 3
Figure 3
WOA shrinking encircling mechanism [37].
Figure 4
Figure 4
WOA spiral updating position [37].
Figure 5
Figure 5
EEG signals of 14 different subjects with 31 attributes of each. These images were generated before preprocessing step.
Figure 6
Figure 6
Images generated after applying NLMS on different subject. The images so shown are result of after preprocessing step. It removed the eye blink artifacts and other noisy artifacts.
Figure 7
Figure 7
24 features extracted and their respective values using DCT (for cba subject).
Figure 8
Figure 8
The DCT plot for the signals whose features were extracted in Figure 6.
Figure 9
Figure 9
Average performance comparison of various techniques used along with particle swarm optimization (PSO) and modified binary particle swarm optimization (MBPSO).
Figure 10
Figure 10
Comparative results of 2 subjects (cba and clm) based on confusion matrix parameters. The results show the comparison of existing and proposed method on 4 different parameters. It also explains the effectiveness of proposed method over existing. (a) Parameter of cba. (b) Parameter of clm.
Figure 11
Figure 11
Average performance comparison of the input EEG dataset.
Figure 12
Figure 12
Existing (nonmodified SVM) and proposed (modified SVM) ROC plots for subject cba. (a) Exiting method (cba). (b) Proposed method (cba).
See this image and copyright information in PMC

References

    1. Rabasa C., Dickson S. L. Impact of stress on metabolism and energy balance. Current Opinion in Behavioral Sciences. 2016;9:71–77. doi: 10.1016/j.cobeha.2016.01.011. - DOI
    1. Khan M., Rizvi Z., Shaikh M. Z., Kazmi W., Shaikh A. Design and implementation of intelligent human stress monitoring system. International Journal of Innovation and Scientific Research. 2014;10(1):179–190.
    1. Rigas G., Goletsis Y., Fotiadis D. I. Real-time driver’s stress event detection. IEEE Transactions on Intelligent Transportation Systems. 2012;13(1):221–234. doi: 10.1109/TITS.2011.2168215. - DOI
    1. Mantri S., Patil V., Mitkar R. EEG based emotional distress analysis—a survey. International Journal of Engineering Research and Development. 2012;4(6):24–28.
    1. Jun G., Smitha K. G. EEG based stress level identification. Proceedings of the IEEE International Conference on Systems, Man, and Cybernetics (SMC); October 2016; Budapest, Hungary. - DOI