Abstract
Stress management is critical for forecasting stress levels and identifying the impact of stress on a person’s socioeconomic life. For effective stress prediction, the Deep Belief Network and Transfer Learning (DBNTL) approach extracts information on the top layers but degrades performance on various levels. As a result, this study offers a unique stress emotion identification technique with discrepancy reduction that enables stress emotion recognition-based classifiers on small-scale emotion and stress data domains. The marginal distribution difference at comparable layers and the combined distribution discrepancy of diverse levels aid stress emotion identification in learning better quality features at the top layers; even distinct emotion and stress domains have feature-level similarities. Because all of the stress emotion detection layers are similarly trained, it evaluates both marginal and joint distribution discrepancies across several layers. Furthermore, a careful balance of these two disparities can improve transferability between emotion and stress domains. Finally, when compared to convolutional neural networks and DBNTL-based stress emotion classification techniques, the experimental results show that the stress emotion identification approach is more efficient.
Similar content being viewed by others
References
Akçay MB, Oğuz K (2020) Speech emotion recognition: emotional models, databases, features, preprocessing methods, supporting modalities, and classifiers. Speech Comm 116:56–76
Banerjee D, Islam K, Xue K, Mei G, Xiao L, Zhang G, Li J (2019) A deep transfer learning approach for improved post-traumatic stress disorder diagnosis. Knowl Inf Syst 60(3):1693–1724
Castaldo R, Melillo P, Bracale U, Caserta M, Triassi M, Pecchia L (2015) Acute mental stress assessment via short term HRV analysis in healthy adults: a systematic review with meta-analysis. Biomed Signal Process Control 18:370–377
Chen LL, Zhang A, Lou XG (2019) Cross-subject driver status detection from physiological signals based on hybrid feature selection and transfer learning. Expert Syst Appl 137:266–280
Dzedzickis A, Kaklauskas A, Bucinskas V (2020) Human emotion recognition: review of sensors and methods. Sensors 20(3):592
Feng K, Chaspari T (2020) A review of generalizable transfer learning in automatic emotion recognition. Front Comput Sci 2:9
Garcia-Ceja E, Riegler M, Kvernberg AK, Torresen J (2020) User-adaptive models for activity and emotion recognition using deep transfer learning and data augmentation. User Model User-Adap Inter 30(3):365–393
He J, Li K, Liao X, Zhang P, Jiang N (2019) Real-time detection of acute cognitive stress using a convolutional neural network from electrocardiographic signal. IEEE Access 7:42710–42717
He J, Li K, Liao X, Zhang P, Jiang N (2019) Real-time detection of acute cognitive stress using a convolutional neural network from electrocardiographic signal. IEEE Access 7:42710–42717
Jaiswal M, Provost EM (2020 Apr 3) Privacy enhanced multimodal neural representations for emotion recognition. In: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 34, No. 05, pp. 7985–7993
Jawharali B, Arunkumar B (2019) Efficient human stress level prediction and prevention using neural network learning through EEG signals. Int J Eng Res Technol 12(1):66–72
Kaur B, Singh D, Roy PP (2018) EEG based emotion classification mechanism in BCI. Procedia Comput Sci 132:752–758
Lan Z, Sourina O, Wang L, Scherer R, Müller-Putz GR (2018) Domain adaptation techniques for EEG-based emotion recognition: a comparative study on two public datasets. IEEE Trans Cogn Develop Syst 11(1):85–94
Li W, Huan W, Hou B, Tian Y, Zhang Z, Song A (2021) Can emotion be transferred?–a review on transfer learning for EEG-based emotion recognition. IEEE Trans Cogn Develop Syst 21:1
Liapis A, Katsanos C, Sotiropoulos D, Xenos M, Karousos N (2015) Recognizing emotions in human computer interaction: studying stress using skin conductance. In: IFIP Conference on Human-Computer Interaction, Springer, Cham. pp. 255–262
Luo J, Chen H, Xu Y, Huang H, Zhao X (2018) An improved grasshopper optimization algorithm with application to financial stress prediction. Appl Math Model 64:654–668
Ma Z, Ma F, Sun B, Li S (2021 Oct 24) Hybrid Mutimodal Fusion for Dimensional Emotion Recognition. In: Proceedings of the 2nd on Multimodal Sentiment Analysis Challenge. pp. 29–36
Masood K, Alghamdi MA (2019) Modeling mental stress using a deep learning framework. IEEE Access 7:68446–68454
Maxhuni A, Hernandez-Leal P, Sucar LE, Osmani V, Morales EF, Mayora O (2016) Stress modelling and prediction in presence of scarce data. J Biomed Inform 63:344–356
Pereira T, Almeida PR, Cunha JP, Aguiar A (2017) Heart rate variability metrics for fine-grained stress level assessment. Comput Methods Prog Biomed 148:71–80
Prasannavenkatesan T (2021) Forecasting hyponatremia in hospitalized patients using multilayer perceptron and multivariate linear regression techniques. Concurr Comput Pract Exp 33:e6248
Prasannavenkatesan T (2021) Probable forecasting of epidemic COVID-19 in using COCUDE model. EAI Endorsed Trans Pervasive Health Technol, Online First. https://doi.org/10.4108/eai.3-2-2021.168601
Shaw A, Simsiri N, Deznaby I, Fiterau M, Rahaman T (2019) Personalized student stress prediction with deep multitask network. arXiv preprint arXiv:1906.11356
Song SH, Kim DK (2017) Development of a stress classification model using deep belief networks for stress monitoring. Healthc Inform Res 23(4):285–292
Sriramprakash S, Prasanna VD, Murthy OR (2017) Stress detection in working people. Procedia Comput Sci 115:359–366
Theerthagiri P, Menakadevi T (2019) Futuristic Speed Prediction Using Auto-Regression and Neural Networks for Mobile Ad hoc Networks. Int J Commun Syst 32(9):e3951
Theerthagiri P, Jeena Jacob I, Usha Ruby A, Yendapalli V (2021) Prediction of COVID-19 possibilities using K-nearest neighbour classification algorithm. Int J Cur Res Rev 13(06):156
Torres EP, Torres EA, Hernández-Álvarez M, Yoo SG (2020) EEG-based BCI emotion recognition: a survey. Sensors. 20(18):5083
UCI repository (n.d.) https://archive.ics.uci.edu/ml/datasets/WESAD/Wearable Stress and Affect Detection.
Uddin MZ, Nilsson EG (2020) Emotion recognition using speech and neural structured learning to facilitate edge intelligence. Eng Appl Artif Intell 94:103775
Usha Ruby A, Prasannavenkatesan T, Jeena Jacob I, Vamsidhar Y (2020) Binary cross entropy with deep learning technique for image classification. Int J Adv Trends Comput Sci Eng 9(4):5393–5397
Wu D, Han X, Yang Z, Wang R (2020) Exploiting transfer learning for emotion recognition under cloud-edge-client collaborations. IEEE J Sel Areas Commun 39(2):479–490
Zhang Q, Chen X, Zhan Q, Yang T, Xia S (2017) Respiration-based emotion recognition with deep learning. Comput Ind 92:84–90
Zhang J, Yin Z, Chen P, Nichele S (2020) Emotion recognition using multi-modal data and machine learning techniques: a tutorial and review. Information Fusion 59:103–126
Zhao J, Mao X, Chen L (2019) Speech emotion recognition using deep 1D & 2D CNN LSTM networks. Biomed Signal Process Control 47:312–323
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Funding/conflicts of interests/competing interests
Nil
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Theerthagiri, P. Stress emotion recognition with discrepancy reduction using transfer learning. Multimed Tools Appl 82, 5949–5963 (2023). https://doi.org/10.1007/s11042-022-13593-6
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-022-13593-6