Deep learning-based stress detection using multimodal biosignals
International Journal of Data Science and Analytics, cilt.22, sa.1, 2026 (ESCI, Scopus)
- Yayın Türü: Makale / Tam Makale
- Cilt numarası: 22 Sayı: 1
- Basım Tarihi: 2026
- Doi Numarası: 10.1007/s41060-026-01270-y
- Dergi Adı: International Journal of Data Science and Analytics
- Derginin Tarandığı İndeksler: Emerging Sources Citation Index (ESCI), Scopus
- Anahtar Kelimeler: Biosignals, LSTM, Multivariate approximation model, Psychological experiments, Stress response
- Açık Arşiv Koleksiyonu: AVESİS Açık Erişim Koleksiyonu
- İstanbul Kültür Üniversitesi Adresli: Evet
Özet
Stress-related health problems drive an urgent need for sensitive, real-time monitoring devices capable of capturing psychophysiological stress dynamics in natural settings. This study presents a stress detection system that uses deep learning, combining synchronized physiological signals and survey data from university students who experienced controlled stress through psychological sessions and examinations. We analyzed two model families with differing complexities: a deep neural network (DNN)-based model for static physiological patterns and a long short-term memory (LSTM)-based model designed to capture temporal dependencies in biosignals. The DNN (86.42% accuracy) was outperformed by the LSTM-based model (94.14% accuracy). The statistical results showed a relationship between stress and gender (females: μ = 2.2, males: μ = 2.7, p < 0.05) and smoking (smokers: μ = 3.7, nonsmokers: μ = 2.2, p < 0.05). Academic elements also impacted stress perception. The stress scores were in accordance with self-reported measurements, which validated the model.