Stress, as defined by psycho-biologists, is a multifaceted response that encompasses both physiological and psychological components. Chronic stress poses a substantial risk to an individual’s well-being, especially for older adults residing in assisted living facilities.

Bio-signal processing at the output combination of biosensors, such as a heart rate sensor, temperature sensor, and GSR (Galvanic Skin Response) sensor, has been shown to indicate the stress level of human beings. The use of machine learning is crucial in detecting the stress level, while the use of Internet of Things (IoT) makes it easier to share the collected data for analysis and decision making. The objective of this work was the design of IoT- and ML-based wearable stress detection devices encompassing biosensors, using bio-signal processing.

The system was evaluated for its performance in terms of finding the stress level by taking a sufficiently large range of samples. Training and testing were conducted on the samples taken from an old age home named ‘SHEOWS’ (Saint Hardyal Educational and Orphans Welfare Society), which is situated at Okhla, New Delhi, India.

Fuzzy logic algorithms were applied to classify stress levels into four distinct categories, 'Relax,' 'Calm,' 'Anxious,' or 'Stressed’, based on the collected sensor data. Machine learning techniques were employed for stress prediction using the collected sensor data and stress level labels were obtained from the fuzzy logic classification. Among the various machine learning algorithms evaluated, the Random Forest model demonstrated superior accuracy compared to other models, achieving an accuracy of 95.06% in detecting the level of stress. The available device needs to be translated into an industrial physical form so that it can be used as an aesthetic wearable device by users, collecting data continuously and transmitting the stress level to the doctor’s dashboard.