• Nuthaki Bhargavi
• Dr .G. Umamaheswara Reddy

The detection and monitoring of stress have a significant impact on one's physical, mental, and social wellbeing. Currently available techniques for categorizing emotional states rely on traditional machine learning algorithms that compute features from a variety of sensor modalities. A new machine learning algorithm called Extreme gradient boost algorithm has been proposed and it does not require the computation of any features. This method for stress identification on individuals delivers improved results and yields the highest accuracy, 97.8%, when compared to the existing methods, using a multimodal dataset recorded via wearable physiological and motion sensors. Three separate physiological states—relaxed, alert, and stressed—are represented by the sensor data in the Wearable Stress and Affect Detection (WESAD) dataset

WESAD, Machine Learning Classifiers, ACC, BVP, EDA

"Machine Learning based Stress Detection using Multimodal Physical Data ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.9, Issue 9, page no.a525-a536, September-2022, Available :http://www.jetir.org/papers/JETIR2209054.pdf

"Machine Learning based Stress Detection using Multimodal Physical Data ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.9, Issue 9, page no. ppa525-a536, September-2022, Available at : http://www.jetir.org/papers/JETIR2209054.pdf