• G.SIVANJANEYA REDDY
• K.MANJU
• YASHASWINI K
• P.HIMASRI
• SD.KAIF

The project titled "Machine Learning-Based Assessment of Mental Stress Using Wearable Sensors" aims to develop an intelligent system for real-time stress detection using various physiological and motion sensors. The system integrates a heart rate sensor to monitor abnormal heartbeat, a GSR (Galvanic Skin Response) sensor to track skin conductivity, a pulse oximeter for abnormal pulse detection, and a MEMS sensor to assess abnormal walking patterns. All sensor data is processed using a Random Forest machine learning algorithm, which identifies potential stress indicators with high accuracy. The Raspberry Pi serves as the processing unit, with data gathered via an ADC module. When abnormal conditions are detected, the system activates a buzzer alert and sends notifications via email to ensure timely response. Additionally, an LCD display provides real-time updates on sensor readings. This wearable sensor-based approach offers a reliable and proactive solution for mental stress assessment, enhancing early intervention and mental health management.

Heart beat sensor, GSR sensor, pulse oximeter sensor, MEMS sensor, Raspberry pi, ML in Random forest algorithm, ADC module, LCD display.

"MACHINE LEARNING BASED ASSESSMENT OF MENTAL STRESS USING WEARABLE SENSORS ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 4, page no.l489-l494, April-2025, Available :http://www.jetir.org/papers/JETIR2504B60.pdf

"MACHINE LEARNING BASED ASSESSMENT OF MENTAL STRESS USING WEARABLE SENSORS ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 4, page no. ppl489-l494, April-2025, Available at : http://www.jetir.org/papers/JETIR2504B60.pdf