Scholarlink

This project seeks to develop an electronic system capable of identifying stress levels in university students through the use of electrophysiological signals and machine learning techniques. Through an exhaustive literature review, specific sensors were selected such as the Grove GSR and the Muscle Sensor V3, integrated in a portable device based on the ESP32 Tiny S3 microcontroller. The data obtained were stored in a web server for analysis. The machine learning model, based on the Random Forest algorithm, demonstrated high accuracy with an effectiveness of 96%, reaching 97% in the training and testing phases, and 90% in cross-validation. These results highlight the system’s ability to correctly classify stress levels. Additionally, the system presented a reliability of 93.68% in data reading, which makes it a promising tool to prevent problems related to academic stress in students.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Detection of Stress Levels in University Students from Electrophysiological Signals Using Machine Learning Techniques

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Shirley Pazmiño,
  • Paulo-C. Torres,
  • M.-Xavier López,
  • Israel Córdova,
  • Patricio Córdova

摘要

This project seeks to develop an electronic system capable of identifying stress levels in university students through the use of electrophysiological signals and machine learning techniques. Through an exhaustive literature review, specific sensors were selected such as the Grove GSR and the Muscle Sensor V3, integrated in a portable device based on the ESP32 Tiny S3 microcontroller. The data obtained were stored in a web server for analysis. The machine learning model, based on the Random Forest algorithm, demonstrated high accuracy with an effectiveness of 96%, reaching 97% in the training and testing phases, and 90% in cross-validation. These results highlight the system’s ability to correctly classify stress levels. Additionally, the system presented a reliability of 93.68% in data reading, which makes it a promising tool to prevent problems related to academic stress in students.