System and method for classification and quantitative estimation of cognitive stress

US10716501B2 · kind B2 · utility

Assignee

• Tata Consultancy Services Limited · IN

Inventors

• Deepan Das · Sherghati, IN
• Tanuka Bhattacharjee · Sherghati, IN
• Shreyasi Datta · Sherghati, IN
• Anirban Dutta Choudhury · Sherghati, IN
• Pratyusha Das · Sherghati, IN
• Arpan Pal · Sherghati, IN

Key dates

• Filing date: Mar 6, 2018
• Grant date: Jul 21, 2020
• Expiry date: Jan 15, 2039

Classification

• Technology area (CPC G): Physics
• CPC primary: G16H50/70
• WIPO field: Medical technology
• WIPO sector: Instruments

Abstract

This disclosure relates generally to stress classification and quantification, and more particularly to system and method for classification and quantitative estimation of cognitive stress from analysis of keystrokes and signals derived from physiological sensors. In one embodiment, a method includes obtaining, while a user is engaged in performance of a task, physiological signals from physiological sensors accessible to the user. Feature sets are identified from the physiological signals which correlate with cognitive stress experienced by the user. Using a regression model, a stress indicator metric comprising a quantitative estimate of the cognitive stress is predicted. The regression model is trained using the feature sets and independently determined quantitative estimates of cognitive stress used as a ground truth to output the value of the stress indicator metric. The ground truth is determined from keystroke data associated with the performance of keyboard-based tasks comprising navigation of moving objects to the target.