Individual performance calibration using physiological stress signals
This work addresses the need for personalized performance calibration in fields like human-computer interaction or healthcare, though it is incremental as it builds on the Yerkes-Dodson Law with new physiological data.
The paper tackled the problem of individual variation in the stress-performance relationship by developing a method to determine each person's optimal performance point using physiological signals, finding that GSR and HR signals can distinguish stress from relaxation and correlate with task complexity, with the optimal point identified just before performance decline.
The relation between performance and stress is described by the Yerkes-Dodson Law but varies significantly between individuals. This paper describes a method for determining the individual optimal performance as a function of physiological signals. The method is based on attention and reasoning tests of increasing complexity under monitoring of three physiological signals: Galvanic Skin Response (GSR), Heart Rate (HR), and Electromyogram (EMG). Based on the test results with 15 different individuals, we first show that two of the signals, GSR and HR, have enough discriminative power to distinguish between relax and stress periods. We then show a positive correlation between the complexity level of the tests and the GSR and HR signals, and we finally determine the optimal performance point as the signal level just before a performance decrease. We also discuss the differences among signals depending on the type of test.