Ultra-Short Window Length and Feature Importance Analysis for Cognitive Load Detection from Wearable Sensors

Abstract

Human cognitive capabilities are under constant pressure in the modern information society. Cognitive load detection would be beneficial in several applications of human–computer interaction, including attention management and user interface adaptation. However, current research into accurate and real-time biosignal-based cognitive load detection lacks understanding of the optimal and minimal window length in data segmentation which would allow for more timely, continuous state detection. This study presents a comparative analysis of ultra-short (30 s or less) window lengths in cognitive load detection with a wearable device. Heart rate, heart rate variability, galvanic skin response, and skin temperature features are extracted at six different window lengths and used to train an Extreme Gradient Boosting classifier to detect between cognitive load and rest. A 25 s window showed the highest accury (67.6%), which is similar to earlier studies using the same dataset. Overall, model accuracy tended to decrease as the window length decreased, and lowest performance (60.0%) was observed with a 5 s window. The contribution of different physiological features to the classification performance and the most useful features that react in short windows are also discussed. The analysis provides a promising basis for future real-time applications with wearable sensors.

In Search of Harmful Stress

“…The statistical features of the EDA signal and its tonic component were predominant in each task but some HR and HRV were also among the most important. This observation is contrary to [11], where HR and HRV features were more important than EDA features in binary cognitive load detection. However, the wearable device and the tasks employed were different which has probably affected the importance scores.…”

“…However, the wearable device and the tasks employed were different which has probably affected the importance scores. Moreover, the tasks in the current study probably induced stronger stress response than in [11], which is reflected as higher activation of EDA.…”

“…Interbeat intervals (IBIs) were extracted by computing the time between heartbeats and heart rate (HR) was computed from IBIs. Feature extraction followed [7,11] and all extracted features are listed in Table 1.…”

“…It has been suggested that electrodermal activity (EDA) could complement HR and HRV measurements and provide more insight into the stress physiology [1]. In recent studies, unobtrusive, wearable devices with HR and EDA sensors have been used successfully to assess stress or cognitive load [2,5,6,11] using machine learning methodology.…”

Artificial Intelligence and Ambient Intelligence

“…The review paper is followed by seven research papers. Jaakko Tervonen et al [14] addressed the issue of human cognitive abilities under pressure in the information society in "Ultra-Short Window Length and Feature Importance Analysis for Cognitive Load Detection from Wearable Sensors". Cognitive load detection is beneficial in several applications of human-computer interaction, for example in autonomous driving.…”