Comparative Study on the Effects of Noise in ML-Based Anxiety Detection
This work addresses the challenge of making anxiety detection models robust to noisy, everyday environments for users of wearable health devices, but it is incremental as it builds on existing datasets and methods.
The study tackled the problem of noise hindering machine learning models for anxiety detection from generalizing to real-world conditions by comparing the effects of various noise intensities on model performance using the WESAD dataset, achieving a baseline accuracy of 98.7% before noise introduction.
Wearable health devices are ushering in a new age of continuous and noninvasive remote monitoring. One application of this technology is in anxiety detection. Many advancements in anxiety detection have happened in controlled lab settings, but noise prevents these advancements from generalizing to real-world conditions. We seek to progress the field by studying how noise impacts model performance and developing models that are robust to noisy, real-world conditions and, hence, attuned to the commotion of everyday life. In this study we look to investigate why and how previous methods have failed. Using the wearable stress and affect detection (WESAD) dataset, we compare the effect of various intensities of noise on machine learning models classifying levels of physiological arousal in the three-class classification problem: baseline vs. stress vs. amusement. Before introducing noise, our baseline model performance reaches 98.7%, compared to Schmidt 2018's 80.3%. We discuss potential sources of this discrepancy in results through a careful evaluation of feature extraction and model architecture choices. Finally, after the introduction of noise, we provide a thorough analysis of the effect of noise on each model architecture.