Mental Stress Detection via Heart Rate Variability using Machine Learning

Abstract

Mental stress is an undesirable condition for everyone. Increased stress can cause many problems, such as depression, heart attacks, and strokes. Psychophysiological conditions possible use as a reference to a person’s mental state of stress. The development of mobile device technology, along with the accompanying sensors, can be used to measure the psychophysiological condition of its users. Heart rate allows measured from the photoplethysmography signal utilizing a smartphone or smartwatch. The heart rate variability is currently one of the most studied methods for assessing mental stress. Our objective is to analyze stress levels on the subjects when performing tasks on the smartphone. This study involved 41 students as respondents. Their heart rate was recorded using a smartphone while they were doing the n-back tasks. The n-back task is one of the performance tasks used to measure working memory and working memory capacity. In this study, the n-back task was also used as a stressor. The heart rate dataset and n-back task results are then processed and analyzed using machine learning to determine stress levels. Compared with three other algorithms (neural network, discriminant analysis, and naïve Bayes), the k-nearest neighbor algorithm is most appropriate to use in the classification of time and frequency domain analysis.

Alignment Between Heart Rate Variability From Fitness Trackers and Perceived Stress: Perspectives From a Large-Scale In Situ Longitudinal Study of Information Workers

“…The size of this effect is, to some degree, expected, given that HRV only measures ANS activity and not HPA activity, thus being an incomplete assessment of stress, even in ideal conditions. That said, we would have expected a stronger relationship between perceived stress and HRV a priori, given its popular use in assessing stress [8,[34][35][36][37]. Nevertheless, despite the small magnitude of the effect, we also found some evidence for incremental prediction in that HRV uniquely predicted perceived stress above and beyond self-reported positive affect, negative affect, and anxiety (Table 7).…”

“…These studies demonstrate that HRV associations with perceived stress obtained in situ and with wearables are less consistent than in laboratory studies. The evidence is inconclusive as to whether HRV in real-life settings could reflect daily or momentary perceived stress, as is often assumed in popular applications [8,[34][35][36][37]. The greatest success comes from a few small-scale studies with simplified (eg, binarized from ordinal ratings with the removal of the more difficult middle cases) stress classification tasks.…”

“…Traditionally used in wearable equipment such as fitness trackers, smartwatches, and armbands, they are easy to fit and have extended battery life, therefore allowing for continuous measurement of BBI and, in consequence, HRV. This has enabled a myriad of applications that use these sensors to measure HRV and provide a measurement of "stress" [8,[34][35][36][37]. However, although HRV is associated with stress in laboratory studies, as discussed previously, HRV only measures one component of the stress response: ANS activity.…”

Real-Time Personalized Physiologically Based Stress Detection for Hazardous Operations

“…To train the machine learning model, participant physiological signals were collected for three stressor levels during either a spaceflight emergency fire procedure on a VR International Space Station (VR-ISS) [46,47] or on a wellvalidated and less-complex N-back mental workload task [48]. Several previous studies have detected stress induced by Nback task via machine learning methods, both alone [48,49] and with another job-specific task [50]. Therefore, comparing a job-specific VR-ISS task to the N-back using the same personalized approach is a way to assess the system's reliability can work for multiple stress detection tasks.…”

Comparative Study of Machine Learning Algorithms in Classifying HRV for the Driver’s Physiological Condition

“…Information from EEG data is mostly employed in studies of brain activity. Mean frequency, energy contents, and bands are examples of frequency domain properties that can be used to determine a driver's state, such as driver fatigueness, which is revealed by the fronto-medial activity ϑ power [12], whereas standard deviation and average value are time-domain measures that provide information about driver alertness [13]. In a previous study, the EEG-Beat algorithm was proposed to perform automated analysis of HRV from the EEG.…”