Mental stress is on the rise as one of the major health problems in modern society. It is important to detect and manage mental stress to prevent various diseases caused by stress and to maintain a healthy life. The purpose of this paper is to present new heart rate variability (HRV) features based on empirical mode decomposition and to detect acute mental stress through short-term HRV (5 min) and ultra-short-term HRV (under 5 min) analysis. HRV signals were acquired from 74 young police officers using acute stressors, including the Trier Social Stress Test and horror movie viewing, and a total of 26 features, including the proposed IMF energy features and general HRV features, were extracted. A support vector machine (SVM) classification model is used to classify the stress and non-stress states through leave-one-subject-out cross-validation. The classification accuracies of short-term HRV and ultra-short-term HRV analysis are 86.5% and 90.5%, respectively. In the results of ultra-short-term HRV analysis using various time lengths, we suggest the optimal duration to detect mental stress, which can be applied to wearable devices or healthcare systems.

With the rapid development of networking and computing technology, users can easily store and interact with sensitive information on smart devices. Since smart devices are vulnerable to unauthorized access or theft, the security of personal information is becoming more important. Gait authentication is attracting attention as a continuous or unconscious biometrics method for smart devices. However, various factors, such as gait variability and sensor state by day, can degrade authentication performance. This study proposed a sensor compensation algorithm that overcomes various factors that may occur in the real world and new 2D cyclogram features to improve user authentication performance. The dataset consists of gait data from 20 people wearing wearable sensors on the wrist and thigh over 3 days. A support vector machine (SVM) model was used for the classification of gait authentication. The results showed that the proposed sensor compensation algorithm could obtain a consistent gait signal by transforming the unstable sensor coordinate system into a stable anatomical coordinate system. Also, 2D cyclogram feature sets could be used to effectively discriminate individual gait patterns. The proposed gait authentication has an accuracy of 99.63%, 94.16%, and 94.2% and an equal error rate (EER) of 0.3%, 5.84%, and 5.8% for the same session (day 1), cross session1 (day 2), and cross session2 (day 3), respectively.