RESUMO
The article deals with the detection of stress using the electrodermal activity (EDA) signal measured at the wrist. We present an approach for feature extraction from EDA. The approach uses frequency spectrum analysis in multiple frequency bands. We evaluate the proposed approach using the 4 Hz EDA signal measured at the wrist in the publicly available Wearable Stress and Affect Detection (WESAD) dataset. Seven existing approaches to stress detection using EDA signals measured by wrist-worn sensors are analysed and the reported results are compared with ours. The proposed approach represents an improvement in accuracy over the other techniques studied. Moreover, we focus on time to detection (TTD) and show that our approach is able to outperform competing techniques, with fewer data points. The proposed feature extraction is computationally inexpensive, thus the presented approach is suitable for use in real-world wearable applications where both short response times and high detection performance are important. We report both binary (stress vs. no stress) as well as three-class (baseline/stress/amusement) results.
Assuntos
Resposta Galvânica da Pele , Punho , Punho/fisiologia , Articulação do PunhoRESUMO
Gathered from a real-world discrete manufacturing floor, this dataset features measurements of pneumatic pressure and electrical current during production. Spanning 7 days and encompassing approximately 150 processed units, the data is organized into time series sampled at 100 Hz. The observed machine performs 24 steps to process each unit. Each measurement in the time series, is annotated, linking it to one of the 24 processing steps performed by the machine for processing of a single piece. Segmenting the time series into contiguous regions of constant processing step labels results in 3674 labeled segments, each encompassing one part of the production process. The dataset enriched with labels facilitates the use of supervised learning techniques, like time series classification, and supports the testing of unsupervised methods, such as clustering of time series data. The focus of this dataset is on an end-of-line testing machine for small consumer-grade electric drive assemblies (device under test - DUT). The machine performs multiple actions in the process of evaluating each DUT, with the dataset capturing the pneumatic pressures and electrical currents involved. These measurements are segmented in alignment with the testing machine's internal state transitions, each corresponding to a distinct action undertaken in manipulating the device under observation. The included segments offer distinct signatures of pressure and current for each action, making the dataset valuable for developing algorithms for the non-invasive monitoring of industrial (specifically discrete) processes.