Stress increases the risk of several mental and
physical health problems like anxiety, hypertension, and cardiovascular diseases. Better guidance and interventions towards
mitigating the impact of stress can be provided if stress can
be monitored continuously. The recent proliferation of wearable
devices and their capability in measuring several physiological
signals related to stress have created the opportunity to measure
stress continuously in the wild. Wearable devices used to measure
physiological signals are mostly placed on the wrist and the
chest. Though currently chest sensors, with/without wrist sensors,
provide better results in detecting stress than using wrist sensors
only, chest devices are not as convenient and prevalent as wrist
devices, particularly in the free-living context. In this paper, we
present a solution to detect stress using wrist sensors that emulate
the gold standard chest sensors. Data from wrist sensors are
translated into the data from chest sensors, and the translated
data is used for stress detection without requiring the users to
wear any device on the chest. We evaluated our solution using a
public dataset, and results show that our solution detects stress
with accuracy comparable to the gold standard chest devices
which are impractical for daily use
more »
« less
Comparing the Predictability of Sensor Modalities to Detect Stress from Wearable Sensor Data
Detecting stress from wearable sensor data enables those struggling with unhealthy stress coping mechanisms to better manage their stress. Previous studies have investigated how mechanisms for detecting stress from sensor data can be optimized, comparing alternative algorithms and approaches to find the best possible outcome. One strategy to make these mechanisms more accessible is to reduce the number of sensors that wearable devices must support. Reducing the number of sensors will enable wearable devices to be a smaller size, require less battery, and last longer, making use of these wearable devices more accessible. To progress towards this more convenient stress detection mechanism, we investigate how learning algorithms perform on singular modalities and compare the outcome with results from multiple modalities. We found that singular modalities performed comparably or better than combined modalities on two stress-detection datasets, suggesting that there is promise for detecting stress with fewer sensor requirements. From the four modalities we tested, acceleration, blood volume pulse, and electrodermal activity, we saw acceleration and electrodermal activity to stand out in a few cases, but all modalities showed potential. Our results are acquired from testing with random holdout and leave-one-subject-out validation, using several machine learning techniques. Our results can inspire work on optimizing stress detection with singular modalities to make the benefits of these detection mechanisms more convenient.
more »
« less
- Award ID(s):
- 1852163
- NSF-PAR ID:
- 10325317
- Date Published:
- Journal Name:
- IEEE Consumer Communications and Networking Conference (CCNC)
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
High testosterone is associated with increased physical performance in sports due to its stimulation with body-muscle ratio, lean mass (muscle and bone), and bone density. Several studies show athletes with better explosive strength and sprint running performances in football, have a higher basal level of testosterone. The results suggest a relationship between testosterone production and the development of fast-twitch muscle fibers, endurance training, lean mass, resistance training in athletes as well as motivation for competition. Thus, monitoring testosterone levels is gaining attention to evaluate athletic performance of one's physical performance in sport, fitness, and bodybuilding as well as prevent health risk factors for low levels of testosterone. There have been attempts using optical, electrical and biochemical sensors to monitor testosterone but are difficult to reproduce in large quantities and suffer from limitations of sensitivity, and detection limits. This can be addressed using Molecularly Imprinted Polymers (MIPs) in a point of care (POC) system. Molecularly Imprinted Polymers (MIPs) are a synthetic polymer with cavities in the polymer matrix serve as recognition sites for a specific template molecule, which are detected using electrochemical amperometry. In this paper, we have used MIPs in conjunction with cyclic voltammetry, to produce a viable, ultrasensitive electrochemical sensor for the detection of testosterone from a human sweat sample. This combination of MIPs and cyclic voltammetry allows for a simple, low-cost, mass-producible, and non-invasive method for detecting testosterone in human males. This method is extremely simple and cheap, allowing for consistent measurement of Testosterone levels in humans and allows for the detection of Testosterone in a POC. In our work, a Screen-printed carbon electrode (SPCE) using polypropylene fabric was used as the base working electrode in a three-electrode system. The screen-printing technique was implemented to layer a carbon paste over both sides of the fabric and was air-dried for one hour at 75⁰C. The SPCE was immersed into an acetate buffer solution that contains a 2.0mM monomer called o-phenylenediamine and with a 0.1mM testosterone template. Electropolymerization was carried out with cyclic voltammetry from a range of 0V to 1.0V, at a scan rate of 50 mV/s, a sensitivity (A/V) of 1e-5A, and for a total of 30 cycles. The set concentration tested was 100-1600 ng/ml of testosterone. The electrochemical characterization will have a potential sweep of -1.2 V to 1.2 V, a scan rate of 0.05 (V/s), a sensitivity (A/V) of 1e-5A, and a singular cycle. The wearable biosensor showed a detection range for testosterone from 100ng to 1600ng, electrochemical results also showed a clear and measurable result with an R-square value of 0.9417 which proves the accuracy of the developed sensor. Although this is not the complete saturation point and theoretically maximum limit of 28,842ng/ml can be achieved although this was not tested. The detectable lowest concentration of testosterone was found to be ~100ng/ml, and it was noted that lower than 100ng gives a weaker signal, In conclusion a novel electrochemical sensor based on a molecularly imprinted polymer used as the extended gate of a field effect transistor was developed for the ultrasensitive detection of sweat Testosterone. This sensing technology paves the way for the low cost, label-free, and point of care detection which can be used for evaluating ang monitoring athletic performance.more » « less
-
Stress detection and monitoring is an active area of research with important implications for an individual's personal, professional, and social health. Current approaches for stress classification use traditional machine learning algorithms trained on features computed from multiple sensor modalities. These methods are data and computation-intensive, rely on hand-crafted features, and lack reproducibility. These limitations impede the practical use of stress detection and classification systems in the real world. To overcome these shortcomings, we propose Stressalyzer, a novel stress classification and personalization framework from single-modality sensor data without feature computation and selection. Stressalyzer uses only Electrodermal activity (EDA) sensor data while providing competitive results compared to the state-of-the-art techniques that use multiple sensor modalities and are computationally expensive due to the calculation of large number of features. Using the dataset collected in a laboratory setting from $15$ subjects, our single-channel neural network-based model achieves a classification accuracy of 92.9% and an f1 score of 0.89 for binary stress classification. Our leave-one-subject-out analysis establishes the subjective nature of stress and shows that personalizing stress models using Stressalyzer significantly improves the model performance. Without model personalization, we found a performance decline in 40% of the subjects, suggesting the need for model personalization.more » « less
-
more » « less
Abstract Opioid use disorder is one of the most pressing public health problems of our time. Mobile health tools, including wearable sensors, have great potential in this space, but have been underutilized. Of specific interest are digital biomarkers, or end-user generated physiologic or behavioral measurements that correlate with health or pathology. The current manuscript describes a longitudinal, observational study of adult patients receiving opioid analgesics for acute painful conditions. Participants in the study are monitored with a wrist-worn E4 sensor, during which time physiologic parameters (heart rate/variability, electrodermal activity, skin temperature, and accelerometry) are collected continuously. Opioid use events are recorded via electronic medical record and self-report. Three-hundred thirty-nine discreet dose opioid events from 36 participant are analyzed among 2070 h of sensor data. Fifty-one features are extracted from the data and initially compared pre- and post-opioid administration, and subsequently are used to generate machine learning models. Model performance is compared based on individual and treatment characteristics. The best performing machine learning model to detect opioid administration is a Channel-Temporal Attention-Temporal Convolutional Network (CTA-TCN) model using raw data from the wearable sensor. History of intravenous drug use is associated with better model performance, while middle age, and co-administration of non-narcotic analgesia or sedative drugs are associated with worse model performance. These characteristics may be candidate input features for future opioid detection model iterations. Once mature, this technology could provide clinicians with actionable data on opioid use patterns in real-world settings, and predictive analytics for early identification of opioid use disorder risk.
-
null (Ed.)Human activity recognition (HAR) is growing in popularity due to its wide-ranging applications in patient rehabilitation and movement disorders. HAR approaches typically start with collecting sensor data for the activities under consideration and then develop algorithms using the dataset. As such, the success of algorithms for HAR depends on the availability and quality of datasets. Most of the existing work on HAR uses data from inertial sensors on wearable devices or smartphones to design HAR algorithms. However, inertial sensors exhibit high noise that makes it difficult to segment the data and classify the activities. Furthermore, existing approaches typically do not make their data available publicly, which makes it difficult or impossible to obtain comparisons of HAR approaches. To address these issues, we present wearable HAR (w-HAR) which contains labeled data of seven activities from 22 users. Our dataset’s unique aspect is the integration of data from inertial and wearable stretch sensors, thus providing two modalities of activity information. The wearable stretch sensor data allows us to create variable-length segment data and ensure that each segment contains a single activity. We also provide a HAR framework to use w-HAR to classify the activities. To this end, we first perform a design space exploration to choose a neural network architecture for activity classification. Then, we use two online learning algorithms to adapt the classifier to users whose data are not included at design time. Experiments on the w-HAR dataset show that our framework achieves 95% accuracy while the online learning algorithms improve the accuracy by as much as 40%.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
