Learning to Predict Human Stress Level with Incomplete Sensor Data from Wearable Devices

Smartphone and wearable devices are widely used in behavioral and clinical research to collect longitudinal data that, along with ground truth data, are used to create models of human behavior. Mobile sensing researchers often program data processing and analysis code from scratch even though many research teams collect data from similar mobile sensors, platforms, and devices. This leads to significant inefficiency in not being able to replicate and build on others' work, inconsistency in quality of code and results, and lack of transparency when code is not shared alongside publications. We provide an overview of Reproducible Analysis Pipeline for Data Streams (RAPIDS), a reproducible pipeline to standardize the preprocessing, feature extraction, analysis, visualization, and reporting of data streams coming from mobile sensors. RAPIDS is formed by a group of R and Python scripts that are executed on top of reproducible virtual environments, orchestrated by a workflow management system, and organized following a consistent file structure for data science projects. We share open source, documented, extensible and tested code to preprocess, extract, and visualize behavioral features from data collected with any Android or iOS smartphone sensing app as well as Fitbit and Empatica wearable devices. RAPIDS allows researchers to process mobile sensor data in a rigorous and reproducible way. This saves time and effort during the data analysis phase of a project and facilitates sharing analysis workflows alongside publications.

Download Full-text

Continuous Stress Detection of Hospital Staff Using Smartwatch Sensors and Classifier Ensemble

10.3233/shti210607 ◽

2021 ◽

Author(s):

Muhammad Ali Fauzi ◽

Bian Yang

Keyword(s):

Stress Level ◽

High Stress ◽

Hospital Staff ◽

Wearable Devices ◽

Classifier Ensembles ◽

Stress Detection ◽

Monitoring Task ◽

The Ensemble Method ◽

The Individual ◽

Voting Strategy

High stress levels among hospital workers could be harmful to both workers and the institution. Enabling the workers to monitor their stress level has many advantages. Knowing their own stress level can help them to stay aware and feel more in control of their response to situations and know when it is time to relax or take some actions to treat it properly. This monitoring task can be enabled by using wearable devices to measure physiological responses related to stress. In this work, we propose a smartwatch sensors based continuous stress detection method using some individual classifiers and classifier ensembles. The experiment results show that all of the classifiers work quite well to detect stress with an accuracy of more than 70%. The results also show that the ensemble method obtained higher accuracy and F1-measure compared to all of the individual classifiers. The best accuracy was obtained by the ensemble with soft voting strategy (ES) with 87.10% while the hard voting strategy (EH) achieved the best F1-measure with 77.45%.

Download Full-text

Managing human stress level: a multimedia sequence approach

10.1109/eeeic/icpseurope51590.2021.9584578 ◽

2021 ◽

Author(s):

Chiara Burattini ◽

Giuseppe Curcio ◽

Giulia D'Aurizio ◽

Gianluca Maria Marcilli ◽

Francesco Brignone ◽

...

Keyword(s):

Stress Level ◽

Human Stress

Download Full-text

A Deep Learning Approach to on-Node Sensor Data Analytics for Mobile or Wearable Devices

IEEE Journal of Biomedical and Health Informatics ◽

10.1109/jbhi.2016.2633287 ◽

2017 ◽

Vol 21 (1) ◽

pp. 56-64 ◽

Cited By ~ 140

Author(s):

Daniele Ravi ◽

Charence Wong ◽

Benny Lo ◽

Guang-Zhong Yang

Keyword(s):

Deep Learning ◽

Data Analytics ◽

Wearable Devices ◽

Sensor Data ◽

Learning Approach

Download Full-text

Shilpa: A Novel Neural Based Approach for Measuring Human Stress Level

2020 11th IEEE Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON) ◽

10.1109/iemcon51383.2020.9284866 ◽

2020 ◽

Author(s):

B.T.N Perera ◽

B.G.D.N Jayarathne ◽

T.G.G.M Dharmakeerthi ◽

K.T.D.D.K Thanthilage ◽

Y.H.P.P Priyadarshana

Keyword(s):

Stress Level ◽

Human Stress

Download Full-text

Assessing the Stress of Surgeons and Surgical Residents Using a Wearable Smart Device

10.21203/rs.3.rs-141190/v1 ◽

2021 ◽

Author(s):

Jin Joo Kim ◽

Chul Seung Lee ◽

Wooree Koh ◽

Jung Hoon Bae ◽

Seung rim Han ◽

...

Keyword(s):

Perceived Stress ◽

Stress Level ◽

Resting State ◽

Short Form ◽

Wearable Devices ◽

Smart Device ◽

Health Care Market ◽

State Trait Anxiety Inventory ◽

Surgical Residents ◽

State Stress

Abstract Although surgeon is one of the most stressful professions, only few studies have attempted to evaluate surgeons’ stress using impractical methods. Meanwhile, many wearable devices have been introduced in the health-care market. This study aimed to assess surgeons’ stress using a wearable device. Data were collected from 13 participants from June to September 2019. We checked level of stress, heart rate (HR) using Vivosmart4 (Garmin, Schaffhausenm, Switzerland) at rest and perioperatively, and also checked their perioperative self-perceived stress using the short-form State-Trait Anxiety Inventory (STAI). The perioperative stress level and HR significantly increased compared with resting state (stress level: 28.6 ± 18.2 at rest vs. 49.6 ± 25.5 before surgery vs. 55.1 ± 25.5 after surgery, p < 0.001; HR: 81.1 ± 6.2 at rest vs. 85.0 ± 11.5 before surgery vs. 85.0 ± 12.2 after surgery, p = 0.001). Scores on the short-form STAI significantly decreased after surgery (12.6 ± 4.9 before surgery vs. 11.7 ± 3.6 after surgery, p = 0.001). Stress level at rest was significantly higher among fellows and residents compared with professors (fellows: 40.7 ± 15.3 vs. residents: 29.9 ± 12.0 vs. professors: 13.2 ± 7.3, p < 0.001). We assessed surgeons’ stress using a smart device and demonstrated that surgery significantly increased stress. The level of stress was higher among fellows and residents compared with professors.

Download Full-text

Evaluation of driver stress level with survey, galvanic skin response sensor data, and force-sensing resistor data

Advances in Mechanical Engineering ◽

10.1177/1687814019891555 ◽

2019 ◽

Vol 11 (12) ◽

pp. 168781401989155 ◽

Cited By ~ 2

Author(s):

Daghan Dogan ◽

Seta Bogosyan ◽

Tankut Acarman

Keyword(s):

Stress Level ◽

Galvanic Skin Response ◽

Traffic Accidents ◽

Urban Traffic ◽

Sensor Data ◽

Force Sensing ◽

Average Accuracy ◽

Skin Response ◽

Main Factors ◽

Driver Stress

Thousands of lives are lost in traffic accidents every year, and most traffic accidents are caused by driver errors. Causes and impairments such as fatigue, inattentiveness, alcohol usage, stress, and drugs are the main factors of these accidents. When a driver is subject to changing and complicated driving tasks in traffic, he or she should be able to assure driving authority to prevent potential hazards and accidents. In this context, the purpose of this study is to determine the stress level of the driver when driving in urban traffic in such situations requiring delegation of driving authority. Thus, the work combines stress questionnaire and galvanic skin response sensor to validate results and fuses with a force-sensing resistor. In this study, a prototype electric vehicle is equipped with sensors providing various drivers’ data including the responses of a force-sensing resistor sensor while galvanic skin is being collected on a specified route. At the end of the trip, the stress level of the drivers is determined by the collected data. Results indicate that the galvanic skin sensor stress results are consistent with the results of the survey with an average accuracy of 87.5%. The force-sensing resistor sensor is only used to determine gender stress. And the force-sensing resistor sensor gender-stress results are consistent with results of the survey with an accuracy of 100%. These results are used to validate the results of post-driving stress survey evaluated by SPSS 23.0 windows statistics software. Data analysis is particularly focused on demographic properties of participators, factor analysis, reliability tests, correlation, T-test, and one-way analysis of variance.

Download Full-text