Abstract
Telework has become a universal working style under the background of COVID-19. With the increased time of working at home, problems, such as lack of physical activities and prolonged sedentary behavior become more prominent. In this situation, a self-managing working pattern regulation may be the most practical way to maintain worker's well-being. To this end, this paper validated the idea of using an Internet of Things (IoT) system (a smartphone and the accompanying smartwatch) to monitor the working status in real-time so as to record the working pattern and nudge the user to have a behavior change. By using the accelerometer and gyroscope enclosed in the smartwatch worn on the right wrist, nine-channel data streams of the two sensors were sent to the paired smartphone for data preprocessing, and action recognition in real time. By considering the cooperativity and orthogonality of the data streams, a shallow convolutional neural network (CNN) model was constructed to recognize the working status from a common working routine. As preliminary research, the results of the CNN model show accurate performance [5-fold cross-validation: 0.97 recall and 0.98 precision; leave-one-out validation: 0.95 recall and 0.94 precision; (support vector machine (SVM): 0.89 recall and 0.90 precision; random forest: 0.95 recall and 0.93 precision)] for the recognition of working status, suggesting the feasibility of this fully online method. Although further validation in a more realistic working scenario should be conducted for this method, this proof-of-concept study clarifies the prospect of a user-friendly online working tracking system. With a tailored working pattern guidance, this method is expected to contribute to the workers' wellness not only during the COVID-19 pandemic but also take effect in the post-COVID-19 era.
Highlights
A great leap of digital healthcare is expected under the background of COVID-19, which has changed the style of socioeconomic organization
In view of the results of the previous researches above, in this research, we extend the signal source by adding the signal of gyroscope and comparing the convolutional neural network (CNN) classification model with random forest (RF) and support vector machine (SVM) in more rigorous off-line [5-fold and leave-one-out (LOO)] and real-time experiments to evaluate the feasibility of working recognition with standalone pair of smartphone and smartwatch
According to the results of the offline LOO validations, the 18-feature two-layers CNN model achieved the best results for working status recognition
Summary
A great leap of digital healthcare is expected under the background of COVID-19, which has changed the style of socioeconomic organization. On the other side of the strengthened working efficiency by saving the commuting time, the side effects caused by prolonged working hours become more visible. Given that the adverse effect of prolonged working hours and the consequent stress have been identified [1, 2], attempts that chopped up the working time with breaks have been tried and. IoT System for Telework Tracking validated [3, 4]. The change of posture may not be able to eliminate the adverse effect of prolonged working hours. Given the difficulty in keeping up to an intervention schedule by the worker himself, a fully automatic intervention system, which can recognize the working status in real-time and generate the behavior-change notification automatically, is valuable. To meet the requirements in simultaneousness and interactiveness, the system should [1] be able to recognize the motion by extracting the information from video or time-series sensor signal in real time, and [2] be able to feedback to the subject in a convenient way
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
