Abstract

Background

Electrical line workers are among the group of workers who have one of the top 10 most dangerous jobs in America [1]. Monitoring workers' activities and specifying their activities is one of the fundamental steps in taking any preventive measures towards providing a safe working environment for these workers [2]. To monitor the safety of workers and prevent injuries, it is essential to propose a framework which does not interfere with their daily tasks. Recent advances in wearable sensors are promising in obtaining this objective, however, the concern about privacy of collected data remains an important issue, preventing their mass adoption in industry [3,4]. The information collected from sensors could vary from sensitive physiological data like heart rate to other types of data such as motion or sound. On the other hand, regardless of the type of data used, the notion of wearing sensors, enabling any type of monitoring, causes hesitance to adopt them by workers. Therefore, addressing this issue and ensuring data confidentiality could facilitate better ergonomic interventions at workplaces with less resistance from workers. It’s not long since data confidentiality has been a pressing issue in the era of artificial intelligence, and various approaches have been proposed to prevent data breaches. Yet, there is still a gap in guaranteeing the data privacy in ergonomics and safety contexts. In this paper, we developed a decentralized learning method which addresses this gap.

Approach

In this study, participants performed 10 main activities of electrical line workers in a lab environment while their acceleration data was collected using a wearable sensor on their dominant wrist. Time, frequency, and wavelet (time and frequency) features were extracted from the filtered accelerometer’s signals as inputs to the model. In this study, we use the federated weighted averaging with adaptive learning rate method to classify the activities of individuals using these features. Our model consisted of a LSTM layer, trained locally on participants' wearables. After each step of local training, the updated weights were iteratively broadcasted to a server to update the global weights. This step ensures data confidentiality, since unlike the centralized models, the training data are not combined on the server, instead only the weights are aggregated and updated. After training, we evaluated the performance of our model to that of frequently used centralized machine learning models such as LSTM, k-nearest neighbors, support vector machine, and random forest [5].

Results

Our results showed that the proposed method has a comparable performance to centralized machine learning algorithms, with a high accuracy of 90%, while ensuring the privacy of the participants. Moreover, using an adaptive learning rate through Adam algorithm on workers’ optimization step improved the classification accuracy of the model.

Conclusion

In this study we present a federated learning method which incorporates adaptive learning rates to classify the activities of electrical line workers based on acceleration signals collected using a single wearable sensor. Our results showed a comparable test accuracy to those of the centralized learning methods, promising great opportunities in adaptation of federated learning methods enabling the privacy-preservation for human activity recognition in a real-time manner.

Application to ergonomics

The outcome of this project is a privacy-preserving federated learning model for activity recognition. The proposed model can be used in similar industries to provide workers’ fatigue monitoring and injury prevention, while providing the opportunity to develop real-time ergonomic interventions for these industries.

References

1. https://www.baileyjavinscarter.com/what-is-the-death-rate-for-power-linemen/

2. Lamooki, S. R., Hajifar, S., Kang, J., Sun, H., Megahed, F. M., & Cavuoto, L. A. (2022). A data analytic end-to-end framework for the automated quantification of ergonomic risk factors across multiple tasks using a single wearable sensor. Applied ergonomics, 102, 103732.

3. Schall Jr, M. C., Sesek, R. F., & Cavuoto, L. A. (2018). Barriers to the adoption of wearable sensors in the workplace: A survey of occupational safety and health professionals. Human factors, 60(3), 351-362.

4. Häikiö, J., Kallio, J., Mäkelä, S. M., & Keränen, J. (2020). IoT-based safety monitoring from the perspective of construction site workers. International Journal of Occupational and Environmental Safety, 4(1), 1-14.

5. Ragani Lamooki, S., Hajifar, S., Hannan, J., Sun, H., Megahed, F., & Cavuoto, L. (2022). Classifying tasks performed by electrical line workers using a wrist-worn sensor: A data analytic approach. Plos one, 17(12), e0261765.

Download

Abstract Only

Share

COinS