A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Monitoring Fatigue in Construction Workers Using Wearable Sensors
Fatigue on construction projects impairs worker efficiency, jeopardizes job site safety, and reduces productivity. This paper presents an innovative fatigue estimation approach that is based on the monitoring of worker heart rate and sleep quality time on construction sites using wearable sensors. An experimental test was developed to simulate a true construction activity. A Borg’s scale of 1 to 10 was used to estimate the fatigue levels of the participants in the experimental test. An experimental pilot study was conducted to monitor the heart rate and sleep quality for three participants using a fitness tracker. Classifiers, such as decision tree, support vector machine (SVM), were then trained using the fitness tracker extracted data. The results obtained showed that the polynomial SVM outperformed all other tested algorithms and was selected for further physical fatigue analysis. The accuracy of the fatigue prediction model was, respectively, 69.23% and 76.92% depending on using heart rate or both heart rate and sleep quality results.
Monitoring Fatigue in Construction Workers Using Wearable Sensors
Fatigue on construction projects impairs worker efficiency, jeopardizes job site safety, and reduces productivity. This paper presents an innovative fatigue estimation approach that is based on the monitoring of worker heart rate and sleep quality time on construction sites using wearable sensors. An experimental test was developed to simulate a true construction activity. A Borg’s scale of 1 to 10 was used to estimate the fatigue levels of the participants in the experimental test. An experimental pilot study was conducted to monitor the heart rate and sleep quality for three participants using a fitness tracker. Classifiers, such as decision tree, support vector machine (SVM), were then trained using the fitness tracker extracted data. The results obtained showed that the polynomial SVM outperformed all other tested algorithms and was selected for further physical fatigue analysis. The accuracy of the fatigue prediction model was, respectively, 69.23% and 76.92% depending on using heart rate or both heart rate and sleep quality results.
Monitoring Fatigue in Construction Workers Using Wearable Sensors
Garimella, Surya Anuradha (author) / Senouci, Ahmed (author) / Kim, Kyungki (author)
Construction Research Congress 2020 ; 2020 ; Tempe, Arizona
2020-11-09
Conference paper
Electronic Resource
English
Monitoring fatigue in construction workers using physiological measurements
| British Library Online Contents | 2017
Monitoring fatigue in construction workers using physiological measurements
| British Library Online Contents | 2017