Sensor-based activity recognition for construction activities on site using stacking ensemble method

İbrahim Karataş; Abdulkadir Budak

doi:10.7764/RDLC.24.2.235

Authors

İbrahim Karataş Civil Engineering Department, Osmaniye Korkut Ata University, Osmaniye (Turkey)
Abdulkadir Budak Civil Engineering Department, Osmaniye Korkut Ata University, Osmaniye (Turkey)

DOI:

https://doi.org/10.7764/RDLC.24.2.235

Keywords:

Worker activity recognition, construction activities, machine learning, sensor technology, construction management.

Abstract

Automatically recognizing workers' activities can improve productivity, safety, and management in construction. This study aimed to collect data using sensors from workers in a real construction site environment to compare various machine learning models for recognizing workers' activities. Additionally, it sought to develop a novel meta-ensemble machine-learning model to enhance prediction accuracy. For this purpose, formwork, rebar, concrete, walling, roughcast, gypsum, painting, and tiling activities were analyzed. The XGB model had the highest prediction accuracy at 96.14%. This study created a stacking meta-ensemble model to increase these prediction accuracy rates further. As a result of trying various variations, the Stacking model, which was formed by combining the SVM, RF, GBM, and XGB models and choosing the XGB model as the meta-learner, reached 98.53% prediction success. The results demonstrate that ensemble machine-learning models surpass basic machine-learning models' ability to predict outcomes accurately. By using this proposed stacking ensemble model, it is expected to create an automatic system that will calculate the productivity, risks, and fatigue of workers in future studies.

Downloads

Download data is not yet available.

References

Akhavian, R., and Behzadan, A. H. (2015). Construction equipment activity recognition for simulation input modeling using mobile sensors and machine learning classifiers. Advanced Engineering Informatics, 29(4), 867–877. https://doi.org/10.1016/j.aei.2015.03.001

Akhavian, R., and Behzadan, A. H. (Eds.) (2016a). Productivity Analysis of Construction Worker Activities Using Smartphone Sensors.

Akhavian, R., and Behzadan, A. H. (2016b). Smartphone-based construction workers' activity recognition and classification. Automation in Construction, 71, 198–209. https://doi.org/10.1016/j.autcon.2016.08.015

Akhavian, R., and Behzadan, A. H. (2018). Coupling human activity recognition and wearable sensors for data-driven construction simulation. Journal of Information Technology in Construction, 23(1), 1–15.

Al Jassmi, H., Al Ahmad, M., and Ahmed, S. (2021). Automatic recognition of labor activity: A machine learning approach to capture activity physiologi-cal patterns using wearable sensors. Construction Innovation, 21(4), 555-575.

Altheimer, J., and Schneider, J. (2024). Smart-watch-based construction worker activity recognition with hand-held power tools. Automation in Construc-tion, 167, 105684.

Antwi-Afari, M. F., Anwer, S., Umer, W., Mi, H.‑Y., Yu, Y., Moon, S., and Hossain, M. U. (2023). Machine learning-based identification and classification of physical fatigue levels: A novel method based on a wearable insole device. International Journal of Industrial Ergonomics, 93, 103404. https://doi.org/10.1016/j.ergon.2022.103404

Antwi-Afari, M. F., Li, H., Seo, J., and Wong, A. Y. L. (2018). Automated detection and classification of construction workers' loss of balance events using wearable insole pressure sensors. Automation in Construction, 96, 189–199. https://doi.org/10.1016/j.autcon.2018.09.010

Antwi-Afari, M. F., Li, H., Umer, W., Yu, Y., and Xing, X. (2020). Construction Activity Recognition and Ergonomic Risk Assessment Using a Wearable Insole Pressure System. Journal of Construction Engineering and Management, 146(7), 4020077. https://doi.org/10.1061/(ASCE)CO.1943-7862.0001849

Bangaru, S. S., Wang, C., and Aghazadeh, F. (2020). Data quality and reliability assessment of wearable EMG and IMU sensor for construction activity recognition. Sensors, 20(18), 5264.

Bangaru, S. S., Wang, C., Busam, S. A., and Aghazadeh, F. (2021). ANN-based automated scaffold builder activity recognition through wearable EMG and IMU sensors. Automation in Construction, 126, 103653. https://doi.org/10.1016/j.autcon.2021.103653

Banos, O., Galvez, J.‑M., Damas, M., Pomares, H., and Rojas, I. (2014). Window size impact in human activity recognition. Sensors (Basel, Switzerland), 14(4), 6474–6499. https://doi.org/10.3390/s140406474

Ding, L., Fang, W., Luo, H., Love, P. E., Zhong, B., and Ouyang, X. (2018). A deep hybrid learning model to detect unsafe behavior: Integrating convolu-tion neural networks and long short-term memory. Automation in Construction, 86, 118–124. https://doi.org/10.1016/j.autcon.2017.11.002

Duan, P., Zhou, J., and Tao, S. (2022). Risk events recognition using smartphone and machine learning in construction workers' material handling tasks. Engineering, Construction and Architectural Management, ahead-of-print(ahead-of-print). https://doi.org/10.1108/ECAM-10-2021-0937

Fang, Y., Cho, Y. K., and Chen, J. (2016). A framework for real-time pro-active safety assistance for mobile crane lifting operations. Automation in Con-struction, 72, 367–379. https://doi.org/10.1016/j.autcon.2016.08.025

Farooq, F., Ahmed, W., Akbar, A., Aslam, F., and Alyousef, R. (2021). Predictive modeling for sustainable high-performance concrete from industrial wastes: A comparison and optimization of models using ensemble learners. Journal of Cleaner Production, 292, 126032. https://doi.org/10.1016/j.jclepro.2021.126032

Farrahi, V., Niemelä, M., Kangas, M., Korpelainen, R., and Jämsä, T. (2019). Calibration and validation of accelerometer-based activity monitors: A systematic review of machine-learning approaches. Gait and Posture, 68, 285–299. https://doi.org/10.1016/j.gaitpost.2018.12.003

Friedman, J. (2001). Greedy Function Approximation: A Gradient Boosting Machine, The Annals of Statistics, 29(5), 1189–1232.

Garcia-Gonzalez, D., Rivero, D., Fernandez-Blanco, E., and Luaces, M. R. (2020). A Public Domain Dataset for Real-Life Human Activity Recognition Using Smartphone Sensors. Sensors (Basel, Switzerland), 20(8). https://doi.org/10.3390/s20082200

Géron, A. (2017). Hands-on machine learning with Scikit-Learn and TensorFlow: Concepts, tools, and techniques to build intelligent systems / Aurélien Géron (First edition). O'Reilly.

Jaselskis, E. J., and El-Misalami, T. (2003). Implementing Radio Frequency Identification in the Construction Process. Journal of Construction Engineering and Management, 129(6), 680–688. https://doi.org/10.1061/(ASCE)0733-9364(2003)129:6(680)

Joshua, L., and Varghese, K. (2011). Accelerometer-Based Activity Recognition in Construction. Journal of Computing in Civil Engineering, 25(5), 370–379. https://doi.org/10.1061/(ASCE)CP.1943-5487.0000097

Joshua, L., and Varghese, K. (2014). Automated recognition of construction labour activity using accelerometers in field situations. International Journal of Productivity and Performance Management, 63(7), 841–862. https://doi.org/10.1108/IJPPM-05-2013-0099

Kang, S., Cho, S., and Kang, P. (2015). Multi-class classification via heterogeneous ensemble of one-class classifiers. Engineering Applications of Artifi-cial Intelligence, 43, 35-43.

Karatas, I., and Budak, A. (2021). Prediction of Labor Activity Recognition in Construction with Machine Learning Algorithms. ICONTECH INTERNA-TIONAL JOURNAL, 5(3), 38–47. https://doi.org/10.46291/ICONTECHvol5iss3pp38-47

Karatas, I., and Budak, A. (2024a). Development and comparative of a new meta-ensemble machine learning model in predicting construction labor productivity. Engineering, Construction and Architectural Management, 31(3), 1123-1144. ahead-of-print(ahead-of-print).

Karatas, I., and Budak, A. (2024b). Deep learning-based recognition of construction activities in real construction site environment. Engineering, Construc-tion and Architectural Management, ahead-of-print(ahead-of-print).

Kayadelen, C., Önal, Y., Altay, G., Öztürk, M., and Serin, S. (2022). Effects of maintenance, traffic and climate condition on International Roughness Index of flexible pavement. International Journal of Pavement Engineering, 1–13. https://doi.org/10.1080/10298436.2022.2038382

Kim, K., and Cho, Y. K. (2020). Effective inertial sensor quantity and locations on a body for deep learning-based worker's motion recognition. Automa-tion in Construction, 113, 103126. https://doi.org/10.1016/j.autcon.2020.103126

Koc, K., Ekmekcioğlu, Ö., Gurgun, A.P. (2021). Integrating feature engineering, genetic algorithm and tree-based machine learning methods to predict the post-accident disability status of construction workers, Automation in Construction, 131, 103896.

Kohavi, R. (Ed.) (1995). A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection.

Luo, H., Xiong, C., Fang, W., Love, P. E., Zhang, B., and Ouyang, X. (2018). Convolutional neural networks: Computer vision-based workforce activity assessment in construction. Automation in Construction, 94, 282–289. https://doi.org/10.1016/j.autcon.2018.06.007

Mekruksavanich, S., and Jitpattanakul, A. (2023). Automatic Recognition of Construction Worker Activities Using Deep Learning Approaches and Wear-able Inertial Sensors. Intelligent Automation and Soft Computing, 36(2).

Nath, N. D., and Behzadan, A. H. (2017). Construction Productivity and Ergonomic Assessment Using Mobile Sensors and Machine Learning. Computing in Civil Engineering, 434–441.

Oloufa, A. A., Ikeda, M., and Oda, H. (2003). Situational awareness of construction equipment using GPS, wireless and web technologies. Automation in Construction, 12(6), 737–748. https://doi.org/10.1016/S0926-5805(03)00057-8

Peddi, A., Huan, L., Bai, Y., and Kim, S. (Eds.) (2009). DEVELOPMENT OF HUMAN POSE ANALYZING ALGORITHMS FOR THE DETERMINATION OF CONSTRUCTION PRODUCTIVITY IN REAL-TIME. ASCE.

Ryu, J., Seo, J., Jebelli, H., and Lee, S. (2019). Automated Action Recognition Using an Accelerometer-Embedded Wristband-Type Activity Tracker. Journal of Construction Engineering and Management, 145(1), 4018114. https://doi.org/10.1061/(ASCE)CO.1943-7862.0001579

Sanhudo, L., Calvetti, D., Martins, J. P., Ramos, N. M., Mêda, P., Gonçalves, M. C., and Sousa, H. (2021). Activity classification using accelerometers and machine learning for complex construction worker activities. Journal of Building Engineering, 35, 102001. https://doi.org/10.1016/j.jobe.2020.102001

Sherafat, B., Ahn, C. R., Akhavian, R., Behzadan, A. H., Golparvar-Fard, M., Kim, H., Lee, Y.‑C., Rashidi, A., and Azar, E. R. (2020). Automated Methods for Activity Recognition of Construction Workers and Equipment: State-of-the-Art Review. Journal of Construction Engineering and Management, 146(6), 3120002. https://doi.org/10.1061/(ASCE)CO.1943-7862.0001843

Sigcha, L., Pavón, I., Nisi, S., and de Arcas, G. (2020). Automatic Identification of Hand-Held Vibrating Tools Through Commercial Smartwatches and Machine Learning. Occupational and Environmental Safety and Health II, 481-489.

Taylor, K. E. (2001). Summarizing multiple aspects of model performance in a single diagram. Journal of Geophysical Research: Atmospheres, 106(D7), 7183–7192. https://doi.org/10.1029/2000JD900719

Un, B., Erdis, E., Aydınlı, S., Genc, O., and Alboga, O. (2024). Forecasting the outcomes of construction contract disputes using machine learning techniques. Engineering, Construction and Architectural Management, ahead-of-print(ahead-of-print).

Yang, Z., Yuan, Y., Zhang, M., Zhao, X., and Tian, B. (2019). Assessment of Construction Workers’ Labor Intensity Based on a Wearable Smartphone System. Journal of Construction Engineering and Management, 145(7), 4019039. https://doi.org/10.1061/(ASCE)CO.1943-7862.0001666

Ying, W., Shou, W., Wang, J., Shi, W., Sun, Y., Ji, D., Gai, H., Wang, X., and Chen, M. (2021). Automatic Scaffolding Workface Assessment for Activity Analysis through Machine Learning. Applied Sciences, 11(9), 4143. https://doi.org/10.3390/app11094143

Zhang, M., Chen, S., Zhao, X., and Yang, Z. (2018). Research on Construction Workers' Activity Recognition Based on a Smartphone. Sensors (Basel, Switzerland), 18(8). https://doi.org/10.3390/s18082667