Data-driven decision-making emerged as critical tool, in response to the significant growth in scale and complexity in construction engineering. Currently, the process is carrying out by utilizing deep learning technique such as Neural Network (NN) and Bidirectional Gated Recurrent Units (BiGRU). NN is great in processing complex features relationship in time-independent data, BiGRU shows great performance in processing data with temporal dependencies. To leverage the advantage of NN and BiGRU, this study proposed a novel hybrid deep machine learning by combining NN and BiGRU. Additionally, integrated Optical Microscope Algorithm, an optimization algorithm inspired by microscope mechanism, for fine-tuning the NN-BiGRU hybrid model (OMA-NN-BIGRU), increasing the model accuracy and generalizability. Through case studies implementation the OMA-NN-BiGRU shows great performance and able to outperform other base and hybrid model with the following regression metrics value for each case. In the case of estimating construction cost: RMSE = 0.121, MAE = 0.0095, MAPE = 7.63 %, R = 0.9948 and R2 = 0.9889, with a RI index of 0.97716. In the case of predicting estimate schedule to completion: RMSE = 0.057, MAE = 0.0453, MAPE = 11.97 %, R = 0.9696 and R2 = 0.8861 with a RI index of 0.92674. In the case of predicting TBM performance: RMSE = 0.0528, MAE = 0.0395, MAPE = 13.7 %, R = 0.9251 and R2 = 0.8515, with a RI index of 0.90946. An accurate prediction model empowers stakeholders in the construction engineering to make informed decisions, leading to project efficiency and success.

Abioye, S. O., Oyedele, L. O., Akanbi, L., Ajayi, A., Davila Delgado, J. M., Bilal, M., Akinade, O. O., & Ahmed, A. (2021). Artificial intelligence in the construction industry: A review of present status, opportunities and future challenges. Journal of Building Engineering, 44, 103299. https://doi.org/https://doi.org/10.1016/j.jobe.2021.103299
Amari, S. (1967). A theory of adaptive pattern classifiers. IEEE Transactions on Electronic Computers(3), 299-307.
Berners-Lee, C. M. (1968). Cybernetics and Forecasting. Nature, 219(5150), 202-203. https://doi.org/10.1038/219202b0
Chen, Z., Zhang, Y., Li, J., Li, X., & Jing, L. (2021). Diagnosing tunnel collapse sections based on TBM tunneling big data and deep learning: A case study on the Yinsong Project, China. Tunnelling and Underground Space Technology, 108, 103700. https://doi.org/https://doi.org/10.1016/j.tust.2020.103700
Cheng, M.-Y., Chang, Y.-H., & Korir, D. (2019). Novel approach to estimating schedule to completion in construction projects using sequence and nonsequence learning. Journal of Construction Engineering and Management, 145(11), 04019072.
Cheng, M.-Y., Khitam, A. F. K., & Tanto, H. H. (2023). Construction worker productivity evaluation using action recognition for foreign labor training and education: A case study of Taiwan. Automation in Construction, 150, 104809. https://doi.org/https://doi.org/10.1016/j.autcon.2023.104809
Cheng, M.-Y., Wu, Y.-W., & Huang, C.-C. (2020). Hybrid Gaussian Process Inference Model for Construction Management Decision Making. International Journal of Information Technology & Decision Making, 19(04), 1015-1036. https://doi.org/10.1142/s0219622020500212
Cho, K., Van Merriënboer, B., Bahdanau, D., & Bengio, Y. (2014). On the properties of neural machine translation: Encoder-decoder approaches. arXiv preprint arXiv:1409.1259.
Dai, Z., Li, P., Zhu, M., Zhu, H., Liu, J., Zhai, Y., & Fan, J. (2023). Dynamic prediction for attitude and position of shield machine in tunneling: A hybrid deep learning method considering dual attention. Advanced Engineering Informatics, 57, 102032. https://doi.org/https://doi.org/10.1016/j.aei.2023.102032
Fu, X., Wu, M., Tiong, R. L. K., & Zhang, L. (2023). Data-driven real-time advanced geological prediction in tunnel construction using a hybrid deep learning approach. Automation in Construction, 146, 104672. https://doi.org/https://doi.org/10.1016/j.autcon.2022.104672
Gosal, F. E., & Tambunan, E. (2021). Effect of side frictions on level of service of DI Panjaitan street in Cawang - East Jakarta. IOP Conference Series: Earth and Environmental Science, 878(1), 012048. https://doi.org/10.1088/1755-1315/878/1/012048
Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural computation, 9(8), 1735-1780.
Hopfield, J. J. (1982). Neural networks and physical systems with emergent collective computational abilities. Proceedings of the national academy of sciences, 79(8), 2554-2558.
Jordan, M. I. (1997). Serial order: A parallel distributed processing approach. In Advances in psychology (Vol. 121, pp. 471-495). Elsevier.
Mehmood, I., Li, H., Qarout, Y., Umer, W., Anwer, S., Wu, H., Hussain, M., & Fordjour Antwi-Afari, M. (2023). Deep learning-based construction equipment operators’ mental fatigue classification using wearable EEG sensor data. Advanced Engineering Informatics, 56, 101978. https://doi.org/https://doi.org/10.1016/j.aei.2023.101978
Meng, X., Zhu, T., & Li, C. (2022). Construction of perfect dispatch learning model based on adaptive GRU. Energy Reports, 8, 668-677. https://doi.org/https://doi.org/10.1016/j.egyr.2022.02.250
Musarat, M. A., Alaloul, W. S., & Liew, M. S. (2021). Impact of inflation rate on construction projects budget: A review. Ain Shams Engineering Journal, 12(1), 407-414. https://doi.org/https://doi.org/10.1016/j.asej.2020.04.009
Rafiei, M. H., & Adeli, H. (2018). Novel machine-learning model for estimating construction costs considering economic variables and indexes. Journal of Construction Engineering and Management, 144(12), 04018106.
Rezaei, M., Mohammadifar, A., Gholami, H., Mina, M., Riksen, M. J. P. M., & Ritsema, C. (2023). Mapping of the wind erodible fraction of soil by bidirectional gated recurrent unit (BiGRU) and bidirectional recurrent neural network (BiRNN) deep learning models. CATENA, 223, 106953. https://doi.org/https://doi.org/10.1016/j.catena.2023.106953
Rosenblatt, F. (1958). The perceptron: A probabilistic model for information storage and organization in the brain. Psychological Review, 65(6), 386-408. https://doi.org/10.1037/h0042519
Schuster, M., & Paliwal, K. K. (1997). Bidirectional recurrent neural networks. IEEE Transactions on Signal Processing, 45(11), 2673-2681. https://doi.org/10.1109/78.650093
Shoar, S., Chileshe, N., & Edwards, J. D. (2022). Machine learning-aided engineering services' cost overruns prediction in high-rise residential building projects: Application of random forest regression. Journal of Building Engineering, 50, 104102. https://doi.org/https://doi.org/10.1016/j.jobe.2022.104102
Sholeh, M. N. (2023). Optical Microscope Algorithm: A Novel Metaheuristic Inspired by Microscope Magnification for Solving Engineering Optimization Problem National Taiwan University of Science and Technology].
Tsanas, A., & Xifara, A. (2012). Accurate quantitative estimation of energy performance of residential buildings using statistical machine learning tools. Energy and Buildings, 49, 560-567. https://doi.org/https://doi.org/10.1016/j.enbuild.2012.03.003
Xiao, H.-H., Yang, W.-K., Hu, J., Zhang, Y.-P., Jing, L.-J., & Chen, Z.-Y. (2022). Significance and methodology: Preprocessing the big data for machine learning on TBM performance. Underground Space, 7(4), 680-701. https://doi.org/https://doi.org/10.1016/j.undsp.2021.12.003
Zhou, J., Qin, Y., Chen, D., Liu, F., & Qian, Q. (2022). Remaining useful life prediction of bearings by a new reinforced memory GRU network. Advanced Engineering Informatics, 53, 101682. https://doi.org/https://doi.org/10.1016/j.aei.2022.101682