Abstracts – Browse Results
Click on the titles below to expand the information about each abstract.
Viewing 13 results ...
Abouhamad, M and Zayed, T (2019) Risk-Based Asset Management Framework for Subway Systems. Journal of Construction Engineering and Management, 145(11).
Ahn, C R, Lee, S, Sun, C, Jebelli, H, Yang, K and Choi, B (2019) Wearable Sensing Technology Applications in Construction Safety and Health. Journal of Construction Engineering and Management, 145(11).
Alruwaythi, O and Goodrum, P (2019) A Difference in Perspective: Impact of Different Formats of Engineering Information and Spatial Cognition on Craft-Worker Eye-Gaze Patterns. Journal of Construction Engineering and Management, 145(11).
Cheng, M, Chang, Y and 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).
- Type: Journal Article
- Keywords: Schedule estimate; Inference model; Time-independent and time-dependent factors; Neural network–long short-term memory (NN-LSTM);
- ISBN/ISSN: 0733-9364
- URL: https://doi.org/10.1061/(ASCE)CO.1943-7862.0001697
- Abstract:
Estimate schedule to completion (ESTC) is a difficult variable to determine accurately during the various phases of construction projects due to the complex, uncertain, and limited nature of currently available information. Currently, most construction managers estimate this variable using their subjective prior experience with budget planning. However, this method is costly and highly prone to inaccuracy. The study developed a novel inference model, the neural network–long short-term memory (NN-LSTM) model, to estimate ESTC accurately by factoring in the sequence and nonsequence factors that significantly influence project duration and that capture the inherent uncertainties in the construction field. NN-LSTM fuses two characteristics of artificial neural networks (ANNs): feedforward neural networks (FNNs) for nonsequential issue, and recurrent neural networks (RNNs) for sequential issue. After a systematic review of the literature, brainstorming, and in-depth interviews with domain experts, a database of 226 historical cases collected from 11 construction projects with 14 influencing factors was created for learning purposes, with 10-fold cross validation used to partition the training and testing data sets. NN-LSTM was then applied to estimate the schedule to completion for the historical cases, with FNN capturing the impact of time-independent factors on project duration and LSTM capturing the long temporal dependency for sequential inputs. The learning results indicated good performance, with a mean absolute percentage error (MAPE) of less than 5% and a mean absolute error (MAE) of 2%, proving the NN-LSTM model to be more reliable than the currently prevailing earned value management (EVM) formulas. Moreover, in subsequent comparison testing NN-LSTM proved to be superior to other artificial intelligence (AI) prediction models. The model has the ability to generate reliable scheduling estimates for project managers in order to facilitate their accurate planning and the monitoring of the time performance of projects, allowing timely action to be taken to remedy foreseen delays and facilitating informed decision-making.
Demirel, H &, Volker, L, Leendertse, W and Hertogh, M (2019) Dealing with Contract Variations in PPPs: Social Mechanisms and Contract Management in Infrastructure Projects. Journal of Construction Engineering and Management, 145(11).
Esmaeeli, A N and Heravi, G (2019) Real Options Approach versus Conventional Approaches to Valuing Highway Projects under Uncertainty. Journal of Construction Engineering and Management, 145(11).
Feng, Y and Trinh, M T (2019) Developing Resilient Safety Culture for Construction Projects. Journal of Construction Engineering and Management, 145(11).
Franco-Duran, D M and Garza, J M d l (2019) Review of Resource-Constrained Scheduling Algorithms. Journal of Construction Engineering and Management, 145(11).
Hamzeh, F R, El Samad, G and Emdanat, S (2019) Advanced Metrics for Construction Planning. Journal of Construction Engineering and Management, 145(11).
Jang, Y, Jeong, I, Cho, Y K and Ahn, Y (2019) Predicting Business Failure of Construction Contractors Using Long Short-Term Memory Recurrent Neural Network. Journal of Construction Engineering and Management, 145(11).
Khalafallah, A and Shalaby, Y (2019) Change Orders: Automating Comparative Data Analysis and Controlling Impacts in Public Projects. Journal of Construction Engineering and Management, 145(11).
Li, K and Cheung, S O (2019) Unveiling Cognitive Biases in Construction Project Dispute Resolution through the Lenses of Third-Party Neutrals. Journal of Construction Engineering and Management, 145(11).
Prakash, A and Phadtare, M (2019) Exploration of Logic in Project Marketing Using Interpretive Structural Modeling. Journal of Construction Engineering and Management, 145(11).