Ke-Xiao Yan

The performances of construction supervisors are essential for the monitoring, control, and coordination of the construction process of a project in order to adhere to a predefined schedule, cost, quality and other factors. However, it is challenging to evaluate their performance due to limitations such as data deficiency, human error, etc. Thus, this paper proposes an approach to data-driven quantitative performance evaluation of construction supervisors by integrating an analytic hierarchy process (AHP) and activity tracking. The proposed approach contains three parts, namely, index extraction, weighting, data-driven index calculation, and then validation by case study. Firstly, performance indexes were developed based on a literature review as well as surveys and function analysis of the information system for construction supervision (CSI system). Then, the weights of and relationships among of the indexes are determined by AHP. After that, with daily workflow and inspection activities tracked in the CSI system, a method and a software module for automatic calculation of indexes were developed. Lastly, the proposed approach was validated by a real-world case. The result showed that the proposed approach can quantify the performance of a construction supervisor systematically and automatically, which shed lights on how to evaluate the performance of a worker based on the tracking of daily activities. The data-driven process enhanced our strong interpretation of member actions and evaluation indexes, and can boost the performance of every member in an organization.

Accurate fire load (combustible objects) information is crucial for safety design and resilience assessment of buildings. Traditional fire load acquisition methods, such as fire load survey, which are time-consuming, tedious, and error-prone, failed to adapt to dynamic changed indoor scenes. As a starting point of automatic fire load estimation, fast recognition and detection of indoor fire load are important. Thus, this research proposes a computer vision-based method to automatically detect indoor fire loads using deep learning-based instance segmentation. First, indoor elements are classified into different categories according to their material composition. Next, an image dataset of indoor scenes with instance annotations is developed. Finally, a deep learning model, based on Mask R-CNN, is developed and trained using transfer learning to detect fire loads in images. Experimental results show that our model achieves promising accuracy, as measured by an average precision (AP) of 40.5% and AP ₅₀ of 59.2%, for instance segmentation on the dataset. A comparison with manual detection demonstrates the method’s high efficiency as it can detect fire load 1200 times faster than humans. This research contributes to the body of knowledge 1) a novel method of high accuracy and efficiency for automated fire load recognition in indoor environments based on instance segmentation; 2) training techniques for a deep learning model in a relatively small dataset of indoor images which includes complex scenes and a variety of instances; and 3) an image dataset with annotations of indoor fire loads. Although instance segmentation has been applied for several years, this is a pioneering research on using it for automated indoor fire load recognition, which paves the foundation for automatic fire load estimation and resilience assessment for the built environment.