Big Data in Construction: Current Applications and Future Opportunities

Spatial-derivative-based compression approach for distributed temperature data

The new generation of distributed optical sensors with improved interrogation, multiplexing, and acquisition techniques with the possibility of performing measurements with high spatial resolution over tens of kilometers of optical fiber has led to the accumulation of a vast volume of data that can present a big challenge to process and store all this data. Looking for simple solutions to this problem, we present in this paper a data compression method for distributed temperature sensors. This compression approach performs the spatial derivative of the temperature signal, constituting a simple and effective method to remove redundant information. Also, this compression methodology is suitable for temperature data, as it follows thermal variations over time and can be applied to any temperature profile with multiple thermal events along the sensing fiber, whether in heating or cooling circumstances. Tests performed with a large amount of experimental data showed that an average compression ratio of 1.5× can be obtained by removing redundant spatial temperature variations without losing spatial resolution.

Portuguese Public Procurement Data for Construction (2015 – 2022)

The Architecture, Engineering and Construction (AEC) sector currently exhibits a significant scarcity of systematised information in databases (DB). This characteristic is a relevant obstacle to implementing new methodologies in the sector, which have proven highly successful in other industries. In addition, this scarcity also contrasts with the intrinsic workflow of the AEC sector, which generates a high volume of documentation throughout the construction process. To help solve this issue, the present work focuses on the systematisation of the data related to the contracting and public tendering procedure in Portugal, summarising the steps to obtain and process this information through the use of scraping algorithms, as well as the subsequential translation of the gathered data into English. The contracting and public tendering procedure is one of the most well-documented procedures at the national level, having all its data available as open-access. The resulting DB comprises 5214 unique contracts, characterised by 37 distinct properties. This paper identifies future development opportunities that can be supported by this DB, such as the application of descriptive statistical analysis techniques and/or Artificial Intelligence (AI) algorithms, namely, Machine Learning (ML) and Natural Language Processing (NLP), to improve construction tendering.

Design of Intelligent Management Platform for Industry–Education Cooperation of Vocational Education by Data Mining

Data are playing an increasingly important role in the development of industry–education cooperation strategies in vocational education and training. The objective of this study was to promote the comprehensive progress of an industry–education cooperation system and improve the effect of the application of big data technology in this system. First, we designed of a big data technology application in an intelligent management platform system for industry–education cooperation. Second, we analyzed the synthetical design of the system. Finally, we optimized and designed a support vector machine (SVM) data mining (DM) algorithm model based on big data, and evaluated the model. The results revealed that the designed algorithm model provides outstanding advantages compared with similar algorithm models. In general, the highest average computation time of the designed SVM algorithm model is about 95 ms. The overall average calculation time linearly decreases around 200 iterations and tends to be stable, and the lowest overall average computation time is about 20 ms. In the DM process, the highest accuracy rate of the model is about 97%, and the lowest is about 92%. The DM accuracy rate is always stable as the number of iterations of the model continues to increase. The designed model slowly increases the occupancy rate of the system in the process of increasing computing time. At about 60 min, the system occupancy rate of the model tends to be stable, and the highest is maintained at about 23%. This study not only provides technical support for the optimization of DM algorithms with big data technology, but also contributes to the integrated development of industry–education cooperation systems.

Framework for Computerizing the Processes of a Job and Automating the Operational Management on Site—A Case Study of Demolition and Reconstruction Construction Site

With regard to the topic of digitization for operational site control, it is clear that while there is an acceleration towards digitization of processes, especially complex ones, there are still clear research gaps to be filled. The present study is part of this line of research and aims to respond to the current demand for digital and sustainable innovation of production processes. It, therefore, aims at defining a framework for the management of an order that takes place in real time. In order to improve the quality of information and organizational processes of an order in a project-oriented logic, a framework has been created: Model Smart Management. The framework integrates project management techniques with digital innovation tools and includes a computerized procedure to monitor and control the operational management of the site: SmartApp. In order to allow the interoperability of information, the platform can be used entirely in the cloud. From the processing of data in the planning phase, ad hoc checklists are developed that include a series of activities closely related to each other to ensure a continuity step by step, allowing users to have an immediate control of the project and of the relevant key performance indicators thanks to an advanced and fully customizable reporting. SmartApp, integrated with a cloud computing system, makes computerized and automated the operational control on site, creating a centralized archive of all company data, reducing time and costs for the management of documentation. Moreover, with the omnichannel system, paper documents are managed and archived through QR-code, optical character recognition on smart devices, so as to achieve a regime of maximum efficiency. This framework was then applied in a case study located in L'Aquila, Italy, represented by a post 2009 earthquake demolition and reconstruction site.

Modeling Profitability-Influencing Risk Factors for Construction Projects: A System Dynamics Approach

This study addressed the complexity involved in integrating the causative risk factors influencing construction profitability. Most of the existing studies cover the individual effects of profitability influencing factors. Very few focus on the systematic impact without incorporating the complexity and associated dynamics, presenting a gap targeted by the current study. The current study aimed to assess causative interrelations and interdependencies between profitability influencing risk factors (PIRF), through systems thinking (ST) and system dynamics (SD) modeling. The SD approach was used to evaluate the integrated impacts on profitability-influencing risk categories (PIRC) in construction projects. The causative influencing factors affecting construction profitability were identified through a comprehensive literature review. These were ranked using content analysis, and categorized into significant issues. Through 250 structured surveys and 15 expert opinion meetings, the path for quantitative and qualitative evaluations was prepared. Following these investigations, a causal loop diagram (CLD) was established using the ST technique, and the integrated effect was quantified using SD modeling. The study finds the rising cost of material, supply chain process, payment issues, planning and scheduling problems, financial difficulties, and effective control of manpower and equipment resources as the most critical PIRFs. The integrated effects of PIRFs on PIRC were quantified using SD modeling. This study helps field professionals with profitability-influencing factors, diagnosing issues, and integrating impacts regarding decision-making and policy formulation. For researchers, it presents a list of factors that can be investigated in detail, and the holistic interrelationships established.

Examining the Nexus between the Vs of Big Data and the Sustainable Challenges in the Textile Industry

Despite its substantial economic power, the textile industry currently faces environmental and social challenges, such as continuous extraction of natural resources, extensive water consumption and contamination, greenhouse gas emissions, increasing generation of waste, and inadequate working conditions. In this context, the literature indicates that Big Data contributes to solving these challenges, enabling the extraction of insights and the improvement of decision-making processes from the volume, variety and velocity of data. However, there is still a gap in the literature regarding the directions of how Big Data must be applied by an organization to achieve this goal. Therefore, this article aims to explore this gap, presenting an analysis regarding the nexus between Big Data and sustainability challenges of the textile industry. To this end, a set of 12 textile industry challenges were extracted from an assessment of 108 case studies. These challenges were categorized and contextualized according to Big Data dimensions, and a discussion of the applicability of Big Data to solving each challenge was presented. From this approach, this article contributes to the textile industry by presenting a categorization of sustainable challenges of the industry and also by providing directions regarding the resolution of such challenges from a data-driven perspective.