4.3.3. Regression Techniques

Based on an input variable, regression predicts the value of the target variable. It is a supervised ML method. Regression is categorized into simple linear and multiple linear regression based on explanatory variables. In simple linear regression, the relationship between two variables (an explanatory variable x and a dependent variable y) is modeled using ML. While in multiple linear regression, two or more explanatory variables are used and their relationship with the dependent variable is modeled. The more common regression technique is multiple linear regression.

Regression has been extensively used in construction research. For example, it has been used to predict properties of concrete cured under hot weather [48], predicting final cost for competitive bids on construction projects [101], determining contingency in international construction projects [102], estimating performance time for construction projects [103], and others. Moreover, regression has been used for cost estimation, which is a difficult task in the early stages of the project. Adoption of parametric methods such as regression and multiple regression can be applied as both analytical and predictive techniques to estimate the overall reliability of the cost estimation.

#### *4.4. The 10 vs. of Big Data*

The bulk and variety of big data gathering enormously each day make it virtually impossible to deal with the data sources seamlessly. On the other hand, the enormity of big data gives it many characteristics that further expand the potential of big data and its applications in different research fields. Figure 9 provides an overview of some of the crucial characteristics of big data, also known as the vs. of big data. The 10 vs. of big data have been discussed in Figure 9. Understanding these characteristics of big data enables the identification of opportunities and challenges. The most crucial properties of big data include their value, volume, velocity, variety, veracity, volatility, validity, variability, vulnerability, and visualization, also known as the 10 vs. of big data [104]. These characteristics of vs. are used to guide research in different areas and fields.

In terms of the use of big data in the field of construction, analyzing the vs. can help explore how big data can be used for developing better construction models in the future. Firstly, big data provide grea<sup>t</sup> value using various databases and sources that inform the research studies and algorithm developments related to computational models of different building structures. In addition to the value of research, big data also provide a bulk of information needed for research simply through the ever-increasing volume of data that becomes available each day. Furthermore, the velocity with which databases expand each day adds variety to the sort of data available for utilization in fields like construction. The variety of data present is not varying just in terms of the data sources but also the types

of data. For example, big data can be present in the form of written text, graphs, pictures, and various other formats to help manage construction project schedules and progress reporting. The increasing amounts of data make the visualization process quite complex. Therefore, it is crucial to develop new ways for data visualization and analysis to keep with the volatility of big data.

**Figure 9.** The 10 vs. of big data.

The 10 vs. of big data are among the crucial characteristics representing the true picture of big data as a field of research. The applications of big data in the construction industry are innumerable and they can all be categorized and managed through understanding the characteristic features (or Vs) of big data. The construction industry benefits immensely as a business by integrating big data technologies. The correlation with the business side of the construction industry has been explored in light of the 10 vs. of big data and it has been found that these characteristics provide an immense business growth potential. Starting from the core attributes of volume, variety and velocity, big data have come a long way in terms of their applications and trends. Today, there are 10 characteristics that define big data and are also crucial for implementing big data into different fields. It is crucial to understand that these 10 vs. of big data can be explained in a context-dependent manner considering the field of research. As for the construction industry, the variety and volume of big data are immense, but there is also a grea<sup>t</sup> deal of variability in the data present. For example, the choice of building materials and the suitability of the selected materials in different projects depend on several different factors. In this case, analyzing the applicability of big data is possible through data-visualizing techniques that can help deal with the volatility and variability of big data. Similarly, the validity and veracity of big data in construction can be judged only after analyzing the value that the data sources bring and the authenticity that these sources present. Therefore, the increasing velocity of big data is not useful as an independent factor. Instead, the application of big data in the construction industry depends on the 10 different characteristics (Vs) which are associated with big data and are explained in Figure 9.

Similarly, these data types can be refined and unstructured, further adding variety to the type of data present for various reporting and research purposes. Veracity refers to the reliability of big data. This is guided by statistics as the enormity of big data makes it hard to identify reliable data sources. Therefore, validating data sources and ensuring that they can be reliably used to guide construction project developments is crucial for research. The veracity of data sources leads to another important characteristic of big data: variability. It is crucial to understand that big data can be highly variable depending on the sources used for extracting the datasets. Understanding these characteristics of big data and analyzing these characteristics given the use of big data in the construction industry can greatly enhance the potential of future construction projects.

Overall, multiple construction-related studies have reported the usage of vs. of big data. For example, velocity has been reported for high-speed construction data processing [105]. Value has been reported for smarter universities and campuses [106]. Volume has been reported for mass level offsite construction material and component production [107]. Variety has been reported for investigating the profitability performance of construction projects [39]. Veracity has been reported for forecasting the success of construction projects [68]. Similarly, variability has been reported for modeling occupational accidents in construction projects [108].

Big data necessitate cost-effective, innovative information processing forms for enhanced insights and decision making. Construction companies can analyze historical datasets and carry out predictive analytics to forecast future events. Data-driven decision making has the potential to reshape the entire business. Together, the 10 attributes or 10 vs. of big data play a crucial role in the construction industry. The volume of data and the velocity through which data are produced at high speed lead to the possibility of validating information related to construction projects. The ability to visualize big data, keep up with the variety of data, and accept the volatility, vulnerability, and variability that come with the veracity of data helps ensure that big data could be truly applicable in the construction industry. Therefore, the value of big data in the construction industry is high and it helps guide future projects.

#### *4.5. Machine Learning Techniques*

One AI subdomain is ML which can be used to learn from the data using computational systems. The tools used for big data ML are presented in Table 2. ML is further categorized into: (i) supervised learning; (ii) unsupervised learning; (iii) association; and (iv) numeric prediction. ML has several applications in the construction industry. It uses different approaches, including rule-based learning approaches, case-based reasoning techniques, artificial neural networks, and hybrid methodologies.

ML has immense potential as a tool in the field of construction. Over the last two decades, several ML algorithms have been proposed to aid and improve the overall process of construction. For example, ML has been used to predict properties of concrete [48], contract managemen<sup>t</sup> [109], site safety and injury prediction [46], delay risks management [45], BIM integrated on-demand site monitoring [47], and other areas of construction engineering and management.

Various ML tools are integrated at different steps along with the construction managemen<sup>t</sup> processes. Different ML interfaces such as PyTorch and Keras.io help develop computational models based on existing data for building futuristic construction models. BIM can also be improved by using big data and ML tools, as these technologies allow the opportunity to explore how technology could be applied to the construction industry [110]. Over the last few years, different algorithms have been explored to predict various project phases and guide construction projects from inception to closure [111]. Firstly, decision trees and similar tools are used for developing an overall project timeline to predict or determine construction project performance in various phases. Secondly, statistical analysis tools are used for analyzing previous projects and choosing guiding principles for future projects [112]. Finally, design tools are integrated with ML algorithms to build 3D con-

struction models and graphics for building models. These computational models enable analyzing construction projects by planning through look-up schedules and looking for ways to improve buildings and other structures [113].

The combined use of big data, ML, and AI holds the potential to develop seamless construction projects and enable the development of structures that can withhold severe weather conditions and disasters. For example, one of the key uses of ML tools in futuristic construction projects can be the development of structures that can stand through natural disasters and provide safety nets to communities during floods and other disasters [114]. Similarly, post-disaster evacuation and rescue of individuals can also be carried out more easily if the area contains structures such as roads and buildings built through the use of statistical modeling, thus providing safe routes for people [115]. Although the automation of construction projects remains a future goal, the integration of different ML algorithms is already underway. Managing costs, timelines, and human resources on a construction project are areas guided by various algorithms and computational models [116]. The ML approach can also be applied to develop leading indicators to classify sites according to their safety risk in construction projects.


**Table 2.** Machine learning tools used for big data.

#### **5. Future Opportunities of Big Data in Construction**

There is immense potential for the use of big data in the construction industry. The use of big data and ML can enable construction automation. These tools can also enhance the overall project by removing various hurdles and roadblocks that tend to slow down different projects. The construction industry is quite dynamic and demanding, with the need for labor strength and human resources to ensure the smooth running of projects. The constant challenge of keeping projects on track and ensuring that new buildings and structures are made up to modern standards puts much strain on the project managemen<sup>t</sup> teams. These roadblocks can greatly be reduced with the use of big data and ML. The core aim of using big data in the construction industry is to enhance the project planning phases and speed up the overall construction process by predicting the possible timelines

for particular projects and identifying what factors can be worked on to improve the overall process [123].

The automation of the construction projects will require the combined use of big data, deep learning, and ML tools. One of the major concerns with such projects is ensuring workers' safety and developing strategies for overcoming potential threats to the overall process. Safety of the workers and the structures is essential for the smoother development of construction projects. The use of big data and related tools can ensure that existing data and information can be used for drafting guiding principles and then building computational models accordingly. For example, using sensor-based wearable personal protective equipment, the big data of near misses, onsite accidents, hazards, and other issues can be generated for developing safety plans and managemen<sup>t</sup> techniques. Similarly, big data, BIM, and cloud-powered simulations can help minimize project waste and help produce superior quality constructed facilities. Further, big data artifacts generated by 3D scanners for as-built drawing development are another key advantage whereby the rehabilitation plans of ancient heritage sites can be developed.

The future holds grea<sup>t</sup> potential for the construction industry through big data integration. Some of the key opportunities for the construction industries lie in using big data for business and environmental sustainability. The current roadblocks faced by the construction industry can be overcome in the future through the integration of information extracted through big data. The use of information gathered from past and present projects can help develop sustainable infrastructure in the long term. It is possible to avoid past mistakes and use better quality products guided by the information found through big data in construction. Future research directions in the field of construction rely heavily on big data as the presence of information sources can help in building better infrastructure and greatly improve building designs and the overall construction business. The construction industry must move towards automation and build upon the integration of technology to make the future use of big data seamless and hassle-free. The use of big data tools, BIM, and CAD can only be possible if the relevant support and integration systems are present [107]. Hence, the future of the construction industry depends on upgrading the present environment gradually.

Overall, the role of big data in enabling the entire process of futuristic construction projects is undeniable. Data play a crucial role in developing training models and smoothly enabling the process of construction. Future developments in this field will also include the generation and use of more algorithms and models that rely on big data, owing to the need to train the models reliably.
