Boruta-grid-search least square support vector machine for NO<sub>2</sub> pollution prediction using big data analytics and IoT emission sensors

Balogun, Habeeb; Alaka, Hafiz; Egwim, Christian Nnaemeka

doi:10.1108/aci-04-2021-0092

Cited by 11 publications

(7 citation statements)

References 21 publications

(24 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…, 2008, Studebaker, 2014; Egwim, 2017; Surendhra Babu and Hayath Babu, 2018; Moselhi et al. , 2020; Balogun et al. , 2021 etc) were not relevant to the effect of BIM on construction projects delay; thus, remaining a total of eighty-eight articles.…”

Section: Results and Analysismentioning

confidence: 99%

Systematic review of critical drivers for delay risk prediction: towards a conceptual framework for BIM-based construction projects

Egwim

Alaka

Demir

et al. 2022

FEBE

Self Cite

View full text Add to dashboard Cite

PurposeThis study aims to develop a comprehensive conceptual framework that serves as a foundation for identifying most critical delay risk drivers for Building Information Modelling (BIM)-based construction projects.Design/methodology/approachA systematic review was conducted using Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) to identify key delay risk drivers in BIM-based construction projects that have significant impact on the performance of delay risk predictive modelling techniques.FindingsThe results show that contractor related driver and external related driver are the most important delay driver categories to be considered when developing delay risk predictive models for BIM-based construction projects.Originality/valueThis study contributes to the body of knowledge by filling the gap in lack of a conceptual framework for selecting key delay risk drivers for BIM-based construction projects, which has hampered scientific progress toward development of extremely effective delay risk predictive models for BIM-based construction projects. Furthermore, this study's analyses further confirmed a positive effect of BIM on construction project delay.

show abstract

Section: Results and Analysismentioning

confidence: 99%

Systematic review of critical drivers for delay risk prediction: towards a conceptual framework for BIM-based construction projects

Egwim

Alaka

Demir

et al. 2022

FEBE

Self Cite

View full text Add to dashboard Cite

show abstract

“…Outliers and missing values (see Figure 3) were detected and dropped thus resulting in a final one million two hundred seventy-nine thousand seven hundred ninety-three rows and twenty-one columns of data set. Furthermore, because of their underlying assumptions that any given data set is normally distributed with zero mean and unit variance, most ML estimators make this a standard condition (Pedregosa et al , 2011; Alaka et al , 2018b; Balogun et al , 2021). Thus, as a final transformation on the data set, standardization feature scaling method was used to normalise the data set.…”

Section: Analysis and Resultsmentioning

confidence: 99%

“…This fact is in line with vast body of knowledge. For instance, it is the viewpoint of Owolabi (Owolabi et al, 2018) and Balogun (Balogun, Alaka and Egwim, 2021b) that more data means there's a better chance it'll include relevant information, which is beneficial as there is a natural desire to use these data assets by businesses to improve decision-making. Also, as briefly mentioned above, before testing the ensemble method hypothesis, this study addressed missing data and outliers and chose certain features from the feature space.…”

Section: Discussionmentioning

confidence: 99%

“…A vital component of such advancements is the use of ML for energy contemporary predictive analytics having been widely adopted across different industries such as health care: aiding in diagnoses of patients using genetic data (Huang et al , 2021; Malik et al , 2021); manufacturing: use in managing workforces production process and allowing predictive maintenance (Chen et al , 2021); education: virtual lectures (Bajaj and Sharma, 2018; Harmon et al , 2021); finance: fraud detection (Iong-Zong Chen and Lai, 2021; Bao et al , 2022); and transportation: self-driving autonomous cars (Manoharan, 2019; Ma et al , 2020), among many others. ML is a sub-set of AI that analyses historical data to provide predictions and then uses those predictions to guide decision-making (Balogun et al , 2021b). A broadly similar point has also recently been made by Sulaimon et al (2022), who argued that those decisions generate results which are used to improve future predictions.…”

Section: Literature Reviewmentioning

confidence: 99%

See 1 more Smart Citation

Comparison of machine learning algorithms for evaluating building energy efficiency using big data analytics

Egwim

Alaka

Egunjobi

et al. 2022

JEDT

Self Cite

View full text Add to dashboard Cite

Purpose This study aims to compare and evaluate the application of commonly used machine learning (ML) algorithms used to develop models for assessing energy efficiency of buildings. Design/methodology/approach This study foremostly combined building energy efficiency ratings from several data sources and used them to create predictive models using a variety of ML methods. Secondly, to test the hypothesis of ensemble techniques, this study designed a hybrid stacking ensemble approach based on the best performing bagging and boosting ensemble methods generated from its predictive analytics. Findings Based on performance evaluation metrics scores, the extra trees model was shown to be the best predictive model. More importantly, this study demonstrated that the cumulative result of ensemble ML algorithms is usually always better in terms of predicted accuracy than a single method. Finally, it was discovered that stacking is a superior ensemble approach for analysing building energy efficiency than bagging and boosting. Research limitations/implications While the proposed contemporary method of analysis is assumed to be applicable in assessing energy efficiency of buildings within the sector, the unique data transformation used in this study may not, as typical of any data driven model, be transferable to the data from other regions other than the UK. Practical implications This study aids in the initial selection of appropriate and high-performing ML algorithms for future analysis. This study also assists building managers, residents, government agencies and other stakeholders in better understanding contributing factors and making better decisions about building energy performance. Furthermore, this study will assist the general public in proactively identifying buildings with high energy demands, potentially lowering energy costs by promoting avoidance behaviour and assisting government agencies in making informed decisions about energy tariffs when this novel model is integrated into an energy monitoring system. Originality/value This study fills a gap in the lack of a reason for selecting appropriate ML algorithms for assessing building energy efficiency. More importantly, this study demonstrated that the cumulative result of ensemble ML algorithms is usually always better in terms of predicted accuracy than a single method.

show abstract

“…owing to its small size (Balogun et al, 2021;Joseph, 2022) . When a univariate analysis was run with the variable results, the results did not bring about good predictive models.…”

Section: Data Pre-processingmentioning

confidence: 99%

A machine learning approach for predicting critical factors determining adoption of offsite construction in Nigeria

Wusu

Alaka²,

Yusuf³

et al. 2022

SASBE

Self Cite

View full text Add to dashboard Cite

PurposeSeveral factors influence OSC adoption, but extant literature did not articulate the dominant barriers or drivers influencing adoption. Therefore, this research has not only ventured into analyzing the core influencing factors but has also employed one of the best-known predictive means, Machine Learning, to identify the most influencing OSC adoption factors.Design/methodology/approachThe research approach is deductive in nature, focusing on finding out the most critical factors through literature review and reinforcing — the factors through a 5- point Likert scale survey questionnaire. The responses received were tested for reliability before being run through Machine Learning algorithms to determine the most influencing OSC factors within the Nigerian Construction Industry (NCI).FindingsThe research outcome identifies seven (7) best-performing algorithms for predicting OSC adoption: Decision Tree, Random Forest, K-Nearest Neighbour, Extra-Trees, AdaBoost, Support Vector Machine and Artificial Neural Network. It also reported finance, awareness, use of Building Information Modeling (BIM) and belief in OSC as the main influencing factors.Research limitations/implicationsData were primarily collected among the NCI professionals/workers and the whole exercise was Nigeria region-based. The research outcome, however, provides a foundation for OSC adoption potential within Nigeria, Africa and beyond.Practical implicationsThe research concluded that with detailed attention paid to the identified factors, OSC usage could find its footing in Nigeria and, consequently, Africa. The models can also serve as a template for other regions where OSC adoption is being considered.Originality/valueThe research establishes the most effective algorithms for the prediction of OSC adoption possibilities as well as critical influencing factors to successfully adopting OSC within the NCI as a means to surmount its housing shortage.

show abstract

Boruta-grid-search least square support vector machine for NO₂ pollution prediction using big data analytics and IoT emission sensors

Cited by 11 publications

References 21 publications

Systematic review of critical drivers for delay risk prediction: towards a conceptual framework for BIM-based construction projects

Systematic review of critical drivers for delay risk prediction: towards a conceptual framework for BIM-based construction projects

Comparison of machine learning algorithms for evaluating building energy efficiency using big data analytics

A machine learning approach for predicting critical factors determining adoption of offsite construction in Nigeria

Contact Info

Product

Resources

About

Boruta-grid-search least square support vector machine for NO2 pollution prediction using big data analytics and IoT emission sensors

Cited by 11 publications

References 21 publications

Systematic review of critical drivers for delay risk prediction: towards a conceptual framework for BIM-based construction projects

Systematic review of critical drivers for delay risk prediction: towards a conceptual framework for BIM-based construction projects

Comparison of machine learning algorithms for evaluating building energy efficiency using big data analytics

A machine learning approach for predicting critical factors determining adoption of offsite construction in Nigeria

Contact Info

Product

Resources

About

Boruta-grid-search least square support vector machine for NO₂ pollution prediction using big data analytics and IoT emission sensors