Varun Kumar Reja

Bio: Varun Kumar Reja is an academic researcher from Indian Institute of Technology Madras. The author has contributed to research in topics: Computer science & Process (computing). The author has an hindex of 1, co-authored 2 publications receiving 8 citations. Previous affiliations of Varun Kumar Reja include University of Technology, Sydney.

Impact of 5G Technology on IoT Applications in Construction Project Management

Abstract: IoT based platforms are enhancing decisionmaking capabilities in many sectors. The impact of IoT in construction has not been significant because of the unstructured nature of the process and the project-based approach to construction. Further, the technology platforms available today do not support high data flow from distributed locations as required for construction. However, it is anticipated that the use of IoT in construction will increase significantly when standards such as 5G are implemented for widespread usage. The first objective of this paper is to identify the potential usage of IoT technology for various construction project processes based on the PMBOK framework for construction. Several works on the applications of IoT which have been published are reviewed, and a framework for construction domain is proposed. The second objective is to identify and discuss the barriers raised by connectivity issues within this framework and influence of 5G technology in overcoming this barrier is elaborated. A comparative quantitative analysis of sample processes is presented to show the potential advantage that 5G technology will bring over 4G with the help of an example.

Mixed Reality-Based Dataset Generation for Learning-Based Scan-to-BIM

Abstract: Generating as-is 3D Models is constantly explored for various construction management applications. The industry has been dependent on either manual or semi-automated workflows for the Scan-to-BIM process, which is laborious as well as time taking. Recently machine learning has opened avenues to recognize geometrical elements from point clouds but has not been much used because of the insufficient labeled dataset. This study aims to set up a semi-automated workflow to create labeled data sets which can be used to train ML algorithms for element identification purpose. The study proposes an interactive user interface using a gaming engine within a mixed reality environment. A workflow for fusing as-is spatial information with the AR/VR based information is presented in Unity 3D. A user-friendly UI is then developed and integrated with the VR environment to help the user to choose the category of the component by visualization. This results in the generation of an accurate as-is 3D Model, which does not require much computation or time. The intention is to propose a smooth workflow to generate datasets for learning-based methodologies in a streamlined Scan-to-BIM Process. However, this process requires user domain knowledge and input. The dataset can be continuously increased and improved to get automated results later.

Impact of Reinforcement Design on Rebar Productivity

Abstract: Impact of Reinforcement Design on Rebar Productivity Amith G Mallya , Varun Kumar Reja , Koshy Varghese Pages 230-237 (2023 Proceedings of the 40th ISARC, Chennai, India, ISBN 978-0-6458322-0-4, ISSN 2413-5844) Abstract: Scheduling is an essential part of project management, and many processes like procurement, fabrication, and resource mobilization are based on these schedules. If the actual targets lag from the pre-planned schedules, waste is generated in the form of idle inventory. It also results in an increased workload on man and machinery, leading to errors and rework. Schedules are impacted by unreliable productivity estimates assumed during planning stages. In construction, project productivity can vary based on several factors. Reinforcement productivity is affected by factors like site layout, labour skill, design, learning effect, etc. The impact of reinforcement design on productivity is poorly studied, especially in heavily reinforced structures. Thus, the main objective of this study is to validate the hypothesis that reinforcement design affects productivity, which can be used to predict productivity for future structures. The methodology for this study is divided into 3 phases; 1st phase involves data collection and literature review, 2nd phase involves modelling rebar productivity by data fitting models to understand the factors of reinforcement design that affect productivity. MATLAB and Microsoft Excel are tools used in the data fitting process. In the final phase, based on this model, appropriate actions are suggested to improve productivity. Discussion on the aspects of reinforcement design that are found to have an impact on productivity is also detailed. Keywords: Reinforcement productivity, Data fitting, Regression analysis, MATLAB, Excel, heavily reinforced structures, rebar density, complexity in design, Delay, work productivity, Buildability, Rebar placement, lean construction management DOI: https://doi.org/10.22260/ISARC2023/0033 Download fulltext Download BibTex Download Endnote (RIS) TeX Import to Mendeley

Discrete Event Simulation Based Approach for Tracking Performance of Segmental Production at Precast Yard

Abstract: Discrete Event Simulation Based Approach for Tracking Performance of Segmental Production at Precast Yard Ashutosh Kumar Rai , Varun Kumar Reja , Koshy Varghese Pages 17-24 (2023 Proceedings of the 40th ISARC, Chennai, India, ISBN 978-0-6458322-0-4, ISSN 2413-5844) Abstract: Efficient performance tracking and monitoring systems can facilitate timely decision-making by management. However, cycle time, which is commonly employed as a monitoring system in segmental production sites, can be time-consuming and only allows for the identification of inefficiencies, rather than supporting decision-making. In this context, operational management concepts with broad applications in manufacturing industries should be utilized. While several tools are offered by operational management, this paper focuses on the implementation of a process analysis tool as a performance tracking system for superstructure construction at a precast yard. Process analysis tools incorporate several operational performance measures, including cycle time, total idle time, direct labor content, and direct labor utilization. These performance measures serve as indicators for evaluating process productivity and can be estimated using an excel spreadsheet. Simulation tools, which enable visualization of the process and the identification of potential issues before implementation, can be valuable. In this regard, modeling in ExtendSim can be beneficial as the segmental production process can be easily visualized, aiding in the identification of station dependencies and allowing for the acquisition of performance measure results with a single click. This study therefore aims to explore the integration of process analysis tools with ExtendSim simulation as a performance tracking system at the precast yard. The values of these operational performance measures will provide management with multiple dimensions for enhancing the efficiency and effectiveness of the segmental production process. Keywords: Productivity, Production, Superstructure, Operational Management, ExtendSim, Simulation, Performance Measurement, Segmental Construction, Process Analysis, Modelling, Precast yard DOI: https://doi.org/10.22260/ISARC2023/0005 Download fulltext Download BibTex Download Endnote (RIS) TeX Import to Mendeley

5G support for Industrial IoT Applications - Challenges, Solutions, and Research gaps

Abstract: Industrial IoT has special communication requirements, including high reliability, low latency, flexibility, and security. These are instinctively provided by the 5G mobile technology, making it a successful candidate for supporting Industrial IoT (IIoT) scenarios. The aim of this paper is to identify current research challenges and solutions in relation to 5G-enabled Industrial IoT, based on the initial requirements and promises of both domains. The methodology of the paper follows the steps of surveying state-of-the art, comparing results to identify further challenges, and drawing conclusions as lessons learned for each research domain. These areas include IIoT applications and their requirements; mobile edge cloud; back-end performance tuning; network function virtualization; and security, blockchains for IIoT, Artificial Intelligence support for 5G, and private campus networks. Beside surveying the current challenges and solutions, the paper aims to provide meaningful comparisons for each of these areas (in relation to 5G-enabled IIoT) to draw conclusions on current research gaps.

Quantitative review of construction 4.0 technology presence in construction project research

Abstract: The development of technologies associated with the fourth industrial revolution is rapid. Construction 4.0 represents the architecture, engineering, construction and operations industries exploration of new technologies, equivalent to Industry 4.0 for the manufacturing industry. These concepts address multiple perspectives besides the technological, such as management and processes. The purpose of this study was to investigate to what extent research regarding construction projects addresses information and communication, automatisation or industrialisation technologies. A scoping review was the method used to perform a quantitative analysis of over two thousand journal papers published from 2015 onwards. The results show that new technologies are addressed separately, while synergy studies are uncommon. Longitudinal analyses show that there was no significant increase in journal papers concerning new technologies from 2015 to 2019. Information and communication was the search criterion with the least number of papers found. The environmental perspective of new technologies was present but the least common from 2019 to 2020. Hence, this review shows that there is an extensive research gap regarding Construction 4.0 technologies in the context of construction projects. Studies regarding synergy and environmental effects of new technologies should increase to start the progress towards a successful entry into the fourth industrial revolution.

5G for Construction: Use Cases and Solutions

Abstract: The world is currently undergoing a new industrial revolution characterized by the digitization and automation of industry through the use of Information and Communication Technologies (ICTs). The construction sector is one of the largest sectors of the industry. Most of the tasks associated with this sector are carried out at worksites that are defined by their dynamism, decentralization, temporality, and the intervention of a large number of workers, subcontractors, machinery, equipment, and materials. These characteristics make this sector a great challenge for the implementation of ICTs. In this paper, the benefits of the use of the Fifth-Generation (5G) of mobile networks in the construction industry are presented. To that end, first, the digitization and automation needs of the sector are jointly analyzed, establishing different use cases and identifying the requirements of each one. Second, the main characteristics of 5G that address these use cases are identified. Third, a global framework for the application of 5G technology to the construction industry is proposed. Finally, an overview of some directions for future work are provided.

Stock Forecasting Model FS-LSTM Based on the 5G Internet of Things

Abstract: This paper analyzed the development of data mining and the development of the fifth generation (5G) for the Internet of Things (IoT) and uses a deep learning method for stock forecasting In order to solve the problems such as low accuracy and training complexity caused by complicated data in stock model forecasting, we proposed a forecasting method based on the feature selection (FS) and Long Short-Term Memory (LSTM) algorithm to predict the closing price of stock Considering its future potential application, this paper takes 4 stock data from the Shenzhen Component Index as an example and constructs the feature set for prediction based on 17 technical indexes which are commonly used in stock market The optimal feature set is decided via FS to reduce the dimension of data and the training complexity The LSTM algorithm is used to forecast closing price of stock The empirical results show that compared with the LSTM model, the FS-LSTM combination model improves the accuracy of prediction and reduces the error between the real value and the forecast value in stock price prediction