The continuous growth of urban populations has led to the persistent problem of traffic congestion, which imposes adverse effects on quality of life, such as commute times, road safety, and the local air quality. Advancements in Internet of Things (IoT) sensor technology have contributed to a plethora of new data streams regarding traffic conditions. Therefore, the recognition and prediction of traffic congestion patterns utilizing such data have become crucial. To that end, the integration of Machine Learning (ML) algorithms can further enhance Intelligent Transportation Systems (ITS), contributing to the smart management of transportation systems and effectively tackling traffic congestion in cities. This study seeks to assess a wide range of models as potential solutions for an ML-based multi-step forecasting approach intended to improve traffic congestion prediction, particularly in areas with limited historical data. Various interpretable predictive algorithms, suitable for handling the complexity and spatiotemporal characteristics of urban traffic flow, were tested and eventually shortlisted based on their predictive performance. The forecasting approach selects the optimal model in each step to maximize the accuracy. The findings demonstrate that, in a 24 h step prediction, variating Ensemble Tree-Based (ETB) regressors like the Light Gradient Boosting Machine (LGBM) exhibit superior performances compared to traditional Deep Learning (DL) methods. Our work provides a valuable contribution to short-term traffic congestion predictions and can enable more efficient scheduling of daily urban transportation.
Intelligent building management systems are proven to lead to energy savings and are an integral component of smart buildings. The procedures developed in the EN standards describe the methodology for calculating the energy savings achieved by improving the automation and control levels of separate services in building systems. However, although this method is used in practice, it is rarely applied or investigated by the research community. Typically, energy savings resulting from a single automation improvement intervention in a building heating system are observed, while the holistic view of combined automation upgrades is not considered. Therefore, the purpose of this study was to assess the energy savings resulting from several upgrades to control levels in the heating system components of the building. In addition, this research provides a rationale for the impact of multiple automation and control options for heating systems as well as examines the difference in energy savings. Finally, an analytical model is developed and demonstrated to assess the feasibility of building automation and control upgrades, by determining the allowed investment according to a set of predefined indicators.
While the AEC industry is moving towards digitalization off-site rebar prefabrication became a common practice. Now most companies use a long-established standard order processing method, where the customer submits 2D paper or PDF-based drawings. Subsequently, the manufacturers are obligated to make additional detailing, redrawing, calculations, and preparation of other required information for manufacturing. Thus, in this typical scenario, there is a great repetition of the same tasks, with the obvious loss of time and increased likelihood of human error. However, improvements can be made by the application of advanced digital production workflow and the use of open BIM standards (e.g., IFC, XML, BVBS). Therefore, this paper presents the typical data flow algorithm in contrast to the automated data flow for reinforcement manufacturing. Further, the two approaches are compared and analyzed based on Multi-Criteria Decision Making (MCDM) methods. The results have shown promising prospects for companies willing to automate their data flow processes by the use of 3D drawings and digital data from the BIM model in their plants.
As cities face growing pressure from climate change, biodiversity loss, and urbanization, there is an urgent need for data-driven tools to support the planning and resilience of green infrastructure. This paper presents a methodology for developing Urban Digital Twins (UDTs) focused on green space planning, monitoring, and regeneration. The process begins with the identification of Key Performance Indicators (KPIs) across five thematic areas: pollution and climate, natural environment, ecosystems, human perception, and public awareness. Based on these KPIs, a set of enabling digital technologies is evaluated through expert ranking, using Kendall’s W concordance coefficient to assess consensus on their relevance. The results highlight strong agreement among experts, with IoT, GIS, and BIM emerging as the most suitable technologies due to their capacity for real-time sensing, semantic integration, and spatial representation. Drawing from these insights, the paper proposes a five-layer reference architecture for UDTs designed to support adaptive, inclusive, and data-driven urban greening efforts. The findings offer guidance for cities and stakeholders aiming to implement UDTs for urban resilience.