In this research, the advantages of the e-scooter tool used in the mail or package delivery process were discussed by considering the Turkish Post Office (PTT) data in the districts of Istanbul (Kadıköy, Üsküdar, Kartal, and Maltepe) in Turkey. The optimization Poisson regression model was utilized to deliver the maximum number of packages or mails with minimum cost and the shortest time in terms of energy consumption, cost, and environmental contribution. Statistical and optimization results of dependent and independent variables were calculated using numerical and categorical features of 100 e-scooter drivers. The Poisson regression analysis determined that the e-scooter driver’s gender (p|0.05 < 0.199) and age (p|0.05 < 0.679) factors were not effective on the dependent variable. We analysed that the experience in the profession (tenure), the size of the area responsible, and environmental factors is effective in the e-scooter distribution activity. The number of packages delivered was 234 in a day, and the delivery cost per package was calculated as 0.51 TL (Turkish Lira) for the optimum values of the dependent variables. The findings show that the choice of e-scooter vehicle in the mail or package delivery process is beneficial in terms of time, cost, energy, and environmental contribution in districts with higher population density. As the most important result, the operation of e-scooter vehicles with electrical energy shows that it is environmentally friendly and has no CO2 emission. The fact that the distribution of packages or mail should now turn to micro-mobility is emerging with the advantages of e-scooter vehicles in the mail and package delivery. Finally, this analysis aims to provide a model for integrating e-scooters in package or mail delivery to local authorities, especially in densely populated areas.

Keywords transportation model, traffic analysis zones, travel demand forecast, travel assignments IntroductionTransportation infrastructure, systems and investments underpin the growth, prosperity and vitality of communities and cities [1]. Transportation infrastructure and systems, however, are under increasing pressure in many cities around the world, where rising expectations for comfort and independent travel have increased the use of private vehicles. The resulting increase in traffic congestion has prompted cities to seek solutions supported by travel demand forecast models. These models allow a systematic review of how travel requirements change under different assumptions and are used by relevant authorities to demonstrate the feasibility and economic success of transportation investments. Since decision making relies in the fidelity of modeling, authorities constantly seek to improve their transport modeling infrastructure. Four-step models have emerged as effective and popular tools based on their straightforward information and operational requirements.Some limitations of four-step models, however, have also prompted the development and initial application of activity-based models [2]. It should be noted that the transition from trip-based modeling to activity-based modeling is characterized by significantly increased data requirements, increased computational times, and implementation difficulties especially in large areas. Bao et al. in [3] have investigated the minimum field size, at which activity-based modeling can be applied in order to obtain reasonable computational times. The study discussed testing the suitability of the radii of the TAZ, when trip based modeling is used in areas where data requirements of activity based models cannot be met.In the current study, the original 540 TAZ of Istanbul have been divided into smaller areas (zones) and the related effect on model consistency is examined. By dividing Istanbul's neighborhoods, which are the smallest administrative areas of the city, we were able to identify areas with similar land use characteristics, and enhanced the infrastructure of the demand prediction model, which now comprises 1,788 TAZ.The remainder of this paper is organized as follows. In Section 2, demand forecasting models are examined and trip-based and activity-based models are discussed. Section 3 overviews

Construction companies are under pressure to enhance their site safety condition, being constantly challenged by rapid technological advancements, growing public concern, and fierce competition. To enhance construction site safety, literature investigated Machine Learning (ML) approaches as risk assessment (RA) tools. However, their deployment requires knowledge for selecting, training, testing, and employing the most appropriate ML predictor. While different ML approaches are recommended by literature, their practicality at construction sites is constrained by the availability, knowledge, and experience of data scientists familiar with the construction sector. This study develops an automated ML system that automatically trains and evaluates different ML to select the most accurate ML-based construction accident severity predictors for the use of construction professionals with limited data science knowledge. A real-life accident dataset is evaluated through automated ML approaches: Auto-Sklearn, AutoKeras, and customized AutoML. The investigated AutoML approaches offer higher scalability, accuracy, and result-oriented severity insight due to their simple input requirements and automated procedures.

Construction risk assessment (RA) based on expert knowledge and experience incorporates uncertainties that reduce its accuracy and effectiveness in implementing countermeasures. To support the construction of RA procedures and enhance associated decision-making processes, machine learning (ML) approaches have recently been investigated in the literature. Most ML approaches have difficulty processing dependency information from real-life construction datasets. This study developed a novel RA model that incorporates a graph convolutional network (GCN) to account for dependency information between construction accidents. For this purpose, the construction accident dataset was restructured into an accident network, wherein the accidents were connected based on the shared project type. The GCN decodes the construction accident network information to predict each construction activity’s severity outcome, resulting in a prediction accuracy of 94%. Compared with the benchmark feedforward network (FFN) model, the GCN demonstrated a higher prediction accuracy and better generalization ability. The developed GCN severity predictor allows construction professionals to identify high-risk construction accident scenarios while considering dependency based on the shared project type. Ultimately, understanding the relational information between construction accidents increases the representativeness of RA severity predictors, enriches ML models’ comprehension, and results in a more reliable safety model for construction professionals.

Buildings are responsible for almost half of the world’s energy consumption, and approximately 40% of total building energy is consumed by the heating ventilation and air conditioning (HVAC) system. The inability of traditional HVAC controllers to respond to sudden changes in occupancy and environmental conditions makes them energy inefficient. Despite the oversimplified building thermal response models and inexact occupancy sensors of traditional building automation systems, investigations into a more efficient and effective sensor-free control mechanism have remained entirely inadequate. This study aims to develop an artificial intelligence (AI)-based occupant-centric HVAC control mechanism for cooling that continually improves its knowledge to increase energy efficiency in a multi-zone commercial building. The study is carried out using two-year occupancy and environmental conditions data of a shopping mall in Istanbul, Turkey. The research model consists of three steps: prediction of hourly occupancy, development of a new HVAC control mechanism, and comparison of the traditional and AI-based control systems via simulation. After determining the attributions for occupancy in the mall, hourly occupancy prediction is made using real data and an artificial neural network (ANN). A sensor-free HVAC control algorithm is developed with the help of occupancy data obtained from the previous stage, building characteristics, and real-time weather forecast information. Finally, a comparison of traditional and AI-based HVAC control mechanisms is performed using IDA Indoor Climate and Energy (ICE) simulation software. The results show that applying AI for HVAC operation achieves savings of a minimum of 10% energy consumption while providing a better thermal comfort level to occupants. The findings of this study demonstrate that the proposed approach can be a very advantageous tool for sustainable development and also used as a standalone control mechanism as it improves.