This study proposes a new optimization technique to estimate the Transportation Energy Demand (TED) employing the Flower Pollination Algorithm (FPA). The TED estimation models were developed based on three parameters, which are Annual Vehicle-Km (AVK), Gross Domestic Product per Capita (GDPperC), and Carbon-dioxide (CO₂) emission according to the linear, power and quadratic forms. These three parameters were determined by the WEKA data mining software program among nine parameters. Randomly selected 80% of historical data for 47 years, from 1970 to 2016, were used for the training of the algorithm, and the remains were used in the testing stage of the models. The performances of the models were evaluated according to six different statistical criteria. Transportation energy demand forecasts by 2035 were carried out using three different scenarios using the TED estimation models. According to the scenarios, it is predicted that the transportation energy demand in Turkey will have doubled by 2035 in comparison with 2016. The FPA approach has been successfully applied in the development of the TED estimation models. The most important impact of this study is to help the creation of strategic action plans for energy policies in the transport sector and to contribute to the more efficient use of limited energy resources in the country.

In this study, a hybrid traffic signal control (HTSC) system based on phase and time optimization was developed. The Flower Pollination Algorithm (FPA) approach was used for phase optimization, while Type-2 Fuzzy Logic, optimized with the Crow Search Algorithm (CSA), was utilized for time optimization. The hybrid system's performance was investigated using nine different traffic conditions and four different intersection geometries. The hybrid system was compared with three controller systems which are a fixed-time signal controller, a signal controller based on the FPA approach (FPA_TSC), and the optimized Type-1 fuzzy logic signal controller (Type-1 FL-TSC). The HTSC approach achieved the best performance with about 32% improvement over the fixed-time traffic controller and it showed 5% and 6% better performance than the FPA_TSC and Type-1 FL-TSC, respectively. Considering the performance of the new hybrid system, it is effective in minimizing delays and driver dissatisfaction occurring from signalization. It also contributes to the reduction of emissions and fuel consumption. The HTSC approach can be used as an alternative signal control method in the control of intersections with high traffic volume due to its fast and effective performance.

This study aims at optimizing fuzzy logic controller (FLC) triangle membership functions (MFs) for different traffic volumes via differential evolution (DE). To achieve this goal, a new FLC with a red time limiter, which actually calculates green time and the extension time of traffic movement phase, is developed to control an intersection. Subsequently, this FLC is optimized with two levels, namely Level-1 and Level-2. Level-1 searches each fuzzy class’s minimum and maximum values (α and β) that generate the lowest average delay per vehicle with DE. Using DE Level-2 inherits Level-1 ranges and reshapes the MFs to explore lower delay values computed by Level-1. The proposed method is tested with nine different traffic scenarios. For each scenario, 15 different headways are applied for a four-leg isolated intersection. The results indicate that the intersection average performance is increased up to 52%, 48%, and 14% at 800, 1600, and 2400 veh/h total intersection volumes, respectively, after Level-1 optimizations. They also reveal that intersection control produces higher delay values in only four scenarios after Level-2 procedures. Consequently, it is shown that the DE has significant potential to optimize FLCs at the intersection signal control. In addition, tuning fuzzy class ranges is found to be more critical than the MF reshaping process in traffic control via FLCs.

In this study, a Long Short-Term Memory (LSTM) model with extra variables such as weather conditions and school days was developed within a multi-scale framework in order to forecast passenger flow in both bus and rail systems, covering both regional and route-level analyses. In addition, the performance of the LSTM model was compared against three separate deep learning models. Among these, the Nonlinear Autoregressive Network with Exogenous Inputs (NARX) time series model produced the lowest error values, achieving a high level of accuracy. While no considerable changes were observed in regional rail passenger flow as a result of the inclusion of weather-related variables, a 2.2% drop in the RMSE value was achieved in bus passenger flow at the regional level; however, this improvement remains relatively modest. In contrast, at the route level, RMSE values declined by 2.4% for rail and 3.69% for bus routes. These findings reveal that the inclusion of weather-related variables significantly improves the prediction of bus passenger flow, underlining the benefits of integrating such data into forecasting models. Furthermore, the findings of this study analytically support transportation planners in making more informed, data-driven decisions regarding scheduling and capacity management.