Taş, Mehmet Bilge Han; Özkan, Kemal; Sarıçiçek, İnci; Yazıcı, Ahmet

The Dynamic Electric Vehicle Routing Problem (D-EVRP) presents a framework that requires electric vehicles to meet demand with limited energy capacity. When dynamic demand flows and charging requirements are considered together, traditional methods cannot provide sufficient adaptation for real-time decision-making. Therefore, a learning-based approach was chosen to ensure that decision-making processes respond quickly to changing conditions. The solution utilizes a model with a Double Deep Q-Network (DDQN) architecture and a discrete valuation structure. Prioritized Experience Replay (PER) was implemented to increase model stability, allowing infrequent but effective experiments to contribute more to the learning process. The state representation is constructed using the vehicle’s location, battery level, load status, and current customer demands. Scalability is ensured by dividing customer locations into clusters using the K-means method, with each cluster handled by an independent representative. The approach was tested with real-world road data obtained from the Meşelik Campus of Osmangazi University in Eskişehir. Experiments conducted under different demand levels and data sizes have shown that the PER-assisted DDQN structure produces more stable and shorter route lengths in dynamic scenarios, but random selection, greedy method and genetic algorithm experience significant performance losses as dynamicity increases.

Gülmez, Hüseyin Nuri; Koç, Yunus; Ertay, Agah Oktay; Döken, Bora; Kartal, Mesut

We present FilterForge, a chat-driven VS Code environment that pulls the synthesis, analysis, simulation, and optimization stages of microwave bandpass filter design, normally coordinated by hand across tools written in different languages, into one workflow. A deployed Model Context Protocol (MCP) server exposes deterministic Python implementations of coupling-matrix synthesis, uniform predistortion, topology reconfiguration, a genetic-algorithm transmission-zero selector, a mode-matching engine for H-plane iris-coupled rectangular waveguide geometries, and a skill that generates PyAEDT/HFSS notebooks for various dimensioning design-curves. A language-model orchestrator turns natural-language requests into typed tool calls, while every reported quantity stays inside the deterministic kernels, so the numerics remain reproducible and model-agnostic. We evaluate the call layer on a 45-task benchmark across the five tool categories: gemini-3-flash reaches (Formula presented.) tool-selection and (Formula presented.) full-call accuracy with an (Formula presented.) pass3 rate, which an ablation traces to the curated tool-selection prompt rather than to raw model capability. The mode-matching engine is validated against full-wave HFSS on a six-pole 4 GHz Chebyshev filter tuned from the chat panel, and on an 8 GHz WR-112 counterpart taken end-to-end with no engineer in the loop, where a deterministic critique gates each round until a manufacturable geometry is reached. We then exercise the full workflow on two folded six-pole WR-90 cross-coupled filters at (Formula presented.), a high-selectivity design synthesized against a stop-band mask and a group-delay-equalized variant whose positive cross-coupling uses a pair of side-wall irises, the latter settling to a peak-to-peak in-band group-delay ripple below (Formula presented.) while recovering the synthesized return loss.

Çelik, Alper; Turan, Ahmet İhsan; Yalciner, Hakan; Kumbasaroglu, Atila

This study presents an analytical investigation and a parametric evaluation of the structural behavior and seismic performance of highly corroded reinforced concrete (RC) columns, based on previously conducted experimental studies by the authors. In the analytical phase, moment–curvature relationships were obtained by considering the deterioration of the mechanical properties of both concrete and reinforcing steel due to corrosion in RC column specimens. By linking the sectional moment–curvature response with the element-level behavior observed in the experimental program, the plastic hinge lengths and rotational capacities of the corroded RC columns were determined. Subsequently, a parametric study was carried out using the analytical framework developed in the first phase on a set of 48 RC column models. In this investigation, axial load ratio, concrete compressive strength, corrosion level, section type, and concrete cover depth were considered as key parameters. The results of the combined experimental and analytical investigations demonstrate that the adopted section analysis approach successfully captures the nonlinear flexural behavior observed in the corroded specimens and provides a reliable basis for evaluating the structural performance and for supporting the assessment of seismic performance of deteriorated RC columns.

Kumbasaroglu, Hediye; Kumbasaroglu, Atila

This article presents the results of a systematic review investigating the potential of agricultural wastes as sustainable and low-carbon alternatives in reinforced concrete (RC) production. Background: The depletion of natural resources and the environmental burden of conventional construction materials necessitate innovative solutions to reduce the carbon footprint of construction. Agricultural wastes, including coconut shells (CSs), rice husk ash (RHA), and palm oil (PO) fuel ash, emerge as promising materials due to their abundance and mechanical benefits. Objective: This review evaluates the potential of agricultural wastes to improve sustainability and enhance the mechanical properties of RC structural elements while reducing carbon emissions. Design: Studies were systematically analyzed to explore the sources, classification, and material properties of agro-wastes (AWs), with a particular focus on their environmental benefits and performance in concrete. Results: Key findings demonstrate that AWs enhance compressive strength, tensile strength, and modulus of elasticity while reducing the carbon footprint of construction. However, challenges such as variability in material properties, limited long-term durability data, and lack of standardized guidelines hinder their broader adoption. Conclusions: AWs hold significant potential as sustainable additives for RC elements, aligning with global sustainability goals. Future research should address material optimization, lifecycle assessments, and regulatory integration to facilitate their mainstream adoption in construction.

Aslan Yıldız, Özge; Sarıçiçek, İnci; Yazıcı, Ahmet

The growth of the urban population and the increase in e-commerce activities have resulted in challenges for last-mile delivery. On the other hand, electric vehicles (EVs) have been introduced to last-mile delivery as an alternative to fossil fuel vehicles. Electric vehicles (EVs) not only play a pivotal role in reducing greenhouse gas emissions and air pollution but also contribute significantly to the development of more energy-efficient and environmentally sustainable urban transportation systems. Within these dynamics, the Electric Vehicle Routing Problem (EVRP) has begun to replace the Vehicle Routing Problem (VRP) in last-mile delivery. While classic vehicle routing ignores fueling, both the location of charging stations and charging time should be included in the Electric Vehicle Routing Problem due to the long recharging time. This study addresses the Capacitated EVRP (CEVRP) with a novel Q-learning algorithm. Q-learning is a model-free reinforcement learning algorithm designed to maximize an agent’s cumulative reward over time by selecting optimal actions. Additionally, a new dataset is also published for the EVRP considering field constraints. For the design of the dataset, real geographical positions have been used, located in the province of Eskisehir, Türkiye. It also includes environmental information, such as streets, intersections, and traffic density, unlike classical EVRP datasets. Optimal solutions are obtained for each instance of the EVRP by using the mathematical model. The results of the proposed Q-learning algorithm are compared with the optimal solutions of the presented dataset. Test results show that the proposed algorithm provides remarkable advantages in obtaining routes in a shorter time for EVs.

Taş, Mehmet Bilge Han; Özkan, Kemal; Sarıçiçek, İnci; Yazici, Ahmet

Transportation mode selection is pivotal for navigating through cities plagued by heavy traffic congestion. This plays a crucial role in ensuring the efficient utilization of time and resources to achieve the desired objectives. Given the complex dynamics of urban mobility, strategically selecting a transportation mode can significantly mitigate delays and enhance overall productivity in densely populated areas. The objective of this study is to find the most efficient result among various transportation modes to make deliveries from different points on a university campus. To solve this problem, reinforcement learning was used and tested on the simulation environment SUMO. Traffic density was increased by using an equal number of different transportation modes, such as driving, cycling, motorbiking, and walking. Various traffic densities were generated, and different reward models were applied to select the best means of transportation. Various probability distributions were used as reward models to avoid the unfair distribution caused by how near or how far the road is when moving from random points to the destination region. As a result of the models created using the applied reward–penalty functions, it was determined that the best means of transportation in areas with a low traffic density is cycling, and in areas with high traffic density, the optimal mode of transportation is motorbiking.

Çakı, Mustafa; Baş, Fatih İrfan

Flexible pavements stand out as the most commonly used worldwide, compared to rigid and composite pavements, owing to their versatility and widespread application. The use of hot mix asphalt (HMA) in flexible pavements causes significant environmental concerns due to high CO2 emissions and energy consumption, whereas warm mix asphalt (WMA) technologies have gained popularity in recent decades, offering a more sustainable alternative by enabling asphalt production at lower temperatures. WMA technologies can be categorized into three main groups: foaming, organic additives, and chemical additives, with each offering distinct benefits for performance and environmental impact. One of the chemical additives used in WMA production is Cecabase RT BIO10. In this study, virgin bitumen with 50/70 penetration was modified by adding Cecabase RT BIO10 at four levels: 0%, 0.3%, 0.4%, and 0.5% by weight. The experimental design employed a Taguchi L16 orthogonal array to systematically evaluate the effects of various factors on modified bitumen performance. Binders were prepared at four temperatures (110 °C, 120 °C, 130 °C, and 140 °C), four mixing durations (15, 20, 25, and 30 min), and four mixing speeds (1000, 2000, 3000, and 4000 rpm), enabling an efficient analysis of each parameter’s impact. The prepared binders were subjected to a series of tests, including penetration, softening point, flash point, rotational thin film oven test (RTFOT), elastic recovery, Marshall stability, ultrasonic pulse velocity (UPV), and FTIR analysis. These tests were conducted to investigate the effects of various parameters and levels on the binder properties. Additionally, stiffness and seismic modules were evaluated to provide a more comprehensive understanding of the binder’s performance. The experiment results revealed that the penetration, elastic recovery percentage, and Marshall stability increased with increasing additive content while the softening point and RTFOT mass loss decreased. At a high service temperature of 40 °C, the stiffness modulus of the modified bitumen decreased slightly. At a low service temperature of −10 °C, it decreased further. Additionally, the incorporation of Cecabase RT BIO10 led to an increase in the seismic modulus. Through optimization using the Taguchi method, the optimal levels were determined to be a 0.4% Cecabase RT BIO10 ratio, 140 °C mixing temperature, 30 min mixing time, and 1000 RPM mixing speed. The optimal responses for each test were identified and integrated into a unified optimal response, resulting in a comprehensive design guide with 95% confidence level estimates for all possible level combinations.

Çolak, Fatih; Ertay, Agah Oktay

Glide-symmetric double-corrugated parallel-plate waveguides (GS-DCPPWs) have essential technical properties such as an electromagnetic bandgap, lower dispersion, and the ability to control the equivalent refractive index. For this reason, a fast and simple analysis and design of GS-DCPPW structures have great importance to improve related microwave systems. This paper introduces a novel design methodology based on the auxiliary functions of generalized scattering matrix (AFGSM) for the dimensional synthesis of GS-DCPPWs. We test the applicability of the AFGSM method on a variety of numerical examples to determine the passband/stopband regions of single and GS-DCPPWs before applying the design procedure. Certain design specifications are chosen, and unit cell dimensions are constructed in accordance with the proposed design technique. Three design scenarios are considered to assess the success of how well the design criteria can be met with the proposed method. The designed unit cells have been periodically connected in a various finite numbers to create periodic filters as a test application for adjusting the electromagnetic bandgap. The success of the periodic GS-DCPPW filters obtained with the proposed design strategy in meeting the specified design requirements has been tested using full-wave electromagnetic simulators (CST Microwave Studio and HFSS). The results indicate that the combined use of the equivalent transmission line circuit and the root-finding routine provided by the proposed method facilitates rapid, efficient, versatile, and approximate designs for corrugated parallel-plate waveguides. Moreover, the design methodology provides the viability of developing a minimal unit cell and a compact periodic filter performance with respect to the literature counterparts.

Şimşek, Mutlu; Çelik, Semet; Akoğuz, Harun

Soil improvement is one of the fundamental practices in civil engineering, with a long-standing history. In today’s context, the rapidly increasing demand for construction driven by urbanization has further emphasized the necessity and significance of soil stabilization techniques. This study aims to determine the optimum parameters for improving sandy soils by incorporating sodium alginate (SA) as a biopolymer additive into the microbial calcium carbonate precipitation (MICP) process. Sand types S1, S2, and S3, each with distinct particle size distributions, were selected, and the specimens were prepared at medium relative density. Three distinct approaches, MICP, SA, and MICP + SA, were tested for comparison. Additionally, two different improvement methods, injection and mixing, were applied to investigate their effects on the geotechnical properties of the soils. In this context, hydraulic conductivity, unconfined compressive strength (UCS), and calcite content tests, as well as scanning electron microscopy (SEM) and energy dispersive X-ray spectroscopy (EDS) analyses, were performed to assess the changes in soil behavior. SA contributed positively to the overall efficiency of the MICP process. The study highlights SA-assisted MICP as an alternative that enhances the microstructural integrity of treated soils and responds to the environmental limitations of conventional methods through sustainable innovation.

Tastimur, Canan; Akin, Erhan; Agrikli, Mehmet

Accurate and robust detection of fabric defects under noisy conditions is a major challenge in textile quality control systems. To address this issue, we introduce a new model called the Logarithmic Deep Residual Shrinkage Network (Log-DRSN), which integrates a deep attention module. Unlike standard residual shrinkage networks, the proposed Log-DRSN applies logarithmic transformation to improve resistance to noise, particularly in cases with subtle defect features. The model is trained and tested on both clean and artificially noised images to mimic real-world manufacturing conditions. The experimental results reveal that Log-DRSN achieves superior accuracy and robustness compared to the classical DRSN, with performance scores of 0.9917 on noiseless data and 0.9640 on noisy data, whereas the classical DRSN achieves 0.9686 and 0.9548, respectively. Despite its improved performance, the Log-DRSN introduces only a slight increase in computation time. These findings highlight the model’s potential for practical deployment in automated fabric defect inspection.