<?xml version="1.0" encoding="utf-8"?>
<rss version="2.0">
    <channel>
        <title>Transport and Telecommunication Journal Feed</title>
        <link>https://sciendo.com/journal/TTJ</link>
        <description>Sciendo RSS Feed for Transport and Telecommunication Journal</description>
        <lastBuildDate>Sun, 10 May 2026 14:07:00 GMT</lastBuildDate>
        <docs>https://validator.w3.org/feed/docs/rss2.html</docs>
        <generator>https://github.com/jpmonette/feed</generator>
        <image>
            <title>Transport and Telecommunication Journal Feed</title>
            <url>https://sciendo-parsed.s3.eu-central-1.amazonaws.com/647398f94e662f30ba543764/cover-image.jpg</url>
            <link>https://sciendo.com/journal/TTJ</link>
        </image>
        <copyright>All rights reserved 2026, Transport and Telecommunication Institute</copyright>
        <item>
            <title><![CDATA[Application of the Elitist Ant System and Clustering Methods for Solving the Constrained Vehicle Routing Problem]]></title>
            <link>https://sciendo.com/article/10.2478/ttj-2026-0014</link>
            <guid>https://sciendo.com/article/10.2478/ttj-2026-0014</guid>
            <pubDate>Sun, 26 Apr 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[

The rapid growth of e-commerce necessitates automated Vehicle Routing Problem (VRP) solutions that account for real urban topology, particularly in metropolises such as Almaty. This study implements a hybrid «Cluster-First, Route-Second» approach. This approach integrates K-Means clustering and Ant Colony Optimization (ACO) using real road distance matrices (OSRM API) instead of Euclidean metrics. Comparative experiments on verified geodata demonstrated the superiority of the method over the Genetic Algorithm. A 42% reduction in route length and the elimination of topological errors were achieved. Decomposition analysis confirmed the optimality of K-Means for driver workload balancing. Practical application on a fleet of 4 vehicles showed the potential to reduce annual mileage by over 31,000 km. This provides financial savings exceeding 1.44 million tenge and a reduction in CO₂ emissions of 11.8 tons, offering a validated tool for sustainable urban logistics.
]]></description>
            <category>ARTICLE</category>
        </item>
        <item>
            <title><![CDATA[Cost Modeling Framework for International Refrigerated Road Transport using Adduced Transport Expenses Per Kilometer]]></title>
            <link>https://sciendo.com/article/10.2478/ttj-2026-0017</link>
            <guid>https://sciendo.com/article/10.2478/ttj-2026-0017</guid>
            <pubDate>Sun, 26 Apr 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[

In international refrigerated road transport, tariff-based pricing practices often overlook the actual cost structure of cold-chain operations and the influence of environmental, regulatory and logistical constraints. This paper develops a structured cost-modelling framework that introduces an Adduced Transport Expenses per 1 km indicator, which consolidates distance-based, time-dependent and organisational costs into a single per‑kilometer measure. All cost components are systematically differentiated across three operational dimensions and normalised by route length and vehicle load, enabling consistent cost benchmarking across routes, seasons and vehicle configurations. The methodology is validated using real operational data from long‑haul refrigerated transport on the Baku–Ankara route, demonstrating how the model can be used to estimate minimum freight tariffs, support more transparent rate negotiations and inform strategic decision-making in international cold‑chain logistics planning.
]]></description>
            <category>ARTICLE</category>
        </item>
        <item>
            <title><![CDATA[Enhancing Information Resources for Urban Freight Management through Image Processing and Analysis]]></title>
            <link>https://sciendo.com/article/10.2478/ttj-2026-0016</link>
            <guid>https://sciendo.com/article/10.2478/ttj-2026-0016</guid>
            <pubDate>Sun, 26 Apr 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[

The issue of incomplete data on the volume and types of freight transport in urban areas is well known, leading to difficulties in managing transport processes and hindering the development of strategic approaches for modern cities. To improve the management of freight flows, it is essential to distinguish freight vehicles from private and public transport. This paper investigates and develops methods for vehicle detection and tracking using cameras mounted on unmanned aerial vehicles (UAVs), aiming to enhance urban logistics data through image processing and analysis algorithms. A multi-camera vehicle detection and tracking algorithm was developed to support the analysis and evaluation of traffic flow efficiency in urban logistics, ultimately contributing to improved transportation management aligned with emission reduction principles.
]]></description>
            <category>ARTICLE</category>
        </item>
        <item>
            <title><![CDATA[Passenger and Freight Demand under Macroeconomic Volatility: Evidence from South Korea and The United States]]></title>
            <link>https://sciendo.com/article/10.2478/ttj-2026-0011</link>
            <guid>https://sciendo.com/article/10.2478/ttj-2026-0011</guid>
            <pubDate>Sun, 26 Apr 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[

This study investigates the asymmetric effects of economic growth and recession on airline demand by focusing on South Korea’s and the United States’ air passenger and freight sectors. Quarterly data from 1990 to 2023 are analyzed to identify the impact of economic fluctuations on air passenger and freight demand, incorporating macroeconomic variables such as the industrial production index, consumer price index, and oil prices. The results reveal a significant asymmetry in how airline demand responds to economic growth versus recessions. In South Korea and the United States, negative shocks lead to more pronounced declines in air passenger and freight demand versus the increases observed during periods of economic growth. Enhancing the aviation sector’s resilience can help protect jobs and maintain crucial transport links. The nuanced understanding of short- and long-term dynamics from this study delivers new insights into the airline sector’s response to macroeconomic shocks.
]]></description>
            <category>ARTICLE</category>
        </item>
        <item>
            <title><![CDATA[Research of Some Hazard Factors and Intensity of a Set Security Events in the Telecommunication System]]></title>
            <link>https://sciendo.com/article/10.2478/ttj-2026-0015</link>
            <guid>https://sciendo.com/article/10.2478/ttj-2026-0015</guid>
            <pubDate>Sun, 26 Apr 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[

The article considers the tasks of the study and analysis some factors danger and intensity of a set of security events in multiservice local and corporate public communication networks. Based on the study, a new approach is proposed for creating a mathematical model danger and intensity of a set security events in multiservice telecommunications networks under the threat of subscriber and network unauthorized access. As a result of the study, analytical formulas were obtained for the formal dependence integrated criteria for the quality of indication as single and multiple security events and hazard factors with a parameter, components of the information security vector and the conditional probability intensity of a set of security events. For a comparative analysis, a numerical calculation was carried out and a graphical dependence of the probability of the degree resistance to security threats in a communication system on the probability danger and the intensity of a set of security events was constructed when using different feedback coefficients. The relevance of using machine learning technology in the tasks of assessing the effectiveness of management based on security events in multiservice communication networks using the k-nearest neighbours (KNN) method, which classifies an object as a class, is considered. Based on the modeling, the metrics for assessing the quality of classification by the KNN algorithm are presented and a graphical dependence True Positive Rate (TPR) and False Positives Rate (FPR) is constructed for comparative analysis.
]]></description>
            <category>ARTICLE</category>
        </item>
        <item>
            <title><![CDATA[Simulation Studies of Various Structures of Optical Switching Networks]]></title>
            <link>https://sciendo.com/article/10.2478/ttj-2026-0013</link>
            <guid>https://sciendo.com/article/10.2478/ttj-2026-0013</guid>
            <pubDate>Sun, 26 Apr 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[

The article presents a research of loss probability in various structures of elastic optical network nodes. To conduct the research, an elastic optical networks simulator, which enables to determine loss probabilities of switching network nodes of any structure, was implemented. The simulator is able to offer network traffic composed of Erlang, Engset, and Pascal traffic streams, specified with input parameters. The article includes topics within the realm of elastic optical networks, provides a description of algorithms implemented in the simulator, its input data and parameters, describes the structures of the examined switching network nodes, and presents research results for individual structures and systems. The studies were conducted on practically utilized switching network node structures like Banyan, Baseline, and Omega and Clos switching network nodes.
]]></description>
            <category>ARTICLE</category>
        </item>
        <item>
            <title><![CDATA[YOLOV10 vs. YOLOV8: Performance Improvements for Vehicle Detection at Multilane Roundabouts]]></title>
            <link>https://sciendo.com/article/10.2478/ttj-2026-0012</link>
            <guid>https://sciendo.com/article/10.2478/ttj-2026-0012</guid>
            <pubDate>Sun, 26 Apr 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[

This study compares YOLOv8 and YOLOv10 for vehicle detection in multilane roundabouts, a complex environment characterized by frequent occlusions and non-linear movement patterns. A large UAV-based dataset was collected from multiple roundabouts, capturing diverse geometric configurations and congestion levels. The dataset was preprocessed, annotated, and used to train and evaluate both algorithms under identical conditions. The results reveal that YOLOv10 models achieve higher recall across all vehicle categories, making them more effective for complete vehicle detection, including those with occlusions. In contrast, YOLOv8 models maintain slightly higher precision, reducing false positives, which is advantageous in applications prioritizing classification accuracy. Larger YOLOv10 models also demonstrate lower inference latency, thereby improving the feasibility of real-time deployment. However, YOLOv8 offers faster training times and is more memory-efficient in smaller configurations. Therefore, YOLOv8 is suitable for resource-limited environments that require high precision, while YOLOv10 excels at recall-oriented tasks. These findings contribute to the advancement of vehicle detection technologies, supporting the development of more effective and scalable intelligent transportation systems.
]]></description>
            <category>ARTICLE</category>
        </item>
        <item>
            <title><![CDATA[Application of Infrared Thermography on Bus Air Compressor Units for Preventive Fault Detection]]></title>
            <link>https://sciendo.com/article/10.2478/ttj-2026-0010</link>
            <guid>https://sciendo.com/article/10.2478/ttj-2026-0010</guid>
            <pubDate>Sun, 26 Apr 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[

The following paper presents the application of Non-destructive Testing methods such as thermography for fault finding in internal components of buses and specifically the air compressor unit. Such units consist of a small internal combustion engine that provides air to the vehicle’s breaks, suspension and passenger door operations. Hoses transferring compressed air from the compressor to the rest of the system can get clogged, leading the air compressor to potential failure and even fire of the unit. Thermal imaging was applied in a number of Mercedes Citaro LE and Volvo B9 buses provided by a bus fleet operator, to evaluate whether such clogging can be detected at an early stage, during routine maintenance of the bus. A number of acquisitions, using a thermal camera were taken, with the air compressor under different loads and under heating or cooling phase of the unit. The paper presents that thermography can be used to detect such failures by observing specific hoses of the unit as well as the overall thermal behaviour of the air compressor.
]]></description>
            <category>ARTICLE</category>
        </item>
        <item>
            <title><![CDATA[A Computer Vision Approach to Evaluating Crosswalk Safety for Vulnerable Road Users]]></title>
            <link>https://sciendo.com/article/10.2478/ttj-2026-0001</link>
            <guid>https://sciendo.com/article/10.2478/ttj-2026-0001</guid>
            <pubDate>Sat, 21 Feb 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[

With advancements in computer vision and cloud computing, Surrogate Safety Measures (SSMs) now provide actionable insights to mitigate safety concerns before collisions occur. This study, conducted as part of the STREET21 research project and contributes to the existing body of knowledge by examining Post-Encroachment Time (PET), a time-based SSM, at a high-traffic urban intersection which many young vulnerable users (university students) cross as pedestrians for their daily commuting needs. In total 513 traffic conflict events were identified and mapped for the purposes of the analysis. The spatial analysis provides critical insights into the patterns of traffic conflicts. Results of the quantitative analysis demonstrate that pedestrian conflicts predominantly involved right-turning vehicles, followed by through vehicles, potentially indicative of red-light violations. The applied methodology underscores the efficacy of video analytics as a scalable alternative to traditional crash data analysis, enabling the evaluation of intersection designs and temporary treatments before permanent implementation.
]]></description>
            <category>ARTICLE</category>
        </item>
        <item>
            <title><![CDATA[Collaborative Multi-Hop Cyclic Redundancy Check and Reputation Approach Against Black Hole Attacks to Enhance Security in Mobile Adhoc Networks]]></title>
            <link>https://sciendo.com/article/10.2478/ttj-2026-0005</link>
            <guid>https://sciendo.com/article/10.2478/ttj-2026-0005</guid>
            <pubDate>Sat, 21 Feb 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[

Mobile Adhoc Networks (MANETs) are networks that can be formed among mobile nodes that self-organize, without necessitating any fixed infrastructure. They are dynamic networks where the nodes can join or leave the network. Due to their decentralized and open environment, MANETs are easy targets for routing attacks; the black hole attack is considered the most severe among them. Several existing security systems rely on key distribution via cryptography for verifying neighboring nodes, but the dynamic topology of the networks, and frequent mobility of nodes, make key distribution less practical. To tackle this problem, the authors have proposed the Collaborative Multi-Hop Cyclic Redundancy Check and Reputation (CMCR) scheme that secures the network without requiring any centralized key distribution. CMCR builds a Cyclic Redundancy Checks (CRC) chain across two to three hops to avoid the CRC at every hop. It also utilizes a reputation system that is distributed, to confirm the behavior of neighboring nodes through collaboration. CMCR will be able to detect black hole attacks both isolated and cooperative while having a lower routing overhead. The CMCR method proposed (the implementation for different network conditions) is further explored using MATLAB simulation. The outcomes are contrasted with existing schemes. From the simulation results obtained, the CMCR method have significantly improved packet delivery, detection accuracy, better control overhead and energy efficiency at higher node mobility and greater attack density as compared to the other algorithms. The proposed CMCR method is evaluated under varying network conditions through MATLAB simulations. Performance metrics such as Packet Delivery Ratio, End-to-End Delay, Throughput, Routing Overhead, Detection Accuracy, and Energy Consumption are measured to determine network performance and security resilience. The simulation results show that the proposed CMCR model has much better packet delivery, detection accuracy, and control overhead with energy efficiency under higher node mobility and increased attack density, compared to existing approaches.
]]></description>
            <category>ARTICLE</category>
        </item>
        <item>
            <title><![CDATA[On a Hybrid Decision Support Framework for Train Selection in Indian Railways: An Integration of Dominance-Based Rough Set Approaches and Machine Learning Models]]></title>
            <link>https://sciendo.com/article/10.2478/ttj-2026-0002</link>
            <guid>https://sciendo.com/article/10.2478/ttj-2026-0002</guid>
            <pubDate>Sat, 21 Feb 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[

The Indian Railway Catering and Tourism Corporation (IRCTC) operates one of the most heavily utilized railway reservation systems globally, reflecting the central role of Indian Railways (IR) as an affordable and essential mode of transportation across the country. However, selecting an appropriate train remains a complex decision-making task for passengers, primarily due to the uncertainty surrounding ticket availability on preferred travel dates. To address this challenge, the present study proposes a hybrid decision support system designed to aid passengers in selecting optimal train options, particularly for tourism-related travel. This research employs a Dominance-Based Rough Set Approach (DRSA) within a Multi-Criteria Decision-Making (MCDM) framework to analyze preference-based data and extract interpretable decision rules in the form of “if...then” statements. These rules assist decision makers in evaluating multiple train-related criteria simultaneously. For comparative purposes, the Classical Rough Set Approach (CRSA) is also implemented to identify the relative advantages and limitations of both rough set methodologies in addressing train selection complexity. In addition, the study integrates machine learning techniques by utilizing two predictive models – Extreme Gradient Boosting (XGBoost) and Support Vector Machine Classifier (SVMC) – to estimate overall train ratings based on user preferences and historical data. Model performance is evaluated using standard classification metrics, including accuracy and precision. By combining MCDM techniques with machine learning algorithms, the proposed hybrid framework enhances the train reservation experience, enabling passengers to make informed, preference-aligned travel decisions through the Indian Railways reservation system.
]]></description>
            <category>ARTICLE</category>
        </item>
        <item>
            <title><![CDATA[Assessment of Service Quality in Public Transport Using an Underperformance Approach: A Case Study of Constantine, Algeria]]></title>
            <link>https://sciendo.com/article/10.2478/ttj-2026-0006</link>
            <guid>https://sciendo.com/article/10.2478/ttj-2026-0006</guid>
            <pubDate>Sat, 21 Feb 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[

The paper proposes a new approach to evaluating the quality of public transport based on underperformance analysis. This approach aims to identify actual service failures by combining objective data and user perceptions. In this context, the objective of this paper is to offer a more reliable evaluation tool adapted to the contexts of developing countries, where certain service deficiencies tend to be normalized. The proposed approach is applied to a real case study in Constantine public transport; a series of objective and subjective indicators are calculated on the basis of infractions provided by local authorities and user perceptions of the service. This approach thus allows for a better understanding of the sources of quality degradation and supports more effective decisions for improving public transport in order to achieve the overall objectives of sustainable mobility.
]]></description>
            <category>ARTICLE</category>
        </item>
        <item>
            <title><![CDATA[Digital Transformation of Logistics Service Providers in the Context of Material Flow Coordination]]></title>
            <link>https://sciendo.com/article/10.2478/ttj-2026-0009</link>
            <guid>https://sciendo.com/article/10.2478/ttj-2026-0009</guid>
            <pubDate>Sat, 21 Feb 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[

The paper explores logistics service providers (LSPs) in the context of material flow coordination and examines the correlation between digitalization and the implementation of selected coordination features. It includes a literature review and interviews with 18 experts in LSP operations to assess how digitalization influences the adoption of key material flow coordination elements. The study aims to determine the impact of technologies used by LSPs on the implementation of these elements, thereby expanding the logistics coordination concept by integrating the role of digitalization. Findings indicate that while LSPs seek to implement basic material flow coordination elements, they lack sufficient knowledge about advanced technologies like AI bots and Digital Twins. A strong positive correlation was observed between the number of technological solutions implemented and experts’ perceptions of coordination capabilities. Different coordination elements require varying levels of technological adoption, with greater implementation leading to improved coordination possibilities. The study provides practical insights for LSP managers regarding the necessary technologies for easier integration of fundamental coordination elements. Additionally, it examines international LSPs to evaluate their potential for digital transformation. The paper highlights the significance of digital solutions in material flow coordination as a crucial mechanism for managing contemporary distribution networks.
]]></description>
            <category>ARTICLE</category>
        </item>
        <item>
            <title><![CDATA[Study of the Behaviour of Alternative Fuel Injection Stratification Through Numerical Analysis]]></title>
            <link>https://sciendo.com/article/10.2478/ttj-2026-0008</link>
            <guid>https://sciendo.com/article/10.2478/ttj-2026-0008</guid>
            <pubDate>Sat, 21 Feb 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[

International agreements and the urgency for the reduction of gases that contribute to climate change have sparked the search for alternative fuels of satisfactory qualities to fulfil the demand posed by internal combustion engines. In spite of this, it is indeed worth analysing their behaviour at every stage on one side or the other and to observe the contrasts depending on the design of the combustion chamber. For this reason, we focus on the injection of three fuels diesel, hydrogen and methane chosen because of their contrasting physical and chemical properties. Their behaviour is compared and its velocity is focused on. In order to perform it, a numerical simulation performed using ANSYS and selected mathematical models coherent with the physical phenomena dictated by the injection of fuel, turbulence, mass conservation, the atomization process. The values for the initial conditions of the study were drawn from literature and data from real experiments dependent on the velocity, pressure and temperature. Results showed that the behaviour was better suited the deeper combustion chamber, and that methane entered with a greater velocity corresponding to being more that %10 than even other fuels, thus favouring the filling of the combustion chamber and consequently assuring better combustion. Their behaviour reflects the way they should be treated and shows that temporary alternatives can ensure a clean transition for the automotive sector.
]]></description>
            <category>ARTICLE</category>
        </item>
        <item>
            <title><![CDATA[Analysis of World Experience and Experimental Implementation of Unmanned Radio Intelligence Systems]]></title>
            <link>https://sciendo.com/article/10.2478/ttj-2026-0007</link>
            <guid>https://sciendo.com/article/10.2478/ttj-2026-0007</guid>
            <pubDate>Sat, 21 Feb 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[

The article presents a comprehensive review and experimental analysis of the development of unmanned systems designed for electronic reconnaissance (REI) tasks. It combines a global assessment of technological trends, engineering solutions, and patent activity in the field of UAV-based radio intelligence platforms with the results of a practical implementation of a prototype SDR-based measurement system. The study outlines structural architectures, modular payload configurations, autonomous navigation strategies, and the integration of artificial intelligence in signal detection and direction-finding. Particular attention is given to approaches for enhancing situational awareness through adaptive signal processing and GNSS-independent navigation. The experimental part demonstrates the design, calibration, and field testing of a multi-antenna SDR system for real-time direction-of-arrival (DOA) estimation. Comparative analysis confirms the system’s accuracy and viability, highlighting the feasibility of compact, low-cost radio intelligence solutions. The paper concludes with recommendations for further R&amp;D in autonomous REI systems, emphasizing AI integration, modular design, and resilience to electronic countermeasures.
]]></description>
            <category>ARTICLE</category>
        </item>
        <item>
            <title><![CDATA[Integrated Modeling and Validation of HHO-Based Nox Reduction in Spark-Ignition Engines]]></title>
            <link>https://sciendo.com/article/10.2478/ttj-2026-0003</link>
            <guid>https://sciendo.com/article/10.2478/ttj-2026-0003</guid>
            <pubDate>Sat, 21 Feb 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[

This study presents the design, testing and optimization of a solar-powered HHO generator integrated into a gasoline-powered car (1.6L, 105 hp). The generator (model B1) is powered entirely by a 180 W photovoltaic (PV) panel via an MPPT controller, avoiding additional load on the alternator and improving net electrical efficiency. Exhaust emissions were measured using a TEXA Gasbox2 analyzer, with additional monitoring of the HHO system pressure using a PDS500G sensor. Comparative road tests (100 km) were carried out with and without the HHO generator. The reported results show a 28.6% reduction in NOx emissions (from 0.042 g/km to 0.030 g/km), as well as improvements in CO and HC values. A parametric model for NOx reduction was developed and an optimization scenario with increased photovoltaic power (300 W) and higher cell current was simulated. Theoretical electrolysis efficiency, hydrogen mass production and predicted energy balance were calculated.
]]></description>
            <category>ARTICLE</category>
        </item>
        <item>
            <title><![CDATA[Modeling the Efficiency of SaaS Solutions in Transport Logistics Infrastructure Recovery]]></title>
            <link>https://sciendo.com/article/10.2478/ttj-2026-0004</link>
            <guid>https://sciendo.com/article/10.2478/ttj-2026-0004</guid>
            <pubDate>Sat, 21 Feb 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[

The purpose of this article is to develop and empirically verify integrated models for assessing the effectiveness of software solutions provided under the service model in the context of rapid restoration of transport and logistics infrastructure after crisis events. Within the framework of the constructed multi-criteria system-dynamic model, the relationships between the scalability parameters of software platforms. The study has formulated a system of indicators for assessing effectiveness, the duration of infrastructure restoration after a disruption, the ratio of costs to the achieved effect and the level of reduction of negative environmental impact. The study’s novelty lies in developing a unified model that addresses key aspects of digital transport infrastructure after a crisis. The practical significance of the results obtained is manifested in the possibility of their application for strategic planning of digital transformation of logistics systems, assessment of the investment attractiveness of technological solutions.
]]></description>
            <category>ARTICLE</category>
        </item>
        <item>
            <title><![CDATA[Enhancing Mode-Choice Models with Conformal Prediction: Uncertainty Quantification and Decision Support Using Tree-Based Machine Learning]]></title>
            <link>https://sciendo.com/article/10.2478/ttj-2025-0027</link>
            <guid>https://sciendo.com/article/10.2478/ttj-2025-0027</guid>
            <pubDate>Fri, 21 Nov 2025 00:00:00 GMT</pubDate>
            <description><![CDATA[

Accurate mode-choice forecasts are vital for effective transportation planning. Transit agencies and city planners rely on precise predictions, but unreliable forecasts can misdirect even the most behaviorally grounded insights. For decades, discrete choice models (DCMs), notably Multinomial Logit (MNL) and Mixed Multinomial Logit (MMNL), have explained why travelers choose particular modes via interpretable parameters, yet they often underperform in forecast accuracy. More recently, machine learning methods (e.g., tree-based algorithms) have come to capture complex, nonlinear patterns, often outperforming DCMs in point-prediction accuracy. However, they lack built-in confidence measures, limiting their use in risk-aware decision making. In this work, we help narrow this gap by wrapping our best ML model in an Inductive Mondrian Conformal Prediction (IMCP) layer with per-mode calibration at 90% nominal coverage. We leverage a survey of approximately 8,000 Italian employees, capturing their socioeconomic attributes and travel habits. Using a tailored preprocessing pipeline, we compare XGBoost, Random Forest, and CatBoost, observing that XGBoost performs best on the test set with an overall accuracy of 89.7% and a macro-average F1 score of 83.6%. Our IMCP layer then produces distribution-free prediction sets that contain the true mode at least 90% of the time, both overall and within each individual mode category. Singleton prediction sets can be treated as high-confidence forecast for capacity planning, while multilabel sets (and the occasional empty sets for highly ambiguous cases) highlight where uncertainty is greatest and pinpoint exactly which individuals merit follow-up surveys or targeted incentives.
]]></description>
            <category>ARTICLE</category>
        </item>
        <item>
            <title><![CDATA[Truck Service Optimisation in Port Areas by Comparing Genetic Algorithm and Cuckoo Search Algorithm]]></title>
            <link>https://sciendo.com/article/10.2478/ttj-2025-0030</link>
            <guid>https://sciendo.com/article/10.2478/ttj-2025-0030</guid>
            <pubDate>Fri, 21 Nov 2025 00:00:00 GMT</pubDate>
            <description><![CDATA[

Efficient truck service optimization in port areas is essential for minimizing congestion, reducing delays and improving overall logistics efficiency. This study presents a comparative analysis of Genetic Algorithm (GA) and Cuckoo Search Algorithm (CSA) for optimizing truck scheduling and resource allocation in dynamic port environments. GA explores a broad solution space using evolutionary operators, while CSA leverages Lévy flight-based search mechanisms to enhance solution quality and escape local optima. The comparison evaluates both algorithms based on key performance metrics, including waiting times and server utilization. Simulation results indicate that the GA produces smaller waiting times, while the CSA exhibits higher. Moreover, the server utilization of the GA is significantly lower than with the CSA. The findings highlight the strengths and limitations of each method, providing valuable insights into their applicability for real-time truck service optimization in smart port management systems.
]]></description>
            <category>ARTICLE</category>
        </item>
        <item>
            <title><![CDATA[Integrating Small and Medium-Sized Ports Into Green Shipping Corridors: A Case Study of Sillamäe-Kotka Ferry Line]]></title>
            <link>https://sciendo.com/article/10.2478/ttj-2025-0029</link>
            <guid>https://sciendo.com/article/10.2478/ttj-2025-0029</guid>
            <pubDate>Fri, 21 Nov 2025 00:00:00 GMT</pubDate>
            <description><![CDATA[

The green transition remains a top priority on the European agenda, with targets to reduce greenhouse gas emissions by 55% by 2030 and achieve climate neutrality by 2050. The European transport sector contributes approximately 20% of total CO₂ emissions, strongly necessitating the need for sustainable transport solutions, so that the assessment of the maritime transport system is considered beyond time and costs to include environmental issues and regional development.
This research examines the potential environmental impact of a newly proposed ferry connection between Eastern Finland and Eastern Estonia, focusing on its role in advancing sustainable transport in the region. The study combines case studies, expert interviews, and survey data collected as part of an ongoing EU project between 2023 and 2025. The findings indicate that by 2030, the Sillamäe-Kotka ferry route could reduce annual CO₂ emissions by over 51 million tonnes, which would be a substantial contribution to regional decarbonization, enhanced freight and passenger transport efficiency, and alignment with the International Maritime Organization’s emission reduction targets. At the same time, this research highlights how maritime connectivity can contribute to a just transition process in Estonia’s Ida-Viru County, a region severely affected by the downturn in the oil shale industry, by facilitating new green economic opportunities, regional labour mobility, and sustainable tourism.
]]></description>
            <category>ARTICLE</category>
        </item>
    </channel>
</rss>