Abstract
Traffic state prediction is critical to decision-making in various traffic management applications. Despite significant advancements in Deep Learning (DL) models, such as Long Short-Term Memory (LSTM), Graph Neural Networks (GNN), and attention-based transformer models, multi-step predictions remain challenging. The state-of-the-art models face a common limitation: the predictions' accuracy decreases as the prediction horizon increases, a phenomenon known as error accumulation. In addition, with the arrival of non-recurrent events and external noise, the models fail to maintain good prediction accuracy. Deep Reinforcement Learning (DRL) has been widely applied to diverse tasks, including optimising intersection traffic signal control. However, its potential to address multi-step traffic prediction challenges remains underexplored. This study introduces an Actor-Critic-based adapted DRL method to explore the solution to the challenges associated with multi-step prediction. The Actor network makes predictions by capturing the temporal correlations of the data sequence, and the Critic network optimises the Actor by evaluating the prediction quality using Q-values. This novel combination of Supervised Learning and Reinforcement Learning (RL) paradigms, along with non-autoregressive modelling, helps the model to mitigate the error accumulation problem and increase its robustness to the arrival of non-recurrent events. It also introduces a Denoising Autoencoder to deal with external noise effectively. The proposed model was trained and evaluated on three benchmark traffic flow and speed datasets. Baseline multi-step prediction models were implemented for comparison based on performance metrics such as Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE). The results reveal that the proposed method outperforms the baselines by achieving average improvements of 0.26 to 21.29% in terms of MAE and RMSE for up to 24 time steps of prediction length on the three used datasets, at the expense of relatively higher computational costs. On top of that, this adapted DRL approach outperforms traditional DRL models, such as Deep Deterministic Policy Gradient (DDPG), in accuracy and computational efficiency.

Abstract

Abstract
We focus on the integration of Formal Methods as mandatory theme in any Computer Science University curriculum. In particular, when considering the ACM Curriculum for Computer Science, the inclusion of Formal Methods as a mandatory Knowledge Area needs arguing for why and how does every computer science graduate benefit from such knowledge. We do not agree with the sentence While there is a belief that formal methods are important and they are growing in importance, we cannot state that every computer science graduate will need to use formal methods in their career. We argue that formal methods are and have to be an integral part of every computer science curriculum. Just as not all graduates will need to know how to work with databases either, it is still important for students to have a basic understanding of how data is stored and managed efficiently. The same way, students have to understand why and how formal methods work, what their formal background is, and how they are justified. No engineer should be ignorant of the foundations of their subject and the formal methods based on these. In this article, we aim at highlighting why every computer scientist needs to be familiar with formal methods. We argue that education in formal methods plays a key role by shaping students' programming mindset, fostering an appreciation for underlying principles, and encouraging the practice of thoughtful program

Abstract

This paper presents an integrated analytical approach to assess the reliability of power electronic converters in Permanent Magnet Synchronous Generator (PMSG)-based wind farms under variable wind conditions. The study focuses on analyzing the impact of wake effect turbulences and thermal management on power converter reliability, driven by the thermal stress induced by fluctuating wind speeds on power converters. Through extensive simulations using FLORIS and MATLAB, the thermal behavior of converters in wind farms affected by wake interactions was examined to identify potential reliability issues. The methodology involved modeling an 80-turbine wind farm in FLORIS to simulate wake effects, processing high-resolution wind speed data in MATLAB to refine wind speed profiles, and using Simulink to simulate the thermal profiles of power electronics. The results of FLORIS simulations highlighted the variations in turbulence intensity (TI) and power output, while the MATLAB and Simulink models quantified critical thermal stresses in power converters, correlating the locations of the turbine rows with temperature fluctuations and potential failures. Machine learning models, including Gradient Boosting and Random Forest Regressor, were utilized to refine and predict the multi-objective reliability function. The findings underscore the importance of understanding and managing thermal dynamics to improve the reliability and operational resilience of the power converter, supporting sustainable wind farm operations in dynamically changing wind conditions.

Abstract
Accurate traffic state prediction is fundamental to Intelligent Transportation Systems, playing a critical role in optimising traffic management, improving mobility, and enhancing the efficiency of transportation networks. Traditional methods often rely on feature engineering, statistical time-series approaches, and non-parametric techniques to model the inherent complexities of traffic states, incorporating external factors such as weather conditions and accidents to refine predictions. However, the effectiveness of long-term traffic state prediction hinges on capturing spatial-temporal dependencies over extended periods. Current models face challenges in dealing with (i) high-dimensional traffic features, (ii) error accumulation for multi-step prediction, and (iii) robustness to external factors effectively. To address these challenges, this study proposes a novel model with a Dynamic Feature Embedding layer designed to transform complex data sequences into meaningful representations and a Deep Linear Projection network that refines these representations through non-linear transformations and gating mechanisms. These two features make the model more scalable when dealing with high-dimensional traffic features. The model also includes a Spatial-Temporal Positional Encoding layer to capture spatial-temporal relationships, masked multi-head attention-based encoder blocks, and a Residual Temporal Convolutional Network to process features and extract short-and long-term temporal patterns. Finally, a Time-Distributed Fully Connected Layer produces accurate traffic state predictions up to 24 timesteps into the future. The proposed architecture uses a direct strategy for multi-step modelling to help predict timesteps non-autoregressively and thus circumvents the error accumulation problem. The model was evaluated against state-of-the-art baselines using two benchmark datasets. Experimental results demonstrated the model's superiority, achieving up to 21.17% and 29.30% average improvements in Root Mean Squared Error and 3.56% and 32.80% improvements in Mean Absolute Error compared to the baselines, respectively. The Friedman Chi-Square statistical test further confirmed the significant performance difference between the proposed model and its counterparts. The adversarial perturbations and random sensor dropout tests demonstrated its good robustness. On top of that, it demonstrated good generalizability through extensive experiments. The model effectively mitigates error accumulation in multi-step predictions while maintaining computational efficiency, making it a promising solution for enhancing Intelligent Transportation Systems.

Abstract
This paper examines the role of digital twins (DTs) in promoting sustainability within seaport operations and logistics. DTs have emerged as promising tools for enhancing seaport performance. Despite the recognized potential of DTs in seaports, there is a paucity of research on their practical implementation and impact on seaport sustainability. Through a systematic literature review, this study seeks to elucidate how DTs contribute to the sustainability of seaports and to identify future research and practical applications. We reviewed and categorized 68 conceptual and practical digital applications into ten core areas that effectively support economic, social, and environmental objectives in seaports. Furthermore, this paper proposes five preliminary potential applications for DTs where practical implementations are currently lacking. The primary findings indicate that DTs can enhance seaport sustainability by facilitating real-time monitoring and decision-making, improving safety and security, optimizing resource utilization, enhancing collaboration and communication, and supporting the development of the seaport ecosystem. Additionally, this study addresses the challenges associated with DT implementation, including high costs, conflicting stakeholder priorities, data quality and availability, and model validation. The paper concludes with a discussion of the implications for seaport managers and policymakers.