Multi-step ahead Time Series Forecasting (TSF) is crucial in domains such as energy management, transportation planning, and weather prediction. Traditional methods often rely on a direct strategy with multiple models or rolling/recursive strategies to predict future values. This can cause development difficulties, increase computational complexity and accumulate errors in specific time steps. In addition, existing sequence-to-sequence (Seq2Seq) models, although very powerful in several domains, can have complex structure with limited interpretability and difficulty to fit tabular TSF data. This paper introduces Seq2SeqT3DT, a novel tolerance-aware Seq2Seq tree model with three-dimensional input, a Decision Tree (DT) designed for multi-step forecasting regression tasks. Unlike conventional DTs, it is capable of directly mapping input sequences of historical data to output sequences of future predictions, within a single model framework. It extends the well-known DT algorithm and builds upon the baseline Seq2SeqDT (also known as multi-output or multi-target DT) by handling multi-dimensional outputs, allowing each leaf node to store a sequence of values, rather than a single prediction. It also features a more robust mechanism for tolerating prediction error through per-step or weighted tolerances, incorporating the option to use temporal derivatives, and applies temporal decay to favor recent features during splitting. We evaluate its performance by comparing it with the baseline Seq2SeqDT and the two established Seq2Seq Deep Learning (DL) models: a Long Short-Term Memory neural network (Seq2SeqLSTM) and a Seq2Seq transformer (Seq2SeqTF), on three forecasting datasets, for energy generation (EGF), energy load (ELF) and traffic congestion prediction (TCP), respectively, on 6-step and 12-steps ahead tasks. Experimental results demonstrate that, in the EGF 12-step task, Seq2SeqT3DT achieved average MAE = 0.1440, RMSE = 0.2800 and R^2 = 0.8619, outperforming all baselines, while in the EGF 6-step task showcased the lowest average RMSE (0.25) and highest R^2 (0.8898). On ELF, all models showed similar performance, with our model illustrating the lowest RMSE (0.2082) for the 12-step task. For the TCP task, our Seq2SeqT3DT was the second-best performer after Seq2SeqTF. These results show that Seq2SeqT3DT achieves better or competitive performance than Seq2SeqDT and Seq2Seq DL models in most cases, offering a promising alternative for multi-step TSF. Seq2SeqT3DT combines the simplicity and interpretability of DTs with the ability to handle complex Seq2Seq relationships, effectively bridging the gap between traditional DTs and modern Seq2Seq DL approaches.
Acoustic power transfer is a promising method for providing power to sensing microsystems installed in locations in which battery replacement, wiring, or energy harvesting from ambient energy is impractical or limited. In this paper, an evaluation of acoustic power transfer along metal surfaces is presented. Commercial audio band magnetostrictive and piezoelectric transducers are used as the transmitter and the receiver, respectively. The study was performed on a 1 m long, 0.5 mm wide, and 3 mm thick aluminum plate, emulating industrial infrastructure or vehicle panels. A power delivery of 44 μW is demonstrated at a 0.8 m transmitter–receiver distance, at a setup-specific 3.64 kHz resonance frequency. The corresponding open-circuit voltage amplitude is over 0.7 V, which is adequate for efficient power management. The receiver mass and volume are 1.57 g and 200 mm3 respectively, yielding 200 μW/cm3 and 25 μW/g power density. This power density is adequate for supporting low-power wireless sensor platforms by integration of acoustic piezoelectric receivers with an acceptable volume overhead compared with the size of typical sensor nodes.
With the continuous growth of the global economy, energy security and climate change issues are increasingly receiving widespread attention from the international community, further highlighting the importance of renewable energy. Currently, various marine renewable energy systems, represented by Floating Offshore Wind Turbines (FOWTs) and Wave Energy Converters (WECs), have progressed from concept validation and prototype sea trials to demonstration projects and pilot deployments. To further enhance the power generation, optimize the system's dynamic performance, and reduce the construction and operation costs of floating offshore wind turbine systems, this study proposes and analyzes a wind-wave integrated system. This system integrates a 5 MW V-shaped FOWT with an array of Salter's Duck Wave Energy Converters (SD WECs). The integrated system effectively captures wave energy generated by the relative motion between the wind turbine and wave energy devices through a Power Take-Off (PTO) system. Under various typical sea conditions, the study first established a numerical simulation model of this integrated system using ANSYS-AQWA software. Subsequently, a multi-field coupled dynamic analysis, encompassing aerodynamic, hydrodynamic, servo-control, and elastic structural aspects, was conducted based on the open-source code F2A, to deeply investigate the integrated system's dynamic characteristics and energy output performance. The research findings provide important theoretical basis and technical support for the efficient development and utilization of marine renewable energy.
Under the globalized environment and entering an era of ‘crises’, the states experience a higher pressure to make their economies more stable and sustainable. The impact of the financial crisis of 2008 and the recent impact of the Covid-19 financial effects have increased the vulnerability to a new financial shock. The article presents the public administration framework and shifts and fiscal data of Denmark and Greece. It also highlights the reforms taken and their recovery approaches. The need for cost allocation in public authorities should be based on the need of ‘resilient’ society and to disseminate a ‘cost culture’.
Background: The rapid integration of Artificial Intelligence (AI) – including Machine Learning (ML) and Generative AI – into software systems is reshaping the software development lifecycle. As AI-driven systems become more dynamic and complex, traditional approaches to Technical Debt (TD) management face increasing limitations. Simultaneously, AI-assisted development introduces new forms of TD, particularly in relation to maintainability, explainability, and data governance. Objective: This study aims to explore how Technical Debt Management (TDM) must adapt in the context of AI-enhanced software development. It investigates (1) the evolution of TD in AI-driven systems, and (2) the implications of using AI technologies within the software engineering process. Methods: We conducted a multivocal literature review, combining insights from both peer-reviewed research and industry sources. Following established guidelines, we systematically analyzed 61 primary sources, categorized TD types and management activities, and identified key challenges and practices emerging in the AI era. Results: Our findings reveal that data-related, infrastructure, and pipeline-related TD are particularly prevalent in ML systems. Machine Learning Operations (MLOps) practices are increasingly recognized as essential for managing such debt, especially in relation to dynamic data dependencies and model retraining. In parallel, AI-generated artifacts and automated pipelines introduce new governance and maintainability challenges. Conclusion: Technical Debt in AI systems demands continuous, automated, and cross-functional management strategies. As software evolves in response to data and usage, new operational paradigms – grounded in practices like MLOps and Small Language Model Operations (SLMOps) – will be vital to ensure long-term software sustainability. This study provides a foundational map for researchers and practitioners navigating the intersection of AI and TD management.
