https://www.mdu.se/

Background/Objectives: The objective evaluation of regional dietary intake remains a core challenge in personalized health management due to complex plate presentations and a lack of culturally specific dataset benchmarks. Methods: This study introduces a confidence-aware hybrid vision-language framework engineered for traditional Turkish food recognition and structured nutritional assessment. Results: We curate a balanced dataset containing 14,711 verified images spanning 40 representative Turkish culinary classes to train and evaluate seven deep learning architectures. Among the visual models, EfficientNet V2-L achieved the highest standalone performance with an accuracy of 93.47%, 0.92 macro-precision, 0.92 macro-recall, and a 0.92 F1 score. To overcome visual ambiguity and automate content analysis, a confidence-aware routing strategy escalates uncertain predictions ( tau<0.70 ) or user-rejected classifications to the Google Gemini 2.5 Flash multimodal large language model (MLLM). Conclusions: This hybrid paradigm yields a combined classification accuracy of 95.50% while validating portion weight estimations within a mean absolute error (MAE) of 18.42 g and total energy within 36.75 kcal. Fully realized as a cross-platform Flutter mobile application, the end-to-end pipeline demonstrates localized plate detection, adaptive portion analysis, and structured nutrient tracking, providing a scalable design for consumer-facing digital nutrition platforms.

Background/Objectives: Accurate estimation of meal composition from food images can support safer and more reliable insulin bolus decision-making for individuals with Type 1 diabetes. Existing food recognition and nutrition estimation systems are often designed for general dietary logging and do not directly integrate food analysis with personalized insulin therapy parameters. Methods: This study presents an image-based nutrition estimation and insulin decision-support module developed within the AI-assisted Diabetes Care (AIDCARE) platform. The proposed system uses a convolutional neural network (CNN) to classify food items from a single meal image, and retrieves reference nutritional values from a food composition database. A separate multimodal large language model (MLLM)-based estimation component is then used to estimate portion size, allowing carbohydrate and nutrient values to be scaled according to the observed serving. Results: A curated food image dataset containing 40 food categories was used to evaluate three CNN architectures: ResNet50, Inception V3, and EfficientNet-B0. EfficientNet-B0 achieved the best classification performance, with 94.91% validation accuracy, 95.55% precision, 94.87% recall, and 94.90% F1-score. The portion-estimation component achieved an MAE of 12.27 g and an RMSE of 15.11 g. The estimated carbohydrate value is combined with user-specific clinical parameters, including the insulin-to-carbohydrate ratio and insulin sensitivity factor, to generate advisory bolus guidance. To support safety, the system requires user confirmation or correction of the recognized food category and estimated portion before insulin guidance is displayed. Conclusions: The proposed system is intended for advisory decision support only and is not designed to replace clinical judgment or autonomous insulin delivery systems.

The proliferation of resource-constrained Internet-of-Things (IoT) and Industrial IoT (IIoT) devices has intensified the need for local, intelligent cybersecurity solutions that do not rely on cloud connectivity. This paper presents a TinyML-based Intrusion Detection System (IDS) framework designed for embedded edge controllers. Two machine-learning IDS models - a Convolutional Neural Network (CNN) and a Random Forest (RF) - were developed and evaluated on the TON-IoT dataset to identify malicious network traffic. Host-side evaluation established baseline performance, while the float-precision RF model was implemented as firmware and validated using hardware-in-the-loop emulation in the Renode RISC-V environment. The resulting binary occupies only 1.6 MB of Flash memory, achieving above 99% detection accuracy with 448 μs average inference latency. These results demonstrate that fully embedded, real-time intrusion detection is feasible within TinyML memory budgets, supporting IEC-62443 compliant anomaly monitoring for industrial devices.

Modelling plays a critical role in many engineering applications. Partial differential equations (PDEs) are ubiquitous, describing various physical phenomena such as fluid flow, electromagnetism, and quantum mechanics. Although some of these equations have analytical solutions, many require high-fidelity simulations of parametric PDEs. In general, high-fidelity simulations are computationally expensive and often infeasible for real-time or multi-query applications. This challenge has led to the development of reduced-order models (ROMs). Over the past few decades, ROMs have emerged as a practical solution for simulating, controlling, and optimizing large-scale and complex dynamical systems. This paper introduces a novel Calibrated Intrusive Reduced-Order Modelling (CIROM) approach for the efficient and accurate simulation of the one-dimensional Burgers' equation, employed as a canonical benchmark because it is a simplified fundamental partial differential equation that captures the behaviour of many real-world phenomena. The proposed method, combining the strengths of proper orthogonal decomposition (POD) and long short-term memory (LSTM) networks, effectively reduces computational complexity while addressing inherent instabilities in classical reduced-order models. Unlike traditional POD-ROMs, which often suffer from error accumulation and instability at high Reynolds numbers, the CIROM employs an iterative LSTM-based error correction mechanism to learn and compensate for truncation and projection errors. This study is benchmark-oriented and does not aim to provide a general PDE solver. The performance of the proposed method is rigorously evaluated across a broad range of Reynolds numbers, including interpolation and extrapolation scenarios, demonstrating robust extrapolation within moderate ranges. Comprehensive numerical experiments confirm that the CIROM outperforms both pure intrusive ROMs and purely data-driven LSTM models in terms of prediction accuracy, stability, and computational cost.

The transition to truly smart cities demands more than layered technologies; it requires convergent intelligence that unifies physical sensing, adaptive control, and ethical security. This editorial paper brief about the special issue entitled “ Measurement, Control and Security of Systems for Smart Cities ”. As smart cities are among the most active research areas, the call for papers for this special issue, “VSI: Systems for Smart Cities” attracted a wide range of manuscripts spanning multiple disciplines, including Computer Science, Electrical and Electronics Engineering, Communication Engineering, Civil Engineering, Mechanical Engineering, Urban Construction, Artificial Intelligence and Machine Learning, Cybersecurity, and Renewable Energy etc. Notably, authors from 16 different countries, including Algeria, Chile, China, Egypt, England, Ethiopia, India, Iran, Jordan, Kosovo, Nigeria, Portugal, Saudi Arabia and United Arab Emirates have contributed their research articles. In this editorial, we synthesize insights from all 30 published articles to present a holistic vision of next-generation urban ecosystems. Together, these works span renewable energy, structural health, healthcare, transportation, noise pollution, public space, and data security, these works collectively redefine what it means to build intelligent infrastructure that is sustainable, equitable, resilient, and trustworthy. We organize these advances around three interwoven pillars: (1) Measurement for Awareness, (2) Control for Adaptation, and (3) Security and Ethics for Trust-and demonstrate how fractional-order controllers, lightweight crack detectors, edge-based triage systems, multimodal transport models, and secure data-mining frameworks all contribute to a human-centered urban future. This synthesis serves as both a technical roadmap and a philosophical compass for the responsible evolution of smart cities. 

Atrial Fibrillation (AFib) is a common cardiac arrhythmia whose global prevalence has risen in recent years. If left untreated, AFib can lead to severe complications such as stroke and heart failure. Because AFib may occur without symptoms, continuous monitoring is critical for timely detection. This paper presents a low-cost Intelto detect AFib from Electrocardiogram (ECG) signals. The study evaluates the feasibility of deploying 1D-CNN models on resource-constrained edge devices and compares edge- and cloud-based computing architectures with respect to inference efficiency. Three 1D-CNN models of increasing complexity are designed, trained, and tested on datasets containing AFib and Normal Sinus Rhythm (NSR) segments. Two experiments are conducted to assess end-to-end delay and prediction time under a controlled experimental setup. The results demonstrate the potential for on-device AFib detection in constrained environments and provide practical insights into selecting suitable architectures for embedded deployment.

Industrial Internet of Things (IIoT) is changing the modern industrial processes through the integration of devices, sensors, and control systems, enabling real-time monitoring, automation, and datadriven decision-making. A significant challenge within IIoT systems, especially in control applications, is achieving guaranteed latency while ensuring high reliability. This paper presents a comprehensive review of recent research in IIoT, with a particular emphasis on the role of fifth generation (5G) wireless communication technologies. It includes an in-depth analysis of experiments conducted via real-world test-beds, providing insights into the performance of IIoT systems utilizing 5G technology. Additionally, the important support which has taken from different simulations and emulations in terms of library, protocols stacks and so on also discussed. We also assess how effectively these test-beds and platforms replicate real-world industrial environments and their capability to evaluate system performance under varying network configurations. Furthermore, we explore key technical parameters commonly used in IIoT research, including throughput, jitter, packet loss, spectral efficiency, and energy efficiency. This paper highlights both the benefits and limitations of employing test-beds for evaluating IIoT systems in industrial applications. It further examines the essential role of futuristic technologies, challenges and outlines research directions aimed at IIoT systems.

The convergence of Federated learning (FL) and Edge computing (EC) has emerged as an essential paradigm, particularly within the Industrial Internet of Things (IIoT) to enable the intelligent decision making. This work diligently examines the current state-of-the-art research at the intersection of FL, EC, and IIoT. An extensive review of the literature explores the diverse applications and challenges associated with this integration. The challenges range from privacy preservation and communication overhead to resource allocation. The incorporation of edge devices at which ensuring the federated learning in distributed manner helps to minimize energy consumption in IIoT, ultimately leads to a sustainable computing environment. By exploring the existing literature and research advancements, our goal is to highlight existing Edge-IoT software and hardware platforms and assess their usability in addressing challenges. In addition, we review existing recent frameworks, methodologies, and models employed to address these challenges, focusing on key performance matrices and its domain such as application, networking, and learning. We highlight the achievements and potential of FL and EC and underscore the need for tailored solutions to suit the unique demands of IIoT. Furthermore, we identify some of the major challenges as opportunities for future research, requires interdisciplinary collaboration and innovative algorithmic solutions. This work can help navigate through the challenges and unlock the full potential, contributing to the advancement of future IIoT applications.

Massive Multiple Input Multiple Output (mMIMO) is a promising solution for enabling green communication in next-generation wireless networks. Integrating mMIMO with Simultaneous Wireless Information and Power Transfer (SWIPT) technology can further enhance the system efficiencies in terms of Energy Efficiency (EE) and spectral efficiency. This paper studies the feasibility and energy-efficient design of a uniform planar antenna (UPA)-assisted mMIMO-enabled SWIPT system. The downlink transmission of the SWIPT mMIMO system over the Rician fading channels is investigated with terminals harvesting energy based on a nonlinear energy harvesting model. We derive approximate expressions for signal-to-interference-plus-noise Ratio (SINR) and harvested power. Additionally, we formulate an EE optimization problem considering user-level quality of service and total transmit power constraints. To solve this nonconvex problem, we jointly optimize the allocated power and Power Splitting (PS) ratios by exploiting the fractional programming and convex-concave procedure approaches. Results demonstrate the superiority of our proposed design compared to the conventional scenarios with equal power allocation and fixed PS ratio algorithms with about 2 to 5 times EE improvements. The Results also indicate a considerably higher growth rate on EE by increasing the number of antennas and Rician factors compared to the two other methods.

Highlights: What are the main findings? A surrogate-based deep reinforcement learning (DRL) framework (FAE–CAE–LSTM) is proposed. Achieves higher accuracy compared to DMD, POD, and conventional autoencoders. Provides 5–10× computational speedup, enabling real-time flow control. Incorporates a CNN–MLP reward estimator that enhances policy performance. What is the implication of the main findings? Enables robust modeling of high-dimensional nonlinear flow dynamics. Reduces dependence on full-order PDE solvers, minimizing control delays. Scalable to turbulent and three-dimensional flow control problems. Offers broad applicability in fluid dynamics, energy systems, and engineering control. In cyber-physical systems governed by nonlinear partial differential equations (PDEs), real-time control is often limited by sparse sensor data and high-dimensional system dynamics. Deep reinforcement learning (DRL) has shown promise for controlling such systems, but training DRL agents directly on full-order simulations is computationally intensive. This paper presents a sensor-driven, non-intrusive reduced-order modeling (NIROM) framework called FAE-CAE-LSTM, which combines convolutional and fully connected autoencoders with a long short-term memory (LSTM) network. The model compresses high-dimensional states into a latent space and captures their temporal evolution. A DRL agent is trained entirely in this reduced space, interacting with the surrogate built from sensor-like spatiotemporal measurements, such as pressure and velocity fields. A CNN-MLP reward estimator provides data-driven feedback without requiring access to governing equations. The method is tested on benchmark systems including Burgers’ equation, the Kuramoto–Sivashinsky equation, and flow past a circular cylinder; accuracy is further validated on flow past a square cylinder. Experimental results show that the proposed approach achieves accurate reconstruction, robust control, and significant computational speedup over traditional simulation-based training. These findings confirm the effectiveness of the FAE-CAE-LSTM surrogate in enabling real-time, sensor-informed, scalable DRL-based control of nonlinear dynamical systems.