Search Results (905)

The Internet of Things has increasingly enabled advancing real-time environmental monitoring through the integration of Low-Power Wide-Area Networks. Among these technologies, LoRa (Long Range) has emerged as a prominent communication technology due to its combination of long-range communication, low energy consumption, and affordability, making it particularly suitable for remote and infrastructure-limited environments. Its adaptability is further enhanced through the use of open-source hardware, renewable energy sources, and intelligent algorithms. Despite LoRa’s limitations in bandwidth and data rate, recent innovations enabled increasingly data-intensive applications, including image transmission. This review critically examines recent advances in image transmission over LoRa networks, synthesising approaches across four interconnected strategies: image compression, packetisation and reliability, communication optimisation, and application-specific techniques. The analysis evaluates trade-offs among image size, transmission latency, energy consumption, coverage, and reconstructed image quality. These considerations are particularly relevant for environmental sensing applications, including water quality assessment, air pollution monitoring, wildlife tracking, and underground mining. This review synthesises recent advances in LoRa-based environmental and visual sensing and highlights persistent challenges, including duty-cycle restrictions, limited throughput, and energy constraints, that must be addressed for broader adoption in data-intensive sensing applications. By analysing current strategies and proposing future directions, including adaptive encoding, lightweight encryption, and energy-aware scheduling, the review demonstrates the potential of LoRa to play an increasingly important role in enabling sustainable, scalable, and accessible Internet of Things solutions across diverse environmental settings. Full article

Hosting capacity (HC) has become a key concept in planning and operating modern distribution networks to sustainably integrate distributed energy resources (DERs), including photovoltaic systems, wind generation, battery energy storage, and electric vehicles. However, the literature shows variation in HC definitions, assessment assumptions, limiting criteria, and reporting practices, complicating cross-study comparison and utility implementation. This paper examines HC from four interconnected perspectives: limiting factors and performance indices, assessment methods, enhancement strategies, and standardization efforts. The review examines the influence of voltage constraints, thermal loading, power quality, protection coordination, network topology, system inertia, regulatory requirements, and load diversity on HC. It compares major assessment approaches, including deterministic, stochastic, time-series, optimization-based, iterative, hybrid, data-driven, and artificial intelligence-based methods, highlighting their strengths, limitations, and suitable applications. The paper also reviews HC enhancement techniques for sustainable network capacity utilization, including network reinforcement, smart inverter control, demand-side flexibility, energy storage, and coordinated multi-layer control. Particular attention is given to emerging HC standardization and the gaps between formal standards and the research frontier, especially in probabilistic, dynamic, and real-time assessment. Overall, HC depends on binding network constraints, operating conditions, assumptions, and controls, while methodological and reporting gaps limit comparability and sustainable DER integration. Full article

To proactively identify performance anomaly evolution and potential operational risks of marine main engines and reserve a sufficient time window for maintenance intervention, this paper proposes a data-driven multi-algorithm fusion framework for performance evaluation and anomaly early warning of marine main engines. The framework first adopts a steady-state detection strategy to filter valid operating conditions and introduces the CLIQUE clustering algorithm to realize adaptive partitioning of high-dimensional operating parameters; comparative experiments with the classical K-means++ clustering algorithm demonstrate that CLIQUE achieves finer-grained operating condition classification without pre-defining the number of clusters and better adapts to the uneven distribution of actual marine engine operating conditions, which addresses the limitations of traditional single-parameter analysis and conventional dimensionality reduction methods in practical shipboard scenarios. On this basis, the Mahalanobis distance evaluation model is constructed under each partitioned operating condition, which further improves the stability and anti-interference performance of quantitative performance assessment for the main engine. Meanwhile, by integrating cumulative anomaly trend analysis and the Yamamoto mutation test, the framework accurately captures statistical mutation characteristics of the performance deviation trajectory and identifies the first mutation point as the retrospective candidate change point, forming a systematic anomaly detection mechanism. Validation using field measurement data from a 6RT-flex82T marine main engine shows that the proposed framework can comprehensively characterize the overall operating state of the main engine and capture long-term performance deviation evolution patterns. Retrospective analysis indicates that the first statistical mutation of the multivariate performance deviation precedes the significant abnormal fluctuation of a single parameter by approximately 20 days, showing the potential of providing a maintenance buffer period. The proposed method can provide technical reference and support for condition-based maintenance of marine main engines and intelligent operation and maintenance of shipboard power equipment. Full article

Metal oxide semiconductor (MOS) gas sensors are widely used for low-cost chemical detection, but their practical performance is still limited by high operating temperature, insufficient selectivity, signal drift, and device-to-device variation. Recent advances in microelectromechanical systems (MEMS), dynamic sensing protocols, and artificial intelligence (AI) provide new opportunities to improve MOS gas sensing from both hardware and data-processing perspectives. MEMS micro-hotplates enable miniaturized devices, low-power heating, rapid thermal control, temperature-modulated operation, and compatibility with integrated readout and interface circuits, while AI methods extract multivariate, nonlinear, and temporal information from cross-sensitive sensor responses. This review summarizes the fundamentals of MOS sensing materials, MEMS micro-hotplate platforms, material–device integration strategies, and AI-assisted data-processing methods ranging from classical statistical analysis to deep learning. Representative strategies are discussed, including single-sensor feature extraction, sensor-array recognition, temperature-modulated sensing, drift compensation, and AI-guided material design. Application studies in food quality assessment, agriculture, medical diagnostics, environmental monitoring, and public safety are further reviewed to show how sensing tasks evolve from odor-fingerprint discrimination to nonlinear feature interpretation, dynamic response analysis, domain adaptation, and deployable intelligent monitoring. Particular attention is given to the role of high-consistency integration of MOS sensing layers on MEMS platforms, since reproducible material loading, morphology, electrode coverage, and thermal coupling are essential for reliable datasets and transferable AI models. Finally, key challenges are discussed, including dataset heterogeneity, long-term drift, edge deployment, and material–device reproducibility. This review highlights that future AI-assisted MOS/MEMS gas sensors require coordinated design of sensing materials, device platforms, fabrication processes, operating protocols, and data-driven models. Full article

Ports are progressively evolving from traditional logistics nodes into integrated energy ecosystems, characterised by increasing electrification of maritime and land-based operations, the deployment of renewable energy sources, and the emergence of new and highly variable energy demand profiles. In this context, the main challenge is not only the availability of renewable energy but also the capacity of port energy systems to provide sufficient electrical power, flexibility, and resilience under increasing operational constraints. These issues are particularly relevant in Mediterranean ports, where limited grid capacity, infrastructure constraints, load variability, and interactions with surrounding urban areas strongly influence energy planning strategies. This paper proposes an integrated framework for the development of sustainable port energy hubs based on renewable generation, energy storage, green hydrogen systems, port microgrids, and intelligent energy management strategies (EMS). The main novelty lies in the integration of these energy vectors within a unified framework that explicitly accounts for the specific operational and infrastructure constraints of Mediterranean ports. The proposed approach aims to optimise the interaction between energy production, distribution, storage, and consumption, with particular attention to the role of hydrogen as a long-duration energy storage vector and as an energy carrier for selected port logistics applications. Through a data-driven Port Energy Baseline Assessment (PEBA), port operational characteristics are translated into quantified energy demand and power requirements, providing the basis for power adequacy assessment and the evaluation of alternative transition pathways. An illustrative application to a representative Mediterranean port, characterized by a peak electricity demand of 42 MW, illustrates how the framework quantifies power requirements, assesses power adequacy under infrastructure constraints, and compares alternative transition pathways based on renewable generation, battery storage, and hydrogen. Full article

Urban-forest monitoring increasingly requires intelligent sensor-driven systems capable of characterizing short-term tree responses while operating efficiently within Internet of Things (IoT) and edge-computing environments. This study proposes a fusion-based artificial intelligence framework that integrates Quantization-Aware Training (QAT)-optimized PointNet++ models with machine-learning regression to predict a short-term dendrometer-derived stem-diameter response expressed in biomass-equivalent units. The framework combines 1024-point LiDAR tree representations, geometric measurements, and environmental sensor data through three components: QAT-optimized PointNet++ models for 34-species classification and trunk–crown part segmentation, frozen model-based prediction and geometric feature extraction, and MLP and XGBoost regression models for prediction of the short-term target. The dataset contained 2694 trees from five regions of South Korea, with the target derived from dendrometer-based stem-diameter measurements recorded over a 14-day interval between 8 September 2022 and 22 September 2022. Importantly, this short-term signal reflects both structural and reversible water-status-related stem dynamics and is therefore not interpreted as direct dry-biomass accumulation or carbon sequestration. The QAT-optimized models retained 92.52% segmentation accuracy (82.67% mIoU) and 80.46% species-classification accuracy, while the regression model reached R² = 0.9663 and RMSE = 0.4437 kg for the defined biomass-equivalent target. Quantization reduced the saved model size of both encoders by approximately 10.5× (21 MB → 2 MB) and accelerated CPU inference by up to 4.1×. These efficiency measurements were obtained on an ×86 desktop CPU and therefore characterize computational compression benefits rather than completed deployment or field validation on a low-power embedded device. These results demonstrate the computational feasibility of combining compressed point-cloud perception with multimodal prediction of short-term dendrometer-derived stem dynamics. Validation over seasonal and multi-year periods using independent biomass-reference measurements would be required before extending the framework to long-term biomass accumulation or carbon-sequestration assessment. Full article

Agentic AI can coordinate distributed energy resources, invoke tools, revise plans, and act through multiple interacting agents. In critical energy systems, however, model-level explainable artificial intelligence (XAI) cannot reveal how goals, constraints, tools, delegations, authority, human intervention, and system changes combine to produce an operational action. This creates a regulatory and engineering gap wherever EU AI Act requirements for transparency, record-keeping, and human oversight apply. The transparency-by-design framework addresses this gap by treating operational transparency as a compositional property created through evidence continuity across model, agent, interaction, system, and lifecycle levels. It translates five regulatory transparency functions into eight components, a seven-stage gated lifecycle, stakeholder responsibilities, evidence artefacts, and acceptance criteria. Together, these elements specify what must be transparent, to whom, when, and how adequacy should be assessed and maintained. Regulatory analysis and thematic synthesis of 101 studies provide the evidence base. Application to an agentic virtual power plant demonstrates how forecasts, goals, plan revisions, inter-agent decisions, operator interventions, execution records, and system versions can be joined within one reconstructable evidence chain. The framework extends XAI from local model explanation to lifecycle-wide operational transparency for compliance-oriented development, without claiming legal conformity or field effectiveness. Full article

Milk and dairy products are highly vulnerable to Economically Motivated Adulteration (EMA), particularly through the substitution of milk fat with cheaper non-milk fats. This paper presents a comprehensive review of analytical approaches used for detecting vegetable oils (e.g., palm, coconut, sunflower) and animal-origin fats such as pork lard and bovine tallow, as well as the fraudulent mixing of milk from different species. Methods for lipid extraction are examined, including traditional gravimetric procedures such as the Röse–Gottlieb method and high-efficiency alternatives such as Accelerated Solvent Extraction and supercritical fluid extraction. Analytical strategies for fraud detection are evaluated, demonstrating that while fatty acid profiling is widely applied, its sensitivity is limited by natural variability. Greater discriminatory power can often be achieved through triacylglycerol analysis combined with mathematical models such as the Precht formulae (which generate S-values), although performance varies depending on the adulterant matrix, adulteration level, reference population, and analytical protocol. Similarly, sterol profiling, particularly the detection of phytosterols like β-sitosterol, is a valuable marker for vegetable oil adulteration but does not provide an equivalent solution for detecting animal fat adulteration. The potential of rapid, non-destructive screening tools, including Fourier-transform infrared and Raman spectroscopy supported by chemometrics, is also assessed. A central analytical challenge in detecting such fraud lies in the complexity and variability of milk fat composition, which hinders any single analytical method from universally identifying all forms of non-milk fat adulteration; therefore, a tiered strategy combining rapid screening tools with high-resolution confirmatory methods is preferable. Future perspectives highlight the increasing importance of green analytical approaches, artificial intelligence, and portable detection systems for enhancing verification within the global dairy supply chain. However, the effectiveness of AI and chemometric methods depends heavily on the availability of representative training datasets and rigorous external validation to avoid overfitting and ensure reliable application across diverse samples. Full article

New energy power systems with high penetration rates feature complex spatiotemporal coupling relationships among generation, transmission, load, and storage. The random fluctuations in wind and solar power output, combined with load uncertainty, exacerbate system operational risks. Traditional static modeling, single-metric evaluation, and centralized analysis methods struggle to adapt to the dynamic, highly uncertain, and multi-constrained operational scenarios of new power systems. To address this, this paper proposes an Artificial Intelligence-based Comprehensive Evaluation Method for Power System Flexibility and Sustainability (AI-FSEA) under privacy and security constraints. This method first establishes an intelligent fusion module for multi-source, heterogeneous power data, which accurately extracts the system’s multidimensional dynamic features through adaptive wavelet denoising and a temporal self-attention mechanism. Second, it establishes a five-objective coupled evaluation model that balances technical, economic, low-carbon, and reliability considerations, with regulation margin loss, response delay, operating costs, carbon emissions, and power supply instability rate as the core optimization objectives, thereby achieving multi-objective trade-off optimization within the system’s feasible domain; furthermore, a Hierarchical Deep Q-Network-Assisted Multi-Objective Evolutionary Algorithm (HDQN-MOEA) is designed, which leverages the value iteration, composite reward mechanism, and feedback clustering screening mechanism of the deep Q-network to enhance the model’s solution accuracy and convergence efficiency. Results from multiple sets of comparative experiments, ablation studies, and uncertainty generalization experiments conducted using the IEEE standard node system and real-world power grid data from East China indicate that, compared with mainstream optimization algorithms such as NSGA-III and TS-NSGA-II, the proposed HDQN-MOEA algorithm achieves an average improvement of 10.2% in the hypervolume metric and an average reduction of 35.6% in the span metric; the results of the ablation experiments confirm that the absence of the multi-source data fusion module, the hierarchical strategy module, or the feedback clustering screening module would result in a 15.3% and 12.1% decrease in the model’s hypervolume metric, respectively, as well as a slight deterioration in population diversity; under three types of highly uncertain operating conditions—random fluctuations in renewable energy, sudden load spikes, and extreme weather—the algorithm proposed in this paper consistently maintains stable optimization performance, meeting convergence accuracy requirements in as few as 5000 iterations. Without increasing the complexity of existing algorithms, it achieves the synergistic optimization of data privacy and security, evaluation accuracy, and operational efficiency. The proposed method can accurately quantify the dynamic flexibility and long-term sustainability of the new power system, providing reliable intelligent technical support for the planning and dispatch of the new power system, the optimal allocation of resources, and low-carbon, sustainable operation. Full article

This study introduces a training-free, self-contained adaptive low-light image enhancement (LLIE) framework driven by a metaheuristic optimization algorithm (MOA) and a context-aware dual image quality assessment (IQA) engine. Although deep-learning-based methods exhibit rapid inference, their static parameters often suffer from severe performance degradation in out-of-distribution (OOD) scenarios—such as those involving unseen sensor noise or environmental shifts. To bridge this generalization gap, the proposed framework operates within a decoupled HSV color space, specifically targeting the luminance ($V$) channel to formulate image enhancement as an instance-specific optimization task. We introduce a novel hybrid Log-Gamma mapping function that mathematically unifies the localized dark-stretching capabilities of logarithmic compression with the global dynamic range regulation of power-law gamma curves, thereby substantially expanding the expressiveness of the transformation space. To govern parameter convergence without reference images, a multi-stage Low-Light Image Discrimination (LLID) engine classifies the input frame by computing context-specific trimmed skewness residuals and global intensity means, effectively mitigating highlight biases. Under normal-light conditions, the swarm intelligence engine optimizes the Log-Gamma coefficients via the Patch-based Contrast Quality Index (PCQI) to maximize structural fidelity; conversely, under severe low-light degradations, the framework leverages the Blind/Referenceless Image Spatial Quality Evaluator (BRISQUE) to minimize spatial artifacts. Using the Marine Predators Algorithm (MPA), the framework iteratively searches the continuous bounding space to fine-tune a parameter matrix tailored exclusively to each image. Empirical evaluations across four benchmark datasets (Bicycle, DF1000, DICM, and VV) validate the effectiveness of the proposed paradigm. The proposed variant, $OLG\left(\mathrm{MPA}\right)$, secured the top average rank in internal algorithm ablation ($\overline{R}=3.10$) and achieved a competitive global average rank ($\overline{R}=2.95$) against four state-of-the-art deep networks, matching the performance of leading data-driven models. Although the evolutionary optimization loop incurs an average per-frame latency of $17.300 \mathrm{s}$, this instance-specific paradigm successfully trades instantaneous processing speed for absolute domain adaptability and predictable, artifact-free image restoration. Full article

Circulating fluidized bed (CFB) boilers combine multiphase dynamics, long transport delays, and multimode operation that challenge condition monitoring and performance evaluation. This structured narrative review surveys artificial intelligence for CFB state monitoring, fault diagnosis, performance assessment, and combustion optimization (2005–2026), supported by a reproducible literature search, structured evidence workbook, and concise quality appraisal. The literature is organized by monitoring objectives and method families from soft sensors and deep learning to physics-informed hybrids, digital twins, and multimodal non-destructive testing. Most included evidence remains single-unit and retrospective or offline; accuracy gains in publications often outpace verified sustained online use. One 150 MW project report estimated approximately EUR 699,000 in annualized benefits (not independently audited). Remaining gaps include cross-unit generalization, standardized benchmarks, secure deployment, and closed-loop diagnostics–maintenance integration. Full article

The increasing penetration of inverter-based resources and the growing complexity of modern power systems have made voltage stability assessment a critical aspect of transmission network operation. This paper presents a review of the main methods and indices adopted for voltage stability assessment, with emphasis on their applicability to real-time monitoring and inverter-dominated grids. The review covers both long-term and short-term voltage stability approaches, including L-index methods, Jacobian- and singular-value-based techniques, Lyapunov-exponent-based methods, trajectory-based indices, and recent artificial intelligence applications. For each method, the main advantages, limitations, computational requirements, and suitability for PMU-based monitoring are discussed. The analysis shows that no single indicator can fully describe all voltage instability phenomena. Instead, combining complementary static and dynamic indices provides a more complete basis for wide-area monitoring and real-time operational support in future power systems. Moreover, the main open challenges related to threshold definition, robustness under evolving grid conditions, and the integration of data-driven techniques into operational stability assessment schemes are discussed. Full article

Background: Emotional intelligence (EI) is an important component of adolescents’ psychological adjustment and social functioning. Creativity-based experiential approaches may support EI development through active emotional processing, reflection, and interpersonal learning; however, empirical evidence in adolescents remains limited. Methods: This quasi-experimental controlled pretest–posttest study included 47 adolescents who self-selected into an experimental group (n = 24) or control group (n = 23) according to their preference regarding participation in the training program. EI was assessed using the Schutte Self-Report Emotional Intelligence Test (SSEIT). The experimental group completed a 12-week creativity-based experiential programme, while the control group continued usual activities. Results: At post-intervention, the experimental group had significantly higher overall EI (p < 0.001, d = 1.60), AES (p < 0.001, d = 1.34), and ERO (p < 0.001, d = 1.24) scores than the control group. Although post-intervention ERS scores were also higher in the experimental group, a large ERS difference was already present at baseline and the experimental group showed no favorable descriptive change in this dimension. Utilization of emotions in problem solving did not differ significantly between groups (p = 0.090, d = 0.50). Conclusions: Participation in creativity-based experiential training was associated with higher post-intervention overall EI, AES, and ERO scores, but demonstrated limited effectiveness for ERS and UEPS. The small sample and insufficient statistical power, together with the non-randomized design and baseline ERS imbalance, preclude firm or causal conclusions. Larger randomized controlled studies using multimethod assessments and long-term follow-up are needed to establish causality, durability, and the mechanisms underlying these associations. Full article

The increasing complexity of healthcare data ecosystems demands educational technologies capable of supporting data-intensive learning through advanced analytics, immersive interfaces, and learning analytics. This paper presents a cloud-based reference architecture and a prospective evaluation protocol for integrating Business Intelligence (BI), Extended Reality (XR), and learning analytics in health data science education. The proposed architecture is informed by a systematic literature review conducted according to the PRISMA 2020 guidelines, which screened 613 records retrieved from four databases and retained 56 studies for qualitative synthesis. The review indicates that, although BI and XR technologies have independently been associated with educational benefits, empirical evidence supporting integrated educational architectures combining BI, XR, and learning analytics remains limited, particularly in health data science education. Based on these findings, the paper specifies a layered reference architecture comprising a cloud analytics engine, an immersive visualization engine, an interoperability layer, and a learning analytics pipeline designed to support adaptive and AI-assisted educational services during subsequent implementation phases. The reference architecture is partially instantiated within the curricular unit Health Data Analysis and Visualization of the Digital Health programme at the Polytechnic University of Porto, where the BI and XR components are currently deployed and used within the course, while the interoperability middleware, learning analytics infrastructure, and AI-assisted services remain under development or are specified as architectural capabilities. To support future empirical validation, the paper also defines a comprehensive prospective evaluation protocol comprising predefined outcomes, established instruments with published psychometric properties, together with an expert-developed health data literacy assessment undergoing content validation, research hypotheses, power analysis, a statistical analysis plan, and ethical and data-governance provisions. The manuscript makes four principal research contributions: (i) a cloud-based reference architecture for BI–XR integration, (ii) a computational learning analytics pipeline specification, (iii) an interoperable system design for health data science education, and (iv) a prospective evaluation protocol to guide the future validation of the proposed reference architecture. Full article

The operational reliability of shaft systems in hydropower units has become increasingly critical as these units are frequently engaged in grid regulation under new power systems. This paper presents a sensor-driven method for operational status assessment and trend prediction of Francis turbine generator unit shaft systems using vibration and swing signals. Time domain features are extracted from the sensor-acquired signals to construct a multi-dimensional quantitative index system for characterizing the operational state, and a combined Entropy Weight–Coefficient of Variation–TOPSIS model with dynamic health thresholds is established for adaptive condition assessment. To address the nonlinear and non-stationary characteristics inherent in such signals, a decomposition–prediction–reconstruction fusion framework is developed, incorporating Variational Mode Decomposition (VMD) for signal decomposition and noise reduction, iTransformer for capturing global multi-variable interactions, and Bidirectional Long Short-Term Memory (BiLSTM) for bidirectional temporal feature extraction. The hybrid model achieves a coefficient of determination R² of 0.9845 on complex vibration and swing signals, demonstrating its superior prediction capability. Based on the prediction results, health scores and dynamic thresholds are calculated to perform trend analysis and health early warning. A case study is conducted using real-world monitoring data from a 306 MW Francis turbine unit. The results demonstrate that the proposed method effectively characterizes the shaft system operational state, achieving a closed-loop integration from condition monitoring to fault diagnosis and predictive maintenance. The operational status assessment and trend prediction analyses are in good agreement with actual operating conditions, providing reliable technical support for the intelligent health management of hydropower units. Full article