Search Results (97)

Background: Emergency triage systems using machine learning traditionally rely on structured tabular data (vital signs), creating a “contextual blind spot” that ignores diagnostic information embedded in unstructured clinical narratives. Hybrid AI models that fuse tabular and text data may improve predictive discrimination, but the magnitude and conditions under which fusion adds value remain unclear. Methods: Five databases (PubMed, Scopus, Web of Science, IEEE Xplore, ACM Digital Library) were searched from 1 January 2015 to 15 December 2025. Eligible studies employed Hybrid AI models integrating structured and unstructured emergency department data with quantitative baseline comparisons. Twenty-five studies (N ≈ 4.8 million encounters) met inclusion criteria. We extracted marginal performance gains (ΔAUC), calibration metrics, and demographic reporting. Synthesis followed SWiM principles with subgroup meta-regression testing our novel “Complexity Gradient” hypothesis. Results: Hybrid models demonstrated superior discrimination compared to tabular baselines, with effect magnitude dependent on clinical task complexity. Low-complexity tasks (tachycardia prediction) showed minimal gains (median ΔAUC + 0.036, IQR: 0.02–0.05), while high-complexity tasks (hypoxia, sepsis) demonstrated substantial improvement (median ΔAUC + 0.111, IQR: 0.09–0.13). Meta-regression confirmed complexity significantly moderated effect size (R² = 0.42, p = 0.003). Only 12% (3/25) of studies reported calibration metrics (Brier scores: 0.089–0.142). Zero studies stratified performance by race/ethnicity; 88% (22/25) failed to report training data demographics. Discussion: The complexity gradient framework explains when multimodal fusion adds predictive value: tasks where diagnostic signal resides in narrative features (temporality, negation) rather than physiological measurements. However, systematic absence of calibration reporting and fairness auditing prevents clinical deployment. Seventy-two percent of studies had high risk of bias in the analysis domain due to retrospective designs without temporal validation. Conclusions: Hybrid triage models show promise for complex diagnostic tasks but require mandatory calibration reporting and demographic performance stratification before clinical implementation. We propose minimum reporting standards including Brier scores, race-stratified metrics, and temporal validation protocols. Full article

The energy transition and electrification are increasing the use of power electronics in low-voltage networks, increasing losses and reducing service availability when harmonic currents are concentrated in the neutral. This study statistically evaluates power quality in a campus-type microgrid with a high proportion of nonlinear loads. The novelty of the work lies in combining field measurements, percentile-based neutral-current severity analysis, and standards-based comparative mitigation assessment in a low-voltage 3P4W campus microgrid. A campaign was carried out using a Fluke 1775 analyzer, recording trends, frequency, and events. Approximately 1900 events were recorded, mainly waveform deviations, interruptions, and rapid voltage changes. Voltage distortion was moderate, with a 95th percentile between 3.6% and 3.8%, while the neutral conductor concentrated the highest severity: neutral-current THD exceeded 220% in the 95th percentile and reached maximums above 700%, with 16.78 A in the 95th percentile at the measurement point. Based on IEC 61000-2-2 and IEEE 519, four mitigation measures were evaluated in DIgSILENT PowerFactory 2024 to estimate and reduce losses and heating: load balancing, detuned compensation, passive filtering, and active filtering. Active mitigation reduced the neutral harmonic component by 80% and the combined strategy decreased the neutral current at the measuring point by 78% (16.78 A to 3.69 A), with an estimated reduction in resistive losses of close to 95%. These results suggest sustainability benefits by reducing energy wasted as heat, extending the useful life of the infrastructure and improving operational resilience. Full article

Exposure to nature has been associated with benefits to human well-being, commonly evaluated using standardized psychological assessments and, more recently, neuroimaging modalities such as Electroencephalography (EEG), functional Magnetic Resonance Imaging (fMRI), and functional Near-Infrared Spectroscopy (fNIRS). This systematic review and meta-analysis addresses the following questions. (1) How is the impact of nature on well-being studied using psychological and neuroimaging modalities and what does it reveal? (2) What are the challenges and opportunities for the deployment of wearable neuroimaging modalities to understand the impact of nature on the brain’s health and well-being? A search on PubMed, IEEE Xplore, and ClinicalTrials.gov (March 2024) identified 33 studies combining neuroimaging and psychological assessments during exposure to real, virtual or imagined natural environments. Studies were analyzed by tasks, populations, neuroimaging modality, psychological assessment, and methodological quality. Most studies were conducted in Asia (n = 23 or 70%). Healthy participants were the dominant target population (70%). In total, 61% of the studies were conducted in natural settings, while 39% used visual imagery. EEG was the most common modality (82%). STAI (n = 8) and POMS (n = 8) were the most common psychological assessments. Only seven studies included clinical populations. Two separate meta-analyses of nine studies with explicit experimental and control groups revealed a significant positive effect of nature exposure on psychological outcomes (Hedges’ g = 0.30; p = 0.0021), and a larger effect on neurophysiological outcomes (Hedges’ g = 0.43; p = 0.0004), both with moderate-to-high heterogeneity. Overall, exposure to nature was associated with reductions in negative emotions in clinical populations. In contrast, healthy populations showed a more balanced psychological response, with nature exposure being associated with both increases in positive emotions and reductions in negative emotions. Notably, 88% of the studies presented methodological weaknesses, highlighting key opportunities for future neuroengineering research on the neural and psychological effects of nature exposure. Full article

The intermittent nature of photovoltaic (PV) energy, especially under nonlinear and unbalanced loading situations, has made it more difficult to ensure steady operation as it is increasingly integrated into modern power systems. The Power Quality (PQ) issues cause severe degradation of both system performance and device lifetime. A novel Neural Power Quality Network (NeuPQ-Net) controlled Unified Power Quality Conditioner (UPQC) combined with a Quasi Z-Source Lift (QZSL) converter for PV applications is presented in this research as a novel solution for addressing these issues. The QZSL converter, which is controlled by a Maximum Power Point Tracking (MPPT) algorithm based on Perturb and Observe (P&O), increases the PV source voltage to the necessary DC-link level. A Zebra Optimisation Algorithm tuned PI (ZOA-PI) controller continually adjusts PI gains for quick and accurate regulation, ensuring steady DC-link voltage. Unlike conventional Synchronous Reference Frame (SRF) or Decoupled Double Synchronous Reference Frame (DDSRF)-based reference generation, the proposed NeuPQ-Net operates directly in the abc domain, eliminating Phase-Locked Loop (PLL) dependency and reducing computational complexity. Simulation and hardware prototype validations demonstrate that the proposed system achieves significant improvements in PQ indices, including reduced Total Harmonic Distortion (THD), faster response to transients, and enhanced voltage regulation, while complying with IEEE-519 standards. Full article

The automatic detection of foliar nutritional deficiencies through computer vision represents a promising alternative within precision agriculture practices, reducing dependence on laboratory analyses and the subjectivity associated with visual inspection. This systematic review maps and compares the application of machine learning (ML) and deep learning (DL) techniques to nutritional diagnosis across different crops, highlighting methodological trends, barriers to model adoption under field conditions, and existing research gaps. Following the PRISMA guidelines (PRISMA-P and PRISMA-2020), searches were conducted in the Scopus, IEEE Xplore, and Web of Science databases, using a defined time frame and explicit inclusion and exclusion criteria, resulting in 200 articles included (2012–2026; last search on 2 February 2026). The results indicate a predominance of DL-based approaches and RGB imagery, with applications concentrated in crops such as rice and in macronutrients, mainly nitrogen (N), phosphorus (P), and potassium (K), and report a marked increase in publications from 2020 onward. Although many studies report high performance, the evidence is largely derived from controlled environments and proprietary datasets, which limit model comparability, reproducibility, and generalization to real-world scenarios. Accordingly, the main research gaps include limited validation under field conditions, identified as the primary practical barrier; the underrepresentation of micronutrients and multiple-deficiency diagnosis; and the need for lightweight architectures suitable for deployment in mobile and edge-computing applications. It is concluded that ML and DL techniques offer promising alternatives for automated nutritional diagnosis; however, advances in data standardization, open-access datasets, and validation under real field conditions are essential for consolidating these technologies in practical applications. Full article

Vehicular communication networks demand highly efficient and accurate channel estimation to ensure reliable data exchange in high mobility scenarios. The IEEE 802.11p standard is widely regarded as the foundation of the Vehicle-to-Vehicle (V2V) communication channel; however, it is constrained by limited pilot resources and a fixed pilot structure, which degrade the performance and effectiveness of traditional estimation techniques, particularly in dynamic environments. Recent advances in deep learning offer significant potential for addressing these issues by improving estimation accuracy and modelling complex channel dynamics. Though deep learning-based methods introduce trade-offs in computational complexity and accuracy, these are crucial constraints in latency-sensitive V2V scenarios. This article presents a comprehensive review of deep learning-based channel estimation techniques, analysing methods for the IEEE 802.11p standard and critically examining their limitations in both classical and deep learning-based approaches. Additionally, the article highlights improvements introduced by IEEE 802.11bd, which features an enhanced pilot structure and advanced modulation schemes, providing a more robust framework for adaptive, efficient channel estimation. By identifying future research pathways that balance delay, complexity, and accuracy, an intelligent and effective transportation system can be established. Full article

The increasing penetration of Distributed Energy Resources (DERs) in active distribution networks introduces significant voltage volatility. Traditional model-based control strategies often struggle to maintain voltage stability due to accurate parameter unavailability and time-varying topology. To address these challenges, this paper proposes a robust Measurement-Feedback Online Gradient Descent (MF-OGD) algorithm for real-time voltage regulation. Unlike conventional methods that rely on explicit network models, the proposed MF-OGD approach leverages real-time voltage measurements to correct gradient estimation errors, thereby implicitly compensating for both parametric mismatches and structural linearization inaccuracies. We provide rigorous theoretical guarantees for closed-loop stability and asymptotic tracking error under bounded disturbances. Furthermore, the framework is extended to a joint active–reactive power control scheme to ensure feasibility under severe operating conditions. Comprehensive simulations on the IEEE 33-bus and IEEE 69-bus standard test feeders validate the scalability and effectiveness of the proposed method. Numerical results demonstrate that the MF-OGD controller successfully maintains nodal voltages within the safety range, limiting the maximum voltage deviation to 0.022 p.u. even under 50% model parameter uncertainty. Additionally, the algorithm achieves a low tracking Root Mean Square Error (RMSE) of approximately 0.014 p.u. in the 69-bus system. Notably, the accumulated regret per node increases only marginally (from 0.032 to 0.038) as the network scale doubles, confirming the algorithm’s superior scalability and robustness compared to conventional open-loop baselines. Full article

The increasing interconnection of inverter-based resources (IBRs) with low short-circuit current has weakened grid strength, making phase-locked loops (PLLs) susceptible to instability due to accumulated phase-angle error under current limiting. This study defines such instability as IBR instability induced by reduced grid robustness and proposes a root-mean-square (RMS) model-based screening method. After fault clearance, the residual q-axis voltage observed by the PLL is treated as a disturbance signal and, using the PLL synchronization equations, is analyzed with a standard second-order formulation. The maximum phase angle at which synchronization fails is defined as ${\theta }_{peak}$, and the corresponding q-axis voltage is defined as $V_{q,crit}$. This value is then mapped to a screening metric $P_{peak}$ suitable for RMS-domain assessment. The proposed methodology is applied to the IEEE 39-bus test system: the stability boundary and $P_{peak}$ are obtained in Power System Simulator for Engineering (PSSE), and the results are validated through electromagnetic transient (EMT) simulations in PSCAD. The findings demonstrate that the RMS-based screening can effectively identify operating conditions that are prone to PLL instability in weak grids, providing a practical tool for planning and operation with high IBR penetration. This screening method supports power system planning for high-penetration inverter-based resources by identifying weak-grid locations that require EMT studies to ensure secure operation after grid faults. Full article

Benchmarking has been central to performance evaluation for more than four decades. Reinhold P. Weicker’s 1990 survey in IEEE Computer offered an early, rigorous critique of standard benchmarks, warning about pitfalls that continue to surface in contemporary practice. This review synthesizes the evolution from classical synthetic benchmarks (Whetstone, Dhrystone) and application kernels (LINPACK) to modern suites (SPEC CPU2017), domain-specific metrics (TPC), data-intensive and graph workloads (Graph500), and Artificial Intelligence/Machine Learning (AI/ML) benchmarks (MLPerf, TPCx-AI). We emphasize energy and sustainability (Green500, SPECpower, MLPerf Power), reproducibility (artifacts, environments, rules), and domain-specific representativeness, especially in biomedical and bioinformatics contexts. Building upon Weicker’s methodological cautions, we formulate a concise checklist for fair, multidimensional, reproducible benchmarking and identify open challenges and future directions. Full article

The displacement of synchronous machines by inverter-based resources raises critical concerns regarding the stability of future low-inertia power systems. Grid-forming (GFM) inverters offer a pathway to address these challenges by autonomously establishing voltage and frequency while emulating inertia and damping. This paper investigates the feasibility of operating a transmission-scale network with 100% GFM penetration by fully replacing all synchronous generators in the IEEE 39-bus system with a heterogeneous mix of droop, virtual synchronous machine (VSM), and synchronverter controls. System stability is assessed under a severe fault-initiated separation, focusing on frequency and voltage metrics defined through center-of-inertia formulations and standard acceptance envelopes. A systematic parameter sweep of virtual inertia (H) and damping ($D_p$) reveals their distinct and complementary roles: inertia primarily shapes the Rate of Change in Frequency and excursion depth, while damping governs convergence speed and steady-state accuracy. All tested parameter combinations remain within established stability limitations, confirming the robust operability of a fully inverter-dominated grid. These findings demonstrate that properly tuned GFM inverters can enable secure and reliable operation of future power systems without reliance on synchronous machines. Full article

Background and Objectives: Dynamic nutrient profiling represents a paradigm shift in personalized nutrition, integrating real-time nutritional assessment with individualized dietary recommendations through advanced algorithmic approaches, biomarker integration, and artificial intelligence. This comprehensive systematic review and meta-analysis examines the current state of dynamic nutrient profiling methodologies for personalized diet planning, evaluating their effectiveness, methodological quality, and clinical outcomes. Methods: Following PRISMA 2020 guidelines, we conducted a comprehensive search of electronic databases (PubMed/MEDLINE, Scopus, Web of Science, IEEE Xplore, and Google Scholar) from inception to December 2024. The protocol was prospectively registered in PROSPERO (Registration: CRD42024512893). Studies were systematically screened using predefined inclusion criteria, quality was assessed using validated tools (RoB 2, ROBINS-I, Newcastle–Ottawa Scale), and data were extracted using standardized forms. Random-effects meta-analyses were performed where appropriate, with heterogeneity assessed using I² statistics. Publication bias was evaluated using funnel plots and Egger’s test. Results: From 2847 initially identified records plus 156 from additional sources, 117 studies met the inclusion criteria after removing 391 duplicates and systematic screening, representing 45,672 participants across 28 countries. Studies employed various methodological approaches: algorithmic-based profiling systems (76 studies), biomarker-integrated approaches (45 studies), and AI-enhanced personalized nutrition platforms (23 studies), with some studies utilizing multiple methodologies. Meta-analysis revealed significant improvements in dietary quality measures (standardized mean difference: 1.24, 95% CI: 0.89–1.59, p < 0.001), dietary adherence (risk ratio: 1.34, 95% CI: 1.18–1.52, p < 0.001), and clinical outcomes including weight reduction (mean difference: −2.8 kg, 95% CI: −4.2 to −1.4, p < 0.001) and improved cardiovascular risk markers. Substantial heterogeneity was observed across studies (I² = 78–92%), attributed to methodological diversity and population characteristics. AI-enhanced systems demonstrated superior effectiveness (SMD = 1.67) compared to traditional algorithmic approaches (SMD = 1.08). However, current evidence is constrained by practical limitations, including the technological accessibility of dynamic profiling systems and equity concerns in vulnerable populations. Additionally, the evidence base shows geographical concentration, with most studies conducted in high-income countries, underscoring the need for research in diverse global settings. These findings have significant implications for shaping public health policies and clinical guidelines aimed at integrating personalized nutrition into healthcare systems and addressing dietary disparities at the population level. Conclusions: Dynamic nutrient profiling demonstrates significant promise for advancing personalized nutrition interventions, with robust evidence supporting improved nutritional and clinical outcomes. However, methodological standardization, long-term validation studies exceeding six months, and comprehensive cost-effectiveness analyses remain critical research priorities. The integration of artificial intelligence and multi-omics data represents the future direction of this rapidly evolving field. Full article

The increasing penetration of distributed energy resources (DERs) in unbalanced distribution networks presents significant challenges for optimal operation, particularly concerning power loss minimization and voltage regulation. This paper proposes a comprehensive Optimal Power Flow (OPF) model that coordinates various assets, including on-load tap changers (OLTCs), reactive power compensators, and controllable electric vehicles (EVs). To solve this complex and non-convex optimization problem, we developed the Shrinking Net Algorithm (SNA), a novel metaheuristic with mathematically proven convergence. The proposed framework was validated using the standard IEEE 123-bus test system. The results demonstrate significant operational improvements: total active power loss was reduced by 32.1%, from 96.103 kW to 65.208 kW. Furthermore, all node voltage violations were eliminated, with the minimum system voltage improving from 0.937 p.u. to a compliant 0.973 p.u. The findings confirm that the proposed SNA is an effective and robust tool for this application, highlighting the substantial economic and technical benefits of coordinated asset control for modern distribution system operators. Full article

Optimally positioning renewable-based distributed generation (DG) units is vital for mitigating technical challenges in active distribution networks (ADNs). With the goal of achieving technical goals such as reduced losses and mitigated unstable voltage, two available optimization methods have been combined for positioning wind-energy DGs: grey wolf optimization (GWO) and opposition-based learning (OBL), which tries out opposite possibilities for each assessed population, thus addressing GWO’s susceptibility to becoming stuck in local optima. This new fusion technique enhances the algorithm’s scrutiny of each area under consideration and reduces the likelihood of premature convergence. Results show that, compared with standard GWO, the proposed OBL-GWO reduced active power losses by up to 95.16%, improved total voltage deviation (TVD) by 99.7%, and increased the minimum bus voltage from 0.907 p.u. to 0.994 p.u. In addition, the voltage stability index (VSI) was also enhanced by nearly 30%. The proposed methodology outperformed both standard GWO on the IEEE 33-bus test system and comparable techniques reported in the literature consistently. By accounting for the uncertainty in wind generation, load demand, and future growth, this framework offers a more reliable and practical planning approach that better reflects real operating conditions. Full article

Distribution System Operators (DSOs) increasingly need planning tools that coordinate utility-influenced assets—such as electric-vehicle charging stations (EVCS) and voltage-support resources—with customer-sited distributed generation (DG). We present a Nash-equilibrium-based Iterative Best Response Algorithm (IBRA-NE) for joint planning of DG and EVCS in radial distribution networks. The framework supports two applicability modes: (i) a DSO-plannable mode that co-optimizes EVCS siting/sizing and utility-controlled reactive support (DG operated as VAR resources or functionally equivalent devices), and (ii) a customer-sited mode that treats DG locations as fixed while optimizing DG reactive set-points/sizes and EVCS siting. The objective minimizes network losses and voltage deviation while incorporating deployment costs and EV charging service penalties, subject to standard operating limits. A backward/forward sweep (BFS) load flow with Monte Carlo simulation (MCS) captures load and generation uncertainty; a Bus Voltage Deviation Index (BVDI) helps identify weak buses. On the EEU 114-bus system, the method reduces base-case losses by up to 57.9% and improves minimum bus voltage from 0.757 p.u. to 0.931 p.u.; performance remains robust under a 20% load increase. The framework explicitly accommodates regulatory contexts where DG siting is customer-driven by treating DG locations as fixed in such cases while optimizing EVCS siting and sizing under DSO planning authority. A mixed scenario with 5 DGs and 3 EVCS demonstrates coordinated benefits and convergence properties relative to PSO, GWO, RFO, and ARFO. Additionally, the proposed algorithm is also tested on the IEEE 69-bus system and results in acceptable performance. The results indicate that game-theoretic coordination, applied in a manner consistent with regulatory roles, provides a practical pathway for DSOs to plan EV infrastructure and reactive support in networks with uncertain DER behavior. Full article

This paper presents an adaptive Maximum Power Point Tracking (MPPT) strategy for grid-connected photovoltaic (PV) systems that uses an Adaptive Neuro-Fuzzy Inference System (ANFIS) optimized by Particle Swarm Optimization (PSO) to enhance energy extraction efficiency under diverse environmental conditions. The proposed ANFIS-PSO-based MPPT controller performs dynamic adjustment Pulse Width Modulation (PWM) switching to minimize Total Harmonic Distortion (THD); this will ensure rapid convergence to the maximum power point (MPP). Unlike conventional Perturb and Observe (P&O) and Incremental Conductance (INC) methods, which struggle with tracking delays and local maxima in partial shading scenarios, the proposed approach efficiently identifies the Global Maximum Power Point (GMPP), improving energy harvesting capabilities. Simulation results in MATLAB/Simulink R2023a demonstrate that under stable irradiance conditions (1000 W/m², 25 °C), the controller was able to achieve an MPPT efficiency of 99.2%, with THD reduced to 2.1%, ensuring grid compliance with IEEE 519 standards. In dynamic irradiance conditions, where sunlight varies linearly between 200 W/m² and 1000 W/m², the controller maintains an MPPT efficiency of 98.7%, with a response time of less than 200 ms, outperforming traditional MPPT algorithms. In the partial shading case, the proposed method effectively avoids local power maxima and successfully tracks the Global Maximum Power Point (GMPP), resulting in a power output of 138 W. In contrast, conventional techniques such as P&O and INC typically fail to escape local maxima under similar conditions, leading to significantly lower power output, often falling well below the true GMPP. This performance disparity underscores the superior tracking capability of the proposed ANFIS-PSO approach in complex irradiance scenarios, where traditional algorithms exhibit substantial energy loss due to their limited global search behavior. The novelty of this work lies in the integration of ANFIS with PSO optimization, enabling an intelligent self-adaptive MPPT strategy that enhances both tracking speed and accuracy while maintaining low computational complexity. This hybrid approach ensures real-time adaptation to environmental fluctuations, making it an optimal solution for grid-connected PV systems requiring high power quality and stability. The proposed controller significantly improves energy harvesting efficiency, minimizes grid disturbances, and enhances overall system robustness, demonstrating its potential for next-generation smart PV systems. Full article