Search Results (6,260)

Multi-station global navigation satellite system (GNSS) displacement-residual forecasting may benefit from neighbouring stations, yet unrestricted spatial aggregation can obscure station-local temporal dynamics and the independent value of spatial information. Whether neighbouring stations provide additional predictive information after a strong station-local forecast has been established remains unclear. Here, we propose the Multi-Scale Graph Residual Adaptation Network (MS-GRAN), a local-first framework that learns bounded spatial residual corrections rather than an unrestricted graph forecast. MS-GRAN first establishes a station-local NLinear forecast and then learns only an incremental residual correction through a training-only correlation–distance graph. The spatial branch integrates causal multi-scale high-frequency residual summaries, sparse non-negative adjacency constraints, neighbour-minus-own residual contrast, and a zero-output-initialized residual head with a gate initialized near zero to ensure a controlled spatial contribution. Experiments on a 90-station Cascadia GNSS benchmark with a fixed 2010–2019/2020–2021/2022–2024 chronological split showed that MS-GRAN achieved a 2.9158 ± 0.0033 mm one-day frozen-test RMSE, compared with 2.9579 ± 0.0006 mm for the matched frozen NLinear backbone. The resulting 1.422% reduction is modest but reproducible: 82-84 out of 90 stations improved across three random seeds, paired station-bootstrap confidence intervals were positive, upper-tail errors decreased more than mean RMSE, and gains remained positive across forecast horizons, network densities, seasons, and missingness strata. Additional controls showed gains of 0.635% for self-only adaptation, 1.265% for rewired placebo graphs, −0.343% for a validation-selected causal pre-local common-mode baseline, and 1.335% for an alternative frozen DLinear backbone. These results support conservative spatial residual adaptation in sparse GNSS networks while showing that residual-adaptation capacity contributes substantially, that simple causal common-mode preprocessing does not reproduce the gain, and that training-only graph topology provides a smaller additional benefit. They do not establish universal spatial transfer, physical event attribution, or earthquake-precursor detection. Full article

Detection systems for antibiotics of the (fluoro)quinolone (FQ) group are in high demand among food safety regulators and agricultural inspectors. At the same time, the application of developed test systems may be complicated by the significant structural diversity of related FQs (including enantiomeric forms), which necessitates the careful evaluation of their selectivity. In this study, five polyclonal antibodies were generated by immunizing rabbits with the S- and R-enantiomers of ofloxacin (OFL) and its racemic mixture used as haptens. The cross-reactivity (CR) of the obtained antibodies toward 26 FQs, structural analogs of OFL, was evaluated using an indirect competitive enzyme-linked immunosorbent assay. Structure–activity relationship models were developed to analyze the obtained CR data. Three machine learning (ML) methods were applied: random forest classifier (RFC), logistic regression (LR), and a support vector classifier (SVC). The SVC model demonstrated the highest predictive performance in terms of the Log Loss metric. In contrast, the LR models showed the best overall balance across six statistical metrics, including precision, recall, and F1 score. Three-dimensional topological descriptors enabled discrimination between the S- and R-isomers of OFL, whereas constitutional and two-dimensional descriptors were less effective. The obtained results contribute to the development of FQ immunoassay systems and their computational analysis using ML approaches. Full article

The global expansion of interconnected edge network components requires immediate strategies for securing low-power computing nodes. Cryptographic algorithms executing over binary extension fields yield considerable computational benefits because their carry-free arithmetic significantly optimizes dynamic power consumption. However, general-purpose silicon architectures lack the dedicated hardware structures to run these finite-field operations efficiently, resulting in severe processing throughput bottlenecks. This study addresses this limitation by introducing a parallelized modular multiplier framework designed to integrate smoothly with the multicore execution environments of modern embedded platforms. Our approach deploys a progressive multiplier reduction (PMR) protocol that segments dense mathematical workloads into distributed structural thread groups. This architectural alignment allows multiplication matrices and spatial field reductions to take place concurrently, balancing localized workloads while decreasing intermediate data buffering demands. We present two distinct topological styles based on column division and row division techniques, deriving comprehensive analytical formulations to capture precise silicon area footprints, critical path delays, and total operational cycle counts. The resulting hardware metrics demonstrate that the parallel PMR design achieves a highly competitive area–delay product alongside optimized dynamic consumption characteristics. This structural paradigm delivers a scalable and robust security alternative for general edge hardware, ensuring system runtime stability while meeting tight environmental power constraints, protecting vital industrial assets, and sustaining emerging macroeconomic infrastructure. Full article

The rapid development of artificial intelligence (AI) has created new opportunities for improving the performance, robustness, and efficiency of electrical machine drive systems. Among AI-based approaches, fuzzy logic control (FLC) has attracted considerable attention because of its ability to handle nonlinear dynamics, parameter uncertainties, and external disturbances without relying on an accurate mathematical model. This review systematically examines FLC-based control strategies for electrical machine drives, with particular emphasis on induction motors, switched reluctance motors, permanent-magnet synchronous motors, synchronous reluctance motors, and brushless DC motors. The review follows the PRISMA 2020 framework, and the selected studies are analyzed according to machine type, FLC architecture, control strategy, optimization method, implementation platform, and validation approach. The reviewed evidence indicates that FLC-based strategies can improve dynamic response, tracking accuracy, robustness, and torque regulation under the specific conditions reported in the literature. Hybrid approaches combining FLC with field-oriented control, direct torque control, sliding-mode control, model predictive control, neural networks, ANFIS, and optimization algorithms provide additional opportunities for adaptation and parameter tuning. However, the reported performance is strongly dependent on machine topology, controller architecture, tuning methodology, computational requirements, and validation platform. The review also identifies important limitations, including the lack of standardized benchmarking, computational complexity, dependence on expert knowledge, and limited HIL and experimental validation of several advanced approaches. Emerging directions include Type-2 and higher-order fuzzy systems, neuro-fuzzy and hybrid AI controllers, data-driven optimization, digital-twin-assisted control, edge computing, and hardware-oriented implementation. The objective of this review is to provide a structured and critical synthesis of the existing evidence, clarify the evolution and practical applicability of AI-driven FLC approaches, and identify research priorities for reliable, computationally efficient, and experimentally validated electrical machine control. Full article

Early-exit deep neural networks (DNNs) can reduce edge-inference latency, but abrupt variations in wireless and computing resources can destabilize split-inference policies. This paper proposes a meta-learning-driven adaptive control framework for joint backbone splitting and early-exit routing in MobileViT. The framework formulates multi-exit splitting as a constrained Markov decision process (CMDP) and introduces splitting-aware multi-dimensional adaptive proximal policy optimization (SMAPPO). SMAPPO combines nonlinear quality-of-service (QoS) penalties with topology-aware action masking, while cross-environment meta-initialization supports edge-local adaptation after resource disturbances. Under the stated simulation assumptions, SMAPPO reached the highest performance-index plateau among six methods in a representative 500-episode stationary trace and achieved the lowest normalized total cost across three latency–energy preference settings. Across ten seeds and nine stationary or disturbed scenarios, online SMAPPO achieved a 77.20% measured accuracy and 22.40 mJ of system energy. With an adaptation horizon of $K=14$, SMAPPO yielded a post-disturbance mean latency of 37.68 ms, a QoS-violation rate of 2.24%, and an on-time completion rate of 98.69%. These results indicate that combining meta-initialization, nonlinear constraint shaping, and topology-aware action masking improves stationary optimization and disturbance recovery within the controlled simulator. Full article

In this paper, a novel four-dimensional variable-order fractional chaotic system is presented through the use of the Liouville–Caputo variable-order fractional derivative to represent the time-varying memory properties of nonlinear dynamical behaviors. Special attention will be paid to the chaotic behavior of the proposed system and their chaotic attractors depending on different memory effects. For calculation of the solutions of such systems, a numerical approach for the variable-order fractional systems is used, and three memory functions of the variable order are considered to investigate their effect on the behavior of the system. The obtained behavior will be analyzed by means of time responses, phase portraits, bifurcation diagrams, the spectrum of the Lyapunov exponents, and the Kaplan–Yorke fractal dimension. From the numerical simulations, it is shown that different fractional orders lead to completely different dynamical regimes and the appearance of symmetric chaotic attractors with different geometrical and topological structures while the physical parameters of the system are kept the same. These results highlight the important role of time-varying memory in controlling and generating chaotic structures in fractional-order nonlinear systems. Full article

This paper presents a comparative analysis of three magnetic-integrated LCL-derived filter configurations for suppressing high-frequency switching harmonics in avionics power-conversion systems: the integrated LLCL filter, the magnetic-integrated multi-trap LCL filter, and the magnetic-integrated trapped-LCL filter. The high-frequency harmonics considered in this study originate primarily from the pulse-width-modulated (PWM) switching process and can increase current distortion, electrical and magnetic losses, component stress, and the potential for electromagnetic interference in aircraft electrical systems. To enable a consistent comparison, the three filter configurations are evaluated within a unified analytical framework under common system-level operating conditions, while retaining their topology-specific passive and magnetic parameters according to their respective design requirements. The framework distinguishes aggregate total harmonic distortion (THD) from attenuation at targeted switching-frequency bands and incorporates the effects of resonant branches and magnetic coupling. The simulated current THD values of the LLCL, multi-trap LCL, and trapped-LCL filters are 0.82%, 0.84%, and 1.13%, respectively, while their estimated total filter losses are 24.98 W, 59.74 W, and 40.49 W. At the 1 kW operating point, these losses correspond to 2.50%, 5.97%, and 4.05% of rated power, respectively. The results show that the LLCL filter achieves the lowest aggregate THD and estimated loss under the investigated conditions, whereas the multi-trap and trapped-LCL configurations provide additional capability for targeted attenuation of selected switching-frequency components through their resonant structures. Hardware-in-the-loop (HIL) results further support the electrical filtering and dynamic behavior of the investigated concepts. The comparison demonstrates that minimum THD, minimum loss, targeted switching-harmonic attenuation, and magnetic integration are distinct design objectives; therefore, topology selection should be based on the specific requirements and constraints of the intended avionics application. Full article

Fruit thinning concentrates nutrients and serves as an essential procedure for cultivating high-quality strawberries with exceptional palatability. It is established that controlling the number of fruits per peduncle to three to five significantly increases the proportion of large fruits and enhances sweetness while effectively reducing the risks of disease infection. Consequently, pesticide application is minimized, thereby ensuring food safety and improving overall product quality. Although precise execution baselines are a prerequisite for automated thinning, current research is largely restricted to isolated fruit recognition, leaving the direct detection of peduncle–fruit topological associations under complex occlusions unaddressed. To address this gap, a lightweight, three-stage (“coarse-to-fine”) detection method tailored for automated thinning is proposed. The pipeline comprises global localization, local cropping with background suppression, and fine secondary inference, which effectively mitigates environmental interference. To support this investigation, a dedicated dataset comprising 1131 high-quality images was constructed. For efficient edge deployment, YOLOv11n was adopted as the baseline architecture, integrated with structural Re-parameterized Convolution (RepConv), Coordinate Attention (CoordAtt), and a dynamic re-weighting loss. This configuration ensures robust feature extraction of slender peduncles with an extremely low parameter overhead. The experimental results demonstrate that with only 2.77 M parameters, the proposed model achieves an mAP@0.5 of 75.73% and an F1-score of 73.85%. Notably, the average false positive (FP) detections per image in complex scenarios were significantly reduced from 1.53 to 0.23. Following deployment on a Jetson Orin Nano Super edge device utilizing TensorRT and FP16 quantization, the end-to-end system inference speed stabilized at 15.58 frames per second (FPS) with near-lossless precision. Ultimately, this method provides a reliable technical foundation for automated thinning decisions, facilitates sustainable greenhouse management, and secures the supply of high-quality food from the source. Full article

Processing-in-Memory (PIM) architectures are transforming system hierarchies by embedding computation within memory and collapsing traditional CPU–memory separation. This co-location enables measured gains in throughput and energy efficiency for data-intensive workloads such as AI inference and graph analytics, but executing untrusted logic inside memory introduces attack surfaces that CPU-centric security models are not designed to address. Side-channel leakage, privilege escalation within PIM logic units, and tenant isolation violations are structurally enabled by the same physical proximity which makes PIM efficient. This survey examines these threats systematically, drawing on 47 systematically selected publications and supplementary references from architecture, systems security, and hardware design venues covering PIM-specific literature from 2015 onward. We developed a structured threat model that characterizes assets, attacker capabilities, and trust boundaries at subarrays and interconnect granularity for both near-bank and near-memory PIM classes. We survey and classify existing attack vectors and countermeasures, organizing them according to the architectural properties they exploit or on which they depend. Drawing on gaps identified in the surveyed literature, we propose a conceptual secure-by-design framework that locates trust enforcement within the memory substrate itself, using physical data locality, internal bandwidth constraints, and memory-disaggregation topology as enforcement primitives rather than adapting CPU-centric enclave models. This framework is a structured design proposal, not a demonstrated implementation. The threat model, defense taxonomy, and design framework constitute a reference baseline for researchers building secure PIM systems and a gap map for future experimental and formal verification. Full article

Nowadays, the volume of heterogeneous data in situational analysis centers is growing exponentially, leading to information overload for decision makers (DMs) and a decrease in the effectiveness of traditional decision support systems (DSS). Intelligent DSSs (ISDSS) demonstrate potential, but face challenges in explainability, heterogeneous data integration, cognitive load, and scalability. This paper proposes a method for intelligent decision support focused on identifying and generating options for resolving emergency situations—conditions that have no exact precedents in the knowledge base. The method includes formalizing the situation using a vector of normalized parameters $S\left(t\right)$, separating it into independent and dependent variables with the construction of a dependency tree, neural network classification of three types of conditions (normal, abnormal, and emergency) with a forecast for a lead interval τ, the synthesis of solutions for emergency situations based on an analysis of proximity graphs to known emergency precedents and evolutionary optimization. A computational experiment was conducted on the open dataset of the Tennessee Eastman Process simulation model with 28 failure types and 200 repeated simulations. The neural network classifier achieved an accuracy of 0.88 and a macro-averaged F1-score of 0.87 on a test set of 200 situations. Graphs of nearby emergency precedents were constructed for 50 synthetic emergency situations; analysis demonstrated the stability of topological characteristics (vertex degree 5.62 ± 1.18, closeness centrality 0.43 ± 0.09), substantiating the applicability of graph neural networks for accelerated control action synthesis. The proposed method reduces dependence on expert assessments and improves the adaptability and explainability of decisions, while the demonstrated stability of the graph-based precedent retrieval lays the groundwork for future full-scale validation of control-action synthesis in next-generation hybrid IDSS. Full article

Collaboration networks are frequently studied as empirical instances of complex social systems, yet standardized methodological frameworks for consistently identifying heterogeneous mesoscopic structural regimes remain limited. This study proposes an integrated multi-criteria classification framework and demonstrates its application to the structural characterization of communities extracted from a large-scale scientific collaboration network. The framework combines community detection, classical network metrics, statistical modeling of weighted degree tails, small-world diagnostics, information-entropy measures, and fractal analysis based on the Song–Havlin–Makse box-covering renormalization framework. As an empirical application, the methodology is applied to the giant coauthorship component of Embrapa’s scientific production (1974–2024), derived from the Brazilian Agricultural Research Database (BDPA), comprising 60,636 nodes. The weighted Louvain algorithm partitions the network into 25 major communities, which are evaluated through an integrated classification protocol combining the Akaike Information Criterion model selection, Kolmogorov–Smirnov goodness-of-fit tests, small-worldness diagnostics, and fractal scaling analysis. The proposed framework identifies three network families, namely Barabási–Albert (BA-like)/scale-free small-world, scale-free fractal (non-BA) and small-world (non-scale-free), while explicitly distinguishing supported and ambiguous classifications according to the overall consistency of the statistical and structural evidence. The results demonstrate that distinct mesoscopic structural regimes coexist within the same connected collaboration system, highlighting the usefulness of the proposed reproducible multi-criteria framework for comparative topological characterization across complex collaboration networks. Full article

Decentralized coordination of multi-agent communication networks underpins autonomous UAV swarms, sensor meshes, and cyber-physical systems that must operate without a single point of failure, yet quantitative design rules linking topology degradation to coordination collapse are still lacking. This paper aims to characterize the fault tolerance of a discrete linear consensus protocol that drives mobile agents’ scalar states toward a common value over a time-varying communication graph. The convergence rate and fault tolerance budget of the protocol are explicitly tied to the algebraic connectivity ${\lambda }_2$ of the graph Laplacian, and three failure regimes—random independent failures ($M_1$), sequential staged failures ($M_2$), and targeted attacks on the highest-degree hubs ($M_3$)—are analyzed using a full-factorial Monte-Carlo experiment of 1620 runs implemented in Python with the Mesa framework and NetworkX. Critical failure thresholds ${\phi }_c$ are 0.42–0.51 for $M_1$, 0.38–0.48 for $M_2$, and 0.28–0.38 for $M_3$; a Kruskal–Wallis test (p < 0.001) confirms the ordering ${\phi }_c^{M^3}<{\phi }_c^{M^2}<{\phi }_c^{M^1}$, providing quantitative design rules for fault-tolerant consensus-driven networks. Full article

Modern power systems are evolving rapidly with growing distributed generation and high penetration of renewables and electric vehicles. Renewable sources, being inherently intermittent and weather dependent, may lead to rapid power fluctuations that challenge grid stability and power quality. Multilevel inverters (MLIs) have become a key enabling technology in modern power grids due to the escalating need for high-power, high-voltage, and high-quality energy conversion. Research on the control of MLIs in modern grid scenarios has significant scope due to the rising penetration of renewables, distributed generation and smart grid technologies. Hence sophisticated control strategies and topology selection of MLIs are required to enhance efficiency and to ensure optimal performance. Emerging areas like AI-based adaptive control find relevance in enabling stable, flexible and sustainable future power systems. In this comprehensive review, the state-of-the-art MLI classification, AI-driven control techniques, and their emerging technological applications are investigated. There is limited exploration of AI-based adaptive control for self-tuning operation and coordinated control of multiple MLIs in microgrids, active filtering and harmonic compensation in MLI-based modern power systems, and vehicle-to-grid (V2G) and bidirectional battery inverter control optimization integrated with MLI control. Full article

In the complex problem of air-to-ground mission planning, multi-UAV systems face significant challenges such as system complexity and heterogeneity, insufficient target observability, and difficulties in collaborating information sharing. To address these issues, this paper proposes a novel learnable sparse attention graph architecture (SAGA). This architecture deeply integrates graph reasoning and policy optimization within the MAPPO framework and includes three innovative mechanisms: (i) a GATv2-based graph neural network encoder that performs multi-round distributed consensus on the communication graph among UAVs via a multi-head attention mechanism, enabling selective aggregation of tactical information; (ii) an edge predictor that learns to prune low-value communication links, generating a sparse and mission-adaptive communication topology; and (iii) an L1 sparsity penalty term that further enhances communication efficiency. In a self-developed simulation environment for heterogeneous multi-UAV mission planning, comprehensive comparative experiments were conducted against the following baseline reinforcement learning algorithms: MADDPG, MATD3, QMIX, MAPPO, TarMAC, DGN, and G2ANet. The experimental results show that SAGA achieves reward values of 390 and 1100 in small-scale and large-scale scenarios, and outperforms the best-performing baseline algorithm by more than 20% across all operational performance metrics. Generalization experiments validate the model’s robust transfer capability under unknown defense deployment modes. Ablation experiments further confirmed the individual contributions of the three components. This study provides an innovative and effective method for mission planning of heterogeneous multi-UAV systems in partially observable adversarial environments. Full article

Thermal energy storage (TES) technologies are essential for renewable energy integration, industrial waste heat recovery, grid flexibility, and improved energy efficiency. Despite advances in sensible heat thermal energy storage (SHTES), latent heat thermal energy storage (LHTES), and thermochemical energy storage (TCES), practical deployment remains constrained by inadequate heat transfer rates, which limit charging and discharging processes, reduce storage utilization, and increase system size and cost. Conventional heat-transfer enhancement approaches, including fins, embedded heat exchangers, conductive additives, porous structures, and flow intensification techniques often introduce trade-offs related to manufacturability, complexity, durability, and energy consumption. Additive manufacturing (AM) has emerged as a promising approach for overcoming these limitations by enabling precise control of internal geometry, porosity, surface-area-to-volume ratio, and fluid pathways. Through the fabrication of architected structures, lattice networks, triply periodic minimal surface (TPMS) geometries, and multifunctional heat-transfer architectures, AM enables geometry-driven optimization of thermal performance that is difficult to achieve using conventional manufacturing methods. These capabilities support the development of compact TES systems with enhanced heat transfer, improved thermal uniformity, and increased energy utilization. This review examines additive manufacturing technologies relevant to TES applications, including powder bed fusion, directed energy deposition, material extrusion, vat photopolymerization, and binder jetting. The relationships among manufacturing processes, material selection, and thermal performance are discussed across SHTES, LHTES, and TCES systems. Particular emphasis is placed on AM-enabled heat-transfer enhancement strategies, phase change material (PCM)-integrated structures, architected thermal networks, embedded heat exchangers, and computational design methodologies such as topology optimization. Current challenges involving material compatibility, scalability, cost, and long-term durability are also evaluated. The review highlights how additive manufacturing is transforming TES design from a material-centered paradigm toward geometry-enabled thermal engineering, creating new opportunities for next-generation energy storage systems. Full article