Search Results (523)

Induction motors remain the workhorse of modern industry thanks to their robustness, cost effectiveness and high efficiency, but the growing demands of electrified transport, high-performance automation and Industry 4.0 impose increasingly stringent control requirements. This paper presents an integrated, application-oriented survey of control strategies for high-performance induction motor drives, covering classic scalar V/f control as a baseline and advanced field-oriented control (FOC), direct torque control (DTC), model predictive control (MPC), nonlinear/robust schemes and intelligent/data-driven and digital twin-assisted solutions. The methods are analyzed within a unified framework in terms of dynamic response, torque and flux ripple, current harmonic distortion, efficiency, robustness, implementation complexity and suitability for sensorless and fault-tolerant operation. Emphasis is placed on hybrid strategies that combine classical vector or DTC structures with MPC, fuzzy and neuro-fuzzy logic, neural network-based observers, reinforcement learning and digital twin-enabled monitoring to reconcile fast dynamics with high efficiency, low ripple and lifecycle reliability. Consolidated comparison tables and a hybrid control map highlight typical performance trends, trade-offs between simplicity and performance, and the complementary roles of AI and digital twins as system-level enablers. The survey also outlines promising research directions toward systematically designed hybrid controllers, lightweight digital twins for embedded platforms and experimentally validated benchmarks that can accelerate the industrial uptake of next-generation induction motor drives. Full article

High-precision urban vegetation mapping is essential for assessing carbon sink capacities, mitigating the urban heat island effect, and supporting sustainable development. Although deep learning and high-resolution remote sensing have advanced automated vegetation monitoring, existing models still face challenges when a common segmentation architecture is evaluated under different imaging geometries. In this study, Cityscapes and ISPRS Vaihingen are treated as two independent benchmarks representing perspective street-level imagery and orthographic aerial imagery, rather than as simultaneous cross-view inputs. “Background dominance” caused by perspective distortion and the “gridding artifacts” inherent in orthographic textures severely constrain segmentation accuracy across varying vegetation scales, particularly for small targets. To address these limitations, we propose a Scale-Aware Mixture of Experts (SA-MoE) architecture for fine-grained vegetation segmentation under two distinct imaging views, together with a scene-specific optimization strategy. The core SA-MoE framework consists of two main components. First, the spatial gating network uses a temperature polarization mechanism with τ = 0.5 to adjust the initial logit maps, sharpening expert-weight differences while preserving stable gradient propagation. Second, we use a heterogeneous expert group with five parallel branches: a pixel-level expert, three spatial experts with different dilation rates, and a global average-pooling expert. A dynamic pixel-level weighted fusion mechanism is then applied, decoupling feature extraction from receptive-field allocation. Furthermore, to address the heterogeneity of “hard samples” and “label noise” across the two benchmark settings, we introduce a scene-specific optimization strategy. Our findings show that the Focal-Dice (FD) loss is more suitable for perspective scenes with severe target imbalance and hard-to-classify vegetation targets, whereas the Cross-Entropy (CE) loss is more robust to boundary jitter in orthographic imagery. Comparative experiments on the Cityscapes (perspective view) and ISPRS Vaihingen (orthographic view) datasets reveal that SA-MoE achieves a highly competitive balance between computational efficiency and fine-grained segmentation, particularly in micro-target recall. Notably, the recall for extra-small (XS) scale targets in the aerial dataset improved by 3.21 percentage points compared to the second-best model. For the street-level dataset, our model achieved competitive global performance in terms of Overall Accuracy (OA), Precision, and F1-Score. However, we also observed a performance trade-off, where Transformer-based models maintained an advantage in preserving fine boundary details for these extra-small targets. In the routing analysis, we observed a pattern that we refer to as “receptive field inversion”, in which the model assigns lower weights to large-dilation experts for large canopy regions in orthophotos. We interpret this pattern as a plausible routing hypothesis. Overall, SA-MoE offers an efficient and adaptive solution for urban vegetation mapping under two imaging views. Full article

Modern smart kitchen automation requires reliable vision-based tools to provide user-advisory decision support during domestic culinary processes. However, standard deep learning models utilizing closed-set Softmax classifiers typically misclassify unknown or Out-of-Distribution (OOD) kitchen objects with high confidence, posing safety and reliability risks. To address this problem without clous dependency, this study introduces a localized open-set metric learning framework based on a modified MobileNetV2 architecture. The conventional Softmax classification layer is replaced with a feature embedding layer evaluated via Cosine Similarity and a calibrated decision threshold. This architecture tracks targeted food items across four operational stages—counter-raw, in-oven-raw, in-oven-cooked, and counter-cooked—while identifying and rejecting OOD objects. To ensure reproducibility, comprehensive experimental validations were conducted on a dedicated internal dataset, providing direct baseline comparisons against mainstream backbones (ResNet50, EfficientNet-B0, and Vision Transformers) stripped of their Softmax layers and evaluated under identical metric constraints. The results demonstrate that the proposed framework achieves a Macro F1-score 92.6% and ultra-low inference latency of 11.5 ms, ensuring an optimized trade-off between Macro $F_1$-score and inference speed on edge computing environments. This framework establishes a robust, self-contained solution for open-set object recognition in localized smart home appliances. Full article

Type I diabetes mellitus (T1DM) is a chronic metabolic disease resulting from insufficient insulin secretion into the bloodstream‚ causing elevated blood glucose concentrations to dangerous levels․ Automated regulation of blood glucose levels in T1DM can be modeled as a nonlinear‚ uncertain‚ and disturbance-affected closed-loop control process with a time delay‚ time-varying insulin sensitivity, and imperfect glucose measurements. This paper presents the design, multi-objective tuning, and robustness evaluation of a fuzzy logic controller (FLC) for automated insulin-infusion regulation. The proposed FLC uses the glucose tracking error and its time derivative as feedback signals to determine the required insulin control action and maintain glucose within the desired range of (70–160 mg/dL). The controller parameters are optimized using the Non-Dominated Sorting Genetic Algorithm II (NSGA-II) to address three competing control objectives: minimizing hypoglycemia risk, minimizing hyperglycemia risk, and reducing total insulin usage. The resulting Pareto-optimal solutions provide a set of trade-off controller designs for decision-makers based on safety, performance, and insulin-efficiency requirements. The robustness of the proposed automated control framework is evaluated under challenging operating conditions, including elevated initial glucose levels, model-parameter uncertainties, external disturbances, variations in insulin sensitivity, distorted glucose measurements, and delayed insulin infusion. A comparative study with a linear quadratic regulator-based controller (LQRC) is conducted as a benchmark. Simulation results demonstrate that the optimized FLC provides superior closed-loop performance and stronger robustness than the LQRC across all tested scenarios. The proposed fuzzy-control framework, therefore, offers a promising automation-based strategy for resilient glucose regulation under uncertainty, measurement imperfections, and actuation delays. Full article

Accurate pavement crack segmentation is essential for structural health monitoring, yet existing methods often face a trade-off between segmentation accuracy and computational efficiency. To address this issue, a novel teacher–student framework, termed RTCS-T and RTCS-S, is proposed. The teacher network RTCS-T is constructed based on the Swin Transformer to capture long-range dependencies and multi-scale contextual information. To further enhance crack representation, a strip refinement module is introduced to model directional structural features, while a cascaded atrous spatial pyramid pooling module is employed to improve multi-scale feature aggregation. Based on the teacher network, a lightweight student model RTCS-S is developed by using depthwise separable convolutions to achieve efficient inference. In addition, a foreground-aware and boundary-aware knowledge distillation strategy is introduced to guide the transfer of structural and contextual information from the teacher to the student. Experiments on the Crack500, DeepCrack, and CFD datasets demonstrated competitive performance against representative segmentation models. On CFD, RTCS-S achieved an F1 Score of 0.7514 and an mIoU of 0.7962. Notably, RTCS-S required only 1.82 M parameters and 1.13 GFLOPs and achieved a model inference speed of 680 FPS on an RTX 4090 GPU. When deployed on an RDK X5 edge-computing platform, the complete pipeline achieved an end-to-end throughput of 34 FPS, with an average latency of approximately 29.4 ms and peak memory consumption of 1.8 GB. These results demonstrate that the proposed framework provides an efficient solution for automated pavement crack detection and shows strong potential for practical road inspection applications. Full article

Distributed fiber optic sensing (DFOS) has emerged as a transformative technology for structural health monitoring (SHM) of railway infrastructure, offering continuous, high-resolution measurements along extended optical fiber lengths, capabilities that conventional point sensors such as strain gauges and accelerometers cannot match. This review critically examines DFOS technology and its railway SHM applications, covering system components, interrogator units, optical fiber cables, and data acquisition systems, alongside the three principal scattering mechanisms: Rayleigh, Brillouin, and Raman, each offering distinct trade-offs in spatial resolution, sensing range, and measurand sensitivity. Field applications across track and sleeper monitoring, bridge health evaluation, tunnel lining assessment, and embankment stability are reviewed and critically compared. The integration of artificial intelligence (AI) and machine learning (ML) with DFOS data streams is discussed, demonstrating detection accuracy exceeding 97% in recent studies. Its main application rail embankment monitoring is discussed. Key challenges are identified, including high interrogator costs, large data volumes, installation complexity in retrofit scenarios, and environmental noise under operational train speeds. Future research priorities include lower-cost interrogation hardware, automated signal processing pipelines, digital twin integration, and standardized performance frameworks to accelerate large-scale adoption across railway networks worldwide. Full article

Automated visual inspection is a cornerstone of modern manufacturing quality assurance, yet the effectiveness of any detection system is fundamentally bounded by the informativeness of the observations it receives. Most vision–language model (VLM) and reinforcement learning methods for industrial defect detection assume a fixed set of observations and optimize only the reasoning applied to them. We introduce ActiveInspect, which formulates inspection as budget-constrained sequential selection of multi-view, multi-modal evidence. Starting from a pre-acquired observation pool, a single policy selects an additional view or modality, zooms into a candidate region, retrieves a matched normal reference, or terminates with a verdict. The policy is initialized by perception-activated supervised fine-tuning (PA-SFT) and subsequently optimized by group relative policy optimization (GRPO) using inspection-specific rewards. Depth and point-cloud measurements are converted into VLM-compatible geometric renderings, while a structured memory integrates evidence across inspection steps. Evaluation on Real-IAD D³, Real-IAD, MVTec 3D-AD, MVTec-AD, VisA, and MMAD demonstrates a consistent improvement in the accuracy–observation trade-off. On Real-IAD D³, ActiveInspect increases image-level area under the receiver operating characteristic curve (I-AUROC) from 0.890 to 0.906 (mean over three training seeds; $p<0.01$) relative to the passive D³M baseline while reducing the average observation count from 3.0 to 2.7. It reaches 99.8% of the I-AUROC obtained by exhaustive evaluation of all 15 observations while using 18% of that observation count, and it reduces per-sample inference time by a factor of 5.3 relative to the exhaustive scan. The largest gains occur for geometry-dependent defects, including dents, warping, and concavities. Full article

Pastures are the dietary basis of grazing systems in regions such as southern Chile, and their botanical composition and management can influence ruminal fermentation and associated by-products. The objective of this study was to evaluate the effects of pasture type and defoliation frequency (DF) on in vitro ruminal fermentation kinetics and methane and ammonia production. Four pasture types were evaluated: Bromus valdivianus Phil. monoculture (Bv), Lolium perenne monoculture (Lp), a binary mixture of both species (LpBv), and a multispecies pasture (Msp). All pastures were managed under two defoliation frequencies (150 and 300 growing degree days [GDDs]) and sampled across four seasons (summer, autumn, winter, and spring). Samples were dried at 60 °C, ground, and incubated for 48 h at 39 °C using the ANKOM RF automated gas production system, with ruminal inoculum collected from rumen-cannulated cows. Total gas production, methane production, and concentrations of volatile fatty acids (VFAs) and ammonia (NH₃) were evaluated. The CH₄ proportion was affected by the DF × season interaction, and CH₄ intensity was affected by the pasture type × DF interaction. Total gas production was greater for Lp than for Bv and Msp and was greater at 300 than at 150 GDD. Total VFAs showed a pasture type × DF × season interaction. Across pasture types, NH₃ concentration was lower at 300 than at 150 GDD. Overall, no treatment consistently reduced methane output. Extending the defoliation interval may reduce ruminal NH₃, but its environmental benefit should be evaluated together with seasonal methane responses and potential trade-offs in forage nutritive value and animal performance. Full article

Background: The reliable integration of large language models (LLMs) into neuroimaging data extraction workflows remains unresolved. Prior benchmarking shows that exact-match accuracy underestimates LLM extraction performance, but whether inter-model consensus and variable complexity can guide automation remains unclear. We evaluated whether inter-model consensus can serve as a confidence signal for human–artificial intelligence (AI) extraction and can guide complexity-stratified workflow triage. Methods: Four frontier LLMs were queried via OpenRouter with an identical zero-shot structured prompt to extract 22 predefined variables from 91 peer-reviewed neuroimaging AI articles, yielding 2002 article–variable items per model. Variables were stratified a priori into low- (n = 7), medium- (n = 8), and high-complexity (n = 7). Performance was compared with an expert reference using exact-match and semantic-equivalence accuracy. Item-level consensus and five triage strategies characterized the efficiency–accuracy trade-off. Results: Semantic-equivalence accuracy converged to 80.5–83.4% across models despite approximately ten percentage-point exact-match differences. Unanimous 4/4 consensus occurred in 45.6% (910/1994) of items, with exact-match accuracy of 85.8%, rising to 95.3% after semantic normalization; however, 14.2% still failed to match the reference. Reliability was complexity-dependent: 96.6% for low-complexity variables, 73.2% for medium-complexity variables, and 38.1% for high-complexity variables. A hybrid strategy auto-accepting 4/4 items and routing 3/4 items to rapid verification reduced estimated review effort by approximately 59%. Conclusions: Inter-model consensus is useful, but it is incomplete and depends on variable complexity. We show that LLM-assisted extraction in neuroimaging AI is a complexity-stratified workflow design problem: low-complexity neuroimaging variables may be selectively automated, while medium-complexity variables require rapid verification, and high-complexity methodological variables should remain human-led. Full article

The escalating frequency of extreme hydrological events under environmental uncertainty poses a severe socio-economic threat to floodplains such as the Brazilian Pantanal, the world’s largest tropical wetland. Mitigating dynamic flooding and drying cycles is highly challenging due to a critical scarcity of in situ monitoring, leaving flood risks poorly understood. To address these data gaps, this study presents an advanced deep learning forecasting framework that integrates multisource environmental data, fusing satellite-derived precipitation (CHIRPS) and global land data assimilation evapotranspiration (GLDAS) data with historical river gauge telemetry. Multi-layered neural network architectures were optimized and combined with progressive moving average filters (10− and 15−day windows) to capture the complex hydrometeorological patterns of the data-scarce Miranda River Watershed. The optimal deep learning configuration, utilizing a robust two-hidden-layer topology (15 and 60 neurons), consistently outperformed standard baselines. Although purely exogenous data blocks successfully minimized satellite noise and captured seasonal trends (NSE ≥ 0.92), structural underestimation of peak flows was observed. When incorporating the previous day’s streamflow (lag t−1) as a physical anchor, this limitation was noticeably alleviated, increasing both the Nash–Sutcliffe Efficiency (NSE) and Coefficient of Determination (R²) values above 0.99. While this performance surge is driven by the strong temporal persistence inherent to the autoregressive lag, it introduces an operational trade-off by restricting the forecast to a reactive 24 h window. In this regard, an evaluation of the operational forecast horizons revealed that the exogenous deep learning blocks maximize warning lead times, providing a vital tool for proactive civil defense and disaster risk reduction. Ultimately, this multisource framework establishes a methodological foundation for automated decision support systems, providing the high-accuracy streamflow forecasting capability required to support future flood mitigation frameworks. Full article

Large Language Model (LLM)-based agents automate complex tasks by integrating external tools such as web browsers, e-mail clients, file readers, and APIs, but this same integration exposes them to indirect prompt injection (IPI) attacks, in which malicious instructions hidden in tool content hijack the agent. A central but often overlooked question is how defending against such attacks affects the LLM and its own task performance and computational efficiency. In this study, we design a comprehensive testbed and a layered defense, Spotlight-Guard, that combines spotlighting-based input isolation, an LLM detection-and-quarantine pipeline, and instruction integrity based on a Hash-based Message Authentication Code (HMAC) into a single framework, and we evaluate it jointly along two axes: security and LLM performance. Experiments on locally hosted 7B-class open-weight models (Qwen-2.5-7B, Mistral-7B, and DeepSeek-Coder) use Attack Success Rate (ASR) for security and benign-task success rate together with confusion-matrix-based metrics (precision, recall, and F1) for task performance, all with bootstrap 95% confidence intervals. Across a stratified, fixed-seed benchmark of 250 adversarial and 250 benign cases per configuration, the full system reduces the ASR from 36.0% to 17.2% while preserving a 97.2% benign-task success rate and raising the detection F1 from 0.749 to 0.892, demonstrating that strong protection need not degrade the model’s task performance. A component ablation isolates each layer’s contribution, an adaptive-attack evaluation confirms a low ASR (6.7%) under attacks crafted to target the pipeline, and an analysis of computational cost (model invocations per request) quantifies the efficiency overhead, characterizing the security–performance trade-off of layered defenses on open-weight LLMs. Full article

Artificial intelligence applications in management, such as fraud detection and churn prediction, are frequently constrained by the class imbalance problem. Standard over-sampling methods, such as SMOTE, rely on local geometric interpolation, which assumes data convexity and struggles to model the disjoint structures typical of managerial datasets. We introduce Fourier-based Adaptive Spectral Synthesis (FASS), an over-sampling method that frames data generation as a signal reconstruction problem. By transforming the minority class data into the frequency domain via the empirical characteristic function, FASS isolates the global manifold structure from high-frequency sampling noise through an automated spectral filtering mechanism. We prove the $L^2$-consistency of the underlying estimator. Empirical evaluations on credit and marketing datasets demonstrate that FASS favorably shifts the precision–recall trade-off compared to geometric baselines, reducing false positives and providing a theoretically consistent, parameter-free approach to learning from imbalanced data. Full article

Early and accurate detection of skin cancer, particularly melanoma, remains a critical challenge in computer-aided diagnosis, motivating the development of reliable and interpretable machine learning solutions. This study presents a comparative algorithmic analysis of deep learning models for automated skin cancer detection using dermoscopic images. Specifically, convolutional neural networks (CNNs) and Vision Transformers (ViTs) are implemented within a unified framework, employing transfer learning and standardized preprocessing techniques on a benchmark dataset. The proposed methodology incorporates data augmentation and class imbalance handling strategies, while model performance is evaluated using clinically relevant metrics, including accuracy, precision, recall, F1-score, and area under the ROC curve. In addition, explainability techniques such as Grad-CAM and attention visualization are employed to enhance model interpretability, and decision threshold analysis is conducted to assess trade-offs between sensitivity and specificity in melanoma detection. Experimental results demonstrate that CNN-based architectures achieve robust performance in capturing local spatial features, while transformer-based models provide competitive results through global contextual representation. However, variations are observed in model calibration and false-negative rates, which are critical for clinical deployment. Overall, the findings highlight the importance of combining algorithmic performance with interpretability and threshold optimization to support reliable and clinically meaningful computer-aided diagnosis systems. Full article

Robotics simulation is a key enabler for automation and control development, allowing safer experimentation, faster design iterations, and reduced development cost. Nevertheless, the current simulator ecosystem is highly fragmented, spanning open-source and commercial tools with different levels of physical fidelity, performance, and ecosystem integration. As a result, simulator selection is frequently driven by familiarity or availability rather than by explicit task requirements, often leading to suboptimal engineering workflows. This paper proposes a task-oriented decision framework to support reproducible and transparent selection of robotics simulators based on a fixed and structured set of evaluation criteria. These criteria cover (i) physical fidelity and contact modelling; (ii) sensor modelling and visual realism; (iii) performance and scalability aspects, including headless execution, parallelism, and GPU acceleration; (iv) ecosystem integration with automation, control, and learning pipelines, including ROS/ROS 2 compatibility; (v) extensibility and programmability; and (vi) practical constraints such as hardware requirements, licensing models, and learning curve. The framework is operationalised through a checklist and scoring matrix guided by four key questions addressing the target task, fidelity-versus-speed priorities, target software stack, and sim-to-real transfer requirements. To examine feasibility in a representative engineering workflow, a URDF-based modelling and simulation pipeline is implemented and used to compare Gazebo, as an open-source physics-based simulator, against MATLAB/Simulink, representing a commercial model-based simulation environment. The comparison reports practical indicators including setup effort, integration complexity, computational requirements, and runtime behaviour for repeated executions of a representative motion-oriented sequence. The results highlight consistent trade-offs across different user profiles and application needs while also revealing open gaps in the field, notably the lack of unified multi-task benchmarks and joint metrics capable of simultaneously capturing simulation fidelity, computational performance, and sim-to-real transfer effectiveness. Full article

Automated 3D city generation, focusing on road networks and building layouts, is in high demand for applications in urban planning, analysis, and simulations. The surge in deep generative models has facilitated automated design in recent years. However, the lack of high-quality datasets and benchmarks hinders the progress of these data-driven methods in generating city configurations. To fill this gap, this study introduces a multimodal dataset designed for the controllable generation of road networks and building layouts (named RoBus), whose public project repository provides release materials, and constitutes a large-scale resource in the field of generative city design. The RoBus dataset comprises aligned images, graphics, labels, and texts, with 72,400 paired samples that cover around 80,000 km² globally. Besides utilizing prevalent generative models, we also introduce baseline models that leverage the multimodal features of RoBus. The experiments establish the dataset’s usability while revealing complementary trade-offs rather than uniform superiority. ControlNet obtains the lowest road network FID ($20.78$), whereas our topology-aware road baseline obtains the highest traffic-convenience score ($0.83$) at the cost of lower fidelity and diversity. For building layouts, our multimodal baseline reduces FID to $17.42$ and building-density Wasserstein distance from $6.12$ to $3.37$ but produces lower diversity and a higher invalid-sample rate than the strongest comparison methods. Full article