Search Results (1,929)

Air source heat pumps (ASHPs) have become a promising alternative to conventional heating and cooling systems, making accurate performance prediction increasingly important. This study presents a comparative analysis of Adaptive Neuro-Fuzzy Inference System (ANFIS) and Artificial Neural Network (ANN) models for evaluating the ASHP performance under varying ambient conditions, examining the symmetry or asymmetry of prediction behavior across cold and hot regimes. Two experimental campaigns were carried out in a controlled climate room: the first primarily covering moderate to high temperatures ($-3 °\mathrm{C}$ to $36 °\mathrm{C}$), and the second mainly covering negative and low ambient temperatures ($-16 °\mathrm{C}$ to $18 °\mathrm{C}$). Performance data were collected to capture system behavior under diverse thermal conditions, making predictions more challenging. Both models were optimized, ANFIS through grid partitioning and ANN via architecture selection. Results demonstrate that ANN models achieved a superior overall accuracy, with mean absolute errors of 0.061 to 0.064 for cold and hot ambient conditions, respectively, showing a particularly strong performance under cold conditions. ANFIS demonstrated remarkable robustness in low-temperature predictions, maintaining less than 3% deviation across variations in water inlet temperature. Both approaches revealed temperature-dependent characteristics: cold-condition modeling required more complex architectures but yielded higher precision, whereas warm-condition modeling performed reliably with simpler configurations but showed slightly reduced accuracy. Full article

Heat exchangers are widely used process equipment in industrial sectors, making the study of their temperature dynamics particularly appealing due to the nonlinearities involved. Model-free approaches enable the use of input and output data to generate specific and accurate estimations for each proposed system. In this work, a model-free identification strategy is proposed using a convolutional neural network to estimate the system’s behavior. Notably, the model does not rely on direct temperature measurements; instead, temperature is inferred from other system signals such as reference, flow, and control inputs. This data-driven approach offers greater specificity and adaptability, often outperforming manufacturer-provided coefficients whose performance may vary from design expectations. The results yielded an $R^2$ index of 0.9951 under nominal conditions and 0.9936 when the system was subjected to disturbances. Full article

In resource-constrained edge agricultural environments, the accurate recognition of toxic weeds poses dual challenges related to model lightweight design and the few-shot generalization capability. To address these challenges, a multi-strategy recognition framework is proposed, which integrates a lightweight backbone network, a pseudo-labeling guidance mechanism, and a contrastive boundary enhancement module. This approach is designed to improve deployment efficiency on low-power devices while ensuring high accuracy in identifying rare toxic weed categories. The proposed model achieves a real-time inference speed of 18.9 FPS on the Jetson Nano platform, with a compact model size of 18.6 MB and power consumption maintained below 5.1 W, demonstrating its efficiency for edge deployment. In standard classification tasks, the model attains 89.64%, 87.91%, 88.76%, and 88.43% in terms of precision, recall, F1-score, and accuracy, respectively, outperforming existing mainstream lightweight models such as ResNet18, MobileNetV2, and MobileViT across all evaluation metrics. In few-shot classification tasks targeting rare toxic weed species, the complete model achieves an accuracy of 80.32%, marking an average improvement of over 13 percentage points compared to ablation variants that exclude pseudo-labeling and self-supervised modules or adopt a CNN-only architecture. The experimental results indicate that the proposed model not only delivers strong overall classification performance but also exhibits superior adaptability for deployment and robustness in low-data regimes, offering an effective solution for the precise identification and ecological control of toxic weeds within intelligent agricultural perception systems. Full article

The Peace-Athabasca Delta (PAD) in northern Alberta, Canada, is one of the world’s largest inland freshwater deltas and is largely located within the Wood Buffalo National Park, a UNESCO World Heritage Site. Owing to its ecological and socioeconomic significance, the PAD has been designated a Ramsar wetland of international importance. A paucity of large-scale Peace River ice jam flooding and concurrent drying trend during the past five decades has motivated various studies on relevant processes and on possible remedial action. In turn, many of these studies are informed by a flood record that was compiled in 1995, based on Historical information and Traditional Knowledge (H-TK flood record). Later work has expressed occasional reservations regarding the accuracy of this record, while much more is now known about the physical and hydroclimatic controls of PAD ice jams. This paper examines the 20th century portion of the H-TK record in the light of recent scientific advances made since the 1990s and of a wealth of hydrometric and climatic indicators, along with eyewitness corroborations, that extend back to the early 1900s. Systematic observational data and monitoring reports that have become available since the 1990s have also provided valuable documentation of PAD flooding. It is concluded that the record of major ice-jam floods is reliable, while the possibility of “missed” events cannot be precluded. The record of minor ice jam floods, which is largely inferred from reversed tributary flows entering Lake Athabasca, may not be reliable because more than half of the reported events might not have occurred at all. The value of the H-TK record is primarily in the major events, which generate overland inundation and can amply recharge various ponds, lakes, and wetlands of the PAD. Implications of the results for pre- and post-regulation flood frequencies and for future park management are discussed. Full article

The integration of Internet of Things (IoT) technologies into public healthcare enables continuous monitoring and sustainable health management. However, conventional frameworks often depend on transmitting and storing raw personal data on centralized servers, posing challenges related to privacy, security, ethical compliance, and long-term sustainability. This study proposes a privacy-preserving framework that avoids the exposure of true health-related data. Sensor nodes encrypt collected measurements and collaborate with a secure computation core to evaluate health indicators under homomorphic encryption, maintaining confidentiality. For example, the system can determine whether a patient’s heart rate within a monitoring window falls inside clinically recommended thresholds, while the framework remains general enough to support a wide range of encrypted computations. A compliance verification client generates zero-knowledge range proofs, allowing external parties to verify whether health indicators meet predefined conditions without accessing actual values. Simulation results confirm the correctness of encrypted computation, controllability of threshold-based compliance judgments, and resistance to inference attacks. The proposed framework provides a practical solution for secure, auditable, and sustainable real-time health assessment in IoT-enabled public healthcare systems. Full article

Automotive manufacturing quality control faces persistent challenges such as limited defect samples, cross-domain variability, and the demand for interpretable decision-making. This work presents an explainable few-shot anomaly detection framework that integrates EfficientNet-based feature extraction, adaptive prototype learning, and component-specific attention mechanisms to address these requirements. The system is designed for rapid adaptation to novel defect types while maintaining interpretability through a multi-modal explainable AI module that combines visual, quantitative, and textual outputs. Evaluation on automotive datasets demonstrates promising performance on evaluated automotive components, achieving 99.4% accuracy for engine wiring inspection and 98.8% for gear inspection, with improvements of 5.2–7.6% over state-of-the-art baselines, including traditional unsupervised methods (PaDiM, PatchCore), advanced approaches (FastFlow, CFA, DRAEM), and few-shot supervised methods (ProtoNet, MatchingNet, RelationNet, FEAT), and with only 0.63% cross-domain degradation between wiring and gear inspection tasks. The architecture operates under real-time industrial constraints, with an average inference time of 18.2 ms, throughput of 60 components per minute, and memory usage below 2 GB on RTX 3080 hardware. Ablation studies confirm the importance of prototype learning (−4.52%), component analyzers (−2.79%), and attention mechanisms (−2.21%), with K = 5 few-shot configuration providing the best trade-off between accuracy and adaptability. Beyond performance, the framework produces interpretable defect localization, root-cause analysis, and severity-based recommendations designed for manufacturing integration with execution systems via standardized industrial protocols. These results demonstrate a practical and scalable approach for intelligent quality control, enabling robust, interpretable, and adaptive inspection within the evaluated automotive components. Full article

Predictive Coding (PC) frameworks claim to model recognition via prediction–error loops, but they often lack explicit biological implementation of fast familiar recognition and impose latency that limits real-time robotic control. We begin with Experience-Based Pattern Matching (EBPM), a biologically grounded mechanism inspired by neural engram reactivation, enabling near-instantaneous recognition of familiar stimuli without iterative inference. Building upon this, we propose Dynamic Integrative Matching and Encoding (DIME), a hybrid system that relies on EBPM under familiar and low-uncertainty conditions and dynamically engages PC when confronted with novelty or high uncertainty. We evaluate EBPM, PC, and DIME across multiple image datasets (MNIST, Fashion-MNIST, CIFAR-10) and on a robotic obstacle-course simulation. Results from multi-seed experiments with ablation and complexity analyses show that EBPM achieves minimal latency (e.g., ~0.03 ms/ex in MNIST, ~0.026 ms/step in robotics) but poor performance in novel or noisy cases; PC exhibits robustness at a high cost; DIME delivers strong trade-offs—boosted accuracy in familiar clean situations (+4–5% over EBPM on CIFAR-10), while cutting PC invocations by ~50% relative to pure PC. Our contributions: (i) formalizing EBPM as a neurocomputational algorithm built from biologically plausible principles, (ii) developing DIME as a dynamic EBPM–PC integrator, (iii) providing ablation and complexity analyses illuminating component roles, and (iv) offering empirical validation in both perceptual and embodied robotic scenarios—paving the way for low-latency recognition systems. Full article

Conventional teacher assessment is labor-intensive and subjective. Prior LLM-based systems improve scale but rely on post hoc rationales and lack built-in trust controls. We propose an explainable-by-design framework that couples (i) Dual-Lens Hierarchical Attention—a global lens aligned to curriculum standards and a local lens aligned to subject-specific rubrics—with (ii) a Trust-Gated Inference module that combines Monte-Carlo-dropout calibration and adversarial debiasing, and (iii) an On-the-Spot Explanation generator that shares the same fused representation and predicted score used for decision making. Thus, explanations are decision-consistent and curriculum-anchored rather than retrofitted. On TeacherEval-2023, EdNet-Math, and MM-TBA, our model attains an Inter-Rater Consistency of 82.4%, Explanation Credibility of 0.78, Fairness Gap of 1.8%, and Expected Calibration Error of 0.032. Faithfulness is verified via attention-to-rubric alignment (78%) and counterfactual deletion tests, while trust gating reduces confidently wrong outputs and triggers reject-and-refer when uncertainty is high. The system retains 99.6% accuracy under cross-domain transfer and degrades only 4.1% with 15% ASR noise, reducing human review workload by 41%. This establishes a reproducible path to trustworthy and pedagogy-aligned LLMs for high-stakes educational evaluation. Full article

Decentralized energy trading has been designed as a scalable substitute for traditional electricity markets. While blockchain technology facilitates efficient transparency and automation for peer-to-peer energy trading, the majority of current proposals lack real-time intelligence and adaptability concerning pricing strategies. This paper presents an innovative machine learning-driven solar energy trading platform on the Ethereum blockchain that uniquely integrates Bayesian-optimized XGBoost models with dynamic pricing mechanisms inherently incorporated within smart contracts. The principal innovation resides in the real-time amalgamation of meteorological data via Chainlink oracles with machine learning-enhanced price optimization, thereby establishing an adaptive system that autonomously responds to fluctuations in supply and demand. In contrast to existing static pricing methodologies, our framework introduces a multi-faceted dynamic pricing model that encompasses peak-hour adjustments, prediction confidence weighting, and weather-influenced corrections. The system dynamically establishes energy prices predicated on real-time supply–demand forecasts through the implementation of role-based access control, cryptographic hash functions, and ongoing integration of meteorological and machine learning data. Utilizing real-world meteorological data from La Trobe University’s UNISOLAR dataset, the Bayesian-optimized XGBoost model attains a remarkable prediction accuracy of 97.45% while facilitating low-latency price updates at 30 min intervals. The proposed system delivers robust transaction validation, secure offer creation, and scalable dynamic pricing through the seamless amalgamation of off-chain machine learning inference with on-chain smart contract execution, thereby providing a validated platform for trustless, real-time, and intelligent decentralized energy markets that effectively address the disparity between theoretical blockchain energy trading and practical implementation needs. Full article

Understanding the intricate relationship between composition, processing conditions, and material properties is essential for optimizing Cu-based alloys. Machine learning offers a powerful tool for decoding these complex interactions, enabling more efficient alloy design. This work introduces a comprehensive machine learning framework aimed at accurately predicting key properties such as hardness and electrical conductivity of low-alloyed Cu-based alloys. By integrating various input parameters, including chemical composition and thermo-mechanical processing parameters, the study develops and validates multiple machine learning models, including Multi-Layer Perceptron with Production-Aware Deep Architecture (MLP-PADA), Deep Feedforward Network with Multi-Regularization Framework (DFF-MRF), Feedforward Network with Self-Adaptive Optimization (FFN-SAO), and Feedforward Network with Materials Mapping (FFN-TMM). On a held-out test set, DFF-MRF achieved the best generalization (R²_test = 0.9066; RMSE_test = 5.3644), followed by MLP-PADA (R²_test = 0.8953; RMSE_test = 5.7080) and FFN-TMM (R²_test = 0.8914; RMSE_test = 5.8126), with FFN-SAO slightly lower (R²_test = 0.8709). Additionally, a computational performance analysis was conducted to evaluate inference time, memory usage, energy consumption, and batch scalability across all models. Feature importance analysis was conducted, revealing that aging temperature, Cr, and aging duration were the most influential factors for hardness. In contrast, aging duration, aging temperature, solution treatment temperature, and Cu played key roles in electrical conductivity. The results demonstrate the effectiveness of these advanced machine learning models in predicting critical material properties, offering insightful advancements for materials science research. This study introduces the first controlled, statistically validated, multi-model benchmark that integrates composition and thermo-mechanical processing with deployment-grade profiling for property prediction of low-alloyed Cu alloys. Full article

Runway surface roughness is recognized as a principal cause of passenger aircraft vibration during taxiing, adversely affecting ride comfort, safety, and even human health. Effective mitigation of such vibrations is therefore essential for improving passenger experience and operational reliability. Previous studies have investigated passive, semi-active, and intelligent controllers such as PID, H∞, and ANFIS; however, the comprehensive application of a robust adaptive neuro-fuzzy inference system (RANFIS) to active landing-gear control has not yet been addressed. The novelty of this work lies in combining robustness with adaptive learning of fuzzy rules and neural network parameters, thereby filling this critical gap in the literature. To investigate this, a six-degrees-of-freedom aircraft dynamic model was developed, and three controllers were comparatively evaluated: model-based neural network (MBNN), adaptive neuro-fuzzy inference system (ANFIS), and the proposed RANFIS. Performance was assessed in terms of rise time, settling time, peak value, and steady-state error under stochastic runway excitations. Simulation results show that while MBNN and ANFIS provide satisfactory control, RANFIS achieved superior performance, reducing vibration peaks to ≤0.3–1.0 cm, shortening settling times to <1.5 s, and decreasing steady-state errors to <0.05 cm. These findings confirm that RANFIS offers a more effective solution for enhancing comfort, safety, and structural durability in next-generation active landing-gear systems. Full article

The evolution of Industrial Internet of Things (IIoT) systems demands flexible and intelligent architectures capable of addressing low-latency requirements, real-time analytics, and adaptive resource management. In this context, softwarized edge computing emerges as a key enabler, supporting advanced IoT deployments through programmable infrastructures, distributed intelligence, and seamless integration with cloud environments. This paper presents an extended and publicly available proof of concept (PoC) for a softwarized, data-driven architecture designed to operate across the cloud/edge/IoT continuum. The proposed architecture incorporates containerized microservices, open standards, and ML-based inference services to enable runtime decision-making and on-the-fly network reconfiguration based on real-time telemetry from IIoT nodes. Unlike traditional solutions, our approach leverages a modular control plane capable of triggering dynamic adaptations in the system through RESTful communication with a cloud-hosted inference engine, thus enhancing responsiveness and autonomy. We evaluate the system in representative IIoT scenarios involving multi-agent collaboration, showcasing its ability to process data at the edge, minimize latency, and support real-time decision-making. This work contributes to the ongoing efforts toward building advanced IoT ecosystems by bridging conceptual designs and practical implementations, offering a robust foundation for future research and deployment in intelligent, software-defined industrial environments. Full article

This study explores the anticancer, antioxidant, and phytochemical activities of Laurus nobilis L. ethanolic leaf extract. The extract demonstrated selective cytotoxicity against four human cancer cell lines, showing strong cytotoxic effect against ovarian (ES2), head and neck (SAS), and colorectal (HT-29) cancer cells, with IC₅₀ values ranging from 3.8 ± 0.3 to 4.4 ± 0.6 µg/mL. Notably, it exhibited only moderate inhibition of the MDA-MB-231 breast cancer cell line (IC₅₀ = 18.5 ± 0.8 µg/mL), possibly reflecting intrinsic differences in cell line sensitivity. Importantly, the extract showed low toxicity toward normal human fibroblasts (HDF), with an IC₅₀ value exceeding 100 µg/mL, indicating a favorable selectivity profile. The flow cytometry analysis showed that the extract caused cell death and stopped the cell cycle in both SAS and ES2 cancer cell lines. In SAS cells, extract treatment significantly increased apoptotic cells (21.1% ± 0.3%) compared to the control (6.3% ± 0.4%), along with G2 phase accumulation, indicating G2 arrest. Similarly, in ES2 cells, apoptosis increased (16.2% ± 1.3% vs. control 8.1% ± 1.0%), and a significant cell accumulation in the S phase was observed, suggesting disruption of cell cycle progression. Antioxidant screenings showed impressive dose-dependent DPPH radical scavenging activity (25–2000 µg/mL), although less potent than ascorbic acid (2.6 µg/mL). UPLC-QTOF/MS phytochemical analysis revealed various phenolic constituents, such as flavonoids and phenolic acids, and an inferred association with the recorded bioactivities. This preliminary work indicates that L. nobilis extracts may act as natural anticancer and antioxidant agents; however, it was limited to in vitro testing with non-standardized samples, underscoring the need for further research to validate and extend these findings for future applications. Full article

Higher requirements have been placed on fault detection for continuously operating machines in modern factories. Manual inspection faces challenges related to timeliness, leading to the emergence of autonomous diagnostic robots. To overcome the safety limitations of existing diagnostic robots in factory environments, a hierarchical fuzzy logic-based navigation and obstacle avoidance algorithm is proposed in this study. The algorithm is constructed based on zero-order Takagi–Sugeno type fuzzy control, comprising subfunctions for navigation, static obstacle avoidance, and dynamic obstacle avoidance. Coordinated navigation and equipment protection are achieved by jointly considering the information of the fault point and surrounding equipment. The concept of a dynamic safety boundary is introduced, wherein the normalized breached level is used to replace the traditional distance-based input. In the inference process for dynamic obstacle avoidance, the relative speed direction is additionally considered. A Mamdani-type fuzzy inference system is employed to infer the necessity of obstacle avoidance and determine the priority target for avoidance, thereby enabling multi-objective planning. Simulation results demonstrate that the proposed algorithm can guide the diagnostic robot to within 30 cm of the fault point while ensuring collision avoidance with both equipment and obstacles, enhancing the completeness and safety of the fault point searching process. Full article

Stealth attacks targeting industrial control systems (ICS) exploit subtle sequences of malicious actions, making them difficult to detect with conventional methods. The OPC Unified Architecture (OPC UA) protocol—now widely adopted in SCADA/ICS environments—enhances OT–IT integration but simultaneously increases the exposure of critical infrastructures to sophisticated cyberattacks. Traditional detection approaches, which rely on instantaneous traffic features and static models, neglect the sequential dimension that is essential for uncovering such gradual intrusions. To address this limitation, we propose a hybrid sequential anomaly detection pipeline that combines Markov chain modeling to capture temporal dependencies with machine learning algorithms for anomaly detection. The pipeline is further augmented by explainability through SHapley Additive exPlanations (SHAP) and causal inference using the PC algorithm. Experimental evaluation on an OPC UA dataset simulating Man-In-The-Middle (MITM) and denial-of-service (DoS) attacks demonstrates that incorporating a second-order sequential memory significantly improves detection: F1-score increases by +2.27%, precision by +2.33%, and recall by +3.02%. SHAP analysis identifies the most influential features and transitions, while the causal graph highlights deviations from the system’s normal structure under attack, thereby providing interpretable insights into the root causes of anomalies. Full article