Search Results (2,683)

Objective Image Quality Assessment (IQA) is a fundamental pillar of computer vision, essential for optimizing tasks ranging from supervised machine learning to real-time video streaming. While IQA aims to quantify image degradation caused by noise and artifacts, a persistent gap remains between technical objective measurements and subjective human perception. Objective IQA has advanced significantly through full-reference (FR) metrics designed to approximate human judgment. Standard measures such as the peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), and root mean square error (RMSE) provide established benchmarks; however, they frequently fail to capture nuanced human visual preferences, often penalizing perceptually insignificant shifts or favoring overly smoothed images. Conversely, modern deep-learning metrics like LPIPS offer better perceptual alignment but remain computationally prohibitive for real-time, resource-constrained environments. This paper addresses these challenges through a dual-purpose approach. First, it provides a comprehensive survey and tutorial of the IQA landscape, offering self-contained mathematical derivations of classical error sensitivity measures, including MSE, RMSE, MAE, Euclidean distance, RMSLE, and Huber loss, as well as artificial neural network (ANN) approaches. This foundational review ensures a rigorous understanding of the field’s mathematical evolution. We introduce the Adaptive Contrast-Weighted Structural Similarity (ACSSIM) framework. ACSSIM is a lightweight hybrid metric that enhances classical FR-IQA by incorporating local weighting derived from human visual system (HVS) properties. Specifically, it targets Weber’s Law-based contrast and entropy, which are key elements of our hybrid quality assessment logic and key components of non-reference image quality metrics. Extensive numerical experiments on the TID2013 and KADID-10k benchmark show that ACSSIM improves correlation with human subjective judgments compared with the baseline PSNR and SSIM. Our results confirm that ACSSIM maintains low computational overhead, bridging the gap between efficiency and accuracy for practical deployment. We made our code publicly available to facilitate future research in efficient perceptual modeling. Full article

Background: Oil-in-water nanoemulsions (NEs) represent versatile platforms for the delivery of hydrophobic compounds and find a wide range of applications in different fields such as food, cosmetics, agriculture, pharmaceutics, and oil and gas industries. Various methodologies can be applied for the preparation of NEs as low-energy and high-energy methods. Among them, high-energy ultrasonication (HEU) is a popular technique in research laboratories or small manufacturing facilities. However, a clear gap remains in understanding how, and to what extent, experimental parameters and the chemical and physical characteristics of the components affect the formation and properties of NEs through HEU. Methods: In this work, a comprehensive screening of factors (oil viscosity and density, surfactant type, processing parameters, and formulation composition) affecting NEs formation and quality was performed and an artificial neural network (ANN) was applied to determine the relative relevance of each parameter. Results: Oil viscosity revealed to be the primary factor affecting droplet size (Z_avg) and polydispersity index (PDI), with high-viscosity oils leading to poor emulsification into nanosized droplets. Higher processing temperatures improved NE formation by reducing viscosity during sonication. Ultrasound amplitude and pulse mode influenced NE characteristics, particularly under challenging conditions. Surfactant type and oil content had, instead, minor effects on the NEs’ features. ANN modelling accurately predicted NEs’ properties and identified critical viscosity limits for successful nanosized emulsification (Z_avg < 300 nm and PDI < 0.4). Conclusions: These findings provide a predictive basis for rational NE design under HEU, serving as a guide for researchers working in different fields. Full article

Although coconut water is recognized for its desirable sensory appeal and nutritional composition, its broader industrial use is constrained by the rapid deterioration that occurs after extraction. In this study, crossflow microfiltration of coconut water with a silicon carbide membrane was optimized by investigating pressure and temperature through a face-centered design (FCD) and artificial neural network modeling coupled with a genetic algorithm (ANN–GA). Permeate flux and fouling index were used as process responses, and the optimized condition was further examined in terms of hydraulic resistance, fouling behavior, and retention of minerals and primary metabolites. Pressure and temperature affected the process differently: permeate flux showed marked nonlinear behavior, whereas fouling index was governed mainly by pressure. At the sample level, ANN described permeate flux more accurately than FCD (R² = 0.99 vs. 0.96), whereas FCD showed better grouped cross-validated predictivity across unseen pressure–temperature conditions (Q² = 0.85 vs. 0.57). For the fouling index, FCD outperformed ANN in both sample-level fit and grouped validation (R² = 0.95 vs. 0.60; Q² = 0.70 vs. 0.61). Both approaches converged on the same favorable operating window, and experimental validation at 60 kPa and 35 °C yielded 1085.23 ± 23.12 L h⁻¹ m⁻² and 83.56 ± 1.56%. During concentration mode, flux decline was severe but predominantly reversible, with high clean-water permeance recovery after chemical cleaning. Resistance partition and fouling modeling indicated that the main hydraulic limitation was associated with concentration polarization and external cake-layer buildup rather than irreversible membrane damage. The clarified fraction also preserved high transmission of major minerals and relevant primary metabolites, indicating that the selected condition combined high productivity, manageable fouling, and satisfactory nutritional retention. Full article

This paper presents a novel approach to designing and implementing an Artificial Neural Network (ANN) for maximum power point tracking (MPPT), trained solely on unshaded photovoltaic (PV) manufacturer datasheets and capable of tracking and predicting the maximum power point (MPP) under changing shading conditions. This is also known as partial shading conditions (PSC). PSC arises when shade covers sections of the PV panel due to clouds, trees, dust, or man-made objects such as tall buildings. The proposed ANN-based MPPT technique addresses a common issue faced by conventional MPPT methods under PSC: inaccurate MPPT. PSC induces oscillations on the power-to-voltage curve, resulting in multiple local maxima (LMPPs). However, existing ANN-based MPPT methods are developed and trained on shaded PV datasets. This Neural Network (NN) tracking method complicates the training, development, and implementation processes. It increases the cost of development and requires physical, real-world data collection that requires hardware and a lot of time. All this can be avoided with unshaded PV datasheets. The input parameters used to train the model are temperature (T) and irradiance (G), and the output parameters are maximum power (Pmp) and maximum voltage (Vmp). The ANN-based MPPT technique demonstrated strong performance, accurately predicting the global MPP (GMPP) under PSC with high correlation and low prediction error. Full article

In casting processes, mechanical properties such as hardness are highly sensitive to both chemical composition and process parameters, making parameter design a complex and uncertain task during the embodiment stage of engineering design. Conventional trial-and-error-based approaches are often costly, time-consuming, and impractical in industrial environments. To address these challenges, this study proposes an optimized fuzzy artificial neural network (FANN)-based decision-support approach for hardness-oriented parameter design in a casting process. The developed model uses chemical composition variables, including carbon, silicon, manganese, phosphorus, sulfur, chromium, copper, and tin, together with process parameters such as casting temperature and casting time as inputs, while Brinell hardness is considered as the output. A dataset consisting of 170 experimental casting samples was employed; 128 samples were used for model development and hyperparameter selection, and 42 samples were reserved as an independent final test set. The proposed model was implemented as a scaled direct FANN weighted ensemble, in which fuzzified input variables were used to predict standardized continuous hardness values. A total of 300 FANN configurations were evaluated using five-fold cross-validation, and the five best-performing configurations were combined through RMSE-based weighted ensemble averaging. The final model was compared with Random Forest, Linear Regression, Ridge Regression, and SVR-RBF models using MSE, RMSE, MAE, R², MAPE, normalized RMSE, and ±5% prediction success rate. The results showed that the optimized FANN ensemble achieved the lowest mean RMSE in the full-data five-fold cross-validation analysis, slightly outperforming the Random Forest benchmark. In the independent final test set, Random Forest produced the lowest prediction error, whereas the proposed FANN ensemble remained competitive and achieved the same ±5% prediction success rate as Random Forest, Linear Regression, and Ridge Regression. Furthermore, a target-hardness case study demonstrated that the proposed approach could identify candidate casting conditions very close to a desired hardness level, with the nearest prediction reaching 202.985 HB for a target value of 203 HB. These findings indicate that the proposed FANN-based framework can serve not only as a hardness prediction model but also as a practical fuzzy decision-support tool for target-hardness-oriented parameter design in casting processes. Full article

In light of the rapid development of the electric vehicle market, permanent magnet synchronous motors (PMSMs) are becoming essential components of propulsion systems. This is due to their high efficiency, remarkable power density, and ability to deliver high torque over a wide speed range. However, the optimal control of these motors under dynamic conditions remains a major challenge due to system nonlinearities, parameter variations, and external disturbances. Conventional strategies such as field-oriented control (FOC), direct torque control (DTC), and fuzzy logic control (FLC) show variable performance in terms of current quality, robustness, and energy efficiency. To overcome these limitations, this study proposes an intelligent control strategy based on artificial neural networks (ANNs), which ensures efficient operation and high control performance under various operating conditions. This approach leverages the learning capabilities of deep neural networks to improve control accuracy, system stability, and overall energy performance. The results obtained show a significant reduction in the current’s total harmonic distortion (THD) as well as an improvement in the stator’s current quality and the electromagnetic torque’s dynamic behavior compared to conventional methods. This improvement reduces overall losses in the electric drive system, thereby contributing to increased vehicle energy efficiency. As a result, the electric vehicle’s range is extended, and the dynamic performance of the PMSM is optimized. These results confirm the potential of artificial intelligence techniques for developing intelligent, robust, and adaptive control systems designed for modern electric propulsion applications. Full article

Cyber-physical smart infrastructures integrate sensing devices, communication networks, control components, and service platforms, which makes them vulnerable to malicious activities that may evolve gradually through several attack stages. The objective of this study is to develop and evaluate a simulation-based cybersecurity framework capable of detecting a proposed novel multi-stage cyber attack and identifying its internal progression within a realistic smart infrastructure environment. To achieve this objective, a NetSim-based cyber-physical smart infrastructure was modeled to generate both normal operational traffic and staged malicious traffic. The generated traffic was captured, processed, labeled, and transformed into a stage-aware cybersecurity dataset. An artificial neural network (ANN) model was then trained and evaluated for two detection tasks: binary classification of normal versus attack traffic and multi-class classification of compromise, coordination, and execution attack stages. Twenty experimental configurations were designed to examine the model under progressively broader infrastructure contexts, including sensing, service, gateway, control, backbone, and full-span operational scenarios. The best binary testing performance was achieved in the eighteenth experimental configuration, representing a broad full-span infrastructure scenario, with 97.96% accuracy, 97.80% precision, 97.65% recall, 97.72% F1-score, and 1.06% false positive rate. For stage-aware multi-class detection, the ANN model achieved 96.97% accuracy, 96.36% macro-averaged precision, 96.20% macro-averaged recall, 96.28% macro-averaged F1-score, and 96.55% weighted F1-score. Macro-averaged metrics report the unweighted average performance across classes, while weighted F1-score accounts for class support. These results show that the proposed simulation-based framework can generate realistic attack-aware traffic data and support reliable ANN-based detection of both attack presence and attack-stage progression. Full article

The objective of this research was to develop an intelligent stress mapping and a smart control platform, utilizing Artificial Intelligence (AI), to increase the fatigue life of a hydraulic crane. The crane’s boom was modeled and co-simulated using ANSYS, ADAMS, and MATLAB. A flexible model of the boom was created in ANSYS and then exported to ADAMS. Stress analysis was performed using the maximum principal hotspot method and the von Mises yield criterion. Stress optimization was conducted using a Neural Network (NN) algorithm, which is a key implementation of AI in this study. Two control platforms, one based on Neural Networks and another on Fuzzy Logic, were designed to apply AI in controlling the crane’s movements. The Neural Network algorithm optimized the crane’s movement by adjusting velocity at critical positions where structural stress was high, while the fuzzy logic-based control algorithm utilized stress feedback from the crane’s structure. Both AI-driven control algorithms were integrated into the physical crane in the lab, and extensive testing demonstrated a significant increase in the crane’s fatigue life, along with effective damping of crane vibrations. This paper introduces a novel AI-driven approach combining Neural Networks and Fuzzy Logic for intelligent stress mapping and control, specifically tailored for hydraulic cranes. Unlike previous works, this research integrates real-time stress feedback into the control process and validates the algorithms through experimental implementation on a prototype crane, significantly improving its fatigue life. Full article

Non-exhaust emissions (NEEs), particularly brake wear particles (BWPs), have become a dominant source of traffic-related particulate matter (PM), accounting for approximately 77% of PM10 and 60% of PM2.5 emissions. Accurate quantification of these emissions is essential under increasingly stringent regulations such as Euro 7. However, measurement reliability is strongly influenced by particle transport and sampling losses. This review provides a state-of-the-art analysis of laboratory-scale methodologies for investigating BWP emissions, focusing on pin-on-disc (PoD) tribometers and inertia dynamometer systems. Particular attention is given to chamber design, airflow management, sampling configurations, and the mechanisms governing particle transport efficiency. The literature indicates that PoD systems are often affected by complex and non-uniform flow fields, leading to incomplete particle capture and reduced representativeness, whereas inertia dynamometers, especially when coupled with constant volume sampling (CVS), provide more controlled and reproducible conditions. Key loss mechanisms, including inertial deposition, diffusion, gravitational settling, and non-isokinetic sampling effects, are major contributors to uncertainty. The reviewed studies highlight that aerodynamic limitations in PoD systems, particularly box-shaped chambers, promote flow recirculation and particle losses. Advanced optimization approaches that combine artificial neural networks (ANNs) with computational fluid dynamics (CFD) simulations show strong potential to improve system design and measurement reliability. Full article

The trend in the power electronics industry toward higher power density and efficiency has brought high-frequency transformers (HFTs) to the forefront of critical applications, including isolated DC–DC converters, electric vehicle chargers, and solid-state transformers. This paper focuses on the leakage inductance of HFTs and presents a systematic comparative framework that evaluates five surrogate modeling and hybrid optimization approaches for the rapid and accurate estimation of leakage inductance. A comprehensive parametric dataset was constructed, comprising 1210 finite element analysis simulations conducted via finite element analysis in the ANSYS Maxwell 2024 R1 environment, varying the number of winding turns, primary winding thickness, and secondary winding thickness of the HFT. All five methods were trained and evaluated on the same dataset under identical conditions. The comparative evaluation demonstrates that the proposed hybrid Gray Wolf optimizer–artificial neural network (GWO-ANN) framework achieved the highest prediction accuracy (R² = 0.9832, MSE = 0.01780, MAE = 0.0935 µH) and the fastest convergence among all tested approaches. The generalization capability of the proposed model was confirmed through blind validation tests across six geometric configurations spanning the full range of the design space, yielding a maximum prediction error of 8.15% and an average error of 2.14%. The functional validity of the proposed parameters was further tested in a third validation layer using MATLAB/Simulink R2024b transformer circuit studies, demonstrating a theoretical efficiency of 96.06%. This three-layer validation approach proves both the parametric and functional reliability of the proposed framework for HFT designs. Full article

The sustainable development of forest ecotourism relies on the effective stimulation of tourists’ environmentally responsible behavior, and the intervention of participatory art and aesthetics provides a new driving force for this process. Taking Xiqiaoshan National Forest Park (Nanhai Land Art Festival) as a case study, we propose an extended stimulus–organism–response (S-O-R) theoretical framework to reveal the psychological perception and transmission mechanism of participatory art and aesthetic experience in empowering the sustainable development of ecotourism. We used a hybrid approach combining PLS-SEM and artificial neural networks (ANNs) to analyze survey data from 596 Chinese tourists. The study found that sensory impressions driven by art and aesthetics significantly and positively influence tourists’ natural connections, perceived value, and ecotourism attitudes. These three constructs function as significant parallel mediators between sensory impressions and environmentally responsible behavior, while chain mediation effects are statistically significant but of small magnitude. The new environmental paradigm (NEP), conceptualized as an individual trait boundary condition, exhibits a significant negative moderating effect on the relationship between sensory impressions and connectedness to nature. ANN sensitivity analysis further complements the findings by demonstrating the prominent nonlinear predictive role of ecotourism attitudes in behavioral transformation. This study extends the application boundaries of the S-O-R theory to art-integrated ecotourism research, clarifies the internalization process of tourist experiences from sensory perception to behavioral enactment, and provides empirical evidence for forest tourism managers to optimize experience design and implement differentiated guidance strategies. Full article

Ground improvement for foundations supported on soft soils is traditionally problematic because of low bearing capacity and a large magnitude of settlement. One sustainable method for mitigating these problems is the use of stone columns (SCs), particularly geosynthetic-encased stone columns (GESCs), to improve load transfer, confinement, and consolidation. This review critically synthesizes recent advances in the analysis and design of SC systems using experimental investigations, numerical simulations, and machine learning (ML)-based methodologies. The article indicates that GESCs, when integrated with modern data-driven techniques, especially hybrid metaheuristic ML models, represent a reliable and sustainable solution for soft soil stabilization. Traditional analytical and empirical methods remain useful; however, they are often inadequate for very soft soils (Undrained shear strength (c_u) < 15 kPa), where excessive bulging and large deformations dominate system behavior. Consequently, intelligent hybrid modeling approaches are emerging as the next generation of optimized, data-driven design tools in geotechnical engineering. Different failure mechanisms of SCs, including bulging, punching shear, and general shear failure, are critically discussed along with the governing design parameters. Previous studies consistently indicate that spacing ratios within the range of s/D = 2–3 can improve the bearing capacity ratio (BCR) by approximately 50–100%. Numerical and experimental studies further demonstrate that SC systems can transfer nearly 60–80% of the applied load through stress concentration and soil arching mechanisms. Furthermore, the application of geosynthetic encasement enhances the performance of SCs in very soft soils by increasing confinement, reducing lateral deformation, and enhancing bearing capacity by nearly 3–6 times compared with ordinary SCs. The review also evaluates the growing role of artificial intelligence techniques in forecasting settlement and bearing capacity behavior. ML techniques such as artificial neural networks (ANN), support vector regression (SVR), random forest (RF), XGBoost, and hybrid metaheuristic–ML models have shown high predictive capability, often achieving prediction errors below 5%. Despite these advancements, many existing ML studies still suffer from limited datasets, a lack of generalization, and insufficient incorporation of physical mechanisms. Full article

The convergence of artificial intelligence (AI), explainable AI (XAI), and neuroscience is fostering new opportunities for understanding both machine and biological intelligence through interpretable and human-centered learning paradigms. In this Perspective, we introduce XAI2Brain as a conceptual framework for brain–AI alignment, positioning mechanistic interpretability as an intermediate layer connecting neural network representations, human understanding, and neuroscience-inspired AI design. Rather than viewing XAI solely as a post hoc transparency tool, we emphasize its emerging role in enabling mechanistic analysis of internal model representations, concept-level reasoning, and interactive human–AI alignment. We define XAI2Brain as a multi-level conceptual framework rather than a deployable system, explicitly aimed at structuring brain–AI alignment across representation-level, mechanism-level, and interaction-level perspectives. We survey the evolution of XAI methodologies—from feature attribution and concept-based explanations to mechanistic and human-centric interpretability approaches—and discuss how these methods may support bidirectional knowledge transfer between AI systems and cognitive neuroscience. Importantly, we adopt a cautious stance on brain–AI analogy, explicitly recognizing that artificial neural representations are not equivalent to biological neural representations, and instead focusing on functional and informational correspondences rather than structural equivalence. Unlike conventional human-in-the-loop or reinforcement learning from human feedback paradigms that primarily optimize behavioral outputs, XAI2Brain focuses on cognitively interpretable and mechanistically grounded alignment between AI systems and human reasoning processes. This alignment promotes interactive human-in-the-loop intelligence, empowering humans to comprehend, guide, and refine AI systems, while enabling AI systems to better interpret human instructions, intentions, and contextual reasoning. We further discuss the challenges of scaling explainability to large generative and multimodal models, including issues of interpretability robustness, cognitive compatibility, evaluation, and ethical accountability. We also highlight key limitations of current mechanistic interpretability methods, including explanation instability, representation superposition, and lack of causal guarantees, underscoring that these challenges remain open research problems. Rather than proposing a complete artificial brain architecture, this Perspective outlines a research roadmap toward more interpretable, adaptive, and neuroscience-inspired AI systems capable of supporting future brain–AI integration and collaborative intelligence. We additionally clarify that this work follows a narrative perspective review methodology with structured thematic synthesis of the literature. By framing explainability as a bridge between mechanistic AI understanding, cognitive science, and human-centered interaction, XAI2Brain highlights the importance of interpretable alignment for the next generation of brain-inspired AI systems. Full article

Photovoltaic power forecasting is important because solar generation varies with weather conditions. Accurate forecasts help improve grid operation, reduce costs, enhance system stability, and support battery management. This paper presents a hybrid methodology that combines statistical analysis and machine learning to forecast photovoltaic power generation. First, the data are cleaned and preprocessed. Then, the input vector is selected using two criteria: collinearity analysis to remove redundant variables, and Granger causality to identify variables with predictive value in a nonlinear autoregressive with exogenous inputs artificial neural network (NARX-ANN) framework. Next, an experimental design is used to evaluate two training algorithms and activation functions for the hidden layer available in Matlab^® version 26.1.0.3276743 (R2026a Update 3, MathWorks Inc., Natick, MA, USA). The methodology is validated by comparing hundreds of input-variable combinations generated through binomial coefficients. A case study using data from Sonora, Mexico, shows that the best model is the Collinearity–Causality (CC)-NARX-4 model, which uses four input variables, a radial basis function in the hidden layer, and Bayesian regularization backpropagation. This model achieves a root-mean-square error (RMSE) of approximately 132 watts (W) for the forecasting stage/forecasting horizon. The results are also compared with a nonlinear autoregressive (NAR) model to assess the predictive benefit of including exogenous inputs. The final outcome is a robust methodology for improving multivariable neural networks through (i) optimized input-vector selection using collinearity and causality tests, validated by an exhaustive combinatorial algorithm; and (ii) a systematic procedure for configuring the hidden-layer transfer function and the neural network training function. Full article

Neural networks are increasingly adopted for performance enhancement in wireless communication infrastructure for 5G and 6G applications. This paper proposes a modular two-box neural network-based system for the behavioral modeling of dynamic nonlinear distortions observed in wireless transmitters. The proposed model, labeled cascaded augmented real-valued artificial neural networks (CAR-VANN), uses a first neural network with an augmented but memoryless input vector feature to model memoryless nonlinear behavior. This model is designed for low-complexity and coarse estimation of the nonlinear distortions. The second neural network, which aims to fine-tune the model output and boost its accuracy, is a conventional augmented real-valued time-delay neural network (ARVTDNN). Experimental validation shows that the CAR-VANN model can achieve the same performance as the ARVTDNN with a significant reduction in the number of parameters (between 35% and 52%). Accordingly, this model can be considered a viable alternative for the computationally efficient modeling of dynamic nonlinear distortions in 5G systems, reducing the computational complexity associated with neural networks-based models without compromising their performance. Full article