Search Results (2,732)

Accurate melt pool geometry prediction is essential for ensuring quality and reliability in Laser Powder Bed Fusion (L-PBF). However, small experimental datasets and limited physical interpretability often restrict the effectiveness of traditional machine learning (ML) models. This study proposes a hybrid framework that integrates an explicit thermal model with ML algorithms to improve prediction under sparse data conditions. The explicit model—calibrated for variable penetration depth and absorptivity—generates synthetic melt pool data, augmenting 36 experimental samples across conduction, transition, and keyhole regimes for 316 L stainless steel. Three ML methods—Multilayer Perceptron (MLP), Random Forest, and XGBoost—are trained using fivefold cross-validation. The hybrid approach significantly improves prediction accuracy, especially in unstable transition regions (D/W ≈ 0.5–1.2), where morphological fluctuations hinder experimental sampling. The best-performing model (MLP) achieves R² > 0.98, with notable reductions in MAE and RMSE. The results highlight the benefit of incorporating physically consistent, nonlinearly distributed synthetic data to enhance generalization and robustness. This physics-augmented learning strategy not only demonstrates scientific novelty by integrating mechanistic modeling into data-driven learning, but also provides a scalable solution for intelligent process optimization, in situ monitoring, and digital twin development in metal additive manufacturing. Full article

Railway systems occupy a predominant role in urban transport, providing efficient, high-capacity mobility. Progress in rail transport allows fast traveling, whilst environmental concerns and CO₂ emissions are on the rise. The integration of railway systems with renewable energy source (RES)-based stations presents a promising avenue to improve the sustainability, reliability, and efficiency of urban transport networks. A storage system is needed to both ensure a continuous power supply and meet train demand at the station. Batteries (BTs) offer high energy density, while supercapacitors (SCs) offer both a large number of charge and discharge cycles, and high-power density. This paper proposes a hybrid RES (photovoltaic and wind), combined with batteries and supercapacitors constituting the hybrid energy storage system (HESS). One major drawback of trains is the long charging time required in stations, so they have been fitted with SCs to allow them to charge up quickly. A new fuzzy energy management strategy (F-EMS) is proposed. This supervision strategy optimizes the power flow between renewable energy sources, HESS, and trains. DC bus voltage regulation is involved, maintaining BT and SC charging levels within acceptable ranges. The simulation results, carried out using MATLAB/Simulink, demonstrate the effectiveness of the suggested fuzzy energy management strategy for various production conditions and train demand. Full article

Cancer remains one of the most significant global health challenges due to its high mortality rates and the limited understanding of its progression. Early diagnosis is critical to improving patient outcomes, especially in skin cancer, where timely detection can significantly enhance recovery rates. Histopathological analysis is a widely used diagnostic method, but it is a time-consuming process that heavily depends on the expertise of highly trained specialists. Recent advances in Artificial Intelligence have shown promising results in image classification, highlighting its potential as a supportive tool for medical diagnosis. In this study, we explore the application of hybrid Artificial Intelligence models for melanoma diagnosis using histopathological images. The dataset used consisted of 506 histopathological images, from which 313 curated images were selected after quality control and preprocessing. We propose a two-step framework that employs an Autoencoder for dimensionality reduction and feature extraction of the images, followed by a classification algorithm to distinguish between melanoma and nevus, trained on the extracted feature vectors from the bottleneck of the Autoencoder. We evaluated Support Vector Machines, Random Forest, Multilayer Perceptron, and K-Nearest Neighbours as classifiers. Among these, the combinations of Autoencoder with K-Nearest Neighbours achieved the best performance and inference time, reaching an average accuracy of approximately 97.95% on the test set and requiring 3.44 min per diagnosis. The baseline comparison results were consistent, demonstrating strong generalisation and outperforming the other models by 2 to 13 percentage points. Full article

In the era of smart agriculture, accurate identification of plant species is critical for effective crop management, biodiversity monitoring, and the sustainable use of medicinal resources. However, existing deep learning approaches often underperform when applied to fine-grained plant classification tasks due to the lack of domain-specific, high-quality datasets and the limited representational capacity of traditional architectures. This study addresses these challenges by introducing a novel, well-curated leaf image dataset consisting of 39 classes of medicinal and aromatic plants collected from the Aromatic and Medicinal Plant Research Station in Odakkali, Kerala, India. To overcome performance bottlenecks observed with a baseline Convolutional Neural Network (CNN) that achieved only 44.94% accuracy, we progressively enhanced model performance through a series of architectural innovations. These included the use of a pre-trained VGG16 network, data augmentation techniques, and fine-tuning of deeper convolutional layers, followed by the integration of Squeeze-and-Excitation (SE) attention blocks. Ultimately, we propose a hybrid deep learning architecture that combines VGG16 with Batch Normalization, Gated Recurrent Units (GRUs), Transformer modules, and Dilated Convolutions. This final model achieved a peak validation accuracy of 95.24%, significantly outperforming several baseline models, such as custom CNN (44.94%), VGG-19 (59.49%), VGG-16 before augmentation (71.52%), Xception (85.44%), Inception v3 (87.97%), VGG-16 after data augumentation (89.24%), VGG-16 after fine-tuning (90.51%), MobileNetV2 (93.67), and VGG16 with SE block (94.94%). These results demonstrate superior capability in capturing both local textures and global morphological features. The proposed solution not only advances the state of the art in plant classification but also contributes a valuable dataset to the research community. Its real-world applicability spans field-based plant identification, biodiversity conservation, and precision agriculture, offering a scalable tool for automated plant recognition in complex ecological and agricultural environments. Full article

The accurate dosing of polyaluminum chloride (PAC) is essential for achieving effective coagulation in drinking water treatment, yet conventional methods such as jar tests are limited in their responsiveness and operational efficiency. This study proposes a hybrid modeling framework that integrates artificial neural networks (ANN) with genetic algorithms (GA) to optimize PAC dosage under variable raw water conditions. Operational data from 400 jar test experiments, collected between 2022 and 2024 at the Yanahurco water treatment plant (Ecuador), were used to train an ANN model capable of predicting six post-treatment water quality indicators, including turbidity, color, and pH. The ANN achieved excellent predictive accuracy (R² > 0.95 for turbidity and color), supporting its use as a surrogate model within a GA-based optimization scheme. The genetic algorithm evaluated dosage strategies by minimizing treatment costs while enforcing compliance with national water quality standards. The results revealed a bimodal dosing pattern, favoring low PAC dosages (~4 ppm) during routine conditions and higher dosages (~12 ppm) when influent quality declined. Optimization yielded a 49% reduction in median chemical costs and improved color compliance from 52% to 63%, while maintaining pH compliance above 97%. Turbidity remained a challenge under some conditions, indicating the potential benefit of complementary coagulants. The proposed ANN–GA approach offers a scalable and adaptive solution for enhancing chemical dosing efficiency in water treatment operations. Full article

This research develops a dual physics-based machine learning system to forecast fuel consumption and CO₂ emissions for a 100 m oil tanker across six operational scenarios: Original, Paint, Advanced Propeller, Fin, Bulbous Bow, and Combined. The combination of hydrodynamic calculations with Monte Carlo simulations provides a solid foundation for training machine learning models, particularly in cases where dataset restrictions are present. The XGBoost model demonstrated superior performance compared to Support Vector Regression, Gaussian Process Regression, Random Forest, and Shallow Neural Network models, achieving near-zero prediction errors that closely matched physics-based calculations. The physics-based analysis demonstrated that the Combined scenario, which combines hull coatings with bulbous bow modifications, produced the largest fuel consumption reduction (5.37% at 15 knots), followed by the Advanced Propeller scenario. The results demonstrate that user inputs (e.g., engine power: 870 kW, speed: 12.7 knots) match the Advanced Propeller scenario, followed by Paint, which indicates that advanced propellers or hull coatings would optimize efficiency. The obtained insights help ship operators modify their operational parameters and designers select essential modifications for sustainable operations. The model maintains its strength at low speeds, where fuel consumption is minimal, making it applicable to other oil tankers. The hybrid approach provides a new tool for maritime efficiency analysis, yielding interpretable results that support International Maritime Organization objectives, despite starting with a limited dataset. The model requires additional research to enhance its predictive accuracy using larger datasets and real-time data collection, which will aid in achieving global environmental stewardship. Full article

Despite rapid advances in robot learning, the coordination of closed-loop manipulation in cluttered environments remains a challenging and relatively underexplored problem. We present a novel two-level hierarchical architecture for a depth vision-equipped robotic arm that integrates pushing, grasping, and high-level decision making. Central to our approach is a prioritised action–selection mechanism that facilitates efficient early-stage learning via behaviour cloning (BC), while enabling scalable exploration through reinforcement learning (RL). A high-level decision neural network (DNN) selects between grasping and pushing actions, and two low-level action neural networks (ANNs) execute the selected primitive. The DNN is trained with RL, while the ANNs follow a hybrid learning scheme combining BC and RL. Notably, we introduce an automated demonstration generator based on oriented bounding boxes, eliminating the need for manual data collection and enabling precise, reproducible BC training signals. We evaluate our method on a challenging manipulation task involving five closely packed cubic objects. Our system achieves a completion rate (CR) of 100%, an average grasping success (AGS) of 93.1% per completion, and only 7.8 average decisions taken for completion (DTC). Comparative analysis against three baselines—a grasping-only policy, a fixed grasp-then-push sequence, and a cloned demonstration policy—highlights the necessity of dynamic decision making and the efficiency of our hierarchical design. In particular, the baselines yield lower AGS (86.6%) and higher DTC (10.6 and 11.4) scores, underscoring the advantages of content-aware, closed-loop control. These results demonstrate that our architecture supports robust, adaptive manipulation and scalable learning, offering a promising direction for autonomous skill coordination in complex environments. Full article

The time series prediction of visibility in terms of various meteorological variables, such as relative humidity, temperature, atmospheric pressure, and wind speed, is presented in this paper using Single-Variable Regression Analysis (SVRA), Artificial Neural Network (ANN), and Hybrid Adaptive Neuro-fuzzy Inference System (ANFIS) techniques for several sub-tropical locations. The initial method used for the prediction of visibility in this study was the SVRA, and the results were enhanced using the ANN and ANFIS techniques. Throughout the study, neural networks with various algorithms and functions were trained with different atmospheric parameters to establish a relationship function between inputs and visibility for all locations. The trained neural models were tested and validated by comparing actual and predicted data to enhance visibility prediction accuracy. Results were compared to assess the efficiency of the proposed systems, measuring the root mean square error (RMSE), coefficient of determination (R²), and mean bias error (MBE) to validate the models. The standard statistical technique, particularly SVRA, revealed that the strongest functional relationship was between visibility and RH, followed by WS, T, and P, in that order. However, to improve accuracy, this study utilized back propagation and hybrid learning algorithms for visibility prediction. Error analysis from the ANN technique showed increased prediction accuracy when all the atmospheric variables were considered together. After testing various neural network models, it was found that the ANFIS model provided the most accurate predicted results, with improvements of 31.59%, 32.70%, 30.53%, 28.95%, 31.82%, and 22.34% over the ANN for Durban, Cape Town, Mthatha, Bloemfontein, Johannesburg, and Mahikeng, respectively. The neuro-fuzzy model demonstrated better accuracy and efficiency by yielding the finest results with the lowest RMSE and highest R² for all cities involved compared to the ANN model and standard statistical techniques. However, the statistical performance analysis between measured and estimated visibility indicated that the ANN produced satisfactory results. The results will find applications in Optical Wireless Communication (OWC), flight operations, and climate change analysis. Full article

This research presents a reinforcement learning framework for stable quadruped locomotion using Proximal Policy Optimization (PPO). We address critical challenges in articulated robot control—including mechanical complexity and trajectory instability by implementing a 12-degree-of-freedom model in PyBullet simulation. Our approach features three key innovations: (1) a hybrid reward function ($R_t=0.72 · e^{-\Delta {\mathrm{CoG}}_t} + 0.25 · v_t - 0.11 · ‖{\tau }_t‖$) explicitly prioritizing center-of-gravity (CoG) stabilization; (2) rigorous benchmarking demonstrating Adam’s superiority over SGD for policy convergence (68% lower reward variance); and (3) a four-metric evaluation protocol quantifying locomotion quality through reward progression, CoG deviation, policy loss, and KL-divergence penalties. Experimental results confirm an 87.5% reduction in vertical CoG oscillation (from 2.0″ to 0.25″) across 1 million training steps. Policy optimization achieved −6.2 × 10⁻⁴ loss with KL penalties converging to 0.13, indicating stable gait generation. The framework’s efficacy is further validated by consistent CoG stabilization during deployment, demonstrating potential for real-world applications requiring robust terrain adaptation. Full article

Accurate prediction of the F-factor averaged over one kilometer (FBAR), a critical wind shear metric, is essential for aviation safety. A central F-factor is used to compute FBAR. i.e., compute the value of FBAR at a point using a spatial interval beginning 500 m prior to the point and ending 500 m beyond the point. Traditional FBAR estimation using the Vicroy method suffers from limited vertical wind speed (W${\phantom{,}}_h$) accuracy, particularly in complex, non-idealized atmospheric conditions. This foundational study proposes a hybrid CNN-BiLSTM-Attention deep learning architecture that integrates spatial feature extraction, sequential dependency modeling, and attention mechanisms to address this limitation. The model was trained and evaluated on data generated by the industry-standard Airborne Doppler Weather Radar Simulation (ADWRS) system, using the DFW microburst case (C1-11) as a benchmark hazardous scenario. Following safety assurance principles aligned with SAE AS6983, the proposed model achieved a W${\phantom{,}}_h$ estimation RMSE (root-mean-squared deviation) of $0.623$ $\mathrm{m} {\mathrm{s}}^{-1}$ (vs. Vicroy’s $14.312$ $\mathrm{m} {\mathrm{s}}^{-1}$) and a correlation of 0.974 on 14,524 test points. This subsequently improved FBAR prediction RMSE by 98.5% (0.0591 vs. 4.0535) and MAE (Mean Absolute Error) by 96.1% (0.0434 vs. 1.1101) compared to Vicroy-derived values. The model demonstrated a 65.3% probability of detection for hazardous downdrafts with a low 1.7% false alarm rate. These results, obtained in a controlled and certifiable simulation environment, highlight deep learning’s potential to enhance the reliability of airborne wind shear detection for civil aircraft, paving the way for next-generation intelligent weather avoidance systems. Full article

This paper proposes a hybrid model that combines convolutional neural networks with natural language processing techniques for least significant bit-based steganography detection in grayscale digital images. The proposed approach identifies hidden messages by analyzing subtle alterations in the least significant bits and validates the linguistic coherence of the extracted content using a semantic filter implemented with spaCy. The system is trained and evaluated on datasets ranging from 5000 to 12,500 images per class, consistently using an 80% training and 20% validation partition. As a result, the model achieves a maximum accuracy and precision of 99.96%, outperforming recognized architectures such as Xu-Net, Yedroudj-Net, and SRNet. Unlike traditional methods, the model reduces false positives by discarding statistically suspicious but semantically incoherent outputs, which is essential in forensic contexts. Full article

High-rise construction presents heightened safety risks due to vertical complexity, spatial constraints, and workforce variability. Conventional safety management often proves insufficient, especially in rapidly urbanizing or resource-limited settings. This study proposes a hybrid methodological framework to systematically identify and prioritize the critical factors influencing occupational safety in Vietnamese high-rise construction projects. Based on 181 valid survey responses from construction professionals, 23 observed variables were developed through extensive literature review and expert consultation. Exploratory Factor Analysis (EFA) was employed to empirically group 23 validated indicators into five key latent dimensions: (1) Safety Training and Inspection, (2) Employer’s Knowledge and Responsibility, (3) Worker’s Competence and Compliance, (4) Working Conditions and Environment, and (5) Safety Equipment and Signage. These dimensions were then structured into an Analytic Hierarchy Process (AHP) model, with pairwise comparisons conducted by industry experts to calculate consistency ratios and derive factor weights across three high-rise project case studies. The findings provide actionable insights for construction managers, safety professionals, and policymakers in developing and underdeveloped countries, supporting data-driven decision-making for safer and more sustainable urban development. Full article

The increasing complexity of manufacturing processes demands accurate defect prediction and interpretable insights into the causes of quality issues. This study proposes a methodology integrating machine learning, clustering, and Explainable Artificial Intelligence (XAI) to support defect analysis and quality control in industrial environments. Using a dataset based on empirical industrial distributions, we train an XGBoost model to classify high- and low-defect scenarios from multidimensional production and quality metrics. The model demonstrates high predictive performance and is analyzed using five XAI techniques (SHAP, LIME, ELI5, PDP, and ICE) to identify the most influential variables linked to defective outcomes. In parallel, we apply Fuzzy C-Means and K-means to segment production data into latent operational profiles, which are also interpreted using XAI to uncover process-level patterns. This approach provides both global and local interpretability, revealing consistent variables across predictive and structural perspectives. After a thorough review, no prior studies have combined supervised learning, unsupervised clustering, and XAI within a unified framework for manufacturing defect analysis. The results demonstrate that this integration enables a transparent, data-driven understanding of production dynamics. The proposed hybrid approach supports the development of intelligent, explainable Industry 4.0 systems. Full article

This study applies Gradient Boosting Machines (GBMs) and principal component regression (PCR) to forecast the closing price of the Johannesburg Stock Exchange (JSE) All-Share Index (ALSI), using daily data from 2009 to 2024, sourced from the Wall Street Journal. The models are evaluated under three training–testing split ratios to assess short-term forecasting performance. Forecast accuracy is assessed using standard error metrics: mean absolute error (MAE), root mean square error (RMSE), mean absolute percentage error (MAPE), and mean absolute scaled error (MASE). Across all test splits, the GBM consistently achieves lower forecast errors than PCR, demonstrating superior predictive accuracy. To validate the significance of this performance difference, the Diebold–Mariano (DM) test is applied, confirming that the forecast errors from the GBM are statistically significantly lower than those of PCR at conventional significance levels. These findings highlight the GBM’s strength in capturing nonlinear relationships and complex interactions in financial time series, particularly when using features such as the USD/ZAR exchange rate, oil, platinum, and gold prices, the S&P 500 index, and calendar-based variables like month and day. Future research should consider integrating additional macroeconomic indicators and exploring alternative or hybrid forecasting models to improve robustness and generalisability across different market conditions. Full article

Reservoir-induced landslides threaten infrastructures and downstream communities, making continuous deformation monitoring vital. Time-series InSAR, notably the SBAS algorithm, provides high-precision surface-displacement mapping but suffers from voids due to layover/shadow effects and temporal decorrelation. Existing deep-learning approaches often operate on fixed-size patches or ignore irregular spatio-temporal dependencies, limiting their ability to recover missing pixels. With this objective, a hybrid spatio-temporal Graph Attention (ST-GAT) framework was developed and trained on SBAS-InSAR values using 24 influential features. A unified spatio-temporal graph is constructed, where each node represents a pixel at a specific acquisition time. The nodes are connected via inverse distance spatial edges to their K-nearest neighbors, and they have bidirectional temporal edges to themselves in adjacent acquisitions. The two spatial GAT layers capture terrain-driven influences, while the two temporal GAT layers model annual deformation trends. A compact MLP with per-map bias converts the fused node embeddings into normalized LOS estimates. The SBAS-InSAR results reveal LOS deformation, with 48% of missing pixels and 20% located near the Dasu dam. ST D-GAT reconstructed fully continuous spatio-temporal displacement fields, filling voids at critical sites. The model was validated and achieved an overall R² (0.907), ρ (0.947), per-map R² ≥ 0.807 with RMSE ≤ 9.99, and a ROC-AUC of 0.91. It also outperformed the six compared baseline models (IDW, KNN, RF, XGBoost, MLP, simple-NN) in both RMSE and R². By combining observed LOS values with 24 covariates in the proposed model, it delivers physically consistent gap-filling and enables continuous, high-resolution landslide monitoring in radar-challenged mountainous terrain. Full article