Artificial Neural Network Research Articles (Page 1)

Automatic recognition of surgical workflows is a complex yet essential task of context-aware systems in the operating room. However, achieving high accuracy in phase recognition remains a challenge due to the complexity of surgical procedures. While recent deep learning models have made significant progress, individual models often exhibit limitations-some may excel at capturing spatial features, while others are better at modeling temporal dependencies or handling class imbalance. This study investigates the use of ensemble learning to combine the complementary strengths of diverse architectures, aiming to mitigate individual model weaknesses and improve performance in surgical phase recognition using the Cholec80 dataset. A variety of advanced deep learning architectures was integrated into a single ensemble. Models were carefully selected and tuned to ensure diversity, resulting in a final set of 15 unique ensembles. Ensemble strategies were explored to determine the most effective method for combining the distinct models. The results demonstrated that ensemble learning significantly improved performance. Among the ensemble strategies tested, majority voting achieved the highest F1-score, followed by the proposed artificial neural network StackingNet. Ensembles with high model diversity showed superior performance compared to those with lower diversity. The optimal ensemble configuration integrated top-performing models from different architectures, leading to improvements in accuracy, F1-score, and Jaccard Index by 1.48%, 3.68%, and 5.43%, respectively, compared to the best individual models. This study demonstrates that ensemble learning can substantially enhance surgical phase recognition by leveraging the complementary strengths of diverse deep learning models. Ensemble size, diversity, and meta-model selection were identified as key factors influencing performance. The resulting improvements translate into clinically meaningful benefits by enabling more reliable context-aware guidance, reducing misclassifications during critical phases, and improving surgeons' trust in artificial intelligence(AI) systems.

The application of machine learning in the evaluation of urinary tract infections incidence in patients in a Nursing and Treatment Facility.

Accurately distinguishing benign from malignant adrenal lesions remains a clinical challenge, especially in oncology patients with indeterminate imaging findings. This study aimed to develop and interpret machine learning (ML) models for classifying adrenal lesions based on 18F-FDG PET/CT imaging and clinical parameters. A retrospective cohort of 255 patients undergoing 18F-FDG PET/CT was analyzed. Imaging features-including adrenal SUVmax, SUVpeak, tumor diameter, CT attenuation, and tumor-to-liver SUVmax ratio (T/L SUVmax)-along with clinical variables were extracted. Two classification tasks were constructed: (1) differentiation of benign and malignant adrenal lesions; and (2) subtyping of malignant lesions into lung cancer metastases or lymphoma. Seven ML models were trained and evaluated using 10-fold cross-validation. SHAP (SHapley Additive exPlanations) analysis was applied to elucidate feature contributions. For the benign/malignant classification, ensemble models (Random Forest, Bagging, XGBoost) achieved outstanding performance (AUC > 0.99), with Bagging yielding 100% recall. T/L SUVmax, adrenal SUVmax, and CT attenuation emerged as top predictors. In malignancy subtyping, the artificial neural network (ANN) attained the highest AUC (0.887) and F1-score (0.851). SHAP analysis highlighted distinct metabolic patterns, with lymphoma showing higher SUVmax and T/L ratios, and lung metastases associated with higher CT values. Machine learning models based on PET/CT-derived features enable highly accurate and interpretable classification of adrenal lesions. Integrating metabolic and anatomical parameters improves diagnostic precision, while SHAP analysis offers clinical transparency, supporting personalized decision-making in adrenal lesion management.

Accurate and timely Fault Detection (FD) remains a fundamental challenge in transmission systems due to the dynamic operating conditions of modern power grids, the diversity of fault types, and fast reclosure events. Conventional fault diagnosis techniques are often constrained by assumptions of static load profiles, dependence on high-rate sampling, or extensive data requirements, which hinder their real-time deployment. To address these limitations, this study proposes a novel Artificial Neural Network (ANN)-based framework for Fault Classification (FC) and localization using only bus voltage measurements. The distinctive contribution lies in the use of physically meaningful features rather than purely statistical ones, thereby ensuring robustness and interpretability. Simulation studies conducted on the IEEE 14-bus system show that the suggested method achieves FC accuracy above 98% and localizes faults with an error margin of less than 2% of line length, outperforming existing data-driven techniques. Furthermore, a new Phasor Measurement Unit (PMU) placement strategy is introduced, which improves observability while reducing hardware requirements, enabling reliable performance even under severely compromised measurement conditions. Achieving 0.89783 accuracy and notable reductions, ANN showed up to 5.66% higher accuracy and over 30% lower error rates, confirming its superior FC capability. These findings underline the potential of the suggested methodology as a scalable and resilient solution for real-time fault management in modern transmission networks.

Prosopis cineraria (L.) Druce, a keystone species in hot arid and semi-arid ecosystems of India, contributes significantly to ecological stabilization, carbon sequestration, and traditional agroforestry systems. This study employs an integrated geospatial and statistical framework to assess the spatial dominance and habitat suitability of P. cineraria across diverse ecological gradients. Using field-based relative importance value (RIV) data from 322 sites, inverse distance weighting (IDW) was applied to interpolate species dominance patterns. Ensemble species distribution modelling (ESDM) was implemented with seven machine learning algorithms (e.g., random forest, MaxEnt, artificial neural network) and environmental predictors-bioclimatic, edaphic, topographic, and anthropogenic-to delineate habitat suitability. Results indicated that bioclimatic variables, particularly precipitation seasonality (Bio15) and temperature extremes (Bio5, Bio6), were the most influential, with random forest achieving the highest predictive accuracy (AUC = 0.98; TSS = 0.89). IDW interpolation identified strong P. cineraria dominance in western-central districts (Jodhpur, Pali, Nagaur), while ESDM projected ~ 428,407 km2 of suitable habitat, largely overlapping with field-derived hotspots. Niche hypervolume analysis revealed a broad core niche but a more restricted realized distribution, constrained by human pressures and environmental factors. These findings provide evidence that could guide zone-specific conservation strategies, including the prioritization of high-RIV areas for in situ protection and ecological restoration in low-dominance regions. While the results highlight the ecological importance of P. cineraria, further field validation and socio-economic assessments are recommended before direct policy application.

ABSTRACT Additive manufacturing (AM) of Ti-6Al-4V often yields high surface roughness (Ra > 10 µm), requiring post-processing for aerospace and biomedical use. This study proposes a lightweight physics-informed artificial neural network (ANN) trained on 20 experimental and ~5,000 surrogate samples derived from an overlap-adjusted energy–roughness relation. Incorporating both process parameters and physics-guided descriptors, the model achieved R² ≈ 0.99 with RMSE < 0.1 µm, predicting polishing outcomes with minimal data. The framework demonstrates that physics-assisted AI can reduce experimental trials from >30 to ~5, enabling sustainable, data-efficient optimization for intelligent laser polishing of AM components.

Manual sperm morphology assessment is recognized as a challenging parameter to standardize due to its subjective nature, often reliant on the operator's expertise. Our study aims to address this issue by developing a predictive model for sperm morphological evaluation utilizing artificial neural networks trained on the SMD/MSS(Sperm Morphology Dataset/Medical School of Sfax) dataset enhanced through data augmentation techniques. A total of 1000 images of individual spermatozoa were acquired using the MMC CASA system. Expert classification, based on the modified David classification for sperm morphology, was conducted by three experts. Data augmentation techniques were employed to augment the database. Subsequently, an algorithm utilizing a Convolutional Neural Network (CNN) was created, trained, and tested for spermatozoa classification. SMD/MSS dataset, initially comprised 1000 images and extended to 6035 images after the application of data augmentation techniques. The deep learning model produced satisfactory results, with an accuracy ranging from 55% to 92%. Our deep learning approach for sperm morphology classification enables the automation, standardization, and acceleration of semen analysis. It underscores the significance of artificial intelligence in medical applications, with a particular focus on its impact in the field of reproductive biology.

Older adults with head and neck squamous cell carcinoma (HNSCC) are underrepresented in clinical trials, limiting evidence-based treatment decisions. Artificial neural networks (ANNs) have demonstrated the ability to personalize treatment recommendations using patient-specific characteristics. To develop and externally validate ANNs for overall survival (OS) and progression-free survival (PFS) in older adults with HNSCC undergoing definitive chemoradiation. This international cohort study included retrospective clinical data from 19 academic cancer centers across Germany, Switzerland, Czech Republic, Cyprus, and the US from the SENIOR registry. ANNs were developed and validated using data from patients 65 years and older with locoregionally advanced HNSCC treated with definitive chemoradiation. Exclusion criteria included induction or adjuvant chemotherapy, history of head and neck cancer, and metastatic disease at treatment initiation. Data were collected from January 2021 to December 2023, and data were analyzed from December 2023 to April 2025. All patients received definitive radiotherapy with concurrent systemic therapy between 2005 and 2019. OS and PFS were predicted using 2 separate ANN models. Patients were classified as high or low risk based on median prediction thresholds. Model performance was assessed with receiver operating characteristic (ROC) area under the curve (AUC) and precision recall AUC. Model explainability was assessed with Shapley additive explanations values. Of 898 patients included in the OS analysis (738 in training cohort and 160 in testing cohort), 665 (74.1%) were male, and the median (IQR) age was 71 (68-76) years. Of 945 included in the PFS analysis (770 in training cohort and 175 in testing cohort), 696 (73.7%) were male, and the median (IQR) age was 71 (68-76) years. The OS ANN stratified patients into high-risk and low-risk groups with significantly different survival, achieving an ROC-AUC of 0.68 (95% CI, 0.60-0.76). The PFS ANN showed similar discrimination, with an ROC-AUC of 0.64 (95% CI, 0.56-0.72). Human papillomavirus status, kidney function (estimated glomerular filtration rate), Eastern Cooperative Oncology Group Performance Status score, and nodal classification were among the most predictive features. In this study, ANN-based models using routine clinical data effectively stratified older adults with HNSCC into prognostic groups. Integration of ANNs into clinical workflows could support personalized treatment decisions for this vulnerable population.

Objectives: To investigate the effect of lime and quarry dust, both individually and in combination, on the geotechnical properties of Puducherry inland clay using Artificial Neural Network (ANN) modelling. Methods: Clay samples were treated individually with varying proportions of lime and QD (7%, 14%, 21%, and 28% by dry weight) as well as in combination to assess improvements in geotechnical behaviour. Laboratory tests, including Atterberg limits, Free Swell Index (FSI), compaction characteristics, direct shear test, and Unconfined Compressive Strength (UCS), were conducted to evaluate changes in soil properties. To forecast the parameters of stabilized soil, the ANN Simulink model was simulated using a neural network fitting tool after training. Findings: The experimental findings showed that the plasticity index was reduced by 25% and 37% with lime and QD stabilization, respectively. Lime- and QD-stabilized clay reduced the optimum moisture content by 20% and 35%, while maximum dry density increased by 10% and 35%, respectively. Cohesion was reduced by 28% in both cases. Regarding UCS, lime-stabilized clay showed an increase up to 21% addition before declining, whereas QD-stabilized clay showed continuous strength gain. FSI decreased by 35% and 28% in lime- and QD-stabilized clay, respectively. The combination of both lime and QD showed superior performance due to synergistic effects. ANN modelling with statistical indicators (R2: 0.95–0.99, RMSE &lt;30%, MAPE &lt;20%) effectively predicted geotechnical properties with less than 25% error. Novelty: Utilizing QD provides a sustainable alternative to lime while improving the geotechnical performance of clay soil comparable to lime. Using QD as a stabilizer also helps in addressing environmental waste disposal issues. Keywords: Stabilization, Artificial neural network, Lime, Quarry dust, Simulink model

Abstract In the last few years, hybrid photovoltaic-thermal (PVT) collectors have become an attractive subject of research because of their ability to convert solar radiation into both electrical and thermal energies. Nonlinear relationships among their control variables, such as design parameters, climatic conditions, heat transfer fluid type, and electrical and thermal performances, require advanced modeling methodologies. This review examines the application of machine learning, especially artificial neural networks (ANNs), in photovoltaic-thermal systems. The paper begins with the state of the art in PVT systems, covering types, applications, recent developments, and more. It then presents a detailed analysis of ANN models, including the General Regression Neural Network (GRNN), Elman Neural Network (ENN), Radial Basis Function Network (RBFN), Multilayer Perceptron (MLP), and Adaptive Neuro-Fuzzy Inference Systems (ANFIS). Furthermore, the review highlights the roles that these models have played in enhancing PVT system performance in previous studies and includes a literature analysis to identify research gaps in this field. According to the literature, ANNs are valuable tools for predicting and optimizing the performance of PVT collectors; however, further exploration of alternative ANN models in novel PVT designs, combined with optimization algorithms, is necessary.&amp;#xD;

ABSTRACT Accurate seepage flow prediction is essential for risk assessment of earth-rockfill dams. This study incorporates convolutional neural network (CNN) with long short-term memory (LSTM), taking into account the advantages of both feature recognition and time series processing, and the CNN-LSTM model is first introduced to predict the dam seepage flow. Afterwards, the efficacy of the developed model is verified through nearly 20 years of monitoring data from two dams at Shenzhen Reservoir. Furthermore, another five well-developed models including support vector regression (SVR), adaptive boosting, artificial neural network, recurrent neural network, and LSTM models are also discussed. The hyperparametric optimisation of these six models is discussed as well. Results show that the type of kernel function significantly influences the accuracy of the SVR model, where the radial basis kernel function performs best. For the neural network model, more attention should be drawn to the choice of hidden nodes over other hyperparameters. In general, the prediction accuracy rankings of the five comparison models differ between the two dams, indicating that the model performance largely depends on the site characteristics. The CNN-LSTM model demonstrates consistently high predictive accuracy, suggesting its potential as a reliable tool for dam seepage flow forecasting.

Indoor localization based on range measurements in wireless sensor networks involves nonlinear measurement models and is susceptible to non-Gaussian noise, which is associated with complex indoor environments. While particle filters (PFs) are well-suited to such systems, they suffer from sample impoverishment, whereby a diminishing sample diversity leads to failures under various conditions. Hence, this paper proposes a novel hybrid localization algorithm that combines a PF, a finite impulse response (FIR) filter, and an artificial neural network. In the proposed algorithm, the PF serves as the main filter for localization because it performs excellently in nonlinear, non-Gaussian systems under normal operation. The neural network is trained to classify whether the system is operating normally or experiencing a failure, based on estimation results from the PF. If a PF failure is detected by the network, the assisting FIR filter is activated to recover the PF from failures. The localization accuracy and reliability of the proposed neural network-aided hybrid particle/FIR filter are confirmed via comparisons with existing algorithms.

A Physical Unclonable Function (PUF) is a lightweight hardware security primitive with diverse applications in Internet of Things (IoT) security. However, the ongoing advancements in machine learning (ML) technologies have significantly impacted the security of PUFs. This paper introduces a dual-state hybrid PUF (DH PUF) that dynamically switches the back-end circuit between a ring oscillator (RO) array and a path selector array based on real-time feedback from a nonlinear front-end circuit. Unlike conventional dual-mode PUFs controlled by static challenges, our design introduces a reverse-order obfuscation mechanism that disrupts the linear correlation between challenges and responses with minimal hardware overhead. The 64-stage DH PUF was implemented on a Xilinx Artix-7 FPGA, and experimental results indicate that the design effectively withstands machine learning attacks. The prediction rates for logistic regression (LR), covariance matrix-adaptive evolutionary strategy (CMA-ES), support vector machine (SVM), and artificial neural network (ANN), deep neural network (DNN) and Multilayer Perceptron (MLP) are all approximately 50%. Additionally, the structure demonstrates a uniqueness of 49.98%, uniformity of 51.32%, and reliability of about 98%. Physically unclonable function, Hardware security, Machine learning, Field-programmable gate array.

In agricultural systems, soil pH and electrical conductivity (EC) are crucial chemical properties that directly affect nutrient availability and microbial activity, but the challenging environment of the Peruvian Andes has limited research on their estimation. This study aimed to develop an ensemble learning method to predict soil pH and EC in Andean agroecosystems using environmental predictors. By using simple and weighted averaging, we developed a heterogeneous ensemble learning approach that integrates machine learning (ML) algorithms, including Support Vector Machine (SVM), Artificial Neural Network (ANN), Random Forest (RF), and Extreme Gradient Boosting (XGBoost). The weighted ensemble assigns weights to models based on their predictive accuracy, measured by R² from spatial cross-validation. Spatial patterns are noticeable, and pH displays greater spatial clustering than EC. Elevation was the most important predictor in ML models for both parameters. Ensemble models significantly outperformed individual models, with the weighted ensemble achieving R² &amp;gt;0.93 and reducing RMSE by approximately 72%. Among standalone models, RF and XGBoost performed best for pH, while SVM performed the best for EC. ANN models were the least effective. Uncertainty analysis indicated high confidence in pH predictions but moderate to high uncertainty in EC predictions, suggesting that EC is more challenging to predict. Ensemble models with optimized weighting provide robust and accurate mapping of spatially autocorrelated soil properties. The high-confidence pH maps are reliable for soil management decisions, while EC predictions, though more uncertain, effectively identify priority areas for future sampling and investigation.

Bathing water quality (BWQ) monitoring and prediction are essential to safeguard public health by informing bathers about the risk of exposure to faecal indicator bacteria (FIBs). Traditional monitoring approaches, such as manual sampling and laboratory analysis, while effective, are often constrained by delayed reporting, limited spatial and temporal coverage, and high operational costs. The integration of artificial intelligence (AI), particularly machine learning (ML), with automated data sources such as environmental sensors and satellite imagery has offered novel predictive and real-time monitoring opportunities in BWQ assessment. This systematic literature review synthesises current research on the application of AI in BWQ assessment, focusing on predictive modelling techniques and remote sensing approaches. Following the PRISMA methodology, 63 relevant studies are reviewed. The review identifies dominant modelling techniques such as Artificial Neural Networks (ANN), Deep Learning (DL), Decision Tree (DT), Random Forest (RF), Multiple Linear Regression (MLR), Support Vector Machine (SVM), and Hybrid and Ensemble Boosting algorithms. The integration of AI with remote sensing platforms such as Google Earth Engine (GEE) has improved the spatial and temporal solution of BWQ monitoring systems. The performance of modelling approaches varied depending on data availability, model flexibility, and integration with alternative data sources like remote sensing. Notable research gaps include short-term faecal pollution prediction and incomplete datasets on key environmental variables, data scarcity, and model interpretability of complex AI models. Emerging trends point towards the potential of near-real-time modelling, Internet of Things (IoT) integration, standardised data protocols, global data sharing, the development of explainable AI models, and integrating remote sensing and cloud-based systems. Future research should prioritise these areas while promoting the integration of AI-driven BWQ systems into public health monitoring and environmental management through multidisciplinary collaboration.

Excavation is a common requirement in engineering construction within rock masses. While excavation volumes are generally limited in road slope projects, they may become substantial in large-scale operations such as deep open pit mines. The interaction between time and cost in excavation processes is strongly controlled by rock mass excavatability, which has been recognized as a key factor in project budgets. Since the 1970s, excavatability assessment has therefore attracted considerable research interest in rock mechanics. In this study, the excavatability cases previously plotted on the Geological Strength Index (GSI) versus Uniaxial Compressive Strength of the Rock Mass (σc_rm) diagram in the literature were improved by employing an Artificial Neural Network (ANN). The ANN approach was used to investigate the boundaries between digger, ripper, and hammer+blasting excavation classes within the available case zones defined by GSI–σc_rm data pairs. The prediction performance of the developed rock mass excavatability chart is highly acceptable, with correct classification rates of 91.1% for blasting+hammer and ripper classes, and 87.2% for the ripper class. Considering GSI and σc_rm as the main input parameters, the proposed ANN-oriented excavatability chart is highly acceptable for preliminary equipment selection during the design stage of surface rock mass excavations, including slope cases.

Line heating processes play a significant role in the fabrication of structural steel components, particularly in industries such as shipbuilding, aerospace, and automotive manufacturing, where dimensional accuracy and minimal defects are critical. Traditional methods, such as the finite element method (FEM) simulations, offer high-fidelity predictions but are hindered by prohibitive computational latency and the need for case-specific re-meshing. This study presents a physics-aware, data-driven neural network that delivers fast, high-fidelity temperature predictions across a broad operating envelope. Each spatiotemporal point is mapped to a one-dimensional feature vector. This vector encodes thermophysical properties, boundary influence factors, heatsource variables, and timing variables. All geometric features are expressed in a path-aligned local coordinate frame, and the inputs are appropriately normalized and nondimensionalized. A lightweight multilayer perceptron (MLP) is trained on FEM-generated induction heating data for steel plates with varying thickness and randomized paths. On a hold-out test set, the model achieves MAE = 0.60 °C, RMSE = 1.27 °C, and R2 = 0.995, with a narrow bootstrapped 99.7% error interval (−0.203 to −0.063 °C). Two independent experiments on an integrated heating and mechanical rolling forming (IHMRF) platform show strong agreement with thermocouple measurements and demonstrate generalization to a plate size not seen during training. Inference is approximately five orders of magnitude (~105) faster than FEM, enabling near-real-time full-field reconstructions or targeted spatiotemporal queries. The approach supports rapid parameter optimization and advances intelligent line heating operations.

Artificial neural network for classifying fracture mechanisms of pure aluminum based on the wavelet transform parameters of acoustic emission signals

A sense of fairness is deeply rooted in human nature, and plays a fundamental role in supporting cooperation. This study investigated the electrophysiological responses to third-party resource allocations and behavioral economics games assessing costly sharing and distributive justice decisions in early and middle childhood across three countries, France, Taiwan, and the United States. To examine the temporal dynamics and cultural differences in the neural development of fairness considerations, both traditional event-related potential and artificial neural network methods were employed. Results demonstrate a marked lack of cross-cultural differences in the electrophysiological profile of fairness yet notable cross-cultural differences in the functional link between electrophysiology and actual distributive behaviors. (PsycInfo Database Record (c) 2025 APA, all rights reserved).

A bstract In holography, flavour probe branes are used to introduce fundamental matter to the AdS/CFT correspondence. At a technical level, the probes are described by extremizing the DBI action and solving the Euler-Lagrange equations of motion. I report on applications of artificial neural networks that allow direct minimization of the regularized DBI action (interpreted as a free energy) without the need to derive and solve the equations of motion. I consider, as examples, magnetic catalysis of chiral symmetry breaking and the meson melting phase transition in the D3/D7 holographic set-up. Finally, I provide a framework which allows the simultaneous learning of the embeddings and the relevant aspects of the dual geometry based on field theory data.