Search Results (14,638)

Background/Objectives. Radiomics is an emerging imaging-based tool that enhances lesion characterization beyond conventional diagnostic approaches. Its potential in evaluating osteolytic lesions of the jaws lies in improving discrimination between benign and malignant entities. This study aimed at developing a predictive model to identify radiomic features capable of distinguishing benign from malignant lesions. Methods. Subjects with preoperative CT or CBCT and histopathological confirmation were included. A pilot cohort was used for feature selection via LASSO regression, which ranked features by frequency and absolute coefficient. Malignancy was coded as class 1, benign lesions as class 0. Positive coefficients indicated association with malignancy, while negative coefficients with benign characteristics. The most stable features were initially trained on the pilot cohort and then validated on an independent test set through machine learning classifiers as LASSO, support vector machine, artificial neural network, random forest e XGboost. Results. The sample comprised 69 subjects (pilot cohort = 57, test cohort = 12). The predictors selected from LASSO regression were: DifferenceEntropy_GLCM (−0.768), CenterOfMassShift_MORPHOLOGICAL (−1.390), INTENSITY-HISTOGRAM_MaximumHistogramGradientGrayLevel (1.139), GLRLM_ShortRunLowGrayLevelEmphasis (−0.742), and Maximum3DDiameter_MORPHOLOGICAL (0.932). As for model performance on test, LASSO achieved the best performance (AUC 0.83), with perfect specificity and sensitivity of 0.71. SVM showed good AUC but poor sensitivity, while random forest and XGBoost performed poorly (AUC 0.57 and 0.37, respectively). Conclusions. The LASSO model proved to be a transparent and robust classifier, suitable for both feature selection and external validation. The selected features demonstrated strong discriminative ability, supporting the potential of radiomics in improving lesion assessment and guiding clinical decision-making. Full article

The large-scale integration of wind energy introduces increased uncertainty and variability in modern power systems, with direct implications for both system design and operation. In addressing similar aspects, energy storage plays a pivotal role as a key source of system flexibility. However, the design and sizing of storage systems remain challenging, especially under conditions of increased uncertainty. In this context, the present study proposes an alternative methodological framework, based on an inverse sizing pathway, i.e., from operations to design. More specifically, the uncertainty embedded in day-ahead forecasting of residual errors, associated with wind power generation and load demand, is currently exploited as a design-relevant signal, while energy storage is treated explicitly as a risk-hedging mechanism. Forecasting residuals spanning a year of operation are incorporated in the problem through probabilistic modeling, leading to the generation of trajectories that correspond to different risk levels and are managed as design scenarios. Regarding the modeling of uncertainties, the study examines two different strategies, namely a global modeling approach and a k-means clustering strategy. Accordingly, by mapping the interplay between storage capacity, uncertainty levels (or risk tolerance), achieved RES shares and system-level costs, we highlight the role of energy storage as a risk-hedging entity rather than merely a means of energy balancing. Our results to that end demonstrate that the achieved shares of RES exhibit increased sensitivity, even within constrained regions of wind power variation, while storage capacity features distinct zones of hedging value and hedging saturation effects emerging beyond certain storage levels. Moreover, evaluation of the two modeling strategies reflects on their complementary character, with the global modeling approach ensuring continuity and the clustering strategy capturing local asymmetries within different operational regimes. In conclusion, the methodology presented in this study bridges the gap between operational forecasting and long-term system design, offering a risk-aware framework for storage sizing, grounded in actual operational signals rather than relying on stationary historical data and relevant scenarios. Full article

Image-based AI offers a low-cost alternative to traditional turbidity sensors in farm ponds, yet the prevailing shift toward Vision Transformers (ViTs) critically overlooks two field realities: the chronic scarcity of annotated data (Small Data) and the strict computational limits of edge hardware. This study presents a frugal computer vision framework that challenges the need for complex architectures in environmental screening. By systematically benchmarking six deep learning models across a calibrated high-turbidity dataset (200–800 NTU, 700 images) under standardized capture conditions, we demonstrate that traditional Convolutional Neural Networks (CNNs) possess a crucial inductive bias for this task. Specifically, ResNet-50 significantly outperformed modern ViTs in both accuracy (96.3% vs. 80.0%) and data efficiency, effectively capturing spatial scattering patterns without the massive data requirements that hindered transformer convergence. Deployed on a resource-constrained Raspberry Pi 4, the CNN-based system achieved an inference latency of 46 ms, demonstrated in an initial hardware-in-the-loop field proof-of-concept (82.4% agreement under baseline, calm-weather conditions, $n=17$). This edge-native approach not only provides actionable spatial turbidity maps to guide on-farm filtration and livestock management decisions but also establishes a critical architectural baseline: under controlled capture protocols, mature CNNs consistently outperform ViTs, establishing them as the optimal architecture for frugal, small-data agricultural Internet of Things (IoT) deployments. Full article

Accurate prediction of syngas composition is essential for process design, optimization, and scale-up, yet it remains challenging due to interactions among operating conditions, biomass properties, and chemical reactions. This study used a database of 450 experimental observations spanning a wide range of biomass feedstocks and operating conditions to compare the predictive performance of Aspen Plus simulations and Machine Learning models in estimating the concentrations of CO, CO₂, H₂, and CH₄ in syngas. Aspen Plus was used to simulate the 4 stages of the biomass gasification process under different operating conditions, with special focus on the three reactor modules (RPlug, RGibbs, and REquil) modeling the last two stages. In parallel, Machine Learning models using four regression algorithms (XGBoost, Support Vector Machines, Random Forest and Artificial Neural Networks), with different preprocessing and data-splitting strategies, were evaluated for predicting syngas composition. The best Machine Learning models achieved R² values of 0.753 (CO), 0.866 (CO₂), 0.879 (H₂) and 0.734 (CH₄) on the test set. These results outperformed the Aspen Plus approach and highlight the potential of Machine Learning models as complementary or alternative tools for modelling biomass gasification. Shapley Additive Explanation analysis identified the most influential input variables, revealing key roles for the steam-to-biomass ratio and the equivalence ratio in predicting syngas composition. This study demonstrates that existing Aspen Plus simulation models require further development to improve performance metrics across a wide range of biomass feedstocks and operating conditions. Full article

This research paper demonstrates how to manage Caputo fractional neutral integro-differential equations which include both integral and nonlinear elements through a unified framework that models dynamic systems with memory-based dynamics. The research establishes sufficient conditions for controllability through fixed point theory in a Banach space framework which requires particular assumptions while the study focuses on the ${\mathfrak{K}}_1<1$ condition which leads to the existence of a controllable solution. The proposed criteria are demonstrated through a numerical example which tests the theoretical results. The real-world case study uses artificial neural network (ANN) technology to predict Litecoin prices through the application of the fractional controllability model which analyzes historical financial data. The hybrid framework enables precise forecasting of nonlinear time series because it combines fractional calculus mathematical principles with ANN learning abilities. The proposed method demonstrates its predictive efficiency. The method shows robust performance through experimental results using cross-validation and performance metrics. The proposed model demonstrates competitive performance while providing additional advantages such as incorporation of memory effects and theoretical controllability. The research establishes a novel connection between fractional dynamical systems and machine learning which serves as an essential tool for studying complicated systems in theoretical research and practical applications. Full article

In-cylinder pressure is a key parameter for evaluating combustion processes and engine performance in spark-ignition engines. However, acquiring high-resolution pressure data over a wide range of operating conditions, particularly under varying spark advance (SA), is costly and technically challenging, which limits its practical application. To address this issue, this study proposes two artificial neural network (ANN)-based methods for in-cylinder pressure reconstruction using data from a three-cylinder gasoline engine under different spark advance conditions. Both methods employ crank angle and spark advance as input features. The first method (ANN-P) directly predicts the in-cylinder pressure profile, achieving a coefficient of determination (R²) exceeding 0.99 on both training and validation datasets, with a root mean square error (RMSE) below 0.13 bar. The model accurately reproduces the pressure evolution throughout the compression, combustion, and expansion processes and enables reliable estimation of indicated mean effective pressure (IMEP). The second method (ANN-HRR) adopts an indirect strategy by first predicting the heat release rate (HRR) and subsequently reconstructing the pressure trace through thermodynamic integration based on a single-zone model. This approach avoids error amplification associated with numerical differentiation and demonstrates improved accuracy in predicting combustion phasing metrics, such as CA10 and CA50. The results indicate that both methods effectively capture the influence of spark timing on combustion characteristics and peak pressure. While ANN-P provides higher accuracy in pressure reconstruction, ANN-HRR offers superior performance in characterizing combustion features. Overall, this study presents a cost-effective and accurate framework for combustion diagnostics, performance calibration, and control optimization of gasoline engines. Full article

Diabetic retinopathy represents one of the leading causes of blindness worldwide, making early diagnosis essential for effective clinical intervention. We propose an explainable method aimed at automatically identifying the severity levels of diabetic retinopathy in retinal images using deep learning. The proposed method considers several convolutional neural network architectures, i.e., VGG16, StandardCNN, ResNet, CustomCNN, EfficientNet, MobileNet, and a novel architecture, i.e., FGNet, specifically designed and developed by the authors for diabetic retinopathy detection. The proposed network achieves an accuracy of 0.75 when trained for 10 epochs and 0.71 for 20 epochs. Explainability behind model prediction is further supported through Gradient-weighted Class Activation Mapping, providing visual insight into the learned decision-making process and potentially supporting early clinical assessment. Full article

To meet the dual requirements of selectivity and rapidity in fuse-based short-circuit protection for shipboard DC Integrated Power Systems (DC IPS), this paper proposes a novel coordination method. This approach employs an artificial neural network (ANN) to map the inherent time–current characteristic (TCC) curves of all fuses onto a unified time–current coordinate plane. Protection selectivity is then evaluated based on the relative positions of these curves, and by prioritizing fuses with shorter operating times, both selectivity and rapid fault clearance are achieved. Furthermore, through a mathematical analysis of the current relationships between faulted and non-faulted distribution circuits, the ANN is formulated to require only current and time data while maintaining robustness to moderate variations in short-circuit transition resistance. The effectiveness of the proposed method is validated using DC IPS cases of a hybrid passenger vessel and a pure electric sightseeing vessel. Compared with conventional coordination methods, the proposed method simultaneously accounts for the TCCs of protective devices and the influence of transition resistance on short-circuit current behavior. The case study results demonstrate that the proposed method achieves both selective and rapid protection, and shows strong potential for broader application in the coordination of multi-source DC power systems. Full article

Accelerated urbanization in Ulaanbaatar, Mongolia, has driven substantial changes in Land Use and Land Cover (LULC), threatening sustainable urban ecosystems. This study investigates historical LULC dynamics (2000–2021) and simulates future expansion scenarios through 2050 using a hybrid Machine Learning (ML) and Cellular Automata-Artificial Neural Network (CA-ANN) approach. Multi-temporal classification was performed using Support Vector Machine (SVM) and Random Forest (RF) algorithms. Both classifiers demonstrated high and comparable accuracy; SVM achieved an average Kappa coefficient of 0.8939 while RF achieved 0.8917, a marginal difference that should be interpreted with caution. Change detection analysis revealed a continuous expansion of built-up areas at the expense of dense forest and grassland, a trend driven largely by accessibility factors. Future projections indicate that even as the rate of urbanization may slow, encroachment on green spaces will persist without policy intervention. This research presents a replicable methodological workflow for monitoring urban sprawl and provides evidence to inform sustainable land management and reforestation strategies in rapidly developing urban regions. Full article

Concurrent with the rising consumption of ultra-processed, high-calorie diets and the decline in physical activity, obesity and related cardiovascular conditions among young adults have continued to increase, becoming an important global public health concern. This study integrates non-invasive Internet of Things (IoT) sensing devices, including the TERUMO ES-P2000 blood pressure monitor (Terumo Corp., Tokyo, Japan) and the PhysioFlow PF07 Enduro cardiac hemodynamic analyzer (Manatec Biomedical, Poissy, France), with an artificial neural network (ANN) for cardiac index (CI) prediction. Through appropriate data preprocessing and model training strategies, the generalization ability and stability of the proposed CI prediction model were significantly enhanced. Experimental results demonstrate that, when using three physiological parameters as input, the ANN achieved a classification accuracy of 97.78%, substantially outperforming traditional approaches. Even under two-parameter input conditions, the model maintained strong predictive performance. These findings confirm the effectiveness and practical potential of the proposed framework for real-time, non-invasive CI assessment. Moreover, this research has received rigorous assessment and approval from the Institutional Review Board (IRB) under application number 202501987B0. Full article

Background: This study investigates the impact of anatomically constrained preprocessing and deep learning architecture selection on benign versus malignant breast lesion classification in contrast-enhanced mammography (CEM), with the goal of improving robustness and clinical reliability across heterogeneous data sources. Methods: In this retrospective multicenter study, CEM images from 300 patients (314 lesions) were combined with 1003 publicly available CEM images, yielding a total of 1120 breast cases. Automatic breast segmentation was performed using the LIBRA framework to generate breast-mask images. Eleven deep learning models, including classical convolutional neural networks, attention-based networks, hybrid convolutional neural networks (CNNs), Transformer architectures, and mammography-specific models, were trained and evaluated using both original DICOM images and breast-mask inputs. Performance was assessed using accuracy, balanced accuracy, sensitivity, specificity, AUROC, and AUPRC on cross-validation and independent test sets. Hyperparameter optimization was conducted for the best-performing architecture. Results: Models trained on breast-mask images consistently outperformed those trained on original DICOM images across all architectures and metrics, with AUROC improvements ranging from +0.06 to +0.21. Among all models, ResNet50 trained on breast-mask images achieved the best performance (AUROC = 0.931; AUPRC = 0.933; balanced accuracy = 0.834), further improved after optimization (balanced accuracy = 0.886; sensitivity = 0.842; specificity = 0.930). Classical CNN architectures demonstrated performance comparable to or exceeding that of more complex hybrid CNN–Transformer models when anatomically focused preprocessing and rigorous optimization were applied. Conclusions: Anatomically constrained preprocessing through breast-mask segmentation substantially enhances deep learning performance and stability in CEM-based breast lesion classification. These findings indicate that input representation quality and training optimization are critical determinants of clinically relevant performance, often outweighing architectural complexity, and may support more reliable AI-assisted decision support in CEM workflows. Full article

Short-chain fatty acids (SCFAs) are key biomarkers of gut microbiota activity; however, routine quantification in fecal samples relies largely on chromatography, which is instrument-intensive and throughput-limited chromatography techniques. Herein, we present a rapid machine-learning-assisted electroanalysis platform for SCFAs profiling that integrates a disposable three-electrode planar gold chip with voltammetric fingerprinting and artificial neural network (ANN)-based signal decoupling. To generate orthogonal chemical information and improve the discrimination of structurally similar species, a dual pretreatment strategy combining acid-catalyzed esterification and alkaline dissociation was employed prior to electrochemical analyses. Differential pulse voltammetry (DPV) and cyclic voltammetry (CV) were employed to acquire high-dimensional fingerprints, from which current-, potential-, and area-based descriptors were extracted using a cross-information feature strategy. A hierarchical modeling framework improved total SCFAs prediction by incorporating ANN-predicted propionate and butyrate concentrations as auxiliary inputs. While linear calibration was achievable in standard mixtures, direct linear models performed poorly in real fecal matrices due to strong sample-dependent matrix interference. In contrast, the ANN captured nonlinear relationships among multifeature inputs and suppressed matrix effects. Validation against gas chromatography–mass spectrometry in an independent fecal test cohort (n = 30) demonstrated excellent agreement and low prediction errors, with mean absolute error/root mean square error values of 0.063/0.072 mM (propionic acid), 0.029/0.034 mM (butyric acid), and 0.135/0.202 mM (total SCFAs). The DPV/CV acquisition requires only minutes per sample, whereas pretreatment takes 1~3 h depending on the target route but can be performed in parallel for batch processing; thus, overall throughput is determined mainly by batch pretreatment rather than per-sample instrument time. This electrochemical–ANN workflow provides a portable, high-throughput alternative to chromatography for fecal SCFAs profiling in clinical screening and microbiome research. Full article

Vector–matrix multiplication (VMM), implemented through multiply–accumulate (MAC) operations, represents the dominant computational primitive in many artificial intelligence (AI) workloads. When executed on conventional von Neumann architectures, VMM operations suffer from important energy consumption and latency due to the separation between memory and processing units. To overcome these limitations, crossbar arrays built from Resistive Random Access Memory (RRAM) cells have been proposed for accelerating VMM computations. In this work, we investigate the key optimization trade-offs associated with implementing RRAM-based neural networks for classification applications. A simple two-layer neural network is first defined and trained in software to generate the weight matrices and bias parameters. Next, three hardware implementation scenarios are evaluated depending on whether negative floating-point numbers are used: Positive Weights Only (PWO), Positive and Negative Weights Only (PNWO), and Positive and Negative Weights with Biases (PNWB). The different implementations are analyzed at the hardware level by examining classification accuracy, energy efficiency, latency, and area overhead. The study further incorporates important RRAM limitations, including restricted conductance range and device variability. Hardware results show that the PWO scenario offers the lowest energy consumption (189 fJ/MAC) and area overhead but results in the lowest accuracy. PNWO and PNWB significantly improve accuracy (+177% and +180%) but increase energy consumption (+63% and +87%) and area (×2 and ×2.1). Under variability effects, PWO achieves better accuracy (94.65%), followed by PNWO (93.11%) and PNWB (92.11%). Full article

Spiking Neural Networks (SNNs) executed on neuromorphic hardware promise energy-efficient, low-latency inference well-suited to edge deployment in size, weight, and power-constrained environments such as autonomous vehicles, wearable devices, and unmanned aerial platforms. However, a coherent research pathway to deployment of neuromorphic devices remains elusive. This paper presents a structured review and position on the state of SNN-based vision across four interconnected dimensions: network architectures, training methodologies, event-based datasets and simulation techniques, and neuromorphic computing hardware. We survey the evolution from shallow convolutional SNNs to spiking Transformers and hybrid designs which leverage the advantages of SNNs and conventional artificial neural networks. We also examine surrogate gradient training and ANN-to-SNN conversion approaches, catalogue real-world and simulated event-based datasets, and assess the landscape of neuromorphic platforms ranging from rigid mixed-signal architectures to fully-configurable digital systems. Our analysis reveals that while each area has matured considerably in isolation, critical integration challenges persist. In particular, event-based datasets remain scarce and lack standardisation, training methodologies introduce systematic gaps relative to deployment hardware, and access to neuromorphic platforms is restricted by proprietary toolchains and limited development kit availability. We conclude that bridging these integration gaps, rather than advancing individual components alone, represents the most important and least addressed work required to realise the potential of SNN-based vision at the edge. Full article

Clothing classification by occasion is an important area in computer vision and artificial intelligence (AI). This task is particularly challenging because of the subtle visual similarities among clothing categories such as formal, party, and casual attire. Variations in color, fabric, patterns, and lighting further increase the complexity of this task. To address this challenge, we used the Fashionpedia dataset to create a balanced subset of 15,000 images. Specifically, we adopted two different methods for labeling these images: automated classification, which relies on category identifications (IDs) and components, and manual labeling performed by human annotators. We then implemented our preprocessing pipeline, which includes several steps: resizing, image normalization, background removal using segmentation masks, and class balancing. We benchmarked traditional models, including artificial neural networks (ANNs), support vector machines (SVMs), and k-nearest neighbors (KNNs), which use a histogram of oriented gradient (HOG) features, as well as deep learning models such as convolutional neural networks (CNNs), the Visual Geometry Group 16 (VGG16) model utilizing transfer learning, and the vision transformer (ViT) model, all evaluated using identical data splits and preprocessing procedures. The traditional models achieved moderate accuracy, ranging from 54% to 66%. In contrast, the ViT model achieved an accuracy of 81.78% with automated classification and 98.09% with manual labeling. This indicates that a higher label accuracy, along with the preprocessing steps used, significantly enhances the performance. Together, these factors improve the effectiveness of ViT in context-aware apparel classification and establish a reliable baseline for future research. Full article