Search Results (2,309)

Resource-limited settings continue to face challenges in the identification of COVID-19, bacterial pneumonia, viral pneumonia, and normal lung conditions because of the overlap of CT appearance and inter-observer variability. We justify a hybrid architecture of deep learning which combines hand-designed descriptors (Histogram of Oriented Gradients, Local Binary Patterns) and a 20-layer Convolutional Neural Network with dual self-attention. Handcrafted features were then trained with Support Vector Machines, and ensemble averaging was used to integrate the results with the CNN. The confidence level of 0.7 was used to mark suspicious cases to be reviewed manually. On a balanced dataset of 14,000 chest CT scans (3500 per class), the model was trained and cross-validated five-fold on a patient-wise basis. It had 97.43% test accuracy and a macro F1-score of 0.97, which was statistically significant compared to standalone CNN (92.0%), ResNet-50 (90.0%), multiscale CNN (94.5%), and ensemble CNN (96.0%). A further 2–3% enhancement was added by the self-attention module that targets the diagnostically salient lung regions. The predictions that were below the confidence limit amounted to only 5 percent, which indicated reliability and clinical usefulness. The framework provides an interpretable and scalable method of diagnosing multiclass lung disease, especially applicable to be deployed in healthcare settings with limited resources. The further development of the work will involve the multi-center validation, optimization of the model, and greater interpretability to be used in the real world. Full article

To improve the safe operation of urban water supply networks and support sustainable water resource management, this study proposes a multi-objective optimization framework for monitoring point placement by integrating pressure-driven analysis (PDA) and the virtual node method (VNM). A PDA-based hydraulic model combined with Wagner’s relationship is employed to overcome the limitations of traditional demand-driven analysis in simulating extreme conditions such as pipe burst events, while the VNM enables efficient representation of burst scenarios without altering network topology. Based on node pressure variations, a binary fault perception matrix is constructed by comparing pressure responses under burst conditions with background noise thresholds to quantify the detectability of pipe burst events by candidate monitoring points. A bi-objective optimization model is then formulated to maximize fault monitoring and minimize the number of monitoring points, and it is solved using the NSGA-III and NSGA-II algorithms. Case studies on the Net3 benchmark network and the real-world Drumchapel network demonstrate that NSGA-III outperforms NSGA-II in terms of convergence performance and spatial perception capability, particularly by reducing spatial redundancy and improving monitoring efficiency under limited monitoring budgets. The proposed framework provides a practical decision-support tool for optimal monitoring point deployment and contributes to the long-term sustainability of urban water supply infrastructure. Full article

Multimodal object detection is currently a research hotspot in computer vision. However, the fusion of visible and infrared modalities inevitably increases computational complexity, making most high-performance detection models difficult to deploy on resource-constrained UAV edge devices. Although pruning and knowledge distillation are widely used for model compression, applying them independently often leads to an unstable accuracy–efficiency trade-off. Therefore, this paper proposes a hybrid lightweight algorithm named SAMKD, which combines selective activation pruning with masked knowledge distillation in a staged manner to improve efficiency while maintaining detection performance. Specifically, the selective activation network pruning model (SAPM) first reduces redundant computation by dynamically adjusting network weights and the activation state of input data to generate a lightweight student network. Then, the mask binary classification knowledge distillation (MBKD) strategy is introduced to compensate for this degradation by guiding the student network to recover missing representation patterns under masked feature learning. Moreover, MBKD reformulates classification logits into multiple foreground–background binary mappings, effectively alleviating the severe foreground–background imbalance commonly observed in UAV aerial imagery. This paper constructs a multimodal UAV aerial imagery object detection dataset, M2UD-18K, which includes 9 types of targets and over 18,000 pairs. Extensive experiments show that SAMKD performs well on the self-constructed M2UD-18K dataset, as well as the public DroneVehicle dataset, achieving a favorable trade-off between detection accuracy and detection speed. Full article

This study presents an edge-based intrusion detection methodology designed to enhance cybersecurity in Internet of Things environments, which remain highly vulnerable to complex attacks. The approach employs an Auxiliary Classifier Generative Adversarial Network capable of classifying network traffic in real-time while simultaneously generating high-fidelity synthetic data within a unified framework. The model is implemented in TensorFlow and deployed on the energy-efficient NVIDIA Jetson Orin Nano, demonstrating the feasibility of executing advanced deep learning models at the edge. Training is conducted on network traffic collected from diverse IoT devices, with preprocessing focused on TCP-based threats. The integration of an auxiliary classifier enables the generation of labeled synthetic samples that mitigate data scarcity and improve supervised learning under imbalanced conditions. Experimental results demonstrate strong detection performance, achieving a precision of 0.89 and a recall of 0.97 using the standard 0.5 decision threshold inherent to the sigmoid-based binary classifier, indicating an effective balance between intrusion detection capability and false-positive reduction, which is critical for reliable operation in IoT scenarios. The generative component enhances data augmentation, robustness, and generalization. These results show that combining generative adversarial learning with edge computing provides a scalable and effective approach for IoT security. Future work will focus on stabilizing training procedures and refining hyperparameters to improve detection performance while maintaining high precision. Full article

The proliferation of Internet of Things (IoT) devices challenges deep learning (DL) deployment due to their limited computational power, while cloud offloading introduces high latency and network strain. Fog computing provides a viable middle ground. We present a resource-aware framework that intelligently partitions DL tasks between fog nodes and the cloud using a novel Binary Search-Inspired Recursive (BSIR) optimization algorithm for rapid, low-overhead decision-making. This is enhanced by a novel module that fine-tunes deployment by analyzing memory at a per-layer level. For true adaptability, a Retrieval-Augmented Generation (RAG) technique consults a knowledge base to dynamically select the best optimization strategy. Our experiments demonstrate dramatic improvements over established metaheuristics. The complete framework boosts memory utilization in fog environments to a remarkable 99%, a substantial leap from the 85.25% achieved by standard algorithms like Genetic Algorithms (GA), Simulated Annealing (SA), and Particle Swarm Optimization (PSO). The enhancement module alone improves these traditional methods by over 13% without added computational cost. Our system consistently operates with a CPU footprint under 3% and makes decisions in fractions of a second, significantly outperforming recent methods in speed and resource efficiency. In contrast, recent DL methods may use 51% CPU and take over 90 s for the same task. This framework effectively reduces cloud dependency, offering a scalable solution for DL in the IoT landscape. Full article

Aiming at the detection challenges caused by the diverse morphology of microcracks in plate heat exchanger sheets, this paper proposes a detection framework that integrates parameter-driven adaptive template generation, binary scale optimization, and feature value threshold segmentation using convolutional networks. First, based on the grayscale characteristics of microcracks, an adaptive template generation model driven by key parameters (width, height, and endpoint grayscale difference) is constructed, obtaining a unique solution by solving the boundary conditions of physical features. Second, to overcome the challenge of microcrack width continuity, a binary scale optimization strategy based on the critical decay ratio k* of the correlation coefficient is designed, enabling the coverage of continuous-width defects with a finite set of templates. Finally, enhanced features are fed into a convolutional network. Utilizing the bimodal characteristic of the feature value distribution, the region corresponding to the extreme values in the top 0.3% before the foreground peak is located using 3σ extreme value statistics, achieving adaptive segmentation to identify defect regions. Evaluation on the self-built microcrack dataset SUT-B1 yielded results of 83.59% recall, 80.55% precision, and an F1 score of 81.98%. This method outperforms small object detection networks, demonstrating its advantage in morphological adaptability for small-sized objects. It also surpasses receptive field optimization modules, proving the necessity of structural optimization. The proposed method demonstrates practicality and scalability in the field of industrial inspection. Full article

Various sensors are increasingly being adopted to support intelligent healthcare systems, which address the growing problem of staff shortages in assisted-living communities. In this context, detecting and assessing pain remain critical yet challenging tasks in both clinical and non-clinical settings. Traditional approaches such as self-reporting, physiological signal monitoring, and facial expression analysis often face limitations related to accessibility, equipment costs, and the need for professional support. To overcome these challenges in this work, we investigate a sensor-assisted system for pain detection and propose a lightweight framework that enables real-time classification of pain levels using acoustic sensors. Our system exploits the spectral features of voice signals that strongly correlate with pain to train Convolutional Neural Network (CNN) models. Our system has been validated through simulations in Jupiter Notebook and a Raspberry Pi-based hardware prototype. The experimental results demonstrate that the proposed three-level pain classification approach obtains an average accuracy of 72.74%, outperforming existing methods with the same pain-level granularity by 18.94–26.74% and achieving performance comparable to that of binary pain detection methods. Our hardware prototype, built from commercial off-the-shelf components for under 100 USD, achieves real-time processing speeds ranging from approximately 6 to 22 s. In addition to CNN models, our experiments demonstrate that other machine learning algorithms, such as Artificial Neural Networks, XGBoost, Random Forests, and Decision Trees, also prove to be applicable within our pain level classification framework. Full article

This study analyzes the ICT infrastructure in teaching practice centers from the perspective of students enrolled in early childhood and primary education degree programs at a Spanish university during the 2024–2025 academic year. A quantitative, cross-sectional design was employed. A questionnaire was distributed to all first- to fourth-year students via the university platform, with a sample of 556 participants. The data collection instrument consisted of an ad hoc adaptation and extension of the validated EdSocEval_V2 questionnaire, ensuring factorial validity. It was used to examine the availability of technological resources for communication and digital management, together with personal and contextual variables to support data classification. Results indicate high availability of basic digital resources, including projectors, Wi-Fi, interactive whiteboards, printers, alongside limited access to robotics, digital tablets, and classrooms of the future. High homogeneity was observed in communication and digital management resources, such as websites, virtual learning environments and corporate email. MANOVA analyses revealed that students perceive ICT infrastructure to be more integrated at higher levels of primary education, with no significant differences based on school ownership. Binary logistic regressions showed that school ownership predicts the availability of certain ICT resources, with private schools exhibiting lower network presence. Full article

Recently, deep learning methods have seen major advancements and are preferred for medical image analysis. Clinically, deep learning techniques for cancer image analysis are among the main applications for early diagnosis, detection, and treatment. Consequently, segmentation of breast histology images is a key step towards diagnosing breast cancer. However, the use of deep learning methods for image analysis is constrained by challenging features in the histology images. These challenges include poor image quality, complex microscopic tissue structures, topological intricacies, and boundary/edge inhomogeneity. Furthermore, this leads to a limited number of images required for analysis. The U-Net model was introduced and gained significant traction for its ability to produce high-accuracy results with very few input images. Many modifications of the U-Net architecture exist. Therefore, this study proposes the watershed encoder–decoder neural network (WEDN) to segment cancerous lesions in supervised breast histology images. Pre-processing of supervised breast histology images via augmentation is introduced to increase the dataset size. The augmented dataset is further enhanced and segmented into the region of interest. Data enhancement methods such as thresholding, opening, dilation, and distance transform are used to highlight foreground and background pixels while removing unwanted parts from the image. Consequently, further segmentation via the connected component analysis method is used to combine image pixel components with similar intensity values and assign them their respective labeled binary masks. The watershed filling method is then applied to these labeled binary mask components to separate and identify the edges/boundaries of the regions of interest (cancerous lesions). This resultant image information is sent to the WEDN model network for feature extraction and learning via training and testing. Residual convolutional block layers of the WEDN model are the learnable layers that extract the region of interest (ROI), which is the cancerous lesion. The method was evaluated on 3000 images–watershed masks, an augmented dataset. The model was trained on 2400 training set images and tested on 600 testing set images. This proposed method produced significant results of $98.53\%$ validation accuracy, $96.98\%$ validation dice coefficient, and $97.84\%$ validation intersection over unit (IoU) metric scores. Full article

Detecting nearshore underwater targets in hyperspectral imagery faces significant challenges due to complex background clutter, weak and distorted underwater target signals. Extracting discriminative features is a critical step. Current methods are often constrained by high spectral redundancy and reliance on manual annotations, leading to suboptimal detection performance. To address these problems, this paper proposes a novel underwater target detection framework that integrates self-supervised band selection with a physically-constrained detection, called the negatively constrained network with self-supervised band selection (NCSS-Net). Specifically, NCSS-Net first generates a target-prior abundance map via Normalized Difference Water Index and spectral unmixing. This abundance map is then converted into a binary target mask through adaptive thresholding. The binary target mask serves as pseudo labels and guides an Artificial Bee Colony algorithm to identify a maximally discriminative band subset. These bands are then fed into a negatively-constrained autoencoder. This network is trained with a specialized loss function to enforce negative correlation between the target and water endmembers, thereby enhancing their separability. Experimental results demonstrate that NCSS-Net outperforms existing state-of-the-art methods, offering an effective and practical solution for nearshore underwater monitoring applications. Our code will be available online upon acceptance. Full article

Volcanic Scoria Lightweight Aggregate Concrete (VSLAC) has been identified as a material with considerable potential for use in carbon-neutral construction; however, its application is often hindered by two main issues. Firstly, the low density of scoria often results in aggregate segregation and stratification. Secondly, its high hygroscopicity can lead to shrinkage cracking. In order to address the aforementioned issues, this study proposes a multi-scale modification strategy. The cementitious matrix was first strengthened using a binary blend of Fly Ash and Ground Granulated Blast Furnace Slag (GGBS), followed by the incorporation of a ternary admixture system containing Styrene-Acrylic Emulsion (SAE), a foaming agent (FA), and alkali-treated Straw Fibres (SF) to enhance workability and durability. The findings of this study demonstrate that a mineral admixture comprising 10% Fly Ash and 10% GGBS results in a substantial enhancement of matrix compactness, culminating in a 20% increase in compressive strength. An orthogonal test was conducted to identify the optimal formulation (D13), which was found to contain 4% SAE, 0.1% FA, and 5% SF. This formulation yielded a compressive strength of 35.2 MPa, a flexural strength of 7.5 MPa, and reduced water absorption to 8.0%. A comparative analysis was conducted between the mineral admixture mix ratio (Control group) and the Optimal mix ratio (Optimization group). The results of this analysis reveal that the Optimization group exhibited superior durability and thermal characteristics. Specifically, the water penetration depth of the optimized composite was successfully restricted to within 3.18 mm, while its thermal insulation performance demonstrated a significant enhancement of 12.3%. In the context of freeze–thaw cycles, the modified concrete demonstrated notable durability, exhibiting a 51.4% reduction in strength loss and a marginal 0.64% restriction in mass loss. SEM analysis revealed that the interaction between SAE and the FA resulted in the densification of the Interfacial Transition Zone (ITZ). In addition, the 3D network formed by SF redistributed internal stresses, thereby shifting the failure mode from brittle fracture to ductile deformation. The findings demonstrate that modifying VSLAC at both micro- and macro-levels can effectively balance structural integrity with thermal efficiency for sustainable construction applications. Full article

In many land cover classification tasks, the limited precision of individual sensors hinders the accurate separation of certain classes, largely due to the complexity of the Earth’s surface morphology. To mitigate these issues, decision fusion methodologies are employed, allowing data from multiple sensors to be synthesized into robust and more conclusive classification outcomes. This study employs fully polarimetric Synthetic Aperture Radar (PolSAR) imagery and leverages the strengths of three decomposition methods, namely Pauli’s, Krogager’s, and Cloude’s, by extracting their respective components for improved detection. From each decomposition method, three scattering components are derived, enabling the extraction of informative features that describe the scattering behavior associated with various land cover types. The extracted scattering features, treated as independent sensors, were used to train three neural network classifiers. The resulting outputs were then considered as local decisions for each land cover type and subsequently fused through a decision fusion rule to generate more complete and accurate classification results. Experimental results demonstrate that the proposed Multi-Class Bahadur–Lazarsfeld Expansion (MC-BLE) fusion significantly enhances classification performance, achieving an overall accuracy (OA) of 95.78% and a Kappa coefficient of 0.94. Compared to individual classification methods, the fusion notably improved per-class accuracy, particularly for complex land cover boundaries. The core innovation of this work is the transformation of the Bahadur–Lazarsfeld Expansion (BLE), originally designed for binary decision fusion into a multi-class framework capable of addressing multiple land cover types, resulting in a more effective and reliable decision fusion strategy. Full article

We aimed to establish a rapid and precise method for identifying and quantifying multi-species vegetable oil (corn oil, olive oil (OLO), soybean oil, and sunflower oil (SUO)) adulterations in camellia oil (CAO), using soft ionization by chemical reaction in transfer–high-resolution mass spectrometry (SICRIT-HRMS) and machine learning methods. The results showed that SICRIT-HRMS could effectively characterize the volatile profiles of pure and adulterated CAO samples, including binary, ternary, quaternary, and quinary adulteration systems. The low m/z region (especially 100–300) exhibited importance to oil classification in multiple feature-selection methods. For qualitative detection, binary classification models based on convolutional neural networks (CNN), Random Forest (RF), and gradient boosting trees (GBT) algorithms showed high accuracies (98.70–100.00%) for identifying CAO adulteration under no dimensionality reduction (NON), principal component analysis (PCA), and uniform manifold approximation and projection (UMAP) strategies. The RF algorithm exhibited relatively high accuracy (96.25–99.45%) in multiclass classification. Moreover, the five models, including CNN, RF, support vector machines (SVM), logistic regression (LR), and GBT, exhibited different performances in distinguishing pure and adulterated CAO. Among 1093 blind oil samples, under NON, PCA, and UMAP: 10, 5, and 67 samples were misclassified by CNN model; 6, 7, and 41 samples were misclassified by RF model; 8, 9, and 82 samples were misclassified by SVM model; 17, 18, and 78 samples were misclassified by LR model; 7, 9, and 43 samples were misclassified by GBT model. For quantitative prediction, the PCA-CNN model performed optimally in predicting adulteration levels in CAO, especially with respect to OLO and SUO, exhibiting a high coefficient of determination for calibration ($R_C^2$, 0.9664–0.9974) and coefficient of determination for prediction ($R_p^2$, 0.9599–0.9963) values, low root mean square error of calibration (RMSEC, 0.9–5.3%) and root mean square error of prediction (RMSEP, 1.1–5.8%) values, and RPD (5.0–16.3) values greater than 3.0. These results indicate that SICRIT-HRMS combined with machine learning can rapidly and accurately identify and quantify multi-species vegetable oil adulterations in CAO, which provides a reference for developing non-targeted and high-throughput detection methods in edible oil authenticity. Full article

The microstructure of the Ti-Al binary system is an area of great interest, as it affects material properties and plasticity. Phase transformations induce microstructural changes; therefore, accurately modeling the phase transformations of the Ti-Al system is necessary to describe plasticity. Interatomic potentials can be a powerful tool to model how materials behave; however, existing potentials lack accuracy in certain aspects. While classical potentials like the Modified Embedded Atom Method (MEAM) perform adequately for modeling a dilute Al solute within Ti’s $\alpha$ phase, they struggle with accurately predicting plasticity. In particular, they struggle with stacking fault energies in intermetallics and to some extent elastic properties. This hinders their effectiveness in investigating the plastic behavior of formed intermetallics in Ti-Al alloys. Classical potentials also fail to predict the $\alpha$-to-$\beta$ phase boundary. Existing machine learning (ML) potentials reproduce the properties of formed intermetallics with density functional theory (DFT) but do not accurately capture the $\alpha$-to-$\beta$ or $\alpha$-to-D0₁₉ phase boundaries. This work uses a rapid artificial neural network (RANN) framework to produce a neural network potential for the Ti-Al binary system. This potential is capable of reproducing the Ti-Al binary phase diagram up to 30% Al concentration. The present interatomic potential ensures stability and allows results near the accuracy of DFT. Using Monte Carlo simulations, the RANN potential accurately predicts the $\alpha$-to-$\beta$ and $\alpha$-to-D0₁₉ phase transitions. The current potential also exhibits accurate elastic constants and stacking fault energies for the L1₀ and D0₁₉ phases. Full article

We propose the Hybrid Spatio-Temporal Transformer with Multi-Branch CNN/RNN and Extreme-Event Head (HST–MB–CREH), a hybrid spatio-temporal deep learning architecture for joint short-term photovoltaic (PV) power forecasting and the detection of rare extreme events, to support the reliable operation of renewable-rich power systems. The model combines a spatio-temporal transformer encoder with three convolutional neural network (CNN)/recurrent neural network (RNN) branches (CNN → long short-term memory (LSTM), LSTM → gated recurrent unit (GRU), CNN → GRU) and a dense pathway for tabular meteorological and calendar features. A multitask output head simultaneously performs the regression of PV power and binary classification of extremes defined above the 95th percentile. We evaluate HST–MB–CREH on the publicly available Renewable Power Generation and Weather Conditions dataset with hourly resolutions from 2017 to 2022, using a 5-fold TimeSeriesSplit protocol to avoid temporal leakage and to cover multiple seasons. Compared with tree ensembles (RandomForest, XGBoost), recurrent baselines (Stacked GRU, LSTM), and advanced hybrid/transformer models (Hybrid Multi-Branch CNN–LSTM/GRU with Dense Path and Extreme-Event Head (HMB–CLED) and Spatio-Temporal Multitask Transformer with Extreme-Event Head (STM–EEH)), the proposed architecture achieves the best overall trade-off between accuracy and rare-event sensitivity, with normalized performance of RMSE_z = 0.2159 ± 0.0167, MAE_z = 0.1100 ± 0.0085, mean absolute percentage error (MAPE) = 9.17 ± 0.45%, R² = 0.9534 ± 0.0072, and AUC_ext = 0.9851 ± 0.0051 across folds. Knowledge extraction is supported via attention-based analysis and permutation feature importance, which highlight the dominant role of global horizontal irradiance, diurnal harmonics, and solar geometry features. The results indicate that hybrid spatio-temporal multitask architectures can substantially improve both the forecast accuracy and robustness to extremes, making HST–MB–CREH a promising building block for intelligent decision-support tools in smart grids with a high share of PV generation. Full article