Search Results (15,944)

This study explores the application of spiking neural networks (SNNs) for click-through rate (CTR) prediction in personalized online advertising systems, introducing a novel hybrid model, the Temporal Rate Spike with Attention Neural Network (TRA–SNN). By leveraging the biological plausibility and energy efficiency of SNNs, combined with attention-based mechanisms, the TRA–SNN model captures temporal dynamics and rate-based patterns to achieve performance comparable to state-of-the-art Artificial Neural Network (ANN)-based models, such as Deep & Cross Network v2 (DCN-V2) and FinalMLP. The models were trained and evaluated on the Avazu and Digix datasets, using standard metrics like AUC-ROC and accuracy. Through rigorous hyperparameter tuning and standardized preprocessing, this study ensures fair comparisons across models, highlighting SNNs’ potential for scalable, sustainable deployment in resource-constrained environments like mobile devices and large-scale ad platforms. This work is the first to apply SNNs to CTR prediction, setting a new benchmark for energy-efficient predictive modeling and opening avenues for future research in hybrid SNN–ANN architectures across domains like finance, healthcare, and autonomous systems. Full article

Background: Psoriasis, an inflammatory skin disorder, involves pyroptosis—a pro-inflammatory cell death process. However, cell-specific pyroptosis dynamics and immune microenvironment interactions remain unclear. Objective: To investigate cell-type-specific pyroptosis patterns in psoriasis and their immunoregulatory mechanisms. Methods: We integrated 21 transcriptomic datasets (from 2007 to 2020) obtained from the GEO database and two single-cell RNA sequencing datasets to quantify pyroptotic activity using Gene Set Variation Analysis and AUCell algorithms. Immune cell infiltration profiles were evaluated via CIBERSORT, while cell-cell communication networks were analyzed by CellChat. In vitro and in vivo experiments were performed to validate key findings. Results: Our analysis revealed that psoriasis patients exhibited significantly elevated levels of pyroptosis compared to healthy controls, with pyroptotic activity reflecting treatment responses. Notably, monocyte-derived macrophages (MDMs) in psoriatic lesions displayed markedly heightened pyroptotic activity. In vitro experiments confirmed that MDMs derived from psoriasis patients overexpressed pyroptosis-related molecules (Caspase 1 and Caspase 4) as well as pro-inflammatory cytokines (TNFα, IL6, IL1β) when compared to healthy controls. Furthermore, these cells showed increased expression of CXCL16, which might potentially activate Th17 cells through CXCR6 signaling, thereby driving skin inflammation. Inhibition of monocyte migration in an imiquimod-induced psoriasiform dermatitis model significantly alleviated skin inflammation and reduced the proportion of M1 macrophages and Th17 cells in lesional skin. Conclusions: This study revealed that MDMs in psoriatic lesions exhibited a hyperactive pyroptotic state, which contributed to disease progression through CXCL16-mediated remodeling of the immune microenvironment. These findings highlight pyroptosis as a potential therapeutic target for psoriasis. Full article

The increasing deployment of photovoltaic (PV) systems necessitates robust fault detection mechanisms to ensure operational reliability and safety. Conventional approaches, however, struggle in complex industrial environments characterized by high noise, data incompleteness, and class imbalance. This study proposes an innovative Advanced CNN-BiLSTM architecture integrating multi-scale feature extraction with hierarchical attention to enhance PV fault detection. The proposed framework employs four parallel CNN branches with kernel sizes of 3, 7, 15, and 31 to capture temporal patterns across various time scales. These features are then integrated by an adaptive feature fusion network that utilizes multi-head attention. A two-layer bidirectional LSTM with temporal attention mechanism processes the fused features for final classification. Comprehensive evaluation on the GPVS-Faults dataset using a progressive difficulty validation framework demonstrates exceptional performance improvements. Under extreme industrial conditions, the proposed method achieves 83.25% accuracy, representing a substantial 119.48% relative improvement over baseline CNN-BiLSTM (37.93%). Ablation studies reveal that the multi-scale CNN contributes 28.0% of the total performance improvement, while adaptive feature fusion accounts for 22.0%. Furthermore, the proposed method demonstrates superior robustness under severe noise (σ = 0.20), high levels of missing data (15%), and significant outlier contamination (8%). These characteristics make the architecture highly suitable for real-world industrial deployment and establish a new paradigm for temporal feature fusion in renewable energy fault detection. Full article

Rapid and accurate transient stability assessment (TSA) is crucial for ensuring secure and stable operation in power systems. However, existing methods fail to adequately exploit the spatiotemporal characteristics in power grid transient data, which constrains the evaluation performance of models. This paper proposes a TSA method built upon an Attention-Based Spatial–Temporal Graph Convolutional Network (ASTGCN) model. First, a spatiotemporal attention module is used to aggregate and extract the spatiotemporal correlations of the transient process in the power system. A spatiotemporal convolution module is then employed to effectively capture the spatial features and temporal evolution patterns of transient stability data. In addition, an adaptive focal loss function is designed to enhance the fitting of unstable samples and increase the weight of misclassified samples, thereby improving global accuracy and reducing the occurrence of missed instability samples. Finally, the simulation results from the New England 10-machine 39-bus system and the NPCC 48-machine 140-bus system validate the effectiveness of the proposed methodology. Full article

This study proposes a hybrid approach to analyze and forecast non-stationary financial time series by combining statistical models with deep neural networks. A model is introduced that integrates three key components: the Generalized Autoregressive Score (GAS) model, which captures volatility dynamics; an attention mechanism (ATT), which identifies the most relevant features within the sequence; and a Long Short-Term Memory (LSTM) neural network, which receives the outputs of the previous modules to generate price forecasts. This architecture is referred to as GAS-ATT-LSTM. Both unidirectional and bidirectional variants were evaluated using real financial data from the Nasdaq Composite Index, Invesco QQQ Trust, ProShares UltraPro QQQ, Bitcoin, and gold and silver futures. The proposed model’s performance was compared against five benchmark architectures: LSTM Bidirectional, GARCH-LSTM Bidirectional, ATT-LSTM, GAS-LSTM, and GAS-LSTM Bidirectional, under sliding windows of 3, 5, and 7 days. The results show that GAS-ATT-LSTM, particularly in its bidirectional form, consistently outperforms the benchmark models across most assets and forecasting horizons. It stands out for its adaptability to varying volatility levels and temporal structures, achieving significant improvements in both accuracy and stability. These findings confirm the effectiveness of the proposed hybrid model as a robust tool for forecasting complex financial time series. Full article

Small and medium-sized enterprises (SMEs) face growing challenges in optimizing their sustainable supply chains because of fragmented logistics data and changing regulatory requirements. In particular, globally operating manufacturing SMEs often lack suitable tools, resulting in manual data collection and making reliable accounting and benchmarking of transport emissions in lifecycle assessments (LCAs) time-consuming and difficult to scale. This paper introduces a novel hybrid AI-supported knowledge graph (KG) which combines large language models (LLMs) with graph-based optimization to automate industrial supply chain route enrichment, completion, and emissions analysis. The proposed solution automatically resolves transportation gaps through generative AI and programming interfaces to create optimal routes for cost, time, and emission determination. The application merges separate routes into a single multi-modal network which allows users to evaluate sustainability against operational performance. A case study shows the capabilities in simplifying data collection for emissions reporting, therefore reducing manual effort and empowering SMEs to align logistics decisions with Industry 5.0 sustainability goals. Full article

This paper presents an advanced time-series forecasting methodology that integrates multiple machine learning models to improve data prediction in enhanced long-range navigation (eLoran) systems. The analysis evaluates five forecasting approaches: multivariate linear regression, long short-term memory (LSTM) networks, random forest (RF), a fusion model combining LSTM and RF, and a dynamic weighting (DW) model. The results demonstrate that the DW model achieves the highest prediction accuracy while maintaining strong computational efficiency, making it particularly suitable for real-time applications with stringent performance requirements. Although the LSTM model effectively captures temporal dependencies, it demands considerable computational resources. The hybrid model utilises the strengths of LSTM and RF to enhance the accuracy but involves extended training times. By contrast, the DW model dynamically adjusts the relative contributions of LSTM and RF on the basis of the data characteristics, thereby enhancing the accuracy while significantly reducing the computational demands. Demonstrating exceptional performance on the ASF2 dataset, the DW model provides a well-balanced solution that combines precision with operational efficiency. This research offers valuable insights into optimising additional secondary phase factor (ASF) prediction in eLoran systems and highlights the broader applicability of real-time forecasting models. Full article

Duck egg quality classification is critical in farms, hatcheries, and salted egg processing plants, where cracked eggs must be identified before further processing or distribution. However, duck eggs present a unique challenge due to their white eggshells, which make cracks difficult to detect visually. In current practice, human inspectors use standard white light for crack detection, and many researchers have focused primarily on improving detection algorithms without addressing lighting limitations. Therefore, this paper presents duck egg crack detection using an adaptive convolutional neural network (CNN) model ensemble with multi-light channels. We began by developing a portable crack detection system capable of controlling various light sources to determine the optimal lighting conditions for crack visibility. A total of 23,904 images were collected and evenly distributed across four lighting channels (red, green, blue, and white), with 1494 images per channel. The dataset was then split into 836 images for training, 209 images for validation, and 449 images for testing per lighting condition. To enhance image quality prior to model training, several image pre-processing techniques were applied, including normalization, histogram equalization (HE), and contrast-limited adaptive histogram equalization (CLAHE). The Adaptive MobileNetV2 was employed to evaluate the performance of crack detection under different lighting and pre-processing conditions. The results indicated that, under red lighting, the model achieved 100.00% accuracy, precision, recall, and F1-score across almost all pre-processing methods. Under green lighting, the highest accuracy of 99.80% was achieved using the image normalization method. For blue lighting, the model reached 100.00% accuracy with the HE method. Under white lighting, the highest accuracy of 99.83% was achieved using both the original and HE methods. Full article

This research is part of a broader investigation into innovative simulation-based approaches for improving traffic efficiency and road safety in roundabout corridors. These corridors, composed of successive roundabouts along arterials, present systemic challenges due to the dynamic interactions between adjacent intersections. While previous studies have addressed localized inefficiencies or proposed isolated interventions, this paper introduces possible replicable methodology based on a microsimulation and surrogate safety analysis to evaluate roundabout corridors as integrated systems. In this context, efficiency refers to the ability of a road corridor to maintain stable traffic conditions under a given demand scenario, with low delay times corresponding to acceptable levels of service. Safety is interpreted as the minimization of vehicle conflicts and critical interactions, evaluated through surrogate measures derived from simulated vehicle trajectories. The proposed approach—implemented through Aimsun Next and the SSAM tool—is tested on two real-world corridors: Via Aurelia Nord in Pisa (Italy) and Route de Marseille in Avignon (France), assessing multiple intersection configurations that combine roundabouts and signal-controlled junctions. Results show how certain layouts can produce unexpected performance outcomes, underlining the importance of system-wide evaluations. The proposed framework aims to support engineers and planners in identifying optimal corridor configurations under realistic operating conditions. Full article

Background: Prolactin receptor (PRLR) signaling affects breastfeeding and potentially breast cancer treatment response. Methods: The prognostic impact of 20 PRLR single nucleotide polymorphisms (SNPs) in relation to adjuvant treatment groups in patients with primary breast cancer (n = 1701, 2002–2016, Sweden) was evaluated. Genomic DNA was genotyped on Illumina OncoArray, and survival analyses with up to 15-year follow-up were performed. Interaction models, adjusted for potential confounders, were created with different adjuvant treatment modalities: chemotherapy, radiotherapy, tamoxifen, and aromatase inhibitors. Results: Five SNPs (rs7734558, rs6860397, rs2962101, rs7732013, and rs4703503) showed interactions with radiotherapy and were utilized to create seven combined genotypes: six unique and one ‘rare’. Patients carrying combined genotype AG/GG/TT/CC/TC or ‘rare’ combinations derived greater benefits from radiotherapy than other patient groups (both HR_adj ≤ 0.29, Bonferroni-adjusted P_int ≤ 0.039). Expression Quantitative Trait Loci (eQTL) analysis revealed that three PRLR SNPs were associated with decreased PRLR expression. To explore potential SNP-associated effects, gene expression and transcriptional networks were analyzed in the METABRIC cohort and indicated that PRLR-low tumors were associated with reduced DNA repair signaling and enhanced anti-tumoral immunity. Conclusions: PRLR merits further evaluation as a putative pharmacogenomic biomarker in relation to radiotherapy for breast cancer patients. Full article

In today’s increasingly interconnected digital world, cyber threats have grown in frequency and sophistication, making intrusion detection systems a critical component of modern cybersecurity frameworks. Traditional IDS methods, often based on static signatures and rule-based systems, are no longer sufficient to detect and respond to complex and evolving attacks. To address these challenges, Artificial Intelligence and machine learning have emerged as powerful tools for enhancing the accuracy, adaptability, and automation of IDS solutions. This study presents a novel, hybrid ensemble learning-based intrusion detection framework that integrates deep learning and traditional ML algorithms with explainable artificial intelligence for real-time cybersecurity applications. The proposed model combines an Artificial Neural Network and Support Vector Machine as base classifiers and employs a Random Forest as a meta-classifier to fuse predictions, improving detection performance. Recursive Feature Elimination is utilized for optimal feature selection, while SHapley Additive exPlanations (SHAP) provide both global and local interpretability of the model’s decisions. The framework is deployed using a Flask-based web interface in the Amazon Elastic Compute Cloud environment, capturing live network traffic and offering sub-second inference with visual alerts. Experimental evaluations using the NSL-KDD dataset demonstrate that the ensemble model outperforms individual classifiers, achieving a high accuracy of 99.40%, along with excellent precision, recall, and F1-score metrics. This research not only enhances detection capabilities but also bridges the trust gap in AI-powered security systems through transparency. The solution shows strong potential for application in critical domains such as finance, healthcare, industrial IoT, and government networks, where real-time and interpretable threat detection is vital. Full article

There is a lack of studies on the effectiveness of polar-transformed spectrograms in the visualization and prediction of cardiac arrhythmias from electrocardiogram (ECG) data. In this study, single-lead ECG waveforms were converted into two-dimensional rectangular time–frequency spectrograms and polar time–frequency spectrograms. Three pre-trained convolutional neural network (CNN) models (ResNet50, MobileNet, and DenseNet121) served as baseline networks for model development and testing. Prediction performance and visualization quality were evaluated across various image resolutions. The trade-offs between image resolution and model capacity were quantitatively analyzed. Polar-transformed spectrograms demonstrated superior delineation of R-R intervals at lower image resolutions (e.g., 96 × 96 pixels) compared to conventional spectrograms. For deep-learning-based classification of cardiac arrhythmias, polar-transformed spectrograms achieved comparable accuracy to conventional spectrograms across all evaluated resolutions. The results suggest that polar-transformed spectrograms are particularly advantageous for deep CNN predictions at lower resolutions, making them suitable for edge computing applications where the reduced use of computing resources, such as memory and power consumption, is desirable. Full article

Steam networks are widely used for industrial heat supply. High-temperature heat pumps (HTHPs) are an increasingly attractive low-emission solution to traditional steam generation, which could also improve the operational efficiency and energy demand flexibility of industrial processes. This work characterises 4-bar steam supply via HTHPs and aims to assess how variations in power input that result from flexible HTHP operation may affect steam flow and temperature, both with and without a downstream steam accumulator (SA). First, steady-state modelling is used for system design. Then, dynamic component models are developed and used to simulate the system response to HTHP power input variations. The performance of different SA integration layouts and sizes is evaluated. Results demonstrate that steam supply fluctuations closely follow changes in HTHP operation. A downstream SA is shown to mitigate these variations to an extent that depends on its capacity. Practical SA sizing recommendations are derived, which allow for the containment of steam supply fluctuations within acceptability. By providing a basis for evaluating the financial viability of flexible HTHP operation for steam provision, the results support clean technology’s development and uptake in industrial steam and district heating networks. Full article

Underground hydrogen storage (UHS) in geological formations offers a promising solution for large-scale energy buffering, but its long-term safety and mechanical stability remain concerns, particularly in fractured rock environments. This study develops a fully coupled thermo-mechanical model to investigate the cyclic response of a dual-cavern hydrogen storage system with polymer-based sealing layers. The model incorporates non-isothermal gas behavior, rock heterogeneity via a Weibull distribution, and fracture networks represented through stochastic geometry. Two operational scenarios, single-cavern and dual-cavern cycling, are simulated to evaluate stress evolution, displacement, and inter-cavity interaction under repeated pressurization. Results reveal that simultaneous operation of adjacent caverns amplifies tensile and compressive stress concentrations, especially in inter-cavity rock bridges (i.e., the intact rock zones separating adjacent caverns) and fracture-dense zones. Polymer sealing layers remain under compressive stress but exhibit increased residual deformation under cyclic loading. Contour analyses further show that fracture orientation and spatial distribution significantly influence stress redistribution and deformation localization. The findings highlight the importance of considering thermo-mechanical coupling and rock fracture mechanics in the design and operation of multicavity UHS systems. This modeling framework provides a robust tool for evaluating storage performance and informing safe deployment in complex geological environments. Full article

Neural Architecture search (NAS) aims to automate the design process of Deep Neural Networks, reducing the Deep Learning (DL) expertise required and avoiding a trial-and-error process. Nonetheless, one of the main drawbacks of NAS is the high consumption of computational resources. Consequently, efficient evaluation methods (EEMs) to assess the quality of candidate architectures are an open research problem. This work tests various EEMs in the Deep Genetic Algorithm (DeepGA), including early stopping, population memory, and training-free proxies. The Fashion MNIST, CIFAR-10, and CIFAR-100 datasets were used for experimentation. The results show that population memory has a valuable impact on avoiding repeated evaluations. Additionally, early stopping achieved competitive performance while significantly reducing the computational cost of the search process. The training-free configurations using the Logsynflow and Linear Regions proxies, as well as a combination of both, were only partially competitive but dramatically reduced the search time. Finally, a comparison of the architectures and hyperparameters obtained with the different algorithm configurations is presented. The training-free search processes resulted in deeper architectures with more fully connected layers and skip connections than the ones obtained with accuracy-guided search configurations. Full article