Search Results (363)

Wireless sensor networks (WSNs) are widely used in environmental monitoring, industrial automation, and smart cities. The Hybrid Energy-Efficient Distributed (HEED) protocol is a popular clustering algorithm designed to prolong network lifetime by balancing energy consumption among sensor nodes. However, HEED relies on simple heuristics for cluster-head (CH) selection, which may not fully exploit the complex spatiotemporal patterns in node energy and topology. This paper introduces a novel protocol, Deep Learning–Hybrid Energy-Efficient Distributed (DL-HEED), which, for the first time, integrates a Graph Neural Network (GNN) into the clustering process. By leveraging the relational structure of WSNs and a comprehensive set of node and network features—including residual energy, node degree, spatial position, and signal strength—DL-HEED enables intelligent, context-aware, and adaptive CH selection. DL-HEED leverages the relational structure of WSNs through deep learning, enabling more adaptive and energy-efficient cluster head selection than traditional heuristic-based protocols. Extensive simulations demonstrate that DL-HEED significantly outperforms classic HEED achieving up to 60% improvement in the network lifetime and energy efficiency as the network size increases. This work establishes DL-HEED as a robust, scalable, and practical solution for next-generation WSN deployments, marking a substantial advancement in the application of deep learning to resource-constrained IoT environments. Full article

Research on commuting patterns has mainly focused on urban and metropolitan areas, and such studies are not typically applied to rural and small-town regions, where workers often face longer commutes due to limited job opportunities and inadequate public transportation. By using the Census Transportation Planning Package (CTPP) data, this research fills that gap by analyzing commuting behavior by ethnic group and industry in south-central Minnesota, which is a predominantly rural area of 13 counties in the United States. The results show that both white and minority groups in District 7 experienced an increase in excess commuting from 2006 to 2016, with the minority group in Nobles County showing a significantly higher rise. Analysis by industry reveals that excess commuting in the leisure and hospitality sector (including arts, entertainment, and food services) in Nobles County increased five-fold during this time, indicating a severe spatial mismatch between jobs and affordable housing. In contrast, manufacturing experienced a decline of 50%, possibly indicating better commuting efficiency or a loss of manufacturing jobs. These findings can help city and transportation planners conduct an in-depth analysis of rural-to-urban commuting patterns and develop potential solutions to improve rural transportation infrastructure and accessibility, such as promoting telecommuting and hybrid work options, expanding shuttle routes, and adding more on-demand transit services in rural areas. Full article

Malware continues to develop, posing significant challenges for traditional signature-based detection systems. Visual malware classification, which transforms malware binaries into grayscale images, has emerged as a promising alternative for recognizing patterns in malicious code. This study presents a hybrid deep learning architecture that combines the local feature extraction capabilities of ConvNeXt-Tiny (a CNN-based model) with the global context modeling of the Swin Transformer. The proposed model is evaluated using three benchmark datasets—Malimg, MaleVis, VirusMNIST—encompassing 61 malware classes. Experimental results show that the hybrid model achieved a validation accuracy of 94.04%, outperforming both the ConvNeXt-Tiny-only model (92.45%) and the Swin Transformer-only model (90.44%). Additionally, we extended our validation dataset to two more datasets—Maldeb and Dumpware-10—to strengthen the empirical foundation of our work. The proposed hybrid model achieved competitive accuracy on both, with 98% on Maldeb and 97% on Dumpware-10. To enhance model interpretability, we employed Gradient-weighted Class Activation Mapping (Grad-CAM), which visualizes the learned representations and reveals the complementary nature of CNN and Transformer modules. The hybrid architecture, combined with explainable AI, offers an effective and interpretable approach for malware classification, facilitating better understanding and trust in automated detection systems. In addition, a real-time deployment scenario is demonstrated to validate the model’s practical applicability in dynamic environments. Full article

With the rapid progression of global industrialization and urbanization, emerging contaminants (ECs) have become pervasive in environmental media, posing considerable risks to ecosystems and human health. While multidisciplinary evidence continues to accumulate regarding their environmental persistence and bioaccumulative hazards, critical knowledge gaps persist in understanding their spatiotemporal distribution, cross-media migration mechanisms, and cascading ecotoxicological consequences. This review systematically investigates the global distribution patterns of ECs in aquatic environments over the past five years and evaluates their potential ecological risks. Furthermore, it examines the performance of various treatment technologies, focusing on economic cost, efficiency, and environmental sustainability. Methodologically aligned with PRISMA 2020 guidelines, this study implements dual independent screening protocols, stringent inclusion–exclusion criteria (n = 327 studies). Key findings reveal the following: (1) Occurrences of ECs show geographical clustering in highly industrialized river basins, particularly in Asia (37.05%), Europe (24.31%), and North America (14.01%), where agricultural pharmaceuticals and fluorinated compounds contribute disproportionately to environmental loading. (2) Complex transboundary pollutant transport through atmospheric deposition and oceanic currents, coupled with compound-specific partitioning behaviors across water–sediment–air interfaces. (3) Emerging hybrid treatment systems (e.g., catalytic membrane bioreactors, plasma-assisted advanced oxidation) achieve > 90% removal for recalcitrant ECs, though requiring 15–40% cost reductions for scalable implementation. This work provides actionable insights for developing adaptive regulatory frameworks and advancing green chemistry principles in environmental engineering practice. Full article

Background: As intelligent systems increasingly operate in high-risk environments, understanding how they perceive and respond to hazards is critical for ensuring safety. Methods: In this study, we conduct a comparative analysis of 60 real-world accident reports, 30 from process control systems (PCSs) and 30 from autonomous vehicles (AVs), to examine differences in risk triggers, perception paradigms, and interaction failures between humans and artificial intelligence (AI). Results: Our findings reveal that PCS risks are predominantly internal to the system and detectable through deterministic, rule-based mechanisms, whereas AVs’ risks are externally driven and managed via probabilistic, multi-modal sensor fusion. More importantly, despite these architectural differences, both domains exhibit recurring human–AI interaction failures, including over-reliance on automation, mode confusion, and delayed intervention. In the case of PCSs, these failures are historically tied to human–automation interaction; this article extrapolates these patterns to anticipate potential human–AI interaction challenges as AI adaptation increases. Conclusions: This study highlights the need for a hybrid risk perception framework and improved human-centered design to enhance situational awareness and responsiveness. While AI has not yet been implemented in PCS incident studies, this work interprets human–automation failures in these cases as indicative of potential challenges in human–AI interaction that may arise in future AI-integrated process systems. Implications extend to developing safer intelligent systems across industrial and transportation sectors. Full article

Gait recognition is a reliable biometric approach that uniquely identifies individuals based on their natural walking patterns. It is widely used to recognize individuals who are challenging to camouflage and do not require a person’s cooperation. The general face-based person recognition system often fails to determine the offender’s identity when they conceal their face by wearing helmets and masks to evade identification. In such cases, gait-based recognition is ideal for identifying offenders, and most existing work leverages a deep learning (DL) model. However, a single model often fails to capture a comprehensive selection of refined patterns in input data when external factors are present, such as variation in viewing angle, clothing, and carrying conditions. In response to this, this paper introduces a fusion-based multi-model gait recognition framework that leverages the potential of convolutional neural networks (CNNs) and a vision transformer (ViT) in an ensemble manner to enhance gait recognition performance. Here, CNNs capture spatiotemporal features, and ViT features multiple attention layers that focus on a particular region of the gait image. The first step in this framework is to obtain the Gait Energy Image (GEI) by averaging a height-normalized gait silhouette sequence over a gait cycle, which can handle the left–right gait symmetry of the gait. After that, the GEI image is fed through multiple pre-trained models and fine-tuned precisely to extract the depth spatiotemporal feature. Later, three separate fusion strategies are conducted, and the first one is decision-level fusion (DLF), which takes each model’s decision and employs majority voting for the final decision. The second is feature-level fusion (FLF), which combines the features from individual models through pointwise addition before performing gait recognition. Finally, a hybrid fusion combines DLF and FLF for gait recognition. The performance of the multi-model fusion-based framework was evaluated on three publicly available gait databases: CASIA-B, OU-ISIR D, and the OU-ISIR Large Population dataset. The experimental results demonstrate that the fusion-enhanced framework achieves superior performance. Full article

In this work, the development of Al-based metal matrix composites (MMCs) is achieved using hybrid SiC and ZrO₂ reinforcement particles for automotive applications. Powder metallurgy (PM) is employed with various combinations of important process parameters for the fabrication of MMCs. MMCs were characterized using scanning electron microscopy (SEM), X-ray diffractometry (XRD), and a microhardness study. All XRD graphs adequately exhibit Al, SiC, and ZrO₂ peaks, indicating that the hybrid MMC products were satisfactorily fabricated with appropriate mixing and sintering at all the considered fabrication conditions. Also, no impurity peaks were observed, confirming high composite purity. MMC products in all the XRD patterns, suitable for the desired applications. According to the SEM investigation, SiC and ZrO₂ reinforcement components are uniformly scattered throughout Al matrix in all produced MMC products. The occurrence of Al, Si, C, Zr, and O in EDS spectra demonstrates the effectiveness of composite ball milling and sintering under all manufacturing conditions. Moreover, an increase in interfacial bonding of fabricated composites at a higher sintering temperature indicated improved physical properties of the developed MMCs. The highest microhardness value is 86.6 HVN amid all the fabricated composites at 7% silica, 14% zirconium dioxide, 500° sintering temperature, 90 min sintering time, and 60 min milling time. An integrated Particle Swarm Optimization–Support Vector Machine (PSO-SVM) model was developed to predict microhardness based on the input parameters. The model demonstrated strong predictive performance, as evidenced by low values of various statistical metrics for both training and testing datasets, highlighting the PSO-SVM model’s robustness and generalization capability. Specifically, the model achieved a coefficient of determination of 0.995 and a root mean square error of 0.920 on the training set, while on the testing set, it attained a coefficient of determination of 0.982 and a root mean square error of 1.557. These results underscore the potential of the PSO-SVM framework, which can be effectively leveraged to optimize process parameters for achieving targeted microhardness levels for the developed Al-SiC-ZrO₂ Composites. Full article

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

In this work magnetic nanoparticles (Fe₃O₄, or ZnFe₂O₄, or SrFe₁₂O₁₉) and BaTiO₃ microparticles were embedded in an epoxy resin for the synthesis of three series of hybrid magnetic polymer nanocomposites. Barium titanate content was kept constant, while magnetic phase content was varied. Fabricated specimens were structurally and morphologically characterized by employing scanning electron microscopy images and X-ray diffraction patterns. Results implied successful synthesis of the hybrid nanocomposites. The magnetic behavior of the pure magnetic nanoparticles and the fabricated nanocomposites was investigated via a Vibrating Sample Magnetometer. The magnetic performance of each type of magnetic phase (i.e., soft and hard) was induced in the nanocomposites, and magnetic performance is strengthened with the increase in magnetic phase content. Initial magnetization curves were used for the determination of mass magnetic susceptibility of all nanocomposites. Magnetic saturation and magnetic remanence have been found to follow a linear relationship with magnetic phase content, giving the opportunity to predict the system’s response in advance. Full article

This study presents a novel predictive framework for estimating electric vehicle (EV) charging demand in smart cities, contributing to the advancement of data-driven infrastructure planning through behavioural and spatial data analysis. Motivated by the accelerating regional demand accompanying EV adoption, this work introduces HCB-Net: a hybrid deep learning model that combines Convolutional Neural Networks (CNNs) for spatial feature extraction with Extreme Gradient Boosting (XGBoost) for robust regression. The framework is trained on user-level survey data from two demographically distinct UK regions, the West Midlands and the North East, incorporating user demographics, commute distance, charging frequency, and home/public charging preferences. HCB-Net achieved superior predictive performance, with a Root Mean Squared Error (RMSE) of 0.1490 and an $R^2$ score of 0.3996. Compared to the best-performing traditional model (Linear Regression, $R^2=0.3520$), HCB-Net improved predictive accuracy by 13.5% in terms of $R^2$, and outperformed other deep learning models such as LSTM ($R^2=-0.3756$) and GRU ($R^2=-0.6276$), which failed to capture spatial patterns effectively. The hybrid model also reduced RMSE by approximately 23% compared to the standalone CNN (RMSE = 0.1666). While the moderate $R^2$ indicates scope for further refinement, these results demonstrate that meaningful and interpretable demand forecasts can be generated from survey-based behavioural data, even in the absence of high-resolution temporal inputs. The model contributes a lightweight and scalable forecasting tool suitable for early-stage smart city planning in contexts where telemetry data are limited, thereby advancing the practical capabilities of EV infrastructure forecasting. Full article

This study proposes a conceptual model that explains the influence of leadership on the relationship between human intelligence (HI) and artificial intelligence (AI). A qualitative, non-systematic literature review was conducted in Scopus and Web of Science of the literature published in the last 5 years, using Boolean combinations of the terms “leadership,” “artificial intelligence,” and “human intelligence.” The thematic analysis allowed the identification of conceptual patterns and research gaps; the model elaborated from the review shows that leadership has an ethical and strategic mediation in the HI-AI relationship in a hybrid space of cooperation, in which automated decisions are put in real context through human judgment and reasoning; ethical governance mechanisms emerge for systems supported by artificial intelligence; and finally, a balancing mechanism to algorithmic efficiency is established through cognitive adaptability. The proposed framework offers organizations some guidelines for human supervision processes for AI-supported systems that integrate ethical evaluations into automated processes. It proposes elements—leadership tools that enhance the relationship between human intelligence and artificial intelligence. This article contributes to the management of organizations by proposing a model that recognizes leadership as a dynamic facilitator between HI and AI, integrating transdisciplinary knowledge of management, technological ethics, and cognitive science, and proposing an ethical interrelationship in the decision-making architectures between HI and AI. The proposed model establishes leadership mediation of human–AI interaction through four axes showing how leadership acts as the axis that brings together human and technological systems to work together. Hierarchical interaction creates a hybrid interaction that is highly flexible, efficient, and has ethical oversight. Finally, the proposed model is an open system that interacts with the environment and is understood as a flexible tool to support strategic decision-making in complex environments. Full article

Background: Lumbar disc herniation (LDH) recurrence remains a pressing clinical challenge, with limited predictive tools available to support early identification and personalized intervention. Predicting recurrence after lumbar disc herniation (LDH) remains clinically important but algorithmically difficult due to extreme class imbalance and low signal-to-noise ratio. Objective: This study proposes a hybrid machine learning framework that integrates supervised classifiers, unsupervised anomaly detection, and decision threshold tuning to predict LDH recurrence using routine clinical data. Methods: A dataset of 977 patients from a Romanian neurosurgical center was used. We trained a deep neural network, random forest, and an autoencoder (trained only on non-recurrence cases) to model baseline and anomalous patterns. Their outputs were stacked into a meta-classifier and optimized via sensitivity-focused threshold tuning. Evaluation was performed via stratified cross-validation and external holdout testing. Results: Baseline models achieved high accuracy but failed to recall recurrence cases (0% sensitivity). The proposed ensemble reached 100% recall internally with a threshold of 0.05. Key predictors included hospital stay duration, L4–L5 herniation, obesity, and hypertension. However, external holdout performance dropped to 0% recall, revealing poor generalization. Conclusions: The ensemble approach enhances detection of rare recurrence cases under internal validation but exhibits poor external performance, emphasizing the challenge of rare-event modeling in clinical datasets. Future work should prioritize external validation, longitudinal modeling, and interpretability to ensure clinical adoption. Full article

Churn prediction has become one of the core concepts in customer relationship management within the insurances, telecom, and internet service provider industries, which is essential in customer retention. Therefore, this study attempts to analyze the effectiveness of the advanced machine learning and deep learning models for churn prediction in the evaluation of the models’ performance across different sectors. This would help conclude whether the varied patterns of the churn throughout different sectors to the level that affects the model performance and to what extent. The work includes three datasets: namely, insurance churn, internet service provider customer churn, and Telecom churn datasets. The implementation and comparison conducted in this study of models include XGBoost, Convolutional Neural Networks (CNNs), and Ensemble Deep Learning with the pre-trained hybrid approach. The results show that the ensemble deep learning model outperforms other models in terms of accuracy and F1-score, achieving accuracies of up to 95.96% in the insurance churn dataset and of 98.42% in the telecom churn dataset. Moreover, traditional machine learning models like XGBoost also produced competitive results for selected datasets. The proposed deep learning ensembles reveal the strength and possibility for churn prediction and provide a benchmark for future research relevant to customer retention strategies. Also, the proposed ensemble deep learning model shows stable performance across different sectors, which reflects its ability to capture the varied churn patterns of different sectors. Full article

The exploitation of renewable energy is essential for mitigating climate change and reducing fossil fuel emissions. Wind energy, the most mature technology, is highly dependent on wind speed, and the accurate prediction of the latter substantially supports wind power generation. In this work, various artificial neural networks (ANNs) were developed and evaluated for their wind speed prediction ability using the ERA5 historical reanalysis data for four potential Offshore Wind Farm Organized Development Areas in Greece, selected as suitable for floating wind installations. The training period for all the ANNs was 80% of the time series length and the remaining 20% of the dataset was the testing period. Of all the ANNs examined, the hybrid model combining Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) networks demonstrated superior forecasting performance compared to the individual models, as evaluated by standard statistical metrics, while it also exhibited a very good performance at high wind speeds, i.e., greater than 15 m/s. The hybrid model achieved the lowest root mean square errors across all the sites—0.52 m/s (Crete), 0.59 m/s (Gyaros), 0.49 m/s (Patras), 0.58 m/s (Pilot 1A), and 0.55 m/s (Pilot 1B)—and an average coefficient of determination (R²) of 97%. Its enhanced accuracy is attributed to the integration of the LSTM and GRU components strengths, enabling it to better capture the temporal patterns in the wind speed data. These findings underscore the potential of hybrid neural networks for improving wind speed forecasting accuracy and reliability, contributing to the more effective integration of wind energy into the power grid and the better planning of offshore wind farm energy generation. Full article

Genomic imprinting is critical for mammalian development, but its regulation varies across species. The insulin-like growth factor 2 receptor (IGF2R), which is a maternally expressed imprinted gene critical for cell proliferation and differentiation, as well as embryonic and placental development, is classically regulated by differentially methylated regions (DMRs) and lncRNA-Airn in mice. However, studies on this in equus are scarce, especially in terms of mechanistic studies. In the present study, heart, liver, spleen, lung, kidney, brain, and muscle samples were obtained from horses, donkeys, and hybrids, and gene expression and imprinting state were tested to investigate the imprinting regulation of Igf2r in these animals. Bisulfite sequencing combined with an allele-specific expression analysis revealed a tissue-specific loss of imprinting in the mule liver and hybrid brain tissues. Strikingly, we found that the maternal-specific expression of equine Igf2r did not rely on the canonical DMRs or lncRNA-Airn. Surprisingly, DNA methylation of a specific region called CpG island 2 (CpGI2) in the Igf2r promoter showed cis-acting inheritance, meaning that the DNA methylation patterns of the parental alleles are retained in hybrid tissues. Notably, the DNA methylation of CpGI2 correlated negatively with Igf2r expression in the spleen (R² = 0.8797, p = 6.46 × 10⁻⁶), lung (R² = 0.8569, p = 1.57 × 10⁻⁵), and kidney (R² = 0.8650, p = 3.85 × 10⁻⁶). Our findings suggest that imprinting may work differently in other species. This study provides a framework for understanding imprinting diversity in hybrids and shows that equine hybrids can be used to study how epigenetic inheritance works. Full article