Adversarial Reinforcement Learning(ARL)models for intelligent devices and Network Intrusion Detection Systems(NIDS)improve systemresilience against sophisticated cyber-attacks.As a core component of ARL,Adversarial Tr...Adversarial Reinforcement Learning(ARL)models for intelligent devices and Network Intrusion Detection Systems(NIDS)improve systemresilience against sophisticated cyber-attacks.As a core component of ARL,Adversarial Training(AT)enables NIDS agents to discover and prevent newattack paths by exposing them to competing examples,thereby increasing detection accuracy,reducing False Positives(FPs),and enhancing network security.To develop robust decision-making capabilities for real-world network disruptions and hostile activity,NIDS agents are trained in adversarial scenarios to monitor the current state and notify management of any abnormal or malicious activity.The accuracy and timeliness of the IDS were crucial to the network’s availability and reliability at this time.This paper analyzes ARL applications in NIDS,revealing State-of-The-Art(SoTA)methodology,issues,and future research prospects.This includes Reinforcement Machine Learning(RML)-based NIDS,which enables an agent to interact with the environment to achieve a goal,andDeep Reinforcement Learning(DRL)-based NIDS,which can solve complex decision-making problems.Additionally,this survey study addresses cybersecurity adversarial circumstances and their importance for ARL and NIDS.Architectural design,RL algorithms,feature representation,and training methodologies are examined in the ARL-NIDS study.This comprehensive study evaluates ARL for intelligent NIDS research,benefiting cybersecurity researchers,practitioners,and policymakers.The report promotes cybersecurity defense research and innovation.展开更多
Motor imbalance is a critical failure mode in rotating machinery,potentially causing severe equipment damage if undetected.Traditional vibration-based diagnostic methods rely on direct sensor contact,leading to instal...Motor imbalance is a critical failure mode in rotating machinery,potentially causing severe equipment damage if undetected.Traditional vibration-based diagnostic methods rely on direct sensor contact,leading to installation challenges and measurement artifacts that can compromise accuracy.This study presents a novel radar-based framework for non-contact motor imbalance detection using 24 GHz continuous-wave radar.A dataset of 1802 experimental trials was sourced,covering four imbalance levels(0,10,20,30 g)across varying motor speeds(500–1500 rpm)and load torques(0–3 Nm).Dual-channel in-phase and quadrature radar signals were captured at 10,000 samples per second for 30-s intervals,preserving both amplitude and phase information for analysis.A multi-domain feature extraction methodology captured imbalance signatures in time,frequency,and complex signal domains.From 65 initial features,statistical analysis using Kruskal–Wallis tests identified significant descriptors,and recursive feature elimination with Random Forest reduced the feature set to 20 dimensions,achieving 69%dimensionality reduction without loss of performance.Six machine learning algorithms,Random Forest,Extra Trees Classifier,Extreme Gradient Boosting,Categorical Boosting,Support Vector Machine with radial basis function kernel,and k-Nearest Neighbors were evaluated with grid-search hyperparameter optimization and five-fold cross-validation.The Extra Trees Classifier achieved the best performance with 98.52%test accuracy,98%cross-validation accuracy,and minimal variance,maintaining per-class precision and recall above 97%.Its superior performance is attributed to its randomized split selection and full bootstrapping strategy,which reduce variance and overfitting while effectively capturing the nonlinear feature interactions and non-normal distributions present in the dataset.The model’s average inference time of 70 ms enables near real-time deployment.Comparative analysis demonstrates that the radar-based framework matches or exceeds traditional contact-based methods while eliminating their inherent limitations,providing a robust,scalable,and noninvasive solution for industrial motor condition monitoring,particularly in hazardous or space-constrained environments.展开更多
This study compared the acute effects of electrical energy transfer(TECAR) and transcutaneous electrical stimulation(TENS) on pain and flexibility after a hamstring injury. Young athletes received either a 20 min TECA...This study compared the acute effects of electrical energy transfer(TECAR) and transcutaneous electrical stimulation(TENS) on pain and flexibility after a hamstring injury. Young athletes received either a 20 min TECAR(n = 24) or TENS(n = 26) session within 5 days following a hamstring injury, while the control(CON, n = 25)group was instructed to rest. Visual analogue scale(VAS), functional Assessment Scale for Acute Hamstring Injuries(FASH), straight leg raise test(SLR), and sit-and-reach scores(STR) were obtained prior to, immediately,24, and 48 h after therapy. Group differences were detected after therapy in VAS and FASH scores(p < 0.05).Compared to pre-therapy measurements, VAS scores showed a greater decrease in the TECAR group(-38.75% to-63.33%) than in the TENS group(-16.67% to-25.00%) and both were greater than in the CON group(-2.81%to-9.81%)(p < 0.05). The TECAR group improved FASH scores(28.57%–48.21%) more than the TENS group(15.89%–27.79%) and both groups more than the CON group(0%–8.33%)(p < 0.05). The increase in SLR and STR was greater in the TECAR group(6.26%–13.96%) than in the TENS(1.72%–9.53%) and CON groups(0%–3.03%). These results suggest that in the acute phase of hamstring injury, the use of TECAR and, to a lesser extent, TENS may relieve pain symptoms and bring some improvements in flexibility more than instructing patients to rest.展开更多
Sustainable energy systems will entail a change in the carbon intensity projections,which should be carried out in a proper manner to facilitate the smooth running of the grid and reduce greenhouse emissions.The prese...Sustainable energy systems will entail a change in the carbon intensity projections,which should be carried out in a proper manner to facilitate the smooth running of the grid and reduce greenhouse emissions.The present article outlines the TransCarbonNet,a novel hybrid deep learning framework with self-attention characteristics added to the bidirectional Long Short-Term Memory(Bi-LSTM)network to forecast the carbon intensity of the grid several days.The proposed temporal fusion model not only learns the local temporal interactions but also the long-term patterns of the carbon emission data;hence,it is able to give suitable forecasts over a period of seven days.TransCarbonNet takes advantage of a multi-head self-attention element to identify significant temporal connections,which means the Bi-LSTM element calculates sequential dependencies in both directions.Massive tests on two actual data sets indicate much improved results in comparison with the existing results,with mean relative errors of 15.3 percent and 12.7 percent,respectively.The framework has given explicable weights of attention that reveal critical periods that influence carbon intensity alterations,and informed decisions on the management of carbon sustainability.The effectiveness of the proposed solution has been validated in numerous cases of operations,and TransCarbonNet is established to be an effective tool when it comes to carbon-friendly optimization of the grid.展开更多
In this work,a computational modelling and analysis framework is developed to investigate the thermal buckling behavior of doubly-curved composite shells reinforced with graphene-origami(G-Ori)auxetic metamaterials.A ...In this work,a computational modelling and analysis framework is developed to investigate the thermal buckling behavior of doubly-curved composite shells reinforced with graphene-origami(G-Ori)auxetic metamaterials.A semi-analytical formulation based on the First-Order Shear Deformation Theory(FSDT)and the principle of virtual displacements is established,and closed-form solutions are derived via Navier’s method for simply supported boundary conditions.The G-Ori metamaterial reinforcements are treated as programmable constructs whose effective thermo-mechanical properties are obtained via micromechanical homogenization and incorporated into the shell model.A comprehensive parametric study examines the influence of folding geometry,dispersion arrangement,reinforcement weight fraction,curvature parameters,and elastic foundation support on the critical buckling temperature(CBT).The results reveal that,under optimal folding geometry and reinforcement alignment with principal stress trajectories,the CBT can increase by more than 150%.Furthermore,the combined effect of G-Ori reinforcement and elastic foundation substantially enhances thermal buckling resistance.These findings establish design guidelines for architected composite shells in applications such as aerospace thermal skins,morphing structures,and thermally-responsive systems,and illustrate the potential of auxetic graphene metamaterials for multifunctional,lightweight,and thermally robust structural components.展开更多
With the increasing growth of online news,fake electronic news detection has become one of the most important paradigms of modern research.Traditional electronic news detection techniques are generally based on contex...With the increasing growth of online news,fake electronic news detection has become one of the most important paradigms of modern research.Traditional electronic news detection techniques are generally based on contextual understanding,sequential dependencies,and/or data imbalance.This makes distinction between genuine and fabricated news a challenging task.To address this problem,we propose a novel hybrid architecture,T5-SA-LSTM,which synergistically integrates the T5 Transformer for semantically rich contextual embedding with the Self-Attentionenhanced(SA)Long Short-Term Memory(LSTM).The LSTM is trained using the Adam optimizer,which provides faster and more stable convergence compared to the Stochastic Gradient Descend(SGD)and Root Mean Square Propagation(RMSProp).The WELFake and FakeNewsPrediction datasets are used,which consist of labeled news articles having fake and real news samples.Tokenization and Synthetic Minority Over-sampling Technique(SMOTE)methods are used for data preprocessing to ensure linguistic normalization and class imbalance.The incorporation of the Self-Attention(SA)mechanism enables the model to highlight critical words and phrases,thereby enhancing predictive accuracy.The proposed model is evaluated using accuracy,precision,recall(sensitivity),and F1-score as performance metrics.The model achieved 99%accuracy on the WELFake dataset and 96.5%accuracy on the FakeNewsPrediction dataset.It outperformed the competitive schemes such as T5-SA-LSTM(RMSProp),T5-SA-LSTM(SGD)and some other models.展开更多
Background:Locally advanced laryngeal squamous cell carcinoma(LA-LSCC)presents clinical challenges due to the lack of reliable non-invasive biomarkers.This study aimed to evaluate miR-449a as a diagnostic and prognost...Background:Locally advanced laryngeal squamous cell carcinoma(LA-LSCC)presents clinical challenges due to the lack of reliable non-invasive biomarkers.This study aimed to evaluate miR-449a as a diagnostic and prognostic biomarker in LA-LSCC.Methods:miR-449a expression was analyzed in tumor tissues,adjacent normal tissues,and serum from 81 LA-LSCC patients and 50 controls using quantitative real-time reverse transcription polymerase chain reaction(qRT-PCR).We assessed the diagnostic accuracy by Receiver Operating Characteristic curve(ROC curves),clinicopathological associations,survival outcomes(Kaplan-Meier),and treatment response dynamics.Results:miR-449a was significantly downregulated in LA-LSCC tissues(p<0.0001)and serum(p<0.0001),with a strong tissue-serum correlation(R^(2)=0.988).Tissue miR-449a demonstrated a diagnostic accuracy(Area Under the Curve,AUC=0.857),while serum showed moderate accuracy(AUC=0.734).High miR-449a expression correlated with favorable clinicopathological features and improved survival(median overall survival:67.82 vs.23.74 months;p=0.0012).Multivariate analysis confirmed miR-449a as an independent prognostic factor(p<0.001).miR-449a levels increased post-treatment,particularly in responders to chemotherapy/radiation(p<0.0001).Conclusion:miR-449a serves as a non-invasive biomarker for LA-LSCC diagnosis,prognosis,and treatment monitoring.Its dynamic expression highlights potential for risk stratification and therapy response prediction,warranting further validation in larger cohorts.展开更多
We present a computer-modeling framework for photovoltaic(PV)source emulation that preserves the exact single-diode physics while enabling iteration-free,real-time evaluation.We derive two closed-form explicit solvers...We present a computer-modeling framework for photovoltaic(PV)source emulation that preserves the exact single-diode physics while enabling iteration-free,real-time evaluation.We derive two closed-form explicit solvers based on the Lambert W function:a voltage-driven V-Lambert solver for high-fidelity I–V computation and a resistance-driven R-Lambert solver designed for seamless integration in a closed-loop PV emulator.Unlike Taylor-linearized explicit models,our proposed formulation retains the exponential nonlinearity of the PV equations.It employs a numerically stable analytical evaluation that eliminates the need for lookup tables and root-finding,all while maintaining limited computational costs and a small memory footprint.The R-Lambert model is integrated into a buck-converter emulator equipped with a discrete PI regulator,which generates current references directly from sensed operating points,thus supporting hardware-constrained implementation.Comprehensive numerical experiments conducted on six commercial modules from various technologies(mono,poly,and multicrystalline)demonstrate significant accuracy improvements under the IEC EN 50530 near-MPP criterion:the V-Lambert solver reduces the±10%Vmpp band error by up to 61 times compared to an explicit-model baseline.Dynamic simulations under varying irradiance,temperature,and load conditions achieve millisecond-scale settling with accurate trajectory tracking.Additionally,processor-in-the-loop experimental validation on an embedded microcontroller supports the simulation results.By unifying exact analytical modeling with embedded realization,this work advances computer modeling for PV emulation,MPPT benchmarking,and controller verification in integrated renewable energy systems.展开更多
Five samples of LiMgPO_(4):Gd were prepared via five different production processes using a solid-state reaction method.The effects of the preparation process on optically stimulated luminescence(OSL)and thermolumines...Five samples of LiMgPO_(4):Gd were prepared via five different production processes using a solid-state reaction method.The effects of the preparation process on optically stimulated luminescence(OSL)and thermoluminescence(TL)were investigated.Considering its high sensitivity,low fading,and minimum detectable dose(MDD),the LiMgPO_(4):Gd phosphor heated to 900℃for 15 h is concluded to be optimal.The effects of annealing on the OSL sensitivity,relative residual OSL signals measured after 24 h of irradiation,and MDD of LiMgPO_(4):Gd phosphors heated to 900℃for 15 h were also investigated.Considering its high sensitivity,low fading,and MDD,annealing at 350℃for 1 h is concluded to be optimal.The OSL signal of LiMgPO_(4):Gd was derived from the principal TL glow peak.For a maximum integration time of 5 s,the OSL signal was stable,with no fading 30 days after irradiation.LiMgPO_(4):Gd eliminated approximately 2.2%of the OSL signal at each readout for a readout time of 0.1 s,which is sufficient for fast and multiple OSL readout.The sensitivity of LiMgPO_(4):Gd phosphor,annealed for 1 h at 350℃with a reading time of 0.1 s,was found to be approximately 98%of that observed forα-Al_(2)O_(3):C(TLD-500k),which should be sufficient for low-dose measurements in personal,workplace,and environmental dosimetry.展开更多
One of the main issues in designing optimum tapered cascades for uranium enrichment for annual fuel production in a power reactor is whether to employ large(fat)or small(thin)cascades.What will be the permissible and ...One of the main issues in designing optimum tapered cascades for uranium enrichment for annual fuel production in a power reactor is whether to employ large(fat)or small(thin)cascades.What will be the permissible and optimal ranges of the number of machines that can be used in a cascade?For the first time,the permissible and optimal ranges of the number of gas centrifuges that can be utilized in a cascade were investigated using two types of centrifuges,and the performance of small and large tapered cascades was discussed.The particle swarm optimization algorithm(PSO)has been used to optimize tapered cascades.The results show:(1)For the first centrifuge,41 cascades(91≤n≤4897)and for the second centrifuge,49 cascades(18≤n≤3839)with small and large sizes can be used in enrichment facilities,and the best cascade for them has 530(with 23 stages)and 39(with 7 stages)centrifuges,respectively.(2)For both centrifuges,when 600≤n(number of centrifuges=n),the large cascade performance changes are relatively insignificant.(3)For both types of gas centrifuges,the annual los s of separation power in enrichment facilities is approximately 1.25%-4.82%of the total separation work required.展开更多
Malware poses a significant threat to the Internet of Things(IoT).It enables unauthorized access to devices in the IoT environment.The lack of unique architectural standards causes challenges in developing robust malw...Malware poses a significant threat to the Internet of Things(IoT).It enables unauthorized access to devices in the IoT environment.The lack of unique architectural standards causes challenges in developing robust malware detection(MD)models.The existing models demand substantial computational resources.This study intends to build a lightweight MD model to detect anomalies in IoT networks.The authors develop a transformation technique,converting the malware binaries into images.MobileNet V2 is fine-tuned using improved grey wolf optimization(IGWO)to extract crucial features of malicious and benign samples.The ResNeXt model is combined with the Linformer’s attention mechanism to identify Malware features.A fully connected layer is integrated with gradientweighted class activation mapping(Grad-CAM)in order to facilitate an interpretable classification model.The proposed model is evaluated using the IoT malware and the IoT-23 datasets.The model performs well on the two datasets with an accuracy of 98.94%,precision of 98.46%,recall of 98.11%,and F1-score of 98.28%on the IoT malware dataset,and an accuracy of 98.23%,precision of 96.80%,recall of 96.64%,and F1-score of 96.71%on the IoT-23 dataset,respectively.The findings indicate that the model has a high standard of classification.The lightweight architecture enables efficient deployment with an inference time of 1.42 s.Inference time has no direct impact on accuracy,precision,recall,or F1-score.However,the inference speed would warrant timely detection in latency-sensitive IoT applications.By achieving a remarkable result,the proposed study offers a comprehensive solution:a scalable,interpretable,and computationally efficient MD model for the evolving IoT landscape.展开更多
The evolution of cities into digitally managed environments requires computational systems that can operate in real time while supporting predictive and adaptive infrastructure management.Earlier approaches have often...The evolution of cities into digitally managed environments requires computational systems that can operate in real time while supporting predictive and adaptive infrastructure management.Earlier approaches have often advanced one dimension—such as Internet of Things(IoT)-based data acquisition,Artificial Intelligence(AI)-driven analytics,or digital twin visualization—without fully integrating these strands into a single operational loop.As a result,many existing solutions encounter bottlenecks in responsiveness,interoperability,and scalability,while also leaving concerns about data privacy unresolved.This research introduces a hybrid AI–IoT–Digital Twin framework that combines continuous sensing,distributed intelligence,and simulation-based decision support.The design incorporates multi-source sensor data,lightweight edge inference through Convolutional Neural Networks(CNN)and Long ShortTerm Memory(LSTM)models,and federated learning enhanced with secure aggregation and differential privacy to maintain confidentiality.A digital twin layer extends these capabilities by simulating city assets such as traffic flows and water networks,generating what-if scenarios,and issuing actionable control signals.Complementary modules,including model compression and synchronization protocols,are embedded to ensure reliability in bandwidth-constrained and heterogeneous urban environments.The framework is validated in two urban domains:traffic management,where it adapts signal cycles based on real-time congestion patterns,and pipeline monitoring,where it anticipates leaks through pressure and vibration data.Experimental results show a 28%reduction in response time,a 35%decrease in maintenance costs,and a marked reduction in false positives relative to conventional baselines.The architecture also demonstrates stability across 50+edge devices under federated training and resilience to uneven node participation.The proposed system provides a scalable and privacy-aware foundation for predictive urban infrastructure management.By closing the loop between sensing,learning,and control,it reduces operator dependence,enhances resource efficiency,and supports transparent governance models for emerging smart cities.展开更多
The biological stabilization of soil using microbially induced carbonate precipitation(MICP)employs ureolytic bacteria to precipitate calcium carbonate(CaCO3),which binds soil particles,enhancing strength,stiffness,an...The biological stabilization of soil using microbially induced carbonate precipitation(MICP)employs ureolytic bacteria to precipitate calcium carbonate(CaCO3),which binds soil particles,enhancing strength,stiffness,and erosion resistance.The unconfinedcompressive strength(UCS),a key measure of soil strength,is critical in geotechnical engineering as it directly reflectsthe mechanical stability of treated soils.This study integrates explainable artificialintelligence(XAI)with geotechnical insights to model the UCS of MICP-treated sands.Using 517 experimental data points and a combination of various input variables—including median grain size(D50),coefficientof uniformity(Cu),void ratio(e),urea concentration(Mu),calcium concentration(Mc),optical density(OD)of bacterial solution,pH,and total injection volume(Vt)—fivemachine learning(ML)models,including eXtreme gradient boosting(XGBoost),Light gradient boosting machine(LightGBM),random forest(RF),gene expression programming(GEP),and multivariate adaptive regression splines(MARS),were developed and optimized.The ensemble models(XGBoost,LightGBM,and RF)were optimized using the Chernobyl disaster optimizer(CDO),a recently developed metaheuristic algorithm.Of these,LightGBM-CDO achieved the highest accuracy for UCS prediction.XAI techniques like feature importance analysis(FIA),SHapley additive exPlanations(SHAP),and partial dependence plots(PDPs)were also used to investigate the complex non-linear relationships between the input and output variables.The results obtained have demonstrated that the XAI-driven models can enhance the predictive accuracy and interpretability of MICP processes,offering a sustainable pathway for optimizing geotechnical applications.展开更多
The aim of this study is to design,build,and evaluate an indirect forced convection solar dryer adapted to semi-arid climate,such as that of Bechar situated in the west south region of Algeria.The tested drying system...The aim of this study is to design,build,and evaluate an indirect forced convection solar dryer adapted to semi-arid climate,such as that of Bechar situated in the west south region of Algeria.The tested drying system consists of a flat-plate solar collector,an insulated two-chamber drying unit,and an Arduino-controlled device that ensures uniformtemperature distribution and real-timemonitoring using DHT22 sensors.Drying testswere conducted on locally grown beet slices at air temperatures of 45℃,60℃,and 80℃,with a constant air velocity of 1.2 m/s and a mass flow rate of 0.0027 kg/s.The collector reached a maximum temperature of 65℃,with thermal efficiencies ranging from 20%to 35%.In these conditions,the drying times were cut down to 200–300 min,and the beet’s moisture content dropped to 0.47,0.27,and 0.24 g/g dry matter,respectively.The experimental data were fitted to several empirical models,including the logarithmic model.The modelled results showed strong agreement with the experimental ones(correlation coefficients r=0.9919–0.9989;standard errors SE=0.017–0.043;root-mean-square errors RMSE=0.016–0.027).The results demonstrate that the system operates efficiently and consistently,making it suitable for the sustainable drying of agricultural and medicinal products in arid climates.展开更多
The increasing number of interconnected devices and the incorporation of smart technology into contemporary healthcare systems have significantly raised the attack surface of cyber threats.The early detection of threa...The increasing number of interconnected devices and the incorporation of smart technology into contemporary healthcare systems have significantly raised the attack surface of cyber threats.The early detection of threats is both necessary and complex,yet these interconnected healthcare settings generate enormous amounts of heterogeneous data.Traditional Intrusion Detection Systems(IDS),which are generally centralized and machine learning-based,often fail to address the rapidly changing nature of cyberattacks and are challenged by ethical concerns related to patient data privacy.Moreover,traditional AI-driven IDS usually face challenges in handling large-scale,heterogeneous healthcare data while ensuring data privacy and operational efficiency.To address these issues,emerging technologies such as Big Data Analytics(BDA)and Federated Learning(FL)provide a hybrid framework for scalable,adaptive intrusion detection in IoT-driven healthcare systems.Big data techniques enable processing large-scale,highdimensional healthcare data,and FL can be used to train a model in a decentralized manner without transferring raw data,thereby maintaining privacy between institutions.This research proposes a privacy-preserving Federated Learning–based model that efficiently detects cyber threats in connected healthcare systems while ensuring distributed big data processing,privacy,and compliance with ethical regulations.To strengthen the reliability of the reported findings,the resultswere validated using cross-dataset testing and 95%confidence intervals derived frombootstrap analysis,confirming consistent performance across heterogeneous healthcare data distributions.This solution takes a significant step toward securing next-generation healthcare infrastructure by combining scalability,privacy,adaptability,and earlydetection capabilities.The proposed global model achieves a test accuracy of 99.93%±0.03(95%CI)and amiss-rate of only 0.07%±0.02,representing state-of-the-art performance in privacy-preserving intrusion detection.The proposed FL-driven IDS framework offers an efficient,privacy-preserving,and scalable solution for securing next-generation healthcare infrastructures by combining adaptability,early detection,and ethical data management.展开更多
Origanum elongatum(OE)is an aromatic,medicinal plant endemic to Morocco that is widely used in traditional medicine due to its biological properties.This study aimed to elucidate the chemical composition of the essent...Origanum elongatum(OE)is an aromatic,medicinal plant endemic to Morocco that is widely used in traditional medicine due to its biological properties.This study aimed to elucidate the chemical composition of the essential oil(EO)obtained from O.elongatum(OEEO)at three stages of its life cycle,including vegetative stage(OEEO-VS),flowering stage(OEEO-FS),and post-flowering(OEEO-PFS),as well as to evaluate its biological and antiradical characteristics.The chemical analysis of the essential oil was conducted using gas chromatography-mass spectrometry(GC-MS).The antibacterial activity was evaluated in vitro through distinct methodologies,namely,disc diffusion and microatmosphere assay;subsequently,the minimum inhibitory concentration(MIC)was then determined.The antioxidant potential was also measured by using the DPPH and FRAP assays.The GC-MS revealed the predominant of p-cymene(26.83%_31.45%),γ-terpinene(8.46%_26.95%),thymol(13%_29.54%),and carvacrol(20.25%_37.26%),in all three samples,with notable variations according to the phenological stage of the samples.The EOs extracted at three phenological stages demonstrated notable antibacterial efficacy against all the phytopathogen tested.The MICs for Erwinia amylovora exhibited a range of 6.25 and 250μg/mL.However,for Agrobacterium tumefaciens C58 and Allorhizobium vitis S4,the MICs spanned 125 and 250μg/mL.In the DPPH test,the IC50 values were 168.25±1.14,147.01±0.78,and 132.01±2.06μg/mL for EOs derived from the vegetative,flowering,and post-flowering period,respectively.In the FRAP test,the EC50 values were 164.22±1.04,215.73±1.48,and 184.06±0.95μg/mL for the same stages.The findings offer promising prospects for the phytochemical development,demonstrating how the phenological stage significantly influences the therapeutic and biotechnological potential of O.elongatum.This has the potential to open up new avenues of research in the pharmaceutical,agronomic,and environmental fields.展开更多
Objective:Deep learning is employed increasingly in Gastroenterology(GI)endoscopy computer-aided diagnostics for polyp segmentation and multi-class disease detection.In the real world,implementation requires high accu...Objective:Deep learning is employed increasingly in Gastroenterology(GI)endoscopy computer-aided diagnostics for polyp segmentation and multi-class disease detection.In the real world,implementation requires high accuracy,therapeutically relevant explanations,strong calibration,domain generalization,and efficiency.Current Convolutional Neural Network(CNN)and transformer models compromise border precision and global context,generate attention maps that fail to align with expert reasoning,deteriorate during cross-center changes,and exhibit inadequate calibration,hence diminishing clinical trust.Methods:HMA-DER is a hierarchical multi-attention architecture that uses dilation-enhanced residual blocks and an explainability-aware Cognitive Alignment Score(CAS)regularizer to directly align attribution maps with reasoning signals from experts.The framework has additions that make it more resilient and a way to test for accuracy,macro-averaged F1 score,Area Under the Receiver Operating Characteristic Curve(AUROC),calibration(Expected Calibration Error(ECE),Brier Score),explainability(CAS,insertion/deletion AUC),cross-dataset transfer,and throughput.Results:HMA-DER gets Dice Similarity Coefficient scores of 89.5%and 86.0%on Kvasir-SEG and CVC-ClinicDB,beating the strongest baseline by+1.9 and+1.7 points.It gets 86.4%and 85.3%macro-F1 and 94.0%and 93.4%AUROC on HyperKvasir and GastroVision,which is better than the baseline by+1.4/+1.6macro-F1 and+1.2/+1.1AUROC.Ablation study shows that hierarchical attention gives the highest(+3.0),followed by CAS regularization(+2–3),dilatation(+1.5–2.0),and residual connections(+2–3).Cross-dataset validation demonstrates competitive zero-shot transfer(e.g.,KS→CVC Dice 82.7%),whereas multi-dataset training diminishes the domain gap,yielding an 88.1%primary-metric average.HMA-DER’s mixed-precision inference can handle 155 pictures per second,which helps with calibration.Conclusion:HMA-DER strikes a compromise between accuracy,explainability,robustness,and efficiency for the use of reliable GI computer-aided diagnosis in real-world clinical settings.展开更多
Accurate prediction of concrete compressive strength is fundamental for optimizing mix designs,improving material utilization,and ensuring structural safety in modern construction.Traditional empirical methods often f...Accurate prediction of concrete compressive strength is fundamental for optimizing mix designs,improving material utilization,and ensuring structural safety in modern construction.Traditional empirical methods often fail to capture the non-linear relationships among concrete constituents,especially with the growing use of supple-mentary cementitious materials and recycled aggregates.This study presents an integrated machine learning framework for concrete strength prediction,combining advanced regression models—namely CatBoost—with metaheuristic optimization algorithms,with a particular focus on the Somersaulting Spider Optimizer(SSO).A comprehensive dataset encompassing diverse mix proportions and material types was used to evaluate baseline machine learning models,including CatBoost,XGBoost,ExtraTrees,and RandomForest.Among these,CatBoost demonstrated superior accuracy across multiple performance metrics.To further enhance predictive capability,several bio-inspired optimizers were employed for hyperparameter tuning.The SSO-CatBoost hybrid achieved the lowest mean squared error and highest correlation coefficients,outperforming other metaheuristic approaches such as Genetic Algorithm,Particle Swarm Optimization,and Grey Wolf Optimizer.Statistical significance was established through Analysis of Variance and Wilcoxon signed-rank testing,confirming the robustness of the optimized models.The proposed methodology not only delivers improved predictive performance but also offers a transparent framework for mix design optimization,supporting data-driven decision making in sustainable and resilient infrastructure development.展开更多
Concrete-filled steel tubes(CFST)are widely utilized in civil engineering due to their superior load-bearing capacity,ductility,and seismic resistance.However,existing design codes,such as AISC and Eurocode 4,tend to ...Concrete-filled steel tubes(CFST)are widely utilized in civil engineering due to their superior load-bearing capacity,ductility,and seismic resistance.However,existing design codes,such as AISC and Eurocode 4,tend to be excessively conservative as they fail to account for the composite action between the steel tube and the concrete core.To address this limitation,this study proposes a hybrid model that integrates XGBoost with the Pied Kingfisher Optimizer(PKO),a nature-inspired algorithm,to enhance the accuracy of shear strength prediction for CFST columns.Additionally,quantile regression is employed to construct prediction intervals for the ultimate shear force,while the Asymmetric Squared Error Loss(ASEL)function is incorporated to mitigate overestimation errors.The computational results demonstrate that the PKO-XGBoost model delivers superior predictive accuracy,achieving a Mean Absolute Percentage Error(MAPE)of 4.431%and R2 of 0.9925 on the test set.Furthermore,the ASEL-PKO-XGBoost model substantially reduces overestimation errors to 28.26%,with negligible impact on predictive performance.Additionally,based on the Genetic Algorithm(GA)and existing equation models,a strength equation model is developed,achieving markedly higher accuracy than existing models(R^(2)=0.934).Lastly,web-based Graphical User Interfaces(GUIs)were developed to enable real-time prediction.展开更多
Deep neural networks have achieved excellent classification results on several computer vision benchmarks.This has led to the popularity of machine learning as a service,where trained algorithms are hosted on the clou...Deep neural networks have achieved excellent classification results on several computer vision benchmarks.This has led to the popularity of machine learning as a service,where trained algorithms are hosted on the cloud and inference can be obtained on real-world data.In most applications,it is important to compress the vision data due to the enormous bandwidth and memory requirements.Video codecs exploit spatial and temporal correlations to achieve high compression ratios,but they are computationally expensive.This work computes the motion fields between consecutive frames to facilitate the efficient classification of videos.However,contrary to the normal practice of reconstructing the full-resolution frames through motion compensation,this work proposes to infer the class label from the block-based computed motion fields directly.Motion fields are a richer and more complex representation of motion vectors,where each motion vector carries the magnitude and direction information.This approach has two advantages:the cost of motion compensation and video decoding is avoided,and the dimensions of the input signal are highly reduced.This results in a shallower network for classification.The neural network can be trained using motion vectors in two ways:complex representations and magnitude-direction pairs.The proposed work trains a convolutional neural network on the direction and magnitude tensors of the motion fields.Our experimental results show 20×faster convergence during training,reduced overfitting,and accelerated inference on a hand gesture recognition dataset compared to full-resolution and downsampled frames.We validate the proposed methodology on the HGds dataset,achieving a testing accuracy of 99.21%,on the HMDB51 dataset,achieving 82.54%accuracy,and on the UCF101 dataset,achieving 97.13%accuracy,outperforming state-of-the-art methods in computational efficiency.展开更多
文摘Adversarial Reinforcement Learning(ARL)models for intelligent devices and Network Intrusion Detection Systems(NIDS)improve systemresilience against sophisticated cyber-attacks.As a core component of ARL,Adversarial Training(AT)enables NIDS agents to discover and prevent newattack paths by exposing them to competing examples,thereby increasing detection accuracy,reducing False Positives(FPs),and enhancing network security.To develop robust decision-making capabilities for real-world network disruptions and hostile activity,NIDS agents are trained in adversarial scenarios to monitor the current state and notify management of any abnormal or malicious activity.The accuracy and timeliness of the IDS were crucial to the network’s availability and reliability at this time.This paper analyzes ARL applications in NIDS,revealing State-of-The-Art(SoTA)methodology,issues,and future research prospects.This includes Reinforcement Machine Learning(RML)-based NIDS,which enables an agent to interact with the environment to achieve a goal,andDeep Reinforcement Learning(DRL)-based NIDS,which can solve complex decision-making problems.Additionally,this survey study addresses cybersecurity adversarial circumstances and their importance for ARL and NIDS.Architectural design,RL algorithms,feature representation,and training methodologies are examined in the ARL-NIDS study.This comprehensive study evaluates ARL for intelligent NIDS research,benefiting cybersecurity researchers,practitioners,and policymakers.The report promotes cybersecurity defense research and innovation.
基金funded by Princess Nourah bint Abdulrahman University Researchers Support-ing Project number(PNURSP2026R346)Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.
文摘Motor imbalance is a critical failure mode in rotating machinery,potentially causing severe equipment damage if undetected.Traditional vibration-based diagnostic methods rely on direct sensor contact,leading to installation challenges and measurement artifacts that can compromise accuracy.This study presents a novel radar-based framework for non-contact motor imbalance detection using 24 GHz continuous-wave radar.A dataset of 1802 experimental trials was sourced,covering four imbalance levels(0,10,20,30 g)across varying motor speeds(500–1500 rpm)and load torques(0–3 Nm).Dual-channel in-phase and quadrature radar signals were captured at 10,000 samples per second for 30-s intervals,preserving both amplitude and phase information for analysis.A multi-domain feature extraction methodology captured imbalance signatures in time,frequency,and complex signal domains.From 65 initial features,statistical analysis using Kruskal–Wallis tests identified significant descriptors,and recursive feature elimination with Random Forest reduced the feature set to 20 dimensions,achieving 69%dimensionality reduction without loss of performance.Six machine learning algorithms,Random Forest,Extra Trees Classifier,Extreme Gradient Boosting,Categorical Boosting,Support Vector Machine with radial basis function kernel,and k-Nearest Neighbors were evaluated with grid-search hyperparameter optimization and five-fold cross-validation.The Extra Trees Classifier achieved the best performance with 98.52%test accuracy,98%cross-validation accuracy,and minimal variance,maintaining per-class precision and recall above 97%.Its superior performance is attributed to its randomized split selection and full bootstrapping strategy,which reduce variance and overfitting while effectively capturing the nonlinear feature interactions and non-normal distributions present in the dataset.The model’s average inference time of 70 ms enables near real-time deployment.Comparative analysis demonstrates that the radar-based framework matches or exceeds traditional contact-based methods while eliminating their inherent limitations,providing a robust,scalable,and noninvasive solution for industrial motor condition monitoring,particularly in hazardous or space-constrained environments.
文摘This study compared the acute effects of electrical energy transfer(TECAR) and transcutaneous electrical stimulation(TENS) on pain and flexibility after a hamstring injury. Young athletes received either a 20 min TECAR(n = 24) or TENS(n = 26) session within 5 days following a hamstring injury, while the control(CON, n = 25)group was instructed to rest. Visual analogue scale(VAS), functional Assessment Scale for Acute Hamstring Injuries(FASH), straight leg raise test(SLR), and sit-and-reach scores(STR) were obtained prior to, immediately,24, and 48 h after therapy. Group differences were detected after therapy in VAS and FASH scores(p < 0.05).Compared to pre-therapy measurements, VAS scores showed a greater decrease in the TECAR group(-38.75% to-63.33%) than in the TENS group(-16.67% to-25.00%) and both were greater than in the CON group(-2.81%to-9.81%)(p < 0.05). The TECAR group improved FASH scores(28.57%–48.21%) more than the TENS group(15.89%–27.79%) and both groups more than the CON group(0%–8.33%)(p < 0.05). The increase in SLR and STR was greater in the TECAR group(6.26%–13.96%) than in the TENS(1.72%–9.53%) and CON groups(0%–3.03%). These results suggest that in the acute phase of hamstring injury, the use of TECAR and, to a lesser extent, TENS may relieve pain symptoms and bring some improvements in flexibility more than instructing patients to rest.
基金funded by the Deanship of Scientific Research and Libraries at Princess Nourah bint Abdulrahman University,through the“Nafea”Program,Grant No.(NP-45-082).
文摘Sustainable energy systems will entail a change in the carbon intensity projections,which should be carried out in a proper manner to facilitate the smooth running of the grid and reduce greenhouse emissions.The present article outlines the TransCarbonNet,a novel hybrid deep learning framework with self-attention characteristics added to the bidirectional Long Short-Term Memory(Bi-LSTM)network to forecast the carbon intensity of the grid several days.The proposed temporal fusion model not only learns the local temporal interactions but also the long-term patterns of the carbon emission data;hence,it is able to give suitable forecasts over a period of seven days.TransCarbonNet takes advantage of a multi-head self-attention element to identify significant temporal connections,which means the Bi-LSTM element calculates sequential dependencies in both directions.Massive tests on two actual data sets indicate much improved results in comparison with the existing results,with mean relative errors of 15.3 percent and 12.7 percent,respectively.The framework has given explicable weights of attention that reveal critical periods that influence carbon intensity alterations,and informed decisions on the management of carbon sustainability.The effectiveness of the proposed solution has been validated in numerous cases of operations,and TransCarbonNet is established to be an effective tool when it comes to carbon-friendly optimization of the grid.
文摘In this work,a computational modelling and analysis framework is developed to investigate the thermal buckling behavior of doubly-curved composite shells reinforced with graphene-origami(G-Ori)auxetic metamaterials.A semi-analytical formulation based on the First-Order Shear Deformation Theory(FSDT)and the principle of virtual displacements is established,and closed-form solutions are derived via Navier’s method for simply supported boundary conditions.The G-Ori metamaterial reinforcements are treated as programmable constructs whose effective thermo-mechanical properties are obtained via micromechanical homogenization and incorporated into the shell model.A comprehensive parametric study examines the influence of folding geometry,dispersion arrangement,reinforcement weight fraction,curvature parameters,and elastic foundation support on the critical buckling temperature(CBT).The results reveal that,under optimal folding geometry and reinforcement alignment with principal stress trajectories,the CBT can increase by more than 150%.Furthermore,the combined effect of G-Ori reinforcement and elastic foundation substantially enhances thermal buckling resistance.These findings establish design guidelines for architected composite shells in applications such as aerospace thermal skins,morphing structures,and thermally-responsive systems,and illustrate the potential of auxetic graphene metamaterials for multifunctional,lightweight,and thermally robust structural components.
基金supported by Princess Nourah bint Abdulrahman University Researchers Supporting Project number(PNURSP2025R195)Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.
文摘With the increasing growth of online news,fake electronic news detection has become one of the most important paradigms of modern research.Traditional electronic news detection techniques are generally based on contextual understanding,sequential dependencies,and/or data imbalance.This makes distinction between genuine and fabricated news a challenging task.To address this problem,we propose a novel hybrid architecture,T5-SA-LSTM,which synergistically integrates the T5 Transformer for semantically rich contextual embedding with the Self-Attentionenhanced(SA)Long Short-Term Memory(LSTM).The LSTM is trained using the Adam optimizer,which provides faster and more stable convergence compared to the Stochastic Gradient Descend(SGD)and Root Mean Square Propagation(RMSProp).The WELFake and FakeNewsPrediction datasets are used,which consist of labeled news articles having fake and real news samples.Tokenization and Synthetic Minority Over-sampling Technique(SMOTE)methods are used for data preprocessing to ensure linguistic normalization and class imbalance.The incorporation of the Self-Attention(SA)mechanism enables the model to highlight critical words and phrases,thereby enhancing predictive accuracy.The proposed model is evaluated using accuracy,precision,recall(sensitivity),and F1-score as performance metrics.The model achieved 99%accuracy on the WELFake dataset and 96.5%accuracy on the FakeNewsPrediction dataset.It outperformed the competitive schemes such as T5-SA-LSTM(RMSProp),T5-SA-LSTM(SGD)and some other models.
基金The authors extend their appreciation to Taif University,Saudi Arabia,for supporting this work through project No.(TU-DSPP-2024-54).
文摘Background:Locally advanced laryngeal squamous cell carcinoma(LA-LSCC)presents clinical challenges due to the lack of reliable non-invasive biomarkers.This study aimed to evaluate miR-449a as a diagnostic and prognostic biomarker in LA-LSCC.Methods:miR-449a expression was analyzed in tumor tissues,adjacent normal tissues,and serum from 81 LA-LSCC patients and 50 controls using quantitative real-time reverse transcription polymerase chain reaction(qRT-PCR).We assessed the diagnostic accuracy by Receiver Operating Characteristic curve(ROC curves),clinicopathological associations,survival outcomes(Kaplan-Meier),and treatment response dynamics.Results:miR-449a was significantly downregulated in LA-LSCC tissues(p<0.0001)and serum(p<0.0001),with a strong tissue-serum correlation(R^(2)=0.988).Tissue miR-449a demonstrated a diagnostic accuracy(Area Under the Curve,AUC=0.857),while serum showed moderate accuracy(AUC=0.734).High miR-449a expression correlated with favorable clinicopathological features and improved survival(median overall survival:67.82 vs.23.74 months;p=0.0012).Multivariate analysis confirmed miR-449a as an independent prognostic factor(p<0.001).miR-449a levels increased post-treatment,particularly in responders to chemotherapy/radiation(p<0.0001).Conclusion:miR-449a serves as a non-invasive biomarker for LA-LSCC diagnosis,prognosis,and treatment monitoring.Its dynamic expression highlights potential for risk stratification and therapy response prediction,warranting further validation in larger cohorts.
基金funded by Scientific Research Deanship at University of Ha’il-Saudi Arabia through project number(RG-24014).
文摘We present a computer-modeling framework for photovoltaic(PV)source emulation that preserves the exact single-diode physics while enabling iteration-free,real-time evaluation.We derive two closed-form explicit solvers based on the Lambert W function:a voltage-driven V-Lambert solver for high-fidelity I–V computation and a resistance-driven R-Lambert solver designed for seamless integration in a closed-loop PV emulator.Unlike Taylor-linearized explicit models,our proposed formulation retains the exponential nonlinearity of the PV equations.It employs a numerically stable analytical evaluation that eliminates the need for lookup tables and root-finding,all while maintaining limited computational costs and a small memory footprint.The R-Lambert model is integrated into a buck-converter emulator equipped with a discrete PI regulator,which generates current references directly from sensed operating points,thus supporting hardware-constrained implementation.Comprehensive numerical experiments conducted on six commercial modules from various technologies(mono,poly,and multicrystalline)demonstrate significant accuracy improvements under the IEC EN 50530 near-MPP criterion:the V-Lambert solver reduces the±10%Vmpp band error by up to 61 times compared to an explicit-model baseline.Dynamic simulations under varying irradiance,temperature,and load conditions achieve millisecond-scale settling with accurate trajectory tracking.Additionally,processor-in-the-loop experimental validation on an embedded microcontroller supports the simulation results.By unifying exact analytical modeling with embedded realization,this work advances computer modeling for PV emulation,MPPT benchmarking,and controller verification in integrated renewable energy systems.
文摘Five samples of LiMgPO_(4):Gd were prepared via five different production processes using a solid-state reaction method.The effects of the preparation process on optically stimulated luminescence(OSL)and thermoluminescence(TL)were investigated.Considering its high sensitivity,low fading,and minimum detectable dose(MDD),the LiMgPO_(4):Gd phosphor heated to 900℃for 15 h is concluded to be optimal.The effects of annealing on the OSL sensitivity,relative residual OSL signals measured after 24 h of irradiation,and MDD of LiMgPO_(4):Gd phosphors heated to 900℃for 15 h were also investigated.Considering its high sensitivity,low fading,and MDD,annealing at 350℃for 1 h is concluded to be optimal.The OSL signal of LiMgPO_(4):Gd was derived from the principal TL glow peak.For a maximum integration time of 5 s,the OSL signal was stable,with no fading 30 days after irradiation.LiMgPO_(4):Gd eliminated approximately 2.2%of the OSL signal at each readout for a readout time of 0.1 s,which is sufficient for fast and multiple OSL readout.The sensitivity of LiMgPO_(4):Gd phosphor,annealed for 1 h at 350℃with a reading time of 0.1 s,was found to be approximately 98%of that observed forα-Al_(2)O_(3):C(TLD-500k),which should be sufficient for low-dose measurements in personal,workplace,and environmental dosimetry.
文摘One of the main issues in designing optimum tapered cascades for uranium enrichment for annual fuel production in a power reactor is whether to employ large(fat)or small(thin)cascades.What will be the permissible and optimal ranges of the number of machines that can be used in a cascade?For the first time,the permissible and optimal ranges of the number of gas centrifuges that can be utilized in a cascade were investigated using two types of centrifuges,and the performance of small and large tapered cascades was discussed.The particle swarm optimization algorithm(PSO)has been used to optimize tapered cascades.The results show:(1)For the first centrifuge,41 cascades(91≤n≤4897)and for the second centrifuge,49 cascades(18≤n≤3839)with small and large sizes can be used in enrichment facilities,and the best cascade for them has 530(with 23 stages)and 39(with 7 stages)centrifuges,respectively.(2)For both centrifuges,when 600≤n(number of centrifuges=n),the large cascade performance changes are relatively insignificant.(3)For both types of gas centrifuges,the annual los s of separation power in enrichment facilities is approximately 1.25%-4.82%of the total separation work required.
基金supported by the Deanship of Scientific Research,Vice Presidency for Graduate Studies and Scientific Research,King Faisal University,Saudi Arabia[Grant No.KFU253774].
文摘Malware poses a significant threat to the Internet of Things(IoT).It enables unauthorized access to devices in the IoT environment.The lack of unique architectural standards causes challenges in developing robust malware detection(MD)models.The existing models demand substantial computational resources.This study intends to build a lightweight MD model to detect anomalies in IoT networks.The authors develop a transformation technique,converting the malware binaries into images.MobileNet V2 is fine-tuned using improved grey wolf optimization(IGWO)to extract crucial features of malicious and benign samples.The ResNeXt model is combined with the Linformer’s attention mechanism to identify Malware features.A fully connected layer is integrated with gradientweighted class activation mapping(Grad-CAM)in order to facilitate an interpretable classification model.The proposed model is evaluated using the IoT malware and the IoT-23 datasets.The model performs well on the two datasets with an accuracy of 98.94%,precision of 98.46%,recall of 98.11%,and F1-score of 98.28%on the IoT malware dataset,and an accuracy of 98.23%,precision of 96.80%,recall of 96.64%,and F1-score of 96.71%on the IoT-23 dataset,respectively.The findings indicate that the model has a high standard of classification.The lightweight architecture enables efficient deployment with an inference time of 1.42 s.Inference time has no direct impact on accuracy,precision,recall,or F1-score.However,the inference speed would warrant timely detection in latency-sensitive IoT applications.By achieving a remarkable result,the proposed study offers a comprehensive solution:a scalable,interpretable,and computationally efficient MD model for the evolving IoT landscape.
基金The researchers would like to thank the Deanship of Graduate Studies and Scientific Research at Qassim University for financial support(QU-APC-2025)。
文摘The evolution of cities into digitally managed environments requires computational systems that can operate in real time while supporting predictive and adaptive infrastructure management.Earlier approaches have often advanced one dimension—such as Internet of Things(IoT)-based data acquisition,Artificial Intelligence(AI)-driven analytics,or digital twin visualization—without fully integrating these strands into a single operational loop.As a result,many existing solutions encounter bottlenecks in responsiveness,interoperability,and scalability,while also leaving concerns about data privacy unresolved.This research introduces a hybrid AI–IoT–Digital Twin framework that combines continuous sensing,distributed intelligence,and simulation-based decision support.The design incorporates multi-source sensor data,lightweight edge inference through Convolutional Neural Networks(CNN)and Long ShortTerm Memory(LSTM)models,and federated learning enhanced with secure aggregation and differential privacy to maintain confidentiality.A digital twin layer extends these capabilities by simulating city assets such as traffic flows and water networks,generating what-if scenarios,and issuing actionable control signals.Complementary modules,including model compression and synchronization protocols,are embedded to ensure reliability in bandwidth-constrained and heterogeneous urban environments.The framework is validated in two urban domains:traffic management,where it adapts signal cycles based on real-time congestion patterns,and pipeline monitoring,where it anticipates leaks through pressure and vibration data.Experimental results show a 28%reduction in response time,a 35%decrease in maintenance costs,and a marked reduction in false positives relative to conventional baselines.The architecture also demonstrates stability across 50+edge devices under federated training and resilience to uneven node participation.The proposed system provides a scalable and privacy-aware foundation for predictive urban infrastructure management.By closing the loop between sensing,learning,and control,it reduces operator dependence,enhances resource efficiency,and supports transparent governance models for emerging smart cities.
文摘The biological stabilization of soil using microbially induced carbonate precipitation(MICP)employs ureolytic bacteria to precipitate calcium carbonate(CaCO3),which binds soil particles,enhancing strength,stiffness,and erosion resistance.The unconfinedcompressive strength(UCS),a key measure of soil strength,is critical in geotechnical engineering as it directly reflectsthe mechanical stability of treated soils.This study integrates explainable artificialintelligence(XAI)with geotechnical insights to model the UCS of MICP-treated sands.Using 517 experimental data points and a combination of various input variables—including median grain size(D50),coefficientof uniformity(Cu),void ratio(e),urea concentration(Mu),calcium concentration(Mc),optical density(OD)of bacterial solution,pH,and total injection volume(Vt)—fivemachine learning(ML)models,including eXtreme gradient boosting(XGBoost),Light gradient boosting machine(LightGBM),random forest(RF),gene expression programming(GEP),and multivariate adaptive regression splines(MARS),were developed and optimized.The ensemble models(XGBoost,LightGBM,and RF)were optimized using the Chernobyl disaster optimizer(CDO),a recently developed metaheuristic algorithm.Of these,LightGBM-CDO achieved the highest accuracy for UCS prediction.XAI techniques like feature importance analysis(FIA),SHapley additive exPlanations(SHAP),and partial dependence plots(PDPs)were also used to investigate the complex non-linear relationships between the input and output variables.The results obtained have demonstrated that the XAI-driven models can enhance the predictive accuracy and interpretability of MICP processes,offering a sustainable pathway for optimizing geotechnical applications.
文摘The aim of this study is to design,build,and evaluate an indirect forced convection solar dryer adapted to semi-arid climate,such as that of Bechar situated in the west south region of Algeria.The tested drying system consists of a flat-plate solar collector,an insulated two-chamber drying unit,and an Arduino-controlled device that ensures uniformtemperature distribution and real-timemonitoring using DHT22 sensors.Drying testswere conducted on locally grown beet slices at air temperatures of 45℃,60℃,and 80℃,with a constant air velocity of 1.2 m/s and a mass flow rate of 0.0027 kg/s.The collector reached a maximum temperature of 65℃,with thermal efficiencies ranging from 20%to 35%.In these conditions,the drying times were cut down to 200–300 min,and the beet’s moisture content dropped to 0.47,0.27,and 0.24 g/g dry matter,respectively.The experimental data were fitted to several empirical models,including the logarithmic model.The modelled results showed strong agreement with the experimental ones(correlation coefficients r=0.9919–0.9989;standard errors SE=0.017–0.043;root-mean-square errors RMSE=0.016–0.027).The results demonstrate that the system operates efficiently and consistently,making it suitable for the sustainable drying of agricultural and medicinal products in arid climates.
文摘The increasing number of interconnected devices and the incorporation of smart technology into contemporary healthcare systems have significantly raised the attack surface of cyber threats.The early detection of threats is both necessary and complex,yet these interconnected healthcare settings generate enormous amounts of heterogeneous data.Traditional Intrusion Detection Systems(IDS),which are generally centralized and machine learning-based,often fail to address the rapidly changing nature of cyberattacks and are challenged by ethical concerns related to patient data privacy.Moreover,traditional AI-driven IDS usually face challenges in handling large-scale,heterogeneous healthcare data while ensuring data privacy and operational efficiency.To address these issues,emerging technologies such as Big Data Analytics(BDA)and Federated Learning(FL)provide a hybrid framework for scalable,adaptive intrusion detection in IoT-driven healthcare systems.Big data techniques enable processing large-scale,highdimensional healthcare data,and FL can be used to train a model in a decentralized manner without transferring raw data,thereby maintaining privacy between institutions.This research proposes a privacy-preserving Federated Learning–based model that efficiently detects cyber threats in connected healthcare systems while ensuring distributed big data processing,privacy,and compliance with ethical regulations.To strengthen the reliability of the reported findings,the resultswere validated using cross-dataset testing and 95%confidence intervals derived frombootstrap analysis,confirming consistent performance across heterogeneous healthcare data distributions.This solution takes a significant step toward securing next-generation healthcare infrastructure by combining scalability,privacy,adaptability,and earlydetection capabilities.The proposed global model achieves a test accuracy of 99.93%±0.03(95%CI)and amiss-rate of only 0.07%±0.02,representing state-of-the-art performance in privacy-preserving intrusion detection.The proposed FL-driven IDS framework offers an efficient,privacy-preserving,and scalable solution for securing next-generation healthcare infrastructures by combining adaptability,early detection,and ethical data management.
文摘Origanum elongatum(OE)is an aromatic,medicinal plant endemic to Morocco that is widely used in traditional medicine due to its biological properties.This study aimed to elucidate the chemical composition of the essential oil(EO)obtained from O.elongatum(OEEO)at three stages of its life cycle,including vegetative stage(OEEO-VS),flowering stage(OEEO-FS),and post-flowering(OEEO-PFS),as well as to evaluate its biological and antiradical characteristics.The chemical analysis of the essential oil was conducted using gas chromatography-mass spectrometry(GC-MS).The antibacterial activity was evaluated in vitro through distinct methodologies,namely,disc diffusion and microatmosphere assay;subsequently,the minimum inhibitory concentration(MIC)was then determined.The antioxidant potential was also measured by using the DPPH and FRAP assays.The GC-MS revealed the predominant of p-cymene(26.83%_31.45%),γ-terpinene(8.46%_26.95%),thymol(13%_29.54%),and carvacrol(20.25%_37.26%),in all three samples,with notable variations according to the phenological stage of the samples.The EOs extracted at three phenological stages demonstrated notable antibacterial efficacy against all the phytopathogen tested.The MICs for Erwinia amylovora exhibited a range of 6.25 and 250μg/mL.However,for Agrobacterium tumefaciens C58 and Allorhizobium vitis S4,the MICs spanned 125 and 250μg/mL.In the DPPH test,the IC50 values were 168.25±1.14,147.01±0.78,and 132.01±2.06μg/mL for EOs derived from the vegetative,flowering,and post-flowering period,respectively.In the FRAP test,the EC50 values were 164.22±1.04,215.73±1.48,and 184.06±0.95μg/mL for the same stages.The findings offer promising prospects for the phytochemical development,demonstrating how the phenological stage significantly influences the therapeutic and biotechnological potential of O.elongatum.This has the potential to open up new avenues of research in the pharmaceutical,agronomic,and environmental fields.
文摘Objective:Deep learning is employed increasingly in Gastroenterology(GI)endoscopy computer-aided diagnostics for polyp segmentation and multi-class disease detection.In the real world,implementation requires high accuracy,therapeutically relevant explanations,strong calibration,domain generalization,and efficiency.Current Convolutional Neural Network(CNN)and transformer models compromise border precision and global context,generate attention maps that fail to align with expert reasoning,deteriorate during cross-center changes,and exhibit inadequate calibration,hence diminishing clinical trust.Methods:HMA-DER is a hierarchical multi-attention architecture that uses dilation-enhanced residual blocks and an explainability-aware Cognitive Alignment Score(CAS)regularizer to directly align attribution maps with reasoning signals from experts.The framework has additions that make it more resilient and a way to test for accuracy,macro-averaged F1 score,Area Under the Receiver Operating Characteristic Curve(AUROC),calibration(Expected Calibration Error(ECE),Brier Score),explainability(CAS,insertion/deletion AUC),cross-dataset transfer,and throughput.Results:HMA-DER gets Dice Similarity Coefficient scores of 89.5%and 86.0%on Kvasir-SEG and CVC-ClinicDB,beating the strongest baseline by+1.9 and+1.7 points.It gets 86.4%and 85.3%macro-F1 and 94.0%and 93.4%AUROC on HyperKvasir and GastroVision,which is better than the baseline by+1.4/+1.6macro-F1 and+1.2/+1.1AUROC.Ablation study shows that hierarchical attention gives the highest(+3.0),followed by CAS regularization(+2–3),dilatation(+1.5–2.0),and residual connections(+2–3).Cross-dataset validation demonstrates competitive zero-shot transfer(e.g.,KS→CVC Dice 82.7%),whereas multi-dataset training diminishes the domain gap,yielding an 88.1%primary-metric average.HMA-DER’s mixed-precision inference can handle 155 pictures per second,which helps with calibration.Conclusion:HMA-DER strikes a compromise between accuracy,explainability,robustness,and efficiency for the use of reliable GI computer-aided diagnosis in real-world clinical settings.
文摘Accurate prediction of concrete compressive strength is fundamental for optimizing mix designs,improving material utilization,and ensuring structural safety in modern construction.Traditional empirical methods often fail to capture the non-linear relationships among concrete constituents,especially with the growing use of supple-mentary cementitious materials and recycled aggregates.This study presents an integrated machine learning framework for concrete strength prediction,combining advanced regression models—namely CatBoost—with metaheuristic optimization algorithms,with a particular focus on the Somersaulting Spider Optimizer(SSO).A comprehensive dataset encompassing diverse mix proportions and material types was used to evaluate baseline machine learning models,including CatBoost,XGBoost,ExtraTrees,and RandomForest.Among these,CatBoost demonstrated superior accuracy across multiple performance metrics.To further enhance predictive capability,several bio-inspired optimizers were employed for hyperparameter tuning.The SSO-CatBoost hybrid achieved the lowest mean squared error and highest correlation coefficients,outperforming other metaheuristic approaches such as Genetic Algorithm,Particle Swarm Optimization,and Grey Wolf Optimizer.Statistical significance was established through Analysis of Variance and Wilcoxon signed-rank testing,confirming the robustness of the optimized models.The proposed methodology not only delivers improved predictive performance but also offers a transparent framework for mix design optimization,supporting data-driven decision making in sustainable and resilient infrastructure development.
基金funded by United Arab Emirates University(UAEU)under the UAEU-AUA grant number G00004577(12N145)with the corresponding grant at Universiti Malaya(UM)under grant number IF019-2024.
文摘Concrete-filled steel tubes(CFST)are widely utilized in civil engineering due to their superior load-bearing capacity,ductility,and seismic resistance.However,existing design codes,such as AISC and Eurocode 4,tend to be excessively conservative as they fail to account for the composite action between the steel tube and the concrete core.To address this limitation,this study proposes a hybrid model that integrates XGBoost with the Pied Kingfisher Optimizer(PKO),a nature-inspired algorithm,to enhance the accuracy of shear strength prediction for CFST columns.Additionally,quantile regression is employed to construct prediction intervals for the ultimate shear force,while the Asymmetric Squared Error Loss(ASEL)function is incorporated to mitigate overestimation errors.The computational results demonstrate that the PKO-XGBoost model delivers superior predictive accuracy,achieving a Mean Absolute Percentage Error(MAPE)of 4.431%and R2 of 0.9925 on the test set.Furthermore,the ASEL-PKO-XGBoost model substantially reduces overestimation errors to 28.26%,with negligible impact on predictive performance.Additionally,based on the Genetic Algorithm(GA)and existing equation models,a strength equation model is developed,achieving markedly higher accuracy than existing models(R^(2)=0.934).Lastly,web-based Graphical User Interfaces(GUIs)were developed to enable real-time prediction.
基金Supported by Princess Nourah bint Abdulrahman University Researchers Supporting Project number(PNURSP2025R896).
文摘Deep neural networks have achieved excellent classification results on several computer vision benchmarks.This has led to the popularity of machine learning as a service,where trained algorithms are hosted on the cloud and inference can be obtained on real-world data.In most applications,it is important to compress the vision data due to the enormous bandwidth and memory requirements.Video codecs exploit spatial and temporal correlations to achieve high compression ratios,but they are computationally expensive.This work computes the motion fields between consecutive frames to facilitate the efficient classification of videos.However,contrary to the normal practice of reconstructing the full-resolution frames through motion compensation,this work proposes to infer the class label from the block-based computed motion fields directly.Motion fields are a richer and more complex representation of motion vectors,where each motion vector carries the magnitude and direction information.This approach has two advantages:the cost of motion compensation and video decoding is avoided,and the dimensions of the input signal are highly reduced.This results in a shallower network for classification.The neural network can be trained using motion vectors in two ways:complex representations and magnitude-direction pairs.The proposed work trains a convolutional neural network on the direction and magnitude tensors of the motion fields.Our experimental results show 20×faster convergence during training,reduced overfitting,and accelerated inference on a hand gesture recognition dataset compared to full-resolution and downsampled frames.We validate the proposed methodology on the HGds dataset,achieving a testing accuracy of 99.21%,on the HMDB51 dataset,achieving 82.54%accuracy,and on the UCF101 dataset,achieving 97.13%accuracy,outperforming state-of-the-art methods in computational efficiency.
