The rapid rise of cyberattacks and the gradual failure of traditional defense systems and approaches led to using artificial intelligence(AI)techniques(such as machine learning(ML)and deep learning(DL))to build more e...The rapid rise of cyberattacks and the gradual failure of traditional defense systems and approaches led to using artificial intelligence(AI)techniques(such as machine learning(ML)and deep learning(DL))to build more efficient and reliable intrusion detection systems(IDSs).However,the advent of larger IDS datasets has negatively impacted the performance and computational complexity of AI-based IDSs.Many researchers used data preprocessing techniques such as feature selection and normalization to overcome such issues.While most of these researchers reported the success of these preprocessing techniques on a shallow level,very few studies have been performed on their effects on a wider scale.Furthermore,the performance of an IDS model is subject to not only the utilized preprocessing techniques but also the dataset and the ML/DL algorithm used,which most of the existing studies give little emphasis on.Thus,this study provides an in-depth analysis of feature selection and normalization effects on IDS models built using three IDS datasets:NSL-KDD,UNSW-NB15,and CSE–CIC–IDS2018,and various AI algorithms.A wrapper-based approach,which tends to give superior performance,and min-max normalization methods were used for feature selection and normalization,respectively.Numerous IDS models were implemented using the full and feature-selected copies of the datasets with and without normalization.The models were evaluated using popular evaluation metrics in IDS modeling,intra-and inter-model comparisons were performed between models and with state-of-the-art works.Random forest(RF)models performed better on NSL-KDD and UNSW-NB15 datasets with accuracies of 99.86%and 96.01%,respectively,whereas artificial neural network(ANN)achieved the best accuracy of 95.43%on the CSE–CIC–IDS2018 dataset.The RF models also achieved an excellent performance compared to recent works.The results show that normalization and feature selection positively affect IDS modeling.Furthermore,while feature selection benefits simpler algorithms(such as RF),normalization is more useful for complex algorithms like ANNs and deep neural networks(DNNs),and algorithms such as Naive Bayes are unsuitable for IDS modeling.The study also found that the UNSW-NB15 and CSE–CIC–IDS2018 datasets are more complex and more suitable for building and evaluating modern-day IDS than the NSL-KDD dataset.Our findings suggest that prioritizing robust algorithms like RF,alongside complex models such as ANN and DNN,can significantly enhance IDS performance.These insights provide valuable guidance for managers to develop more effective security measures by focusing on high detection rates and low false alert rates.展开更多
On-device Artificial Intelligence(AI)accelerators capable of not only inference but also training neural network models are in increasing demand in the industrial AI field,where frequent retraining is crucial due to f...On-device Artificial Intelligence(AI)accelerators capable of not only inference but also training neural network models are in increasing demand in the industrial AI field,where frequent retraining is crucial due to frequent production changes.Batch normalization(BN)is fundamental to training convolutional neural networks(CNNs),but its implementation in compact accelerator chips remains challenging due to computational complexity,particularly in calculating statistical parameters and gradients across mini-batches.Existing accelerator architectures either compromise the training accuracy of CNNs through approximations or require substantial computational resources,limiting their practical deployment.We present a hardware-optimized BN accelerator that maintains training accuracy while significantly reducing computational overhead through three novel techniques:(1)resourcesharing for efficient resource utilization across forward and backward passes,(2)interleaved buffering for reduced dynamic random-access memory(DRAM)access latencies,and(3)zero-skipping for minimal gradient computation.Implemented on a VCU118 Field Programmable Gate Array(FPGA)on 100 MHz and validated using You Only Look Once version 2-tiny(YOLOv2-tiny)on the PASCALVisualObjectClasses(VOC)dataset,our normalization accelerator achieves a 72%reduction in processing time and 83%lower power consumption compared to a 2.4 GHz Intel Central Processing Unit(CPU)software normalization implementation,while maintaining accuracy(0.51%mean Average Precision(mAP)drop at floating-point 32 bits(FP32),1.35%at brain floating-point 16 bits(bfloat16)).When integrated into a neural processing unit(NPU),the design demonstrates 63%and 97%performance improvements over AMD CPU and Reduced Instruction Set Computing-V(RISC-V)implementations,respectively.These results confirm that our proposed BN hardware design enables efficient,high-accuracy,and power-saving on-device training for modern CNNs.Our results demonstrate that efficient hardware implementation of standard batch normalization is achievable without sacrificing accuracy,enabling practical on-device CNN training with significantly reduced computational and power requirements.展开更多
Current spatio-temporal action detection methods lack sufficient capabilities in extracting and comprehending spatio-temporal information. This paper introduces an end-to-end Adaptive Cross-Scale Fusion Encoder-Decode...Current spatio-temporal action detection methods lack sufficient capabilities in extracting and comprehending spatio-temporal information. This paper introduces an end-to-end Adaptive Cross-Scale Fusion Encoder-Decoder (ACSF-ED) network to predict the action and locate the object efficiently. In the Adaptive Cross-Scale Fusion Spatio-Temporal Encoder (ACSF ST-Encoder), the Asymptotic Cross-scale Feature-fusion Module (ACCFM) is designed to address the issue of information degradation caused by the propagation of high-level semantic information, thereby extracting high-quality multi-scale features to provide superior features for subsequent spatio-temporal information modeling. Within the Shared-Head Decoder structure, a shared classification and regression detection head is constructed. A multi-constraint loss function composed of one-to-one, one-to-many, and contrastive denoising losses is designed to address the problem of insufficient constraint force in predicting results with traditional methods. This loss function enhances the accuracy of model classification predictions and improves the proximity of regression position predictions to ground truth objects. The proposed method model is evaluated on the popular dataset UCF101-24 and JHMDB-21. Experimental results demonstrate that the proposed method achieves an accuracy of 81.52% on the Frame-mAP metric, surpassing current existing methods.展开更多
In tissue engineering(TE),tissue-inducing scaffolds are a promising solution for organ and tissue repair owing to their ability to attract stem cells in vivo,thereby inducing endogenous tissue regeneration through top...In tissue engineering(TE),tissue-inducing scaffolds are a promising solution for organ and tissue repair owing to their ability to attract stem cells in vivo,thereby inducing endogenous tissue regeneration through topological cues.An ideal TE scaffold should possess biomimetic cross-scale structures,similar to that of natural extracellular matrices,at the nano-to macro-scale level.Although freeform fabrication of TE scaffolds can be achieved through 3D printing,this method is limited in simultaneously building multiscale structures.To address this challenge,low-temperature fields were adopted in the traditional fabrication processes,such as casting and 3D printing.Ice crystals grow during scaffold fabrication and act as a template to control the nano-and micro-structures.These microstructures can be optimized by adjusting various parameters,such as the direction and magnitude of the low-temperature field.By preserving the macro-features fabricated using traditional methods,additional micro-structures with smaller scales can be incorporated simultaneously,realizing cross-scale structures that provide a better mimic of natural organs and tissues.In this paper,we present a state-of-the-art review of three low-temperature-field-assisted fabrication methods—freeze casting,cryogenic3D printing,and freeze spinning.Fundamental working principles,fabrication setups,processes,and examples of biomedical applications are introduced.The challenges and outlook for low-temperature-assisted fabrication are also discussed.展开更多
Renormalization group analysis has been proposed to eliminate secular terms in perturbation solutions of differential equations and thus expand the domain of their validity.Here we extend the method to treat periodic ...Renormalization group analysis has been proposed to eliminate secular terms in perturbation solutions of differential equations and thus expand the domain of their validity.Here we extend the method to treat periodic orbits or limit cycles.Interesting normal forms could be derived through a generalization of the concept'resonance',which offers nontrivial analytic approximations.Compared with traditional techniques such as multi-scale methods,the current scheme proceeds in a very straightforward and simple way,delivering not only the period and the amplitude but also the transient path to limit cycles.The method is demonstrated with several examples including the Duffing oscillator,van der Pol equation and Lorenz equation.The obtained solutions match well with numerical results and with those derived by traditional analytic methods.展开更多
In recent decades,brain tumors have emerged as a serious neurological disorder that often leads to death.Hence,Brain Tumor Segmentation(BTS)is significant to enable the visualization,classification,and delineation of ...In recent decades,brain tumors have emerged as a serious neurological disorder that often leads to death.Hence,Brain Tumor Segmentation(BTS)is significant to enable the visualization,classification,and delineation of tumor regions in Magnetic Resonance Imaging(MRI).However,BTS remains a challenging task because of noise,non-uniform object texture,diverse image content and clustered objects.To address these challenges,a novel model is implemented in this research.The key objective of this research is to improve segmentation accuracy and generalization in BTS by incorporating Switchable Normalization into Faster R-CNN,which effectively captures the fine-grained tumor features to enhance segmentation precision.MRI images are initially acquired from three online datasets:Dataset 1—Brain Tumor Segmentation(BraTS)2018,Dataset 2—BraTS 2019,and Dataset 3—BraTS 2020.Subsequently,the Switchable Normalization-based Faster Regions with Convolutional Neural Networks(SNFRC)model is proposed for improved BTS in MRI images.In the proposed model,Switchable Normalization is integrated into the conventional architecture,enhancing generalization capability and reducing overfitting to unseen image data,which is essential due to the typically limited size of available datasets.The network depth is increased to obtain discriminative semantic features that improve segmentation performance.Specifically,Switchable Normalization captures the diverse feature representations from the brain images.The Faster R-CNN model develops end-to-end training and effective regional proposal generation,with an enhanced training stability using Switchable Normalization,to perform an effective segmentation in MRI images.From the experimental results,the proposed model attains segmentation accuracies of 99.41%,98.12%,and 96.71%on Datasets 1,2,and 3,respectively,outperforming conventional deep learning models used for BTS.展开更多
Global and local modeling is essential for image super-resolution tasks.However,current efforts often lack explicit consideration of the cross-scale knowledge in large-scale earth observation scenarios,resulting in su...Global and local modeling is essential for image super-resolution tasks.However,current efforts often lack explicit consideration of the cross-scale knowledge in large-scale earth observation scenarios,resulting in suboptimal single-scale representations in global and local modeling.The key motivation of this work is inspired by two observations:1)There exists hierarchical features at the local and global regions in remote sensing images,and 2)they exhibit scale variation of similar ground objects(e.g.cross-scale similarity).In light of these,this paper presents an effective method to grasp the global and local image hierarchies by systematically exploring the cross-scale correlation.Specifically,we developed a Cross-scale Self-Attention(CSA)to model the global features,which introduces an auxiliary token space to calculate cross-scale self-attention matrices,thus exploring global dependency from diverse token scales.To extract the cross-scale localities,a Cross-scale Channel Attention(CCA)is devised,where multi-scale features are explored and progressively incorporated into an enriched feature.Moreover,by hierarchically deploying CSA and CCA into transformer groups,the proposed Cross-scale Hierarchical Transformer(CHT)can effectively explore cross-scale representations in remote sensing images,leading to a favorable reconstruction performance.Comprehensive experiments and analysis on four remote sensing datasets have demonstrated the superiority of CHT in both simulated and real-world remote sensing scenes.In particular,our CHT outperforms the state-of-the-art approach(TransENet)in terms of PSNR by 0.11 dB on average,but only accounts for 54.8%of its parameters.展开更多
Remodeling tumor microenvironment(TME)is a very promising and effective strategy to enhance the effects of chemotherapy,photodynamic therapy,and immunotherapy.Normalization of tumor vasculature as well as depletion of...Remodeling tumor microenvironment(TME)is a very promising and effective strategy to enhance the effects of chemotherapy,photodynamic therapy,and immunotherapy.Normalization of tumor vasculature as well as depletion of glutathione(GSH)can improve the TME.Here,we developed a novel therapeutic nanoparticle functional enzyme ultra QDAU5 nanoparticles(FEUQ Nps)based on a fluorescence-on and releasable strategy by combining a vascular normalization inducer,a GSH depleting agent,and an activated fluorophore.In which the cleavage of disulfide bonds releases active molecules that induce vascular normalization and improve the hypoxic microenvironment.In addition,it may deplete GSH in cancer cells,thus inducing the production of reactive oxygen species(ROS)and lipid peroxide(LPO)and promoting iron toxicity.It may also lead to endoplasmic stress and release of calmodulin,which activates the immune system.Meanwhile,quenched fluorophores are turned on in the presence of galactosidase(GLU)for tumor-specific labeling.In summary,we developed novel therapeutic agent nanoparticles with the function of vascular normalization inducers to achieve specific labeling of hepatocellular carcinoma while exerting efficient antitumor effects in vivo.展开更多
Tumor vascular normalization has emerged as a promising strategy for synergistic therapy recently.Based on the strategy of“fluorescence turn on-controllable release”,a novel bifunctional candidate was con-structed b...Tumor vascular normalization has emerged as a promising strategy for synergistic therapy recently.Based on the strategy of“fluorescence turn on-controllable release”,a novel bifunctional candidate was con-structed based on previous developed vascular normalization inducer QDAU5,which could self-assemble to form functional enzyme infrared QDAU5 nanoparticles(FEIRQ NPs).Subsequently,biological evaluation demonstrated that the FEIRQ NPs could induce ferroptosis,endoplasmic reticulum stress,and antigen pre-conditioning and maturation of dendritic cells and CD8^(+)T cells,leading to excellent antitumor efficacy in the absence of cytotoxic drugs.Additionally,FEIRQ NPs show high fluorescence intensity upon expo-sure to theβ-galactosidase(β-Gal)enzyme expressed in ovarian cancer,enabling real-time monitoring of therapeutic effects.Overall,our findings suggest a prospering strategy to early diagnosis and efficient therapy for ovarian cancer without cytotoxicity.展开更多
Background:Isotonic crystalloids are recommended as the first choice for fluid therapy in acute pan-creatitis(AP),with normal saline(NS)and lactate Ringer’s(LR)used most often.Evidence based recom-mendations on the t...Background:Isotonic crystalloids are recommended as the first choice for fluid therapy in acute pan-creatitis(AP),with normal saline(NS)and lactate Ringer’s(LR)used most often.Evidence based recom-mendations on the type of fluid are conflicting and generally come from small single-center randomized controlled trials(RCTs).We therefore conducted a systematic review and meta-analysis to compare the effect of balanced solutions(BS)versus NS on patient-centered clinical outcomes in AP.Methods:From four databases searched up to October 2024,we included only RCTs of adult patients with AP that compared the use of BS(including LR,acetate Ringer’s,etc.)with NS.The primary out-come was the disease advances from AP to moderately severe and severe AP(MSAP/SAP).Trial sequential analyses(TSA)were conducted to control for type-I and type-II errors and Grading of Recommendations Assessment,Development,and Evaluation(GRADE)was used to assess the quality of evidence.Results:Six RCTs were identified and included,involving 260 patients treated with BS and 298 patients with NS.Patients who received the BS had less MSAP/SAP[odds ratio(OR)=0.50,95%confidence in-terval(CI):0.29 to 0.85,P=0.01,I^(2)=0%;5 studies,299 patients],reduced the need of ICU admission(OR=0.60,95%CI:0.39 to 0.93,P=0.02,I^(2)=0%;5 studies,507 patients)and shorter length of hospital stay[mean difference(MD)=-0.88,95%CI:-1.48 to-0.28,P=0.004,I^(2)=0%;6 studies,558 patients;confirmed by TSA with high certainty]compared with those who received NS.The evidence for most of the clinical outcomes was rated as moderate to low due to the risk of bias,imprecision and inconsistency.Conclusions:BS,compared with NS,was associated with improved clinical outcomes in patients with AP.However,given the moderate to low quality of evidence for most of the outcomes assessed,further trials are warranted.展开更多
A conceptual model of intermittent joints is introduced to the cyclic shear test in the laboratory to explore the effects of loading parameters on its shear behavior under cyclic shear loading.The results show that th...A conceptual model of intermittent joints is introduced to the cyclic shear test in the laboratory to explore the effects of loading parameters on its shear behavior under cyclic shear loading.The results show that the loading parameters(initial normal stress,normal stiffness,and shear velocity)determine propagation paths of the wing and secondary cracks in rock bridges during the initial shear cycle,creating different morphologies of macroscopic step-path rupture surfaces and asperities on them.The differences in stress state and rupture surface induce different cyclic shear responses.It shows that high initial normal stress accelerates asperity degradation,raises shear resistance,and promotes compression of intermittent joints.In addition,high normal stiffness provides higher normal stress and shear resistance during the initial cycles and inhibits the dilation and compression of intermittent joints.High shear velocity results in a higher shear resistance,greater dilation,and greater compression.Finally,shear strength is most sensitive to initial normal stress,followed by shear velocity and normal stiffness.Moreover,average dilation angle is most sensitive to initial normal stress,followed by normal stiffness and shear velocity.During the shear cycles,frictional coefficient is affected by asperity degradation,backfilling of rock debris,and frictional area,exhibiting a non-monotonic behavior.展开更多
In this paper,we mainly focus on a type of nonlinear Choquard equations with nonconstant potential.Under appropriate hypotheses on potential function and nonlinear terms,we prove that the above Choquard equation with ...In this paper,we mainly focus on a type of nonlinear Choquard equations with nonconstant potential.Under appropriate hypotheses on potential function and nonlinear terms,we prove that the above Choquard equation with prescribed 2-norm has some normalized solutions by introducing variational methods.展开更多
This article studies a class of nonlinear Kirchhoff equations with exponential critical growth,trapping potential,and perturbation.Under appropriate assumptions about f and h,the article obtained the existence of norm...This article studies a class of nonlinear Kirchhoff equations with exponential critical growth,trapping potential,and perturbation.Under appropriate assumptions about f and h,the article obtained the existence of normalized positive solutions for this equation via the Trudinger-Moser inequality and variational methods.Moreover,these solutions are also ground state solutions.Additionally,the article also characterized the asymptotic behavior of solutions.The results of this article expand the research of relevant literature.展开更多
The present study focuses on simulating supercavitating projectile tail-slaps with an analytical method.A model of 3σ-normal distribution tail-slaps for a supercavitating projectile is established.Meanwhile,theσ-κe...The present study focuses on simulating supercavitating projectile tail-slaps with an analytical method.A model of 3σ-normal distribution tail-slaps for a supercavitating projectile is established.Meanwhile,theσ-κequation is derived,which is included in this model.Next,the supercavitating projectile tail-slaps are simulated by combining the proposed model and the Logvinovich supercavity section expansion equation.The results show that the number of tail-slaps depends on where the initial several tail-slaps are under the same initial condition.If the distances between the initial several tail-slap positions are large,the number of tail-slaps will considerably decrease,and vice versa.Furthermore,a series of simulations is employed to analyze the influence of the initial angular velocity and the centroid.Analysis of variance is used to evaluate simulation results.The evaluation results suggest that the projectile’s initial angular velocity and centroid have a major impact on the tail-slap number.The larger the value of initial angular velocity,the higher the probability of an increase in tail-slap number.Additionally,the closer the centroid is to the projectile head,the less likely a tail-slap number increase.This study offers important insights into supercavitating projectile tail-slap research.展开更多
Consider the Kirchhoff equation with Hartree type nonlinearity■where a,b>0,λ,μ∈R,2<q<6,0<α<3,and Iαis the Riesz potential integral operator of orderα.Solutions with prescribed mass■,also known a...Consider the Kirchhoff equation with Hartree type nonlinearity■where a,b>0,λ,μ∈R,2<q<6,0<α<3,and Iαis the Riesz potential integral operator of orderα.Solutions with prescribed mass■,also known as normalized solutions,are of particular interest in the current paper.Under various assumptions onμ,c and q,we establish the existence,nonexistence and asymptotic behavior of normalized solutions for the above elliptic equation.展开更多
In this paper,we investigate the existence and multiplicity of normalized solutions for the following fractional Schrödinger equations{(-△)^(s)u+λu=|u|^(p-2)u-|u|^(q-2)u,x∈R^(N),∫_(R^(N))|u|^(2)dx=c>0,wher...In this paper,we investigate the existence and multiplicity of normalized solutions for the following fractional Schrödinger equations{(-△)^(s)u+λu=|u|^(p-2)u-|u|^(q-2)u,x∈R^(N),∫_(R^(N))|u|^(2)dx=c>0,where N≥2,s∈(0,1),2+4s/N<p<q≤2_(s)^(*)=2N/N-2s,(-△)^(s)represents the fractional Laplacian operator of order s,and the frequencyλ∈R is unknown and appears as a Lagrange multiplier.Specifically,we show that there exists a c>0 such that if c>c,then the problem(P)has at least two normalized solutions,including a normalized ground state solution and a mountain pass type solution.We mainly extend the results in[Commun Pure Appl Anal,2022,21:4113–4145],which dealt with the problem(P)for the case 2<p<q<2+4s/N.展开更多
This paper introduces a novel numerical method based on an energy-minimizing normalized residual network(EMNorm Res Net)to compute the ground-state solution of Bose-Einstein condensates at zero or low temperatures.Sta...This paper introduces a novel numerical method based on an energy-minimizing normalized residual network(EMNorm Res Net)to compute the ground-state solution of Bose-Einstein condensates at zero or low temperatures.Starting from the three-dimensional Gross-Pitaevskii equation(GPE),we reduce it to the 1D and 2D GPEs because of the radial symmetry and cylindrical symmetry.The ground-state solution is formulated by minimizing the energy functional under constraints,which is directly solved using the EM-Norm Res Net approach.The paper provides detailed solutions for the ground states in 1D,2D(with radial symmetry),and 3D(with cylindrical symmetry).We use the Thomas-Fermi approximation as the target function to pre-train the neural network.Then,the formal network is trained using the energy minimization method.In contrast to traditional numerical methods,our neural network approach introduces two key innovations:(i)a novel normalization technique designed for high-dimensional systems within an energy-based loss function;(ii)improved training efficiency and model robustness by incorporating gradient stabilization techniques into residual networks.Extensive numerical experiments validate the method's accuracy across different spatial dimensions.展开更多
Anomaly detection in wind turbines involves emphasizing its ability to improve operational efficiency,reduce maintenance costs,extend their lifespan,and enhance reliability in the wind energy sector.This is particular...Anomaly detection in wind turbines involves emphasizing its ability to improve operational efficiency,reduce maintenance costs,extend their lifespan,and enhance reliability in the wind energy sector.This is particularly necessary in offshore wind,currently one of the most critical assets for achieving sustainable energy generation goals,due to the harsh marine environment and the difficulty of maintenance tasks.To address this problem,this work proposes a data-driven methodology for detecting power generation anomalies in offshore wind turbines,using normalized and linearized operational data.The proposed framework transforms heterogeneous wind speed and power measurements into a unified scale,enabling the development of a new wind power index(WPi)that quantifies deviations from expected performance.Additionally,spatial and temporal coherence analyses of turbines within a wind farm ensure the validity of these normalized measurements across different wind turbine models and operating conditions.Furthermore,a Support Vector Machine(SVM)refines the classification process,effectively distinguishing measurement errors from actual power generation failures.Validation of this strategy using real-world data from the Alpha Ventus wind farm demonstrates that the proposed approach not only improves predictive maintenance but also optimizes energy production,highlighting its potential for broad application in offshore wind installations.展开更多
Urban spaces are becoming increasingly congested,and excavations are frequently performed close to existing underground structures such as tunnels.Understanding the mechanical response of proximal soil and tunnels to ...Urban spaces are becoming increasingly congested,and excavations are frequently performed close to existing underground structures such as tunnels.Understanding the mechanical response of proximal soil and tunnels to these excavations is important for efficient and safe underground construction.However,previous investigations of this issue have predominantly made assumptions of plane-strain conditions and normal gravity states,and focused on the performance of tunnels affected by excavation and unloading in sandy strata.In this study,a 3D centrifuge model test is conducted to investigate the influence of excavation on an adjacent existing tunnel in normally consolidated clay.The testing results indicate that the excavation has a significant impact on the horizontal deformation of the retaining wall and tunnel.Moreover,the settlements of the ground surface and the tunnel are mainly affected by the long-term period after excavation.The excavation is found to induce ground movement towards the pit,resulting in prolonged fluctuations in pore water pressure and lateral earth pressure.The testing results are compared with numerical simulations,achieving consistency.A numerical parametric study on the tunnel location shows that when the tunnel is closer to the retaining wall,the decreases in lateral earth pressure and pore water pressure during excavation are more pronounced.展开更多
文摘The rapid rise of cyberattacks and the gradual failure of traditional defense systems and approaches led to using artificial intelligence(AI)techniques(such as machine learning(ML)and deep learning(DL))to build more efficient and reliable intrusion detection systems(IDSs).However,the advent of larger IDS datasets has negatively impacted the performance and computational complexity of AI-based IDSs.Many researchers used data preprocessing techniques such as feature selection and normalization to overcome such issues.While most of these researchers reported the success of these preprocessing techniques on a shallow level,very few studies have been performed on their effects on a wider scale.Furthermore,the performance of an IDS model is subject to not only the utilized preprocessing techniques but also the dataset and the ML/DL algorithm used,which most of the existing studies give little emphasis on.Thus,this study provides an in-depth analysis of feature selection and normalization effects on IDS models built using three IDS datasets:NSL-KDD,UNSW-NB15,and CSE–CIC–IDS2018,and various AI algorithms.A wrapper-based approach,which tends to give superior performance,and min-max normalization methods were used for feature selection and normalization,respectively.Numerous IDS models were implemented using the full and feature-selected copies of the datasets with and without normalization.The models were evaluated using popular evaluation metrics in IDS modeling,intra-and inter-model comparisons were performed between models and with state-of-the-art works.Random forest(RF)models performed better on NSL-KDD and UNSW-NB15 datasets with accuracies of 99.86%and 96.01%,respectively,whereas artificial neural network(ANN)achieved the best accuracy of 95.43%on the CSE–CIC–IDS2018 dataset.The RF models also achieved an excellent performance compared to recent works.The results show that normalization and feature selection positively affect IDS modeling.Furthermore,while feature selection benefits simpler algorithms(such as RF),normalization is more useful for complex algorithms like ANNs and deep neural networks(DNNs),and algorithms such as Naive Bayes are unsuitable for IDS modeling.The study also found that the UNSW-NB15 and CSE–CIC–IDS2018 datasets are more complex and more suitable for building and evaluating modern-day IDS than the NSL-KDD dataset.Our findings suggest that prioritizing robust algorithms like RF,alongside complex models such as ANN and DNN,can significantly enhance IDS performance.These insights provide valuable guidance for managers to develop more effective security measures by focusing on high detection rates and low false alert rates.
基金supported by the National Research Foundation of Korea(NRF)grant for RLRC funded by the Korea government(MSIT)(No.2022R1A5A8026986,RLRC)supported by Institute of Information&Communications Technology Planning&Evaluation(IITP)grant funded by the Korea government(MSIT)(No.2020-0-01304,Development of Self-Learnable Mobile Recursive Neural Network Processor Technology)+3 种基金supported by the MSIT(Ministry of Science and ICT),Republic of Korea,under the Grand Information Technology Research Center support program(IITP-2024-2020-0-01462,Grand-ICT)supervised by the IITP(Institute for Information&Communications Technology Planning&Evaluation)supported by the Korea Technology and Information Promotion Agency for SMEs(TIPA)supported by the Korean government(Ministry of SMEs and Startups)’s Smart Manufacturing Innovation R&D(RS-2024-00434259).
文摘On-device Artificial Intelligence(AI)accelerators capable of not only inference but also training neural network models are in increasing demand in the industrial AI field,where frequent retraining is crucial due to frequent production changes.Batch normalization(BN)is fundamental to training convolutional neural networks(CNNs),but its implementation in compact accelerator chips remains challenging due to computational complexity,particularly in calculating statistical parameters and gradients across mini-batches.Existing accelerator architectures either compromise the training accuracy of CNNs through approximations or require substantial computational resources,limiting their practical deployment.We present a hardware-optimized BN accelerator that maintains training accuracy while significantly reducing computational overhead through three novel techniques:(1)resourcesharing for efficient resource utilization across forward and backward passes,(2)interleaved buffering for reduced dynamic random-access memory(DRAM)access latencies,and(3)zero-skipping for minimal gradient computation.Implemented on a VCU118 Field Programmable Gate Array(FPGA)on 100 MHz and validated using You Only Look Once version 2-tiny(YOLOv2-tiny)on the PASCALVisualObjectClasses(VOC)dataset,our normalization accelerator achieves a 72%reduction in processing time and 83%lower power consumption compared to a 2.4 GHz Intel Central Processing Unit(CPU)software normalization implementation,while maintaining accuracy(0.51%mean Average Precision(mAP)drop at floating-point 32 bits(FP32),1.35%at brain floating-point 16 bits(bfloat16)).When integrated into a neural processing unit(NPU),the design demonstrates 63%and 97%performance improvements over AMD CPU and Reduced Instruction Set Computing-V(RISC-V)implementations,respectively.These results confirm that our proposed BN hardware design enables efficient,high-accuracy,and power-saving on-device training for modern CNNs.Our results demonstrate that efficient hardware implementation of standard batch normalization is achievable without sacrificing accuracy,enabling practical on-device CNN training with significantly reduced computational and power requirements.
基金support for this work was supported by Key Lab of Intelligent and Green Flexographic Printing under Grant ZBKT202301.
文摘Current spatio-temporal action detection methods lack sufficient capabilities in extracting and comprehending spatio-temporal information. This paper introduces an end-to-end Adaptive Cross-Scale Fusion Encoder-Decoder (ACSF-ED) network to predict the action and locate the object efficiently. In the Adaptive Cross-Scale Fusion Spatio-Temporal Encoder (ACSF ST-Encoder), the Asymptotic Cross-scale Feature-fusion Module (ACCFM) is designed to address the issue of information degradation caused by the propagation of high-level semantic information, thereby extracting high-quality multi-scale features to provide superior features for subsequent spatio-temporal information modeling. Within the Shared-Head Decoder structure, a shared classification and regression detection head is constructed. A multi-constraint loss function composed of one-to-one, one-to-many, and contrastive denoising losses is designed to address the problem of insufficient constraint force in predicting results with traditional methods. This loss function enhances the accuracy of model classification predictions and improves the proximity of regression position predictions to ground truth objects. The proposed method model is evaluated on the popular dataset UCF101-24 and JHMDB-21. Experimental results demonstrate that the proposed method achieves an accuracy of 81.52% on the Frame-mAP metric, surpassing current existing methods.
基金National Natural Science Foundation Council of China(Grant No.52305359)Hubei Provincial Natural Science Foundation of China(Grant No.2023AFB141)National Medical Products Administration Key Laboratory for Dental Materials(PKUSS20240401)。
文摘In tissue engineering(TE),tissue-inducing scaffolds are a promising solution for organ and tissue repair owing to their ability to attract stem cells in vivo,thereby inducing endogenous tissue regeneration through topological cues.An ideal TE scaffold should possess biomimetic cross-scale structures,similar to that of natural extracellular matrices,at the nano-to macro-scale level.Although freeform fabrication of TE scaffolds can be achieved through 3D printing,this method is limited in simultaneously building multiscale structures.To address this challenge,low-temperature fields were adopted in the traditional fabrication processes,such as casting and 3D printing.Ice crystals grow during scaffold fabrication and act as a template to control the nano-and micro-structures.These microstructures can be optimized by adjusting various parameters,such as the direction and magnitude of the low-temperature field.By preserving the macro-features fabricated using traditional methods,additional micro-structures with smaller scales can be incorporated simultaneously,realizing cross-scale structures that provide a better mimic of natural organs and tissues.In this paper,we present a state-of-the-art review of three low-temperature-field-assisted fabrication methods—freeze casting,cryogenic3D printing,and freeze spinning.Fundamental working principles,fabrication setups,processes,and examples of biomedical applications are introduced.The challenges and outlook for low-temperature-assisted fabrication are also discussed.
文摘Renormalization group analysis has been proposed to eliminate secular terms in perturbation solutions of differential equations and thus expand the domain of their validity.Here we extend the method to treat periodic orbits or limit cycles.Interesting normal forms could be derived through a generalization of the concept'resonance',which offers nontrivial analytic approximations.Compared with traditional techniques such as multi-scale methods,the current scheme proceeds in a very straightforward and simple way,delivering not only the period and the amplitude but also the transient path to limit cycles.The method is demonstrated with several examples including the Duffing oscillator,van der Pol equation and Lorenz equation.The obtained solutions match well with numerical results and with those derived by traditional analytic methods.
基金supported by the Basic Science Research Program through the National Research Foundation of Korea(NRF)funded by the Ministry of Science and ICT(NRF-2022R1A2C2012243).
文摘In recent decades,brain tumors have emerged as a serious neurological disorder that often leads to death.Hence,Brain Tumor Segmentation(BTS)is significant to enable the visualization,classification,and delineation of tumor regions in Magnetic Resonance Imaging(MRI).However,BTS remains a challenging task because of noise,non-uniform object texture,diverse image content and clustered objects.To address these challenges,a novel model is implemented in this research.The key objective of this research is to improve segmentation accuracy and generalization in BTS by incorporating Switchable Normalization into Faster R-CNN,which effectively captures the fine-grained tumor features to enhance segmentation precision.MRI images are initially acquired from three online datasets:Dataset 1—Brain Tumor Segmentation(BraTS)2018,Dataset 2—BraTS 2019,and Dataset 3—BraTS 2020.Subsequently,the Switchable Normalization-based Faster Regions with Convolutional Neural Networks(SNFRC)model is proposed for improved BTS in MRI images.In the proposed model,Switchable Normalization is integrated into the conventional architecture,enhancing generalization capability and reducing overfitting to unseen image data,which is essential due to the typically limited size of available datasets.The network depth is increased to obtain discriminative semantic features that improve segmentation performance.Specifically,Switchable Normalization captures the diverse feature representations from the brain images.The Faster R-CNN model develops end-to-end training and effective regional proposal generation,with an enhanced training stability using Switchable Normalization,to perform an effective segmentation in MRI images.From the experimental results,the proposed model attains segmentation accuracies of 99.41%,98.12%,and 96.71%on Datasets 1,2,and 3,respectively,outperforming conventional deep learning models used for BTS.
基金supported in part by the National Natural Science Foundation of China[grant numbers 42230108,and 61971319].
文摘Global and local modeling is essential for image super-resolution tasks.However,current efforts often lack explicit consideration of the cross-scale knowledge in large-scale earth observation scenarios,resulting in suboptimal single-scale representations in global and local modeling.The key motivation of this work is inspired by two observations:1)There exists hierarchical features at the local and global regions in remote sensing images,and 2)they exhibit scale variation of similar ground objects(e.g.cross-scale similarity).In light of these,this paper presents an effective method to grasp the global and local image hierarchies by systematically exploring the cross-scale correlation.Specifically,we developed a Cross-scale Self-Attention(CSA)to model the global features,which introduces an auxiliary token space to calculate cross-scale self-attention matrices,thus exploring global dependency from diverse token scales.To extract the cross-scale localities,a Cross-scale Channel Attention(CCA)is devised,where multi-scale features are explored and progressively incorporated into an enriched feature.Moreover,by hierarchically deploying CSA and CCA into transformer groups,the proposed Cross-scale Hierarchical Transformer(CHT)can effectively explore cross-scale representations in remote sensing images,leading to a favorable reconstruction performance.Comprehensive experiments and analysis on four remote sensing datasets have demonstrated the superiority of CHT in both simulated and real-world remote sensing scenes.In particular,our CHT outperforms the state-of-the-art approach(TransENet)in terms of PSNR by 0.11 dB on average,but only accounts for 54.8%of its parameters.
基金supported by the National Natural Science Foundation of China(NSFC,No.82173742)the Science Fund for Distinguished Young Scholars of Shaanxi Province(No.2022JC-54)the Key Research and Development Program of Shaanxi Province(No.2023-YBSF-131).
文摘Remodeling tumor microenvironment(TME)is a very promising and effective strategy to enhance the effects of chemotherapy,photodynamic therapy,and immunotherapy.Normalization of tumor vasculature as well as depletion of glutathione(GSH)can improve the TME.Here,we developed a novel therapeutic nanoparticle functional enzyme ultra QDAU5 nanoparticles(FEUQ Nps)based on a fluorescence-on and releasable strategy by combining a vascular normalization inducer,a GSH depleting agent,and an activated fluorophore.In which the cleavage of disulfide bonds releases active molecules that induce vascular normalization and improve the hypoxic microenvironment.In addition,it may deplete GSH in cancer cells,thus inducing the production of reactive oxygen species(ROS)and lipid peroxide(LPO)and promoting iron toxicity.It may also lead to endoplasmic stress and release of calmodulin,which activates the immune system.Meanwhile,quenched fluorophores are turned on in the presence of galactosidase(GLU)for tumor-specific labeling.In summary,we developed novel therapeutic agent nanoparticles with the function of vascular normalization inducers to achieve specific labeling of hepatocellular carcinoma while exerting efficient antitumor effects in vivo.
基金supported by the National Natural Science Foundation of China(NSFC,Nos.82373793,82173742)the Science Fund for Distinguished Young Scholars of Shaanxi Province(No.2022JC-54)the Key Research and Development Program of Shaanxi Province(No.2023-YBSF-131).
文摘Tumor vascular normalization has emerged as a promising strategy for synergistic therapy recently.Based on the strategy of“fluorescence turn on-controllable release”,a novel bifunctional candidate was con-structed based on previous developed vascular normalization inducer QDAU5,which could self-assemble to form functional enzyme infrared QDAU5 nanoparticles(FEIRQ NPs).Subsequently,biological evaluation demonstrated that the FEIRQ NPs could induce ferroptosis,endoplasmic reticulum stress,and antigen pre-conditioning and maturation of dendritic cells and CD8^(+)T cells,leading to excellent antitumor efficacy in the absence of cytotoxic drugs.Additionally,FEIRQ NPs show high fluorescence intensity upon expo-sure to theβ-galactosidase(β-Gal)enzyme expressed in ovarian cancer,enabling real-time monitoring of therapeutic effects.Overall,our findings suggest a prospering strategy to early diagnosis and efficient therapy for ovarian cancer without cytotoxicity.
文摘Background:Isotonic crystalloids are recommended as the first choice for fluid therapy in acute pan-creatitis(AP),with normal saline(NS)and lactate Ringer’s(LR)used most often.Evidence based recom-mendations on the type of fluid are conflicting and generally come from small single-center randomized controlled trials(RCTs).We therefore conducted a systematic review and meta-analysis to compare the effect of balanced solutions(BS)versus NS on patient-centered clinical outcomes in AP.Methods:From four databases searched up to October 2024,we included only RCTs of adult patients with AP that compared the use of BS(including LR,acetate Ringer’s,etc.)with NS.The primary out-come was the disease advances from AP to moderately severe and severe AP(MSAP/SAP).Trial sequential analyses(TSA)were conducted to control for type-I and type-II errors and Grading of Recommendations Assessment,Development,and Evaluation(GRADE)was used to assess the quality of evidence.Results:Six RCTs were identified and included,involving 260 patients treated with BS and 298 patients with NS.Patients who received the BS had less MSAP/SAP[odds ratio(OR)=0.50,95%confidence in-terval(CI):0.29 to 0.85,P=0.01,I^(2)=0%;5 studies,299 patients],reduced the need of ICU admission(OR=0.60,95%CI:0.39 to 0.93,P=0.02,I^(2)=0%;5 studies,507 patients)and shorter length of hospital stay[mean difference(MD)=-0.88,95%CI:-1.48 to-0.28,P=0.004,I^(2)=0%;6 studies,558 patients;confirmed by TSA with high certainty]compared with those who received NS.The evidence for most of the clinical outcomes was rated as moderate to low due to the risk of bias,imprecision and inconsistency.Conclusions:BS,compared with NS,was associated with improved clinical outcomes in patients with AP.However,given the moderate to low quality of evidence for most of the outcomes assessed,further trials are warranted.
基金financially supported by the National Natural Science Foundation of China(Grant No.42172292)Taishan Scholars Project Special Funding,and Shandong Energy Group(Grant No.SNKJ 2022A01-R26).
文摘A conceptual model of intermittent joints is introduced to the cyclic shear test in the laboratory to explore the effects of loading parameters on its shear behavior under cyclic shear loading.The results show that the loading parameters(initial normal stress,normal stiffness,and shear velocity)determine propagation paths of the wing and secondary cracks in rock bridges during the initial shear cycle,creating different morphologies of macroscopic step-path rupture surfaces and asperities on them.The differences in stress state and rupture surface induce different cyclic shear responses.It shows that high initial normal stress accelerates asperity degradation,raises shear resistance,and promotes compression of intermittent joints.In addition,high normal stiffness provides higher normal stress and shear resistance during the initial cycles and inhibits the dilation and compression of intermittent joints.High shear velocity results in a higher shear resistance,greater dilation,and greater compression.Finally,shear strength is most sensitive to initial normal stress,followed by shear velocity and normal stiffness.Moreover,average dilation angle is most sensitive to initial normal stress,followed by normal stiffness and shear velocity.During the shear cycles,frictional coefficient is affected by asperity degradation,backfilling of rock debris,and frictional area,exhibiting a non-monotonic behavior.
基金Supported by the National Natural Science Foundation of China(11671403,11671236,12101192)Henan Provincial General Natural Science Foundation Project(232300420113)。
文摘In this paper,we mainly focus on a type of nonlinear Choquard equations with nonconstant potential.Under appropriate hypotheses on potential function and nonlinear terms,we prove that the above Choquard equation with prescribed 2-norm has some normalized solutions by introducing variational methods.
基金Supported by National Natural Science Foundation of China(11671403,11671236)Henan Provincial General Natural Science Foundation Project(232300420113)。
文摘This article studies a class of nonlinear Kirchhoff equations with exponential critical growth,trapping potential,and perturbation.Under appropriate assumptions about f and h,the article obtained the existence of normalized positive solutions for this equation via the Trudinger-Moser inequality and variational methods.Moreover,these solutions are also ground state solutions.Additionally,the article also characterized the asymptotic behavior of solutions.The results of this article expand the research of relevant literature.
基金Supported by the National Natural Science Foundation of China(Grant No.62101590).
文摘The present study focuses on simulating supercavitating projectile tail-slaps with an analytical method.A model of 3σ-normal distribution tail-slaps for a supercavitating projectile is established.Meanwhile,theσ-κequation is derived,which is included in this model.Next,the supercavitating projectile tail-slaps are simulated by combining the proposed model and the Logvinovich supercavity section expansion equation.The results show that the number of tail-slaps depends on where the initial several tail-slaps are under the same initial condition.If the distances between the initial several tail-slap positions are large,the number of tail-slaps will considerably decrease,and vice versa.Furthermore,a series of simulations is employed to analyze the influence of the initial angular velocity and the centroid.Analysis of variance is used to evaluate simulation results.The evaluation results suggest that the projectile’s initial angular velocity and centroid have a major impact on the tail-slap number.The larger the value of initial angular velocity,the higher the probability of an increase in tail-slap number.Additionally,the closer the centroid is to the projectile head,the less likely a tail-slap number increase.This study offers important insights into supercavitating projectile tail-slap research.
基金supported by National Natural Science Foundation of China(Grant Nos.12271313,12071266,12101376)supported by National Natural Science Foundation of China(Grant Nos.12171204,12371107)+3 种基金National Natural Science Foundation of China(Grant No.12031015)Fundamental Research Program of Shanxi Province(Grant Nos.202203021211300,202203021211309,20210302124528)Shanxi Scholarship Council of China(Grant No.2020-005)supported by National Key R&D Program of China(Grant No.2022YFA1005601)。
文摘Consider the Kirchhoff equation with Hartree type nonlinearity■where a,b>0,λ,μ∈R,2<q<6,0<α<3,and Iαis the Riesz potential integral operator of orderα.Solutions with prescribed mass■,also known as normalized solutions,are of particular interest in the current paper.Under various assumptions onμ,c and q,we establish the existence,nonexistence and asymptotic behavior of normalized solutions for the above elliptic equation.
基金supported by the NNSF of China(12471103)the Natural Science Foundation of Guangdong Province(2024A1515012370)the Guangzhou Basic and Applied Basic Research(2023A04J1316)。
文摘In this paper,we investigate the existence and multiplicity of normalized solutions for the following fractional Schrödinger equations{(-△)^(s)u+λu=|u|^(p-2)u-|u|^(q-2)u,x∈R^(N),∫_(R^(N))|u|^(2)dx=c>0,where N≥2,s∈(0,1),2+4s/N<p<q≤2_(s)^(*)=2N/N-2s,(-△)^(s)represents the fractional Laplacian operator of order s,and the frequencyλ∈R is unknown and appears as a Lagrange multiplier.Specifically,we show that there exists a c>0 such that if c>c,then the problem(P)has at least two normalized solutions,including a normalized ground state solution and a mountain pass type solution.We mainly extend the results in[Commun Pure Appl Anal,2022,21:4113–4145],which dealt with the problem(P)for the case 2<p<q<2+4s/N.
基金supported by the National Natural Science Foundation of China(Grant No.11971411)。
文摘This paper introduces a novel numerical method based on an energy-minimizing normalized residual network(EMNorm Res Net)to compute the ground-state solution of Bose-Einstein condensates at zero or low temperatures.Starting from the three-dimensional Gross-Pitaevskii equation(GPE),we reduce it to the 1D and 2D GPEs because of the radial symmetry and cylindrical symmetry.The ground-state solution is formulated by minimizing the energy functional under constraints,which is directly solved using the EM-Norm Res Net approach.The paper provides detailed solutions for the ground states in 1D,2D(with radial symmetry),and 3D(with cylindrical symmetry).We use the Thomas-Fermi approximation as the target function to pre-train the neural network.Then,the formal network is trained using the energy minimization method.In contrast to traditional numerical methods,our neural network approach introduces two key innovations:(i)a novel normalization technique designed for high-dimensional systems within an energy-based loss function;(ii)improved training efficiency and model robustness by incorporating gradient stabilization techniques into residual networks.Extensive numerical experiments validate the method's accuracy across different spatial dimensions.
基金supported by the Spanish Ministry of Science and Innovation under the MCI/AEI/FEDER project number PID2021-123543OBC21.
文摘Anomaly detection in wind turbines involves emphasizing its ability to improve operational efficiency,reduce maintenance costs,extend their lifespan,and enhance reliability in the wind energy sector.This is particularly necessary in offshore wind,currently one of the most critical assets for achieving sustainable energy generation goals,due to the harsh marine environment and the difficulty of maintenance tasks.To address this problem,this work proposes a data-driven methodology for detecting power generation anomalies in offshore wind turbines,using normalized and linearized operational data.The proposed framework transforms heterogeneous wind speed and power measurements into a unified scale,enabling the development of a new wind power index(WPi)that quantifies deviations from expected performance.Additionally,spatial and temporal coherence analyses of turbines within a wind farm ensure the validity of these normalized measurements across different wind turbine models and operating conditions.Furthermore,a Support Vector Machine(SVM)refines the classification process,effectively distinguishing measurement errors from actual power generation failures.Validation of this strategy using real-world data from the Alpha Ventus wind farm demonstrates that the proposed approach not only improves predictive maintenance but also optimizes energy production,highlighting its potential for broad application in offshore wind installations.
基金supported by the National Natural Science Foundation of China(Nos.52378341,51938005,and 52090082).
文摘Urban spaces are becoming increasingly congested,and excavations are frequently performed close to existing underground structures such as tunnels.Understanding the mechanical response of proximal soil and tunnels to these excavations is important for efficient and safe underground construction.However,previous investigations of this issue have predominantly made assumptions of plane-strain conditions and normal gravity states,and focused on the performance of tunnels affected by excavation and unloading in sandy strata.In this study,a 3D centrifuge model test is conducted to investigate the influence of excavation on an adjacent existing tunnel in normally consolidated clay.The testing results indicate that the excavation has a significant impact on the horizontal deformation of the retaining wall and tunnel.Moreover,the settlements of the ground surface and the tunnel are mainly affected by the long-term period after excavation.The excavation is found to induce ground movement towards the pit,resulting in prolonged fluctuations in pore water pressure and lateral earth pressure.The testing results are compared with numerical simulations,achieving consistency.A numerical parametric study on the tunnel location shows that when the tunnel is closer to the retaining wall,the decreases in lateral earth pressure and pore water pressure during excavation are more pronounced.
