The electrocatalytic reduction of nitric oxide for ammonia synthesis(NORR)is a key green energy conversion technology.Its efficiency relies on high-performance electrocatalysts to enhance both ammonia yield(Y_(NH3))an...The electrocatalytic reduction of nitric oxide for ammonia synthesis(NORR)is a key green energy conversion technology.Its efficiency relies on high-performance electrocatalysts to enhance both ammonia yield(Y_(NH3))and Faradaic efficiency(F_(NH3)).However,conventional experimental methods for screening high-activity NORR catalysts often entail high resource consumption and time costs.Machine learning combined with SHAP feature analysis was employed to establish a stacked ensemble model that integrates multiple algorithms,to allow for a systematic investigation of the key descriptors governing NORR performance based on an experimental dataset.Evaluation of eight model algorithms revealed that the Stacked-SVR model achieved an R^(2)of 0.9223 and an RMSE of 0.0608 for predicting on the test set,whereas the Stacked-RF model achieved an R^(2)of 0.9042 and an RMSE of 0.0900 for predicting.The stacked ensemble model integrates the strengths of individual algorithms and demonstrates strong NORR prediction performance while avoiding overfitting.SHAP feature analysis results revealed that the Cu content in the catalyst composition has the most significant impact on catalytic performance.Moreover,the combination of the wet chemical reduction synthesis,a carbon fiber(CF)conductive substrate,and HCl electrolyte is more favorable for enhancing catalytic activity.Additionally,moderately lowering the working potential,controlling the electrolyte volume at low to medium levels,reducing catalyst loading,and increasing electrolyte concentration were found to synergistically enhance both and.展开更多
The soil-water retention curve(SWRC)plays a pivotal role in understanding water movement across numerous geological engineering applications.Despite significant advancements in theoretical modeling approaches,accurate...The soil-water retention curve(SWRC)plays a pivotal role in understanding water movement across numerous geological engineering applications.Despite significant advancements in theoretical modeling approaches,accurate prediction of SWRCs remains challenging due to the inherently sparse and incomplete nature of site-specific data.This study compiled a comprehensive dataset of SWRCs spanning a wide suction range from various published literature sources.Based on this dataset,multiple machine learning(ML)algorithms were employed to predict SWRCs.The performance of each algorithm was evaluated and ranked using four statistical indicators that quantify simulation accuracy.Feature importance analysis was subsequently conducted to reduce dimensionality by eliminating weakly correlated variables,thereby enhancing both model adaptability and computational efficiency.Following dimensionality reduction,a base learner pool was constructed and integrated through stacked generalization to create a multi-algorithm ensemble model.The proposed stacked model demonstrated robust performance in simulating SWRCs across diverse soil types,using only basic physical properties as inputs,achieving accuracy comparable to or marginally superior to the LightGBM model.The principal advantage of the stacked approach lies in its substantially improved accuracy within high suction ranges,effectively overcoming the limitations observed in LightGBM and enhancing the estimation under these conditions.This study provides valuable insights for researchers evaluating SWRCs through ML algorithms and demonstrates the potential of ensemble techniques in geotechnical prediction tasks.展开更多
Intrusion detection in Internet of Things(IoT)environments presents challenges due to heterogeneous devices,diverse attack vectors,and highly imbalanced datasets.Existing research on the ToN-IoT dataset has largely em...Intrusion detection in Internet of Things(IoT)environments presents challenges due to heterogeneous devices,diverse attack vectors,and highly imbalanced datasets.Existing research on the ToN-IoT dataset has largely emphasized binary classification and single-model pipelines,which often showstrong performance but limited generalizability,probabilistic reliability,and operational interpretability.This study proposes a stacked ensemble deep learning framework that integrates random forest,extreme gradient boosting,and a deep neural network as base learners,with CatBoost as the meta-learner.On the ToN-IoT Linux process dataset,the model achieved near-perfect discrimination(macro area under the curve=0.998),robust calibration,and superior F1-scores compared with standalone classifiers.Interpretability was achieved through SHapley Additive exPlanations–based feature attribution,which highlights actionable drivers ofmalicious behavior,such as command-line patterns,process scheduling anomalies,and CPU usage spikes,and aligns these indicators with MITRE ATT&CK tactics and techniques.Complementary analyses,including cumulative lift and sensitivity-specificity trade-offs,revealed the framework’s suitability for deployment in security operations centers,where calibrated risk scores,transparent explanations,and resource-aware triage are essential.These contributions bridge methodological rigor in artificial intelligence/machine learning with operational priorities in cybersecurity,delivering a scalable and explainable intrusion detection system suitable for real-world deployment in IoT environments.展开更多
Dear Editor,This letter presents techniques to simplify dataset generation for instance segmentation of raw meat products,a critical step toward automating food production lines.Accurate segmentation is essential for ...Dear Editor,This letter presents techniques to simplify dataset generation for instance segmentation of raw meat products,a critical step toward automating food production lines.Accurate segmentation is essential for addressing challenges such as occlusions,indistinct edges,and stacked configurations,which demand large,diverse datasets.To meet these demands,we propose two complementary approaches:a semi-automatic annotation interface using tools like the segment anything model(SAM)and GrabCut and a synthetic data generation pipeline leveraging 3D-scanned models.These methods reduce reliance on real meat,mitigate food waste,and improve scalability.Experimental results demonstrate that incorporating synthetic data enhances segmentation model performance and,when combined with real data,further boosts accuracy,paving the way for more efficient automation in the food industry.展开更多
A multi-phase stacked interleaved buck converter(SIBC)is suitable for large-power water electrolysis applications due to its merits of high current output capability and zero output current ripple.However,the auxiliar...A multi-phase stacked interleaved buck converter(SIBC)is suitable for large-power water electrolysis applications due to its merits of high current output capability and zero output current ripple.However,the auxiliary converter used to compensate for the current ripple still has to withstand high voltage stress.This paper proposes a new multi-phase SIBC applied in the multicarrier energy system integrating electricity,heat,and hydrogen.A resistor-capacitor voltage divider is used to provide the input voltage of the auxiliary converter and as a heater for the thermal loads.Thus,the voltage stress of the auxiliary converter can be reduced at a low cost,and the size of the filter inductor can be reduced.With accurate voltage and current analysis and appropriate parameter design,the voltage stresses of both the switches and capacitors in the auxiliary converter can be further limited within an expected range.The experimental results verify the correctness of the topology,modulation,analysis,and design methods.A comparison with the conventional method is made in terms of cost,volume,and efficiency to show the advantages of the proposed method.展开更多
Deep Learning has been widely used to model soft sensors in modern industrial processes with nonlinear variables and uncertainty.Due to the outstanding ability for high-level feature extraction,stacked autoencoder(SAE...Deep Learning has been widely used to model soft sensors in modern industrial processes with nonlinear variables and uncertainty.Due to the outstanding ability for high-level feature extraction,stacked autoencoder(SAE)has been widely used to improve the model accuracy of soft sensors.However,with the increase of network layers,SAE may encounter serious information loss issues,which affect the modeling performance of soft sensors.Besides,there are typically very few labeled samples in the data set,which brings challenges to traditional neural networks to solve.In this paper,a multi-scale feature fused stacked autoencoder(MFF-SAE)is suggested for feature representation related to hierarchical output,where stacked autoencoder,mutual information(MI)and multi-scale feature fusion(MFF)strategies are integrated.Based on correlation analysis between output and input variables,critical hidden variables are extracted from the original variables in each autoencoder's input layer,which are correspondingly given varying weights.Besides,an integration strategy based on multi-scale feature fusion is adopted to mitigate the impact of information loss with the deepening of the network layers.Then,the MFF-SAE method is designed and stacked to form deep networks.Two practical industrial processes are utilized to evaluate the performance of MFF-SAE.Results from simulations indicate that in comparison to other cutting-edge techniques,the proposed method may considerably enhance the accuracy of soft sensor modeling,where the suggested method reduces the root mean square error(RMSE)by 71.8%,17.1%and 64.7%,15.1%,respectively.展开更多
Spectrum prediction is considered as a key technology to assist spectrum decision.Despite the great efforts that have been put on the construction of spectrum prediction,achieving accurate spectrum prediction emphasiz...Spectrum prediction is considered as a key technology to assist spectrum decision.Despite the great efforts that have been put on the construction of spectrum prediction,achieving accurate spectrum prediction emphasizes the need for more advanced solutions.In this paper,we propose a new multichannel multi-step spectrum prediction method using Transformer and stacked bidirectional LSTM(Bi-LSTM),named TSB.Specifically,we use multi-head attention and stacked Bi-LSTM to build a new Transformer based on encoder-decoder architecture.The self-attention mechanism composed of multiple layers of multi-head attention can continuously attend to all positions of the multichannel spectrum sequences.The stacked Bi-LSTM can learn these focused coding features by multi-head attention layer by layer.The advantage of this fusion mode is that it can deeply capture the long-term dependence of multichannel spectrum data.We have conducted extensive experiments on a dataset generated by a real simulation platform.The results show that the proposed algorithm performs better than the baselines.展开更多
Healthcare networks prove to be an urgent issue in terms of intrusion detection due to the critical consequences of cyber threats and the extreme sensitivity of medical information.The proposed Auto-Stack ID in the st...Healthcare networks prove to be an urgent issue in terms of intrusion detection due to the critical consequences of cyber threats and the extreme sensitivity of medical information.The proposed Auto-Stack ID in the study is a stacked ensemble of encoder-enhanced auctions that can be used to improve intrusion detection in healthcare networks.TheWUSTL-EHMS 2020 dataset trains and evaluates themodel,constituting an imbalanced class distribution(87.46% normal traffic and 12.53% intrusion attacks).To address this imbalance,the study balances the effect of training Bias through Stratified K-fold cross-validation(K=5),so that each class is represented similarly on training and validation splits.Second,the Auto-Stack ID method combines many base classifiers such as TabNet,LightGBM,Gaussian Naive Bayes,Histogram-Based Gradient Boosting(HGB),and Logistic Regression.We apply a two-stage training process based on the first stage,where we have base classifiers that predict out-of-fold(OOF)predictions,which we use as inputs for the second-stage meta-learner XGBoost.The meta-learner learns to refine predictions to capture complicated interactions between base models,thus improving detection accuracy without introducing bias,overfitting,or requiring domain knowledge of the meta-data.In addition,the auto-stack ID model got 98.41% accuracy and 93.45%F1 score,better than individual classifiers.It can identify intrusions due to its 90.55% recall and 96.53% precision with minimal false positives.These findings identify its suitability in ensuring healthcare networks’security through ensemble learning.Ongoing efforts will be deployed in real time to improve response to evolving threats.展开更多
Carbonaceous material has attracted much attention in the application of sodium-ion batteries(SIBs)anode.However,sluggish reaction kinetics and structure stability impede the application.Therefore,a stacked layered su...Carbonaceous material has attracted much attention in the application of sodium-ion batteries(SIBs)anode.However,sluggish reaction kinetics and structure stability impede the application.Therefore,a stacked layered sulfur-carbon complex with long-chain C–S_(x)–C bond(M-SC-S)is prepared.The layered structure ensures structural stability,and long-chain C–S_(x)–C bond expanding interlayer spacing boosts facile Na+diffusion.When assembled into cells,a high-quality solid-electrolyte interphase film would be formed due to a good match between the M-SC-S electrode and ether electrolyte.Moreover,an electrochemical activation process would happen between the Cu current collector and proper S-doped electrode material to in-situ form Cu_(2)S.The formation of Cu_(2)S in active material can not only provide more active sites for sodium storage and enhance pseudo-capacitance,but also reinforce the electrode/current collector interface and decrease the interfacial transfer resistance for rapid Na+kinetics.The synergistic effect of structure design and interface engineering optimizes the sodium storage system.Thus,the M-SC-S electrode delivers an excellent cyclic performance(321.6 mAh g^(−1)after 1000 cycles at 2 A g^(−1)with a capacity retention rate of 97.4%)and good rate capability(282.8 mAh g^(−1)after 4000 cycles even at a high current density of 10 A g^(−1)).The full cell also has an impressive cyclic performance(151.4 mAh g^(−1)after 500 cycles at 0.5 A g^(−1)).展开更多
In the context of intelligent manufacturing,the modern hot strip mill process(HSMP)shows characteristics such as diversification of products,multi-specification batch production,and demand-oriented customization.These...In the context of intelligent manufacturing,the modern hot strip mill process(HSMP)shows characteristics such as diversification of products,multi-specification batch production,and demand-oriented customization.These characteristics pose significant challenges to ensuring process stability and consistency of product performance.Therefore,exploring the potential relationship between product performance and the production process,and developing a comprehensive performance evaluation method adapted to modern HSMP have become an urgent issue.A comprehensive performance evaluation method for HSMP by integrating multi-task learning and stacked performance-related autoencoder is proposed to solve the problems such as incomplete performance indicators(PIs)data,insufficient real-time acquisition requirements,and coupling of multiple PIs.First,according to the existing Chinese standards,a comprehensive performance evaluation grade strategy for strip steel is designed.The random forest model is established to predict and complete the parts of PIs data that could not be obtained in real-time.Second,a stacked performance-related autoencoder(SPAE)model is proposed to extract the deep features closely related to the product performance.Then,considering the correlation between PIs,the multi-task learning framework is introduced to output the subitem ratings and comprehensive product performance rating results of the strip steel online in real-time,where each task represents a subitem of comprehensive performance.Finally,the effectiveness of the method is verified on a real HSMP dataset,and the results show that the accuracy of the proposed method is as high as 94.8%,which is superior to the other comparative methods.展开更多
The adoption of deep learning-based side-channel analysis(DL-SCA)is crucial for leak detection in secure products.Many previous studies have applied this method to break targets protected with countermeasures.Despite ...The adoption of deep learning-based side-channel analysis(DL-SCA)is crucial for leak detection in secure products.Many previous studies have applied this method to break targets protected with countermeasures.Despite the increasing number of studies,the problem of model overfitting.Recent research mainly focuses on exploring hyperparameters and network architectures,while offering limited insights into the effects of external factors on side-channel attacks,such as the number and type of models.This paper proposes a Side-channel Analysis method based on a Stacking ensemble,called Stacking-SCA.In our method,multiple models are deeply integrated.Through the extended application of base models and the meta-model,Stacking-SCA effectively improves the output class probabilities of the model,leading to better generalization.Furthermore,this method shows that the attack performance is sensitive to changes in the number of models.Next,five independent subsets are extracted from the original ASCAD database as multi-segment datasets,which are mutually independent.This method shows how these subsets are used as inputs for Stacking-SCA to enhance its attack convergence.The experimental results show that Stacking-SCA outperforms the current state-of-the-art results on several considered datasets,significantly reducing the number of attack traces required to achieve a guessing entropy of 1.Additionally,different hyperparameter sizes are adjusted to further validate the robustness of the method.展开更多
A new 2-Π lumped element equivalent circuit model for high-k stacked on-chip transformers is proposed. The model parameters are extracted with high precision, mainly based on analytical methods. The developed model e...A new 2-Π lumped element equivalent circuit model for high-k stacked on-chip transformers is proposed. The model parameters are extracted with high precision, mainly based on analytical methods. The developed model enables fast and accurate time domain transient analysis and noise analysis in RFIC simulation since all elements in the model are fre- quency independent. The validity of the proposed model has been demonstrated by a fabricated monolithic stacked trans- former in TSMC＇s 0.13μm mixed-signal （MS）/RF CMOS＇ process.展开更多
In aircraft assembly, interlayer burr formation in dry drilling of stacked metal materials is a common problem. Traditional manual deburring operation seriously affects the assembly qual- ity and assembly efficiency, ...In aircraft assembly, interlayer burr formation in dry drilling of stacked metal materials is a common problem. Traditional manual deburring operation seriously affects the assembly qual- ity and assembly efficiency, is time-consuming and costly, and is not conducive to aircraft automatic assembly based on industrial robot. In this paper, the formation of drilling exit burr and the influ- ence of interlayer gap on interlayer burr formation were studied, and the mechanism of interlayer gap formation in drilling stacked aluminum alloy plates was investigated, a simplified mathematical model of interlayer gap based on the theory of plates and shells and finite element method was established. The relationship between interlayer gap and interlayer burr, as well as the effect of feed rate and pressing force on interlayer burr height and interlayer gap was discussed. The result shows that theoretical interlayer gap has a positive correlation with interlayer burr height and preloading nressing force is an effective method to control interlaver burr formation.展开更多
Stacked（insect and herbicide resistant） transgenic rice T1c-19 with cry1C＊/bar genes, its receptor rice Minghui 63（herein MH63） and a local two-line hybrid indica rice Fengliangyou Xiang 1（used as a control） we...Stacked（insect and herbicide resistant） transgenic rice T1c-19 with cry1C＊/bar genes, its receptor rice Minghui 63（herein MH63） and a local two-line hybrid indica rice Fengliangyou Xiang 1（used as a control） were compared for agronomic performance under field conditions without the relevant selection pressures. Agronomic traits（plant height, tiller number, and aboveground dry biomass）, reproductive ability（pollen viability, panicle length, and filled grain number of main panicles, seed set, and grain yield）, and weediness characteristics（seed shattering, seed overwintering ability, and volunteer seedling recruitment） were used to assess the potential weediness without selection pressure of stacked transgene rice T1c-19. In wet direct-seeded and transplanted rice fields, T1c-19 and its receptor MH63 performed similarly regarding vegetative growth and reproductive ability, but both of them were significantly inferior to the control. T1c-19 did not display weed characteristics; it had weak overwintering ability, low seed shattering and failed to establish volunteers. Exogenous insect and herbicide resistance genes did not confer competitive advantage to transgenic rice T1c-19 grown in the field without the relevant selection pressures.展开更多
The utilization of neutrons markedly affects the medical isotope yield of a subcritical system driven by an external D-T neutron source.The general methods to improve the utilization of neutrons include moderating mul...The utilization of neutrons markedly affects the medical isotope yield of a subcritical system driven by an external D-T neutron source.The general methods to improve the utilization of neutrons include moderating multiplying,and reflecting neutrons,which ignores the use of neutrons that backscatter to the source direction.In this study,a stacked structure was formed by assembling the multiplier and the low-enriched uranium solution to enable the full use of neutrons that backscatter to the source direction and further improve the utilization of neutrons.A model based on SuperMC was used to evaluate the neutronics and safety behavior of the subcritical system,such as the neutron effective multiplication factor,neutron energy spectrum,medical isotope yield,and heat deposition.Based on the calculation results,when the intensity of the neutron source was 59×10^(13)n/s,the optimized design with a stacked structure could increase the yield of ^(99)Mo to182 Ci/day,which is approximately 16% higher than that obtained with a single-layer structure.The inlet H_(2)O coolant velocity of 1.0 m/s and initial temperature of 20℃ were also found to be sufficient to prevent boiling of the fuel solution.展开更多
Compared to single-trait transgenic crops, stacked transgenic plants may be more prone to become weedy, and transgene flow from stacked transgenic plants to weedy relatives may pose a potential environmental risk beca...Compared to single-trait transgenic crops, stacked transgenic plants may be more prone to become weedy, and transgene flow from stacked transgenic plants to weedy relatives may pose a potential environmental risk because these hybrids could be more advantageous under specific environmental conditions. Evaluation of the potential environmental risk caused by stacked transgenes is essential for assessing the environmental consequences caused by crop-weed transgene flow. The agronomic performance of fitness-related traits was assessed in F1+(transgene positive) hybrids(using the transgenic line T1 c-19 as the paternal parent) in monoculture and mixed planting under presence or absence glufosinate pressure in the presence or absence of natural insect pressure and then compared with the performance of F1–(transgene negative) hybrids(using the non-transgenic line Minghui 63(MH63) as the paternal parent) and their weedy rice counterparts. The results demonstrated that compared with the F1– hybrids and weedy rice counterparts, the F1+ hybrid presented higher performance(P<0.05) or non-significant changes(P>0.05) under natural insect pressure, respectively, lower performance(P<0.05) or non-significant changes(P>0.05) in the absence of insect pressure in monoculture planting, respectively. And compared to weedy rice counterparts, the F1+ hybrid presented higher performance(P<0.05) or non-significant changes(P>0.05) in the presence or absence of insect pressure in mixed planting, respectively. The F1+ hybrids presented nonsignificant changes(P>0.05) under the presence or absence glufosinate pressure under insect or non-insect pressure in monoculture planting. The all F1+ hybrids and two of three F1– hybrids had significantly lower(P<0.05) seed shattering than the weedy rice counterparts. The potential risk of gene flow from T1 c-19 to weedy rice should be prevented due to the greater fitness advantage of F1 hybrids in the majority of cases.展开更多
With the rapid development of mechanical equipment,mechanical health monitoring field has entered the era of big data.Deep learning has made a great achievement in the processing of large data of image and speech due ...With the rapid development of mechanical equipment,mechanical health monitoring field has entered the era of big data.Deep learning has made a great achievement in the processing of large data of image and speech due to the powerful modeling capabilities,this also brings influence to the mechanical fault diagnosis field.Therefore,according to the characteristics of motor vibration signals(nonstationary and difficult to deal with)and mechanical‘big data’,combined with deep learning,a motor fault diagnosis method based on stacked de-noising auto-encoder is proposed.The frequency domain signals obtained by the Fourier transform are used as input to the network.This method can extract features adaptively and unsupervised,and get rid of the dependence of traditional machine learning methods on human extraction features.A supervised fine tuning of the model is then carried out by backpropagation.The Asynchronous motor in Drivetrain Dynamics Simulator system was taken as the research object,the effectiveness of the proposed method was verified by a large number of data,and research on visualization of network output,the results shown that the SDAE method is more efficient and more intelligent.展开更多
文摘The electrocatalytic reduction of nitric oxide for ammonia synthesis(NORR)is a key green energy conversion technology.Its efficiency relies on high-performance electrocatalysts to enhance both ammonia yield(Y_(NH3))and Faradaic efficiency(F_(NH3)).However,conventional experimental methods for screening high-activity NORR catalysts often entail high resource consumption and time costs.Machine learning combined with SHAP feature analysis was employed to establish a stacked ensemble model that integrates multiple algorithms,to allow for a systematic investigation of the key descriptors governing NORR performance based on an experimental dataset.Evaluation of eight model algorithms revealed that the Stacked-SVR model achieved an R^(2)of 0.9223 and an RMSE of 0.0608 for predicting on the test set,whereas the Stacked-RF model achieved an R^(2)of 0.9042 and an RMSE of 0.0900 for predicting.The stacked ensemble model integrates the strengths of individual algorithms and demonstrates strong NORR prediction performance while avoiding overfitting.SHAP feature analysis results revealed that the Cu content in the catalyst composition has the most significant impact on catalytic performance.Moreover,the combination of the wet chemical reduction synthesis,a carbon fiber(CF)conductive substrate,and HCl electrolyte is more favorable for enhancing catalytic activity.Additionally,moderately lowering the working potential,controlling the electrolyte volume at low to medium levels,reducing catalyst loading,and increasing electrolyte concentration were found to synergistically enhance both and.
基金the National Natural Science Foundation of China(Grant No.42272312)Ningbo Youth Science and Technology Innovation Talent Project(Grant No.2024QL057)the Zhejiang Provincial Xinmiao Talents Program(Grant No.2024R405B093).
文摘The soil-water retention curve(SWRC)plays a pivotal role in understanding water movement across numerous geological engineering applications.Despite significant advancements in theoretical modeling approaches,accurate prediction of SWRCs remains challenging due to the inherently sparse and incomplete nature of site-specific data.This study compiled a comprehensive dataset of SWRCs spanning a wide suction range from various published literature sources.Based on this dataset,multiple machine learning(ML)algorithms were employed to predict SWRCs.The performance of each algorithm was evaluated and ranked using four statistical indicators that quantify simulation accuracy.Feature importance analysis was subsequently conducted to reduce dimensionality by eliminating weakly correlated variables,thereby enhancing both model adaptability and computational efficiency.Following dimensionality reduction,a base learner pool was constructed and integrated through stacked generalization to create a multi-algorithm ensemble model.The proposed stacked model demonstrated robust performance in simulating SWRCs across diverse soil types,using only basic physical properties as inputs,achieving accuracy comparable to or marginally superior to the LightGBM model.The principal advantage of the stacked approach lies in its substantially improved accuracy within high suction ranges,effectively overcoming the limitations observed in LightGBM and enhancing the estimation under these conditions.This study provides valuable insights for researchers evaluating SWRCs through ML algorithms and demonstrates the potential of ensemble techniques in geotechnical prediction tasks.
文摘Intrusion detection in Internet of Things(IoT)environments presents challenges due to heterogeneous devices,diverse attack vectors,and highly imbalanced datasets.Existing research on the ToN-IoT dataset has largely emphasized binary classification and single-model pipelines,which often showstrong performance but limited generalizability,probabilistic reliability,and operational interpretability.This study proposes a stacked ensemble deep learning framework that integrates random forest,extreme gradient boosting,and a deep neural network as base learners,with CatBoost as the meta-learner.On the ToN-IoT Linux process dataset,the model achieved near-perfect discrimination(macro area under the curve=0.998),robust calibration,and superior F1-scores compared with standalone classifiers.Interpretability was achieved through SHapley Additive exPlanations–based feature attribution,which highlights actionable drivers ofmalicious behavior,such as command-line patterns,process scheduling anomalies,and CPU usage spikes,and aligns these indicators with MITRE ATT&CK tactics and techniques.Complementary analyses,including cumulative lift and sensitivity-specificity trade-offs,revealed the framework’s suitability for deployment in security operations centers,where calibrated risk scores,transparent explanations,and resource-aware triage are essential.These contributions bridge methodological rigor in artificial intelligence/machine learning with operational priorities in cybersecurity,delivering a scalable and explainable intrusion detection system suitable for real-world deployment in IoT environments.
基金supported by European Union’s Horizon Europe research and innovation programme,project AGILEHAND(Smart Grading,Handling and Packaging Solutions for Soft and Deformable Products in Agile and Reconfigurable Lines)(101092043).
文摘Dear Editor,This letter presents techniques to simplify dataset generation for instance segmentation of raw meat products,a critical step toward automating food production lines.Accurate segmentation is essential for addressing challenges such as occlusions,indistinct edges,and stacked configurations,which demand large,diverse datasets.To meet these demands,we propose two complementary approaches:a semi-automatic annotation interface using tools like the segment anything model(SAM)and GrabCut and a synthetic data generation pipeline leveraging 3D-scanned models.These methods reduce reliance on real meat,mitigate food waste,and improve scalability.Experimental results demonstrate that incorporating synthetic data enhances segmentation model performance and,when combined with real data,further boosts accuracy,paving the way for more efficient automation in the food industry.
基金supported in part by the National Natural Science Foundation of China(52077190)Cultivation Project for Basic Research and Innovation of Yanshan University(2021LGQN007)Science and Technology Project of Hebei Education Department(QN2024202).
文摘A multi-phase stacked interleaved buck converter(SIBC)is suitable for large-power water electrolysis applications due to its merits of high current output capability and zero output current ripple.However,the auxiliary converter used to compensate for the current ripple still has to withstand high voltage stress.This paper proposes a new multi-phase SIBC applied in the multicarrier energy system integrating electricity,heat,and hydrogen.A resistor-capacitor voltage divider is used to provide the input voltage of the auxiliary converter and as a heater for the thermal loads.Thus,the voltage stress of the auxiliary converter can be reduced at a low cost,and the size of the filter inductor can be reduced.With accurate voltage and current analysis and appropriate parameter design,the voltage stresses of both the switches and capacitors in the auxiliary converter can be further limited within an expected range.The experimental results verify the correctness of the topology,modulation,analysis,and design methods.A comparison with the conventional method is made in terms of cost,volume,and efficiency to show the advantages of the proposed method.
基金supported by the National Key Research and Development Program of China(2023YFB3307800)National Natural Science Foundation of China(62394343,62373155)+2 种基金Major Science and Technology Project of Xinjiang(No.2022A01006-4)State Key Laboratory of Industrial Control Technology,China(Grant No.ICT2024A26)Fundamental Research Funds for the Central Universities.
文摘Deep Learning has been widely used to model soft sensors in modern industrial processes with nonlinear variables and uncertainty.Due to the outstanding ability for high-level feature extraction,stacked autoencoder(SAE)has been widely used to improve the model accuracy of soft sensors.However,with the increase of network layers,SAE may encounter serious information loss issues,which affect the modeling performance of soft sensors.Besides,there are typically very few labeled samples in the data set,which brings challenges to traditional neural networks to solve.In this paper,a multi-scale feature fused stacked autoencoder(MFF-SAE)is suggested for feature representation related to hierarchical output,where stacked autoencoder,mutual information(MI)and multi-scale feature fusion(MFF)strategies are integrated.Based on correlation analysis between output and input variables,critical hidden variables are extracted from the original variables in each autoencoder's input layer,which are correspondingly given varying weights.Besides,an integration strategy based on multi-scale feature fusion is adopted to mitigate the impact of information loss with the deepening of the network layers.Then,the MFF-SAE method is designed and stacked to form deep networks.Two practical industrial processes are utilized to evaluate the performance of MFF-SAE.Results from simulations indicate that in comparison to other cutting-edge techniques,the proposed method may considerably enhance the accuracy of soft sensor modeling,where the suggested method reduces the root mean square error(RMSE)by 71.8%,17.1%and 64.7%,15.1%,respectively.
基金supported in part by the National Natural Science Foundation of China under Grants 62231015,62427801in part by Jiangsu Province Frontier Leading Technology Basic Research Project BK20232030.
文摘Spectrum prediction is considered as a key technology to assist spectrum decision.Despite the great efforts that have been put on the construction of spectrum prediction,achieving accurate spectrum prediction emphasizes the need for more advanced solutions.In this paper,we propose a new multichannel multi-step spectrum prediction method using Transformer and stacked bidirectional LSTM(Bi-LSTM),named TSB.Specifically,we use multi-head attention and stacked Bi-LSTM to build a new Transformer based on encoder-decoder architecture.The self-attention mechanism composed of multiple layers of multi-head attention can continuously attend to all positions of the multichannel spectrum sequences.The stacked Bi-LSTM can learn these focused coding features by multi-head attention layer by layer.The advantage of this fusion mode is that it can deeply capture the long-term dependence of multichannel spectrum data.We have conducted extensive experiments on a dataset generated by a real simulation platform.The results show that the proposed algorithm performs better than the baselines.
基金funded by Princess Nourah bint Abdulrahman University Researchers Supporting Project number(PNURSP2025R319),Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia and Prince Sultan University for covering the article processing charges(APC)associated with this publicationResearchers Supporting Project Number(RSPD2025R1107),King Saud University,Riyadh,Saudi Arabia.
文摘Healthcare networks prove to be an urgent issue in terms of intrusion detection due to the critical consequences of cyber threats and the extreme sensitivity of medical information.The proposed Auto-Stack ID in the study is a stacked ensemble of encoder-enhanced auctions that can be used to improve intrusion detection in healthcare networks.TheWUSTL-EHMS 2020 dataset trains and evaluates themodel,constituting an imbalanced class distribution(87.46% normal traffic and 12.53% intrusion attacks).To address this imbalance,the study balances the effect of training Bias through Stratified K-fold cross-validation(K=5),so that each class is represented similarly on training and validation splits.Second,the Auto-Stack ID method combines many base classifiers such as TabNet,LightGBM,Gaussian Naive Bayes,Histogram-Based Gradient Boosting(HGB),and Logistic Regression.We apply a two-stage training process based on the first stage,where we have base classifiers that predict out-of-fold(OOF)predictions,which we use as inputs for the second-stage meta-learner XGBoost.The meta-learner learns to refine predictions to capture complicated interactions between base models,thus improving detection accuracy without introducing bias,overfitting,or requiring domain knowledge of the meta-data.In addition,the auto-stack ID model got 98.41% accuracy and 93.45%F1 score,better than individual classifiers.It can identify intrusions due to its 90.55% recall and 96.53% precision with minimal false positives.These findings identify its suitability in ensuring healthcare networks’security through ensemble learning.Ongoing efforts will be deployed in real time to improve response to evolving threats.
基金supported by the Key Research and Development Program of Wuhan(2025010102030005)the National Nature Science Foundation of Jiangsu Province(BK20221259)。
文摘Carbonaceous material has attracted much attention in the application of sodium-ion batteries(SIBs)anode.However,sluggish reaction kinetics and structure stability impede the application.Therefore,a stacked layered sulfur-carbon complex with long-chain C–S_(x)–C bond(M-SC-S)is prepared.The layered structure ensures structural stability,and long-chain C–S_(x)–C bond expanding interlayer spacing boosts facile Na+diffusion.When assembled into cells,a high-quality solid-electrolyte interphase film would be formed due to a good match between the M-SC-S electrode and ether electrolyte.Moreover,an electrochemical activation process would happen between the Cu current collector and proper S-doped electrode material to in-situ form Cu_(2)S.The formation of Cu_(2)S in active material can not only provide more active sites for sodium storage and enhance pseudo-capacitance,but also reinforce the electrode/current collector interface and decrease the interfacial transfer resistance for rapid Na+kinetics.The synergistic effect of structure design and interface engineering optimizes the sodium storage system.Thus,the M-SC-S electrode delivers an excellent cyclic performance(321.6 mAh g^(−1)after 1000 cycles at 2 A g^(−1)with a capacity retention rate of 97.4%)and good rate capability(282.8 mAh g^(−1)after 4000 cycles even at a high current density of 10 A g^(−1)).The full cell also has an impressive cyclic performance(151.4 mAh g^(−1)after 500 cycles at 0.5 A g^(−1)).
基金supported by the National Natural Science Foundation of China(NSFC)under Grants(Nos.U21A20483,62373040 and 62273031).
文摘In the context of intelligent manufacturing,the modern hot strip mill process(HSMP)shows characteristics such as diversification of products,multi-specification batch production,and demand-oriented customization.These characteristics pose significant challenges to ensuring process stability and consistency of product performance.Therefore,exploring the potential relationship between product performance and the production process,and developing a comprehensive performance evaluation method adapted to modern HSMP have become an urgent issue.A comprehensive performance evaluation method for HSMP by integrating multi-task learning and stacked performance-related autoencoder is proposed to solve the problems such as incomplete performance indicators(PIs)data,insufficient real-time acquisition requirements,and coupling of multiple PIs.First,according to the existing Chinese standards,a comprehensive performance evaluation grade strategy for strip steel is designed.The random forest model is established to predict and complete the parts of PIs data that could not be obtained in real-time.Second,a stacked performance-related autoencoder(SPAE)model is proposed to extract the deep features closely related to the product performance.Then,considering the correlation between PIs,the multi-task learning framework is introduced to output the subitem ratings and comprehensive product performance rating results of the strip steel online in real-time,where each task represents a subitem of comprehensive performance.Finally,the effectiveness of the method is verified on a real HSMP dataset,and the results show that the accuracy of the proposed method is as high as 94.8%,which is superior to the other comparative methods.
基金supported by the Hunan Provincial Natural Science Foundation of China(2022JJ30103)“the 14th Five-Year Plan”Key Disciplines and Application-Oriented Special Disciplines of Hunan Province(Xiangjiaotong[2022]351)the Science and Technology Innovation Program of Hunan Province(2016TP1020).
文摘The adoption of deep learning-based side-channel analysis(DL-SCA)is crucial for leak detection in secure products.Many previous studies have applied this method to break targets protected with countermeasures.Despite the increasing number of studies,the problem of model overfitting.Recent research mainly focuses on exploring hyperparameters and network architectures,while offering limited insights into the effects of external factors on side-channel attacks,such as the number and type of models.This paper proposes a Side-channel Analysis method based on a Stacking ensemble,called Stacking-SCA.In our method,multiple models are deeply integrated.Through the extended application of base models and the meta-model,Stacking-SCA effectively improves the output class probabilities of the model,leading to better generalization.Furthermore,this method shows that the attack performance is sensitive to changes in the number of models.Next,five independent subsets are extracted from the original ASCAD database as multi-segment datasets,which are mutually independent.This method shows how these subsets are used as inputs for Stacking-SCA to enhance its attack convergence.The experimental results show that Stacking-SCA outperforms the current state-of-the-art results on several considered datasets,significantly reducing the number of attack traces required to achieve a guessing entropy of 1.Additionally,different hyperparameter sizes are adjusted to further validate the robustness of the method.
文摘A new 2-Π lumped element equivalent circuit model for high-k stacked on-chip transformers is proposed. The model parameters are extracted with high precision, mainly based on analytical methods. The developed model enables fast and accurate time domain transient analysis and noise analysis in RFIC simulation since all elements in the model are fre- quency independent. The validity of the proposed model has been demonstrated by a fabricated monolithic stacked trans- former in TSMC＇s 0.13μm mixed-signal （MS）/RF CMOS＇ process.
基金the financial support of the Aeronautical Science Foundation of China(Nos.2013ZE52067,2014ZE52057)
文摘In aircraft assembly, interlayer burr formation in dry drilling of stacked metal materials is a common problem. Traditional manual deburring operation seriously affects the assembly qual- ity and assembly efficiency, is time-consuming and costly, and is not conducive to aircraft automatic assembly based on industrial robot. In this paper, the formation of drilling exit burr and the influ- ence of interlayer gap on interlayer burr formation were studied, and the mechanism of interlayer gap formation in drilling stacked aluminum alloy plates was investigated, a simplified mathematical model of interlayer gap based on the theory of plates and shells and finite element method was established. The relationship between interlayer gap and interlayer burr, as well as the effect of feed rate and pressing force on interlayer burr height and interlayer gap was discussed. The result shows that theoretical interlayer gap has a positive correlation with interlayer burr height and preloading nressing force is an effective method to control interlaver burr formation.
基金supported by the China Transgenic Organism Research and Commercialization Project (2016ZX08011-001)the National Natural Science Fund Project (31270579)+1 种基金the Specialized Research Fund for the Doctoral Program of Higher Education, China (20130097130006)the 111 Project of China (B07030)
文摘Stacked（insect and herbicide resistant） transgenic rice T1c-19 with cry1C＊/bar genes, its receptor rice Minghui 63（herein MH63） and a local two-line hybrid indica rice Fengliangyou Xiang 1（used as a control） were compared for agronomic performance under field conditions without the relevant selection pressures. Agronomic traits（plant height, tiller number, and aboveground dry biomass）, reproductive ability（pollen viability, panicle length, and filled grain number of main panicles, seed set, and grain yield）, and weediness characteristics（seed shattering, seed overwintering ability, and volunteer seedling recruitment） were used to assess the potential weediness without selection pressure of stacked transgene rice T1c-19. In wet direct-seeded and transplanted rice fields, T1c-19 and its receptor MH63 performed similarly regarding vegetative growth and reproductive ability, but both of them were significantly inferior to the control. T1c-19 did not display weed characteristics; it had weak overwintering ability, low seed shattering and failed to establish volunteers. Exogenous insect and herbicide resistance genes did not confer competitive advantage to transgenic rice T1c-19 grown in the field without the relevant selection pressures.
基金supported by the Natural Science Foundation of Anhui Province(No.1808085MA10)Anhui Provincial Key R&D Program(No.202104g0102007)the National Natural Science Foundation of China(No.21805283)。
文摘The utilization of neutrons markedly affects the medical isotope yield of a subcritical system driven by an external D-T neutron source.The general methods to improve the utilization of neutrons include moderating multiplying,and reflecting neutrons,which ignores the use of neutrons that backscatter to the source direction.In this study,a stacked structure was formed by assembling the multiplier and the low-enriched uranium solution to enable the full use of neutrons that backscatter to the source direction and further improve the utilization of neutrons.A model based on SuperMC was used to evaluate the neutronics and safety behavior of the subcritical system,such as the neutron effective multiplication factor,neutron energy spectrum,medical isotope yield,and heat deposition.Based on the calculation results,when the intensity of the neutron source was 59×10^(13)n/s,the optimized design with a stacked structure could increase the yield of ^(99)Mo to182 Ci/day,which is approximately 16% higher than that obtained with a single-layer structure.The inlet H_(2)O coolant velocity of 1.0 m/s and initial temperature of 20℃ were also found to be sufficient to prevent boiling of the fuel solution.
基金financially supported by the China Transgenic Organism Research and Commercialization Project (2016ZX08011-001)
文摘Compared to single-trait transgenic crops, stacked transgenic plants may be more prone to become weedy, and transgene flow from stacked transgenic plants to weedy relatives may pose a potential environmental risk because these hybrids could be more advantageous under specific environmental conditions. Evaluation of the potential environmental risk caused by stacked transgenes is essential for assessing the environmental consequences caused by crop-weed transgene flow. The agronomic performance of fitness-related traits was assessed in F1+(transgene positive) hybrids(using the transgenic line T1 c-19 as the paternal parent) in monoculture and mixed planting under presence or absence glufosinate pressure in the presence or absence of natural insect pressure and then compared with the performance of F1–(transgene negative) hybrids(using the non-transgenic line Minghui 63(MH63) as the paternal parent) and their weedy rice counterparts. The results demonstrated that compared with the F1– hybrids and weedy rice counterparts, the F1+ hybrid presented higher performance(P<0.05) or non-significant changes(P>0.05) under natural insect pressure, respectively, lower performance(P<0.05) or non-significant changes(P>0.05) in the absence of insect pressure in monoculture planting, respectively. And compared to weedy rice counterparts, the F1+ hybrid presented higher performance(P<0.05) or non-significant changes(P>0.05) in the presence or absence of insect pressure in mixed planting, respectively. The F1+ hybrids presented nonsignificant changes(P>0.05) under the presence or absence glufosinate pressure under insect or non-insect pressure in monoculture planting. The all F1+ hybrids and two of three F1– hybrids had significantly lower(P<0.05) seed shattering than the weedy rice counterparts. The potential risk of gene flow from T1 c-19 to weedy rice should be prevented due to the greater fitness advantage of F1 hybrids in the majority of cases.
基金This research is supported financially by Natural Science Foundation of China(Grant No.51505234,51405241,51575283).
文摘With the rapid development of mechanical equipment,mechanical health monitoring field has entered the era of big data.Deep learning has made a great achievement in the processing of large data of image and speech due to the powerful modeling capabilities,this also brings influence to the mechanical fault diagnosis field.Therefore,according to the characteristics of motor vibration signals(nonstationary and difficult to deal with)and mechanical‘big data’,combined with deep learning,a motor fault diagnosis method based on stacked de-noising auto-encoder is proposed.The frequency domain signals obtained by the Fourier transform are used as input to the network.This method can extract features adaptively and unsupervised,and get rid of the dependence of traditional machine learning methods on human extraction features.A supervised fine tuning of the model is then carried out by backpropagation.The Asynchronous motor in Drivetrain Dynamics Simulator system was taken as the research object,the effectiveness of the proposed method was verified by a large number of data,and research on visualization of network output,the results shown that the SDAE method is more efficient and more intelligent.
