In order to suppress the influence of temperature changes on the performance of accelerometers,a digital quartz resonant accelerometer with low temperature drift is developed using a quartz resonator cluster as a tran...In order to suppress the influence of temperature changes on the performance of accelerometers,a digital quartz resonant accelerometer with low temperature drift is developed using a quartz resonator cluster as a transducer element.In addition,a digital intellectual property(IP) is designed in FPGA to achieve signal processing and fusion of integrated resonators.A testing system for digital quartz resonant accelerometers is established to characterize the performance under different conditions.The scale factor of the accelerometer prototype reaches 3561.63 Hz/g in the range of -1 g to +1 g,and 3542.5 Hz/g in the range of-10 g to+10 g.In different measurement ranges,the linear correlation coefficient R~2 of the accelerometer achieves greater than 0.998.The temperature drift of the accelerometer prototype is tested using a constant temperature test chamber,with a temperature change from -20℃ to 80℃.After temperature-drift compensation,the zero bias temperature coefficient falls to 0.08 mg/℃,and the scale factor temperature coefficient is 65.43 ppm/℃.The experimental results show that the digital quartz resonant accelerometer exhibits excellent sensitivity and low temperature drift.展开更多
Many real⁃world machine learning applications face the challenge of dealing with changing data over time,known as concept drift,and the issue of data indeterminacy,where all the true labels available are unrealistic.T...Many real⁃world machine learning applications face the challenge of dealing with changing data over time,known as concept drift,and the issue of data indeterminacy,where all the true labels available are unrealistic.This can lead to a decrease in the accuracy of the prediction models.The aim of this study is to introduce a new approach for detecting drift,which is based on neutrosophic set theory.This approach takes into account uncertainty in the prediction model and is able to handle indeterminate information,considering its impact on the models performance.The proposed method reads data into windows and calculates a set of values based on the concept of neutrosophic membership.These values are then used in the Neutrosophic Support Vector Machine(N⁃SVM).To address the issue of indeterminate true label data,the values issued by N⁃SVM are expressed as entropy and used as input for the ADWIN(Adaptive Windowing)change detector.When a drift is detected,the prediction model is retrained by including only the most recent instances with the original training data set.The proposed method gives promising results in terms of drift detection accuracy compared to the state of existing drift detection methods such as KSWIN,ADWIN,and DWM.展开更多
In this paper,we investigate the weighted Dirichlet eigenvalue problem of polynomial operator of the drifting Laplacian on the cigar soliton■as follows■where is a positive continuous function on,denotes the outward ...In this paper,we investigate the weighted Dirichlet eigenvalue problem of polynomial operator of the drifting Laplacian on the cigar soliton■as follows■where is a positive continuous function on,denotes the outward unit normal to the boundary,and are two nonnegative constants.We establish some universal inequalities for eigenvalues of this problem.展开更多
The particle identification(PID)of hadrons plays a crucial role in particle physics experiments,especially in flavor physics and jet tagging.The cluster counting method,which measures the number of primary ionizations...The particle identification(PID)of hadrons plays a crucial role in particle physics experiments,especially in flavor physics and jet tagging.The cluster counting method,which measures the number of primary ionizations in gaseous detectors,is a promising breakthrough in PID.However,developing an effective reconstruction algorithm for cluster counting remains challenging.To address this challenge,we propose a cluster counting algorithm based on long short-term memory and dynamic graph convolutional neural networks for the CEPC drift chamber.Experiments on Monte Carlo simulated samples demonstrate that our machine learning-based algorithm surpasses traditional methods.It improves the K/πseparation of PID by 10%,meeting the PID requirements of CEPC.展开更多
Ever since the research in machine learning gained traction in recent years,it has been employed to address challenges in a wide variety of domains,including mechanical devices.Most of the machine learning models are ...Ever since the research in machine learning gained traction in recent years,it has been employed to address challenges in a wide variety of domains,including mechanical devices.Most of the machine learning models are built on the assumption of a static learning environment,but in practical situations,the data generated by the process is dynamic.This evolution of the data is termed concept drift.This research paper presents an approach for predictingmechanical failure in real-time using incremental learning based on the statistically calculated parameters of mechanical equipment.The method proposed here is applicable to allmechanical devices that are susceptible to failure or operational degradation.The proposed method in this paper is equipped with the capacity to detect the drift in data generation and adaptation.The proposed approach evaluates the machine learning and deep learning models for their efficacy in handling the errors related to industrial machines due to their dynamic nature.It is observed that,in the settings without concept drift in the data,methods like SVM and Random Forest performed better compared to deep neural networks.However,this resulted in poor sensitivity for the smallest drift in the machine data reported as a drift.In this perspective,DNN generated the stable drift detection method;it reported an accuracy of 84%and an AUC of 0.87 while detecting only a single drift point,indicating the stability to performbetter in detecting and adapting to new data in the drifting environments under industrial measurement settings.展开更多
The primary goal of software defect prediction (SDP) is to pinpoint code modules that are likely to contain defects, thereby enabling software quality assurance teams to strategically allocate their resources and manp...The primary goal of software defect prediction (SDP) is to pinpoint code modules that are likely to contain defects, thereby enabling software quality assurance teams to strategically allocate their resources and manpower. Within-project defect prediction (WPDP) is a widely used method in SDP. Despite various improvements, current methods still face challenges such as coarse-grained prediction and ineffective handling of data drift due to differences in project distribution. To address these issues, we propose a fine-grained SDP method called DIDP (drift-immune defect prediction), based on drift-immune graph neural networks (DI-GNN). DIDP converts source code into graph representations and uses DI-GNN to mitigate data drift at the model level. It also analyses key statements leading to file defects for a more detailed SDP approach. We evaluated the performance of DIDP in WPDP by examining its file-level and statement-level accuracy compared to state-of-the-art methods, and by examining its cross-project prediction accuracy. The results of the experiment show that DIDP showed significant improvements in F1-score and Recall@Top20%LOC compared to existing methods, even with large software version changes. DIDP also performed well in cross-project SDP. Our study demonstrates that DIDP achieves impressive prediction results in WPDP, effectively mitigating data drift and accurately predicting defective files. Additionally, DIDP can rank the risk of statements in defective files, aiding developers and testers in identifying potential code issues.展开更多
Purpose:This research addresses the challenge of concept drift in AI-enabled software,particularly within autonomous vehicle systems where concept drift in object recognition(like pedestrian detection)can lead to misc...Purpose:This research addresses the challenge of concept drift in AI-enabled software,particularly within autonomous vehicle systems where concept drift in object recognition(like pedestrian detection)can lead to misclassifications and safety risks.This study introduces a proactive framework to detect early signs of domain-specific concept drift by leveraging domain analysis and natural language processing techniques.This method is designed to help maintain the relevance of domain knowledge and prevent potential failures in AI systems due to evolving concept definitions.Design/methodology/approach:The proposed framework integrates natural language processing and image analysis to continuously update and monitor key domain concepts against evolving external data sources,such as social media and news.By identifying terms and features closely associated with core concepts,the system anticipates and flags significant changes.This was tested in the automotive domain on the pedestrian concept,where the framework was evaluated for its capacity to detect shifts in the recognition of pedestrians,particularly during events like Halloween and specific car accidents.Findings:The framework demonstrated an ability to detect shifts in the domain concept of pedestrians,as evidenced by contextual changes around major events.While it successfully identified pedestrian-related drift,the system’s accuracy varied when overlapping with larger social events.The results indicate the model’s potential to foresee relevant shifts before they impact autonomous systems,although further refinement is needed to handle high-impact concurrent events.Research limitations:This study focused on detecting concept drift in the pedestrian domain within autonomous vehicles,with results varying across domains.To assess generalizability,we tested the framework for airplane-related incidents and demonstrated adaptability.However,unpredictable events and data biases from social media and news may obscure domain-specific drifts.Further evaluation across diverse applications is needed to enhance robustness in evolving AI environments.Practical implications:The proactive detection of concept drift has significant implications for AI-driven domains,especially in safety-critical applications like autonomous driving.By identifying early signs of drift,this framework provides actionable insights for AI system updates,potentially reducing misclassification risks and enhancing public safety.Moreover,it enables timely interventions,reducing costly and labor-intensive retraining requirements by focusing only on the relevant aspects of evolving concepts.This method offers a streamlined approach for maintaining AI system performance in environments where domain knowledge rapidly changes.Originality/value:This study contributes a novel domain-agnostic framework that combines natural language processing with image analysis to predict concept drift early.This unique approach,which is focused on real-time data sources,offers an effective and scalable solution for addressing the evolving nature of domain-specific concepts in AI applications.展开更多
Cardiovascular diseases(CVDs)continue to present a leading cause ofmortalityworldwide,emphasizing the importance of early and accurate prediction.Electrocardiogram(ECG)signals,central to cardiac monitoring,have increa...Cardiovascular diseases(CVDs)continue to present a leading cause ofmortalityworldwide,emphasizing the importance of early and accurate prediction.Electrocardiogram(ECG)signals,central to cardiac monitoring,have increasingly been integratedwithDeep Learning(DL)for real-time prediction of CVDs.However,DL models are prone to performance degradation due to concept drift and to catastrophic forgetting.To address this issue,we propose a realtime CVDs prediction approach,referred to as ADWIN-GFR that combines Convolutional Neural Network(CNN)layers,for spatial feature extraction,with Gated Recurrent Units(GRU),for temporal modeling,alongside adaptive drift detection and mitigation mechanisms.The proposed approach integratesAdaptiveWindowing(ADWIN)for realtime concept drift detection,a fine-tuning strategy based on Generative Features Replay(GFR)to preserve previously acquired knowledge,and a dynamic replay buffer ensuring variance,diversity,and data distribution coverage.Extensive experiments conducted on the MIT-BIH arrhythmia dataset demonstrate that ADWIN-GFR outperforms standard fine-tuning techniques,achieving an average post-drift accuracy of 95.4%,amacro F1-score of 93.9%,and a remarkably low forgetting score of 0.9%.It also exhibits an average drift detection delay of 12 steps and achieves an adaptation gain of 17.2%.These findings underscore the potential of ADWIN-GFR for deployment in real-world cardiac monitoring systems,including wearable ECG devices and hospital-based patient monitoring platforms.展开更多
A half-size prototype of the multi wire drift chamber for the cooling storage ring external-target experiment(CEE)was assembled and tested in the 350 MeV/u Kr+Fe reactions at the heavy-ion research facility in Lanzhou...A half-size prototype of the multi wire drift chamber for the cooling storage ring external-target experiment(CEE)was assembled and tested in the 350 MeV/u Kr+Fe reactions at the heavy-ion research facility in Lanzhou.The prototype consists of six sense layers,where the sense wires are stretched in three directions X,U,and V;meeting 0?,30?,and-30?,respectively,with respect to the vertical axis.The sensitive area of the prototype is 76 cm×76 cm.The amplified and shaped signals from the anode wires were digitized in a serial capacity array.When operating at a high voltage of 1500 V on the anode wires,the efficiency for each layer is greater than 95%.The tracking residual is approximately 301±2μm.This performance satisfies the requirements of CEE.展开更多
During the 10th Chinese Arctic scientific expedition carried out in the summer of 2019,the surface current in the high-latitude areas of the Arctic Ocean was observed using a self-developed surface drifting buoy,which...During the 10th Chinese Arctic scientific expedition carried out in the summer of 2019,the surface current in the high-latitude areas of the Arctic Ocean was observed using a self-developed surface drifting buoy,which was initially deployed in the Chukchi Sea.The buoy traversed the Chukchi Sea,Chukchi Abyssal Plain,Mendeleev Ridge,Makarov Basin,and Canada Basin over a period of 632 d.After returning to the Mendeleev Ridge,it continued to drift toward the pole.Overall,the track of the buoy reflected the characteristics of the transpolar drift and Chukchi Slope Current,as well as the inertial flow,cross-ridge surface flow,and even the surface disorganized flow for some time intervals.The results showed that:(1)the transpolar drift mainly occurs in the Chukchi Abyssal Plain,Mendeleev Ridge,and western Canada Basin to the east of the ridge where sea ice concentration is high,and the average northward flow velocity in the region between 79.41°N and 86.32°N was 5.1 cm/s;(2)the average surface velocity of the Chukchi Slope Current was 13.5 cm/s,and while this current moves westward along the continental slope,it also extends northwestward across the continental slope and flows to the deep sea;and(3)when sea ice concentration was less than 50%,the inertial flow was more significant(the maximum observed inertial flow was 26 cm/s,and the radius of the inertia circle was 3.6 km).展开更多
Serious startup drift of the Ring Laser Gyroscope(RLG)is observed during cold startup process,which will dramatically degrade the performances of the corresponding Inertial Navigation System(INS).In this paper,correla...Serious startup drift of the Ring Laser Gyroscope(RLG)is observed during cold startup process,which will dramatically degrade the performances of the corresponding Inertial Navigation System(INS).In this paper,correlation analysis method,which analyzes the relationship between the startup drift of the RLG and the temperature change,is used to determine the significant temperature-related terms during gyroscope startup.Based on the significant temperature-related terms and the startup time length,a startup drift compensation model for RLG based on monotonicity-constrained Radial Basis Function(RBF)neural network is proposed and validated.Compared with the raw RLG data without compensation,the standard deviation of the RLG output with the proposed constrained RBF network model is decreased by more than 46%,and the peak-to-peak value is decreased by more than 35%.Compared with the traditional multiple regression model,the standard deviation and peak-to-peak value of the RLG output are decreased by more than 10%and 6%,respectively.Compared with the common RBF network model,the standard deviation and peak-to-peak value of the RLG output are decreased by more than 8%and 3%,respectively.Navigation experiments also validate the effectiveness of the compensation model.展开更多
The effect of Stokes drift production(SDP),which includes Coriolis-Stokes forcing,Langmuir circulation,and Craik-Lei-bovich vortexes,on the upper ocean during typhoon passage in the Bohai Sea(BS),China,is investigated...The effect of Stokes drift production(SDP),which includes Coriolis-Stokes forcing,Langmuir circulation,and Craik-Lei-bovich vortexes,on the upper ocean during typhoon passage in the Bohai Sea(BS),China,is investigated by using a coupled wave-current model.The role of SDP in turbulent mixing and the further dynamics during the entire typhoon period are comprehensively stud-ied.Experimental results show that SDP greatly increases turbulent mixing at all depths under typhoon conditions by up to seven times that under normal weather conditions.SDP generally strengthens sea surface cooling by more than 0.4℃,with the maximum reduction in sea surface temperature(SST)at the during-typhoon stage exceeding 2℃,which is approximately seven times larger than that under normal weather conditions.The SDP-induced decrease in current speed can exceed 0.2ms^(-1),and the change in current direction is generally opposite the wind direction.These results suggest that Stokes drift depresses the effect of strong winds on currents by intensifying turbulent mixing.Mixed layer depth(MLD)is distinctly increased by O(1)during typhoons due to SDP and can deepen by more than 5m.In addition,the continuous effects of SDP on SST,current,and MLD at the after-typhoon stage indi-cate a hysteretic response between SDP and typhoon actions.展开更多
Ocean waves and Stokes drift are generated by typhoons.This study investigated the characteristics of ocean waves and wave-induced Stokes drift and their effects during Typhoon Mangkhut using European Centre for Mediu...Ocean waves and Stokes drift are generated by typhoons.This study investigated the characteristics of ocean waves and wave-induced Stokes drift and their effects during Typhoon Mangkhut using European Centre for MediumRange Weather Forecasts(ECMWF)ERA5 datasets and observational data.The results revealed that the typhoon generated intense cyclones and huge typhoon waves with a maximum wind speed of 45 m/s,a minimum pressure of955 h Pa,and a maximum significant wave height of 12 m.The Stokes drift caused by typhoon waves exceeded 0.6m/s,the Stokes depth scale exceeded 18 m,and the maximum Stokes transport reached 6 m^(2)/s.The spatial distribution of 10-m wind speed,typhoon wave height,Stokes drift,Stokes depth,and Stokes transport during the typhoon was highly correlated with the typhoon track.The distribution along the typhoon track showed significant zonal asymmetry,with greater intensity on the right side of the typhoon track than on the left side.These findings provide important insights into the impact of typhoons on ocean waves and Stokes drift,thus improving our understanding of the interactions between typhoons and the ocean environment.This study also investigated the contribution of Stokes transport to the total net transport during typhoons using Ekman-Stokes Numbers as a comparative measure.The results indicated that the ratio of Stokes transport to the total net transport reached up to 50%within the typhoon radius,while it was approximately 30%outside the radius.Strong Stokes transport induced by typhoon waves led to divergence in the transport direction,which resulted in upwelling of the lower ocean as a compensation current.Thus,Stokes transport played a crucial role in the vertical mixing of the ocean during typhoons.The findings suggested that Stokes transport should be paid more attention to,particularly in high latitude ocean regions,where strong winds can amplify its effects.展开更多
Pesticide adjuvants,as crop protection products,have been widely used to reduce drift loss and improve utilization efficiency by regulating droplet spectrum.However,the coordinated regulation mechanisms of adjuvants a...Pesticide adjuvants,as crop protection products,have been widely used to reduce drift loss and improve utilization efficiency by regulating droplet spectrum.However,the coordinated regulation mechanisms of adjuvants and nozzles on droplet spectrum remain unclear.Here,we established the relationship between droplet spectrum evolution and liquid atomization by investigating the typical characteristics of droplet diameter distribution near the nozzle.Based on this,the regulation mechanisms of distinctive pesticide adjuvants on droplet spectrum were clarified,and the corresponding drift reduction performances were quantitively evaluated by wind tunnel experiments.It shows that the droplet diameter firstly shifts to the smaller due to the liquid sheet breakup and then prefers to increase caused by droplet interactions.Reducing the surface tension of sprayed liquid facilitates the uniform liquid breakup and increasing the viscosity inhibits the liquid deformation,which prolong the atomization process and effectively improve the droplet spectrum.As a result,the drift losses of flat-fan and hollow cone nozzles are reduced by about 50%after adding organosilicon and vegetable oil adjuvants.By contrast,the air induction nozzle shows a superior anti-drift ability,regardless of distinctive adjuvants.Our findings provide insights into rational adjuvant design and nozzle selection in the field application.展开更多
The circular electron-positron collider(CEPC)is designed to precisely measure the properties of the Higgs boson,study electroweak interactions at the Z-boson peak,and search for new physics beyond the Standard Model.A...The circular electron-positron collider(CEPC)is designed to precisely measure the properties of the Higgs boson,study electroweak interactions at the Z-boson peak,and search for new physics beyond the Standard Model.As a component of the 4th conceptual CEPC detector,the drift chamber facilitates the measurement of charged particles.This study implemented a Geant4-based simulation and track reconstruction for the drift chamber.For the simulation,detector construction and response were implemented and added to the CEPC simulation chain.The development of track reconstruction involves track finding using the combinatorial Kalman filter method and track fitting using the tool of GenFit.Using the simulated data,the tracking performance was studied.The results showed that both the reconstruction resolution and tracking efficiency satisfied the requirements of the CEPC experiment.展开更多
An integral quality control(QC)procedure that integrates various QC methods and considers the design indexes and operational status of the instruments for the observations of drifting air-sea interface buoy was develo...An integral quality control(QC)procedure that integrates various QC methods and considers the design indexes and operational status of the instruments for the observations of drifting air-sea interface buoy was developed in the order of basic in-spection followed by targeted QC.The innovative method of combining a moving Hampel filter and local anomaly detection com-plies with statistical laws and physical processes,which guarantees the QC performance of meteorological variables.Two sets of observation data were used to verify the applicability and effectiveness of the QC procedure,and the effect was evaluated using the observations of the Kuroshio Extension Observatory buoy as the reference.The results showed that the outliers in the time series can be correctly identified and processed,and the quality of data improved significantly.The linear correlation between the quality-controlled observations and the reference increased,and the difference decreased.The correlation coefficient of wind speed before and after QC increased from 0.77 to 0.82,and the maximum absolute error decreased by approximately 2.8ms^(-1).In addition,air pressure and relative humidity were optimized by 10^(-3)–10^(-2) orders of magnitude.For the sea surface temperature,the weight of coefficients of the continuity test algorithm was optimized based on the sea area of data acquisition,which effectively expanded the applicability of the algorithm.展开更多
In order to realize the thrust estimation of the Hall thruster during its flight mission,this study establishes an estimation method based on measurement of the Hall drift current.In this method,the Hall drift current...In order to realize the thrust estimation of the Hall thruster during its flight mission,this study establishes an estimation method based on measurement of the Hall drift current.In this method,the Hall drift current is calculated from an inverse magnetostatic problem,which is formulated according to its induced magnetic flux density detected by sensors,and then the thrust is estimated by multiplying the Hall drift current with the characteristic magnetic flux density of the thruster itself.In addition,a three-wire torsion pendulum micro-thrust measurement system is utilized to verify the estimate values obtained from the proposed method.The errors were found to be less than 8%when the discharge voltage ranged from 250 V to 350 V and the anode flow rate ranged from 30 sccm to 50 sccm,indicating the possibility that the proposed thrust estimate method could be practically applied.Moreover,the measurement accuracy of the magnetic flux density is suggested to be lower than 0.015 mT and improvement on the inverse problem solution is required in the future.展开更多
The existence of a significant electron drift instability(EDI) in the Hall thruster is considered as one of the possible causes of the abnormal increase in axial electron mobility near the outlet of the channel. In re...The existence of a significant electron drift instability(EDI) in the Hall thruster is considered as one of the possible causes of the abnormal increase in axial electron mobility near the outlet of the channel. In recent years, extensive simulation research on the characteristics of EDI has been conducted, but the excitation mechanism and growth mechanism of EDI in linear stage and nonlinear stage remain unclear. In this work, a one-dimensional PIC model in the azimuthal direction of the thruster near-exit region is established to gain further insights into the mechanism of the EDI in detail, and the effects of different types of propellants on EDI characteristics are discussed. The changes in axial electron transport caused by EDI under different types of propellants and electromagnetic field strengths are also examined. The results indicate that EDI undergoes a short linear growth phase before transitioning to the nonlinear phase and finally reaching saturation through the ion Landau damping. The EDI drives a significant ion heating in the azimuthal direction through electron–ion friction before entering the quasi-steady state, which increases the axial mobility of the electrons. Using lighter atomic weight propellant can effectively suppress the oscillation amplitude of EDI, but it will increase the linear growth rate, frequency, and phase velocity of EDI. Compared with the classical mobility, the axial electron mobility under the EDI increases by three orders of magnitude, which is consistent with experimental phenomena. The change of propellant type is insufficient to significantly change the axial electron mobility. It is also found that the collisions between electrons and neutral gasescan significantly affect the axial electron mobility under the influence of EDI, and lead the strength of the electric field to increase and the strength of the magnetic field to decrease, thereby both effectively suppressing the axial transport of electrons.展开更多
The amorphous phase-change materials with spontaneous structural relaxation leads to the resistance drift with the time for phase-change neuron synaptic devices. Here, we modify the phase change properties of the conv...The amorphous phase-change materials with spontaneous structural relaxation leads to the resistance drift with the time for phase-change neuron synaptic devices. Here, we modify the phase change properties of the conventional Ge_2Sb_2Te_5(GST) material by introducing an SnS phase. It is found that the resistance drift coefficient of SnS-doped GST was decreased from 0.06 to 0.01. It can be proposed that the origin originates from the precipitation of GST nanocrystals accompanied by the precipitation of SnS crystals compared to single-phase GST compound systems. We also found that the decrease in resistance drift can be attributed to the narrowed bandgap from 0.65 to 0.43 eV after SnS-doping. Thus, this study reveals the quantitative relationship between the resistance drift and the band gap and proposes a new idea for alleviating the resistance drift by composition optimization, which is of great significance for finding a promising phase change material.展开更多
文摘In order to suppress the influence of temperature changes on the performance of accelerometers,a digital quartz resonant accelerometer with low temperature drift is developed using a quartz resonator cluster as a transducer element.In addition,a digital intellectual property(IP) is designed in FPGA to achieve signal processing and fusion of integrated resonators.A testing system for digital quartz resonant accelerometers is established to characterize the performance under different conditions.The scale factor of the accelerometer prototype reaches 3561.63 Hz/g in the range of -1 g to +1 g,and 3542.5 Hz/g in the range of-10 g to+10 g.In different measurement ranges,the linear correlation coefficient R~2 of the accelerometer achieves greater than 0.998.The temperature drift of the accelerometer prototype is tested using a constant temperature test chamber,with a temperature change from -20℃ to 80℃.After temperature-drift compensation,the zero bias temperature coefficient falls to 0.08 mg/℃,and the scale factor temperature coefficient is 65.43 ppm/℃.The experimental results show that the digital quartz resonant accelerometer exhibits excellent sensitivity and low temperature drift.
文摘Many real⁃world machine learning applications face the challenge of dealing with changing data over time,known as concept drift,and the issue of data indeterminacy,where all the true labels available are unrealistic.This can lead to a decrease in the accuracy of the prediction models.The aim of this study is to introduce a new approach for detecting drift,which is based on neutrosophic set theory.This approach takes into account uncertainty in the prediction model and is able to handle indeterminate information,considering its impact on the models performance.The proposed method reads data into windows and calculates a set of values based on the concept of neutrosophic membership.These values are then used in the Neutrosophic Support Vector Machine(N⁃SVM).To address the issue of indeterminate true label data,the values issued by N⁃SVM are expressed as entropy and used as input for the ADWIN(Adaptive Windowing)change detector.When a drift is detected,the prediction model is retrained by including only the most recent instances with the original training data set.The proposed method gives promising results in terms of drift detection accuracy compared to the state of existing drift detection methods such as KSWIN,ADWIN,and DWM.
基金Supported by National Natural Science Foundation of China(11001130,12272062)Fundamental Research Funds for the Central Universities(30917011335).
文摘In this paper,we investigate the weighted Dirichlet eigenvalue problem of polynomial operator of the drifting Laplacian on the cigar soliton■as follows■where is a positive continuous function on,denotes the outward unit normal to the boundary,and are two nonnegative constants.We establish some universal inequalities for eigenvalues of this problem.
基金supported by National Natural Science Foundation of China(NSFC)(Nos.12475200 and 12275296)Joint Fund of Research utilizing Large-Scale Scientific Facility of the NSFC and CAS(No.U2032114)Institute of High Energy Physics(Chinese Academy of Sciences)Innovative Project on Sciences and Technologies(Nos.E3545BU210 and E25456U210).
文摘The particle identification(PID)of hadrons plays a crucial role in particle physics experiments,especially in flavor physics and jet tagging.The cluster counting method,which measures the number of primary ionizations in gaseous detectors,is a promising breakthrough in PID.However,developing an effective reconstruction algorithm for cluster counting remains challenging.To address this challenge,we propose a cluster counting algorithm based on long short-term memory and dynamic graph convolutional neural networks for the CEPC drift chamber.Experiments on Monte Carlo simulated samples demonstrate that our machine learning-based algorithm surpasses traditional methods.It improves the K/πseparation of PID by 10%,meeting the PID requirements of CEPC.
文摘Ever since the research in machine learning gained traction in recent years,it has been employed to address challenges in a wide variety of domains,including mechanical devices.Most of the machine learning models are built on the assumption of a static learning environment,but in practical situations,the data generated by the process is dynamic.This evolution of the data is termed concept drift.This research paper presents an approach for predictingmechanical failure in real-time using incremental learning based on the statistically calculated parameters of mechanical equipment.The method proposed here is applicable to allmechanical devices that are susceptible to failure or operational degradation.The proposed method in this paper is equipped with the capacity to detect the drift in data generation and adaptation.The proposed approach evaluates the machine learning and deep learning models for their efficacy in handling the errors related to industrial machines due to their dynamic nature.It is observed that,in the settings without concept drift in the data,methods like SVM and Random Forest performed better compared to deep neural networks.However,this resulted in poor sensitivity for the smallest drift in the machine data reported as a drift.In this perspective,DNN generated the stable drift detection method;it reported an accuracy of 84%and an AUC of 0.87 while detecting only a single drift point,indicating the stability to performbetter in detecting and adapting to new data in the drifting environments under industrial measurement settings.
基金The authors would like to express appreciation to the National Natural Science Foundation of China(Grant No.61762067)for their financial support.
文摘The primary goal of software defect prediction (SDP) is to pinpoint code modules that are likely to contain defects, thereby enabling software quality assurance teams to strategically allocate their resources and manpower. Within-project defect prediction (WPDP) is a widely used method in SDP. Despite various improvements, current methods still face challenges such as coarse-grained prediction and ineffective handling of data drift due to differences in project distribution. To address these issues, we propose a fine-grained SDP method called DIDP (drift-immune defect prediction), based on drift-immune graph neural networks (DI-GNN). DIDP converts source code into graph representations and uses DI-GNN to mitigate data drift at the model level. It also analyses key statements leading to file defects for a more detailed SDP approach. We evaluated the performance of DIDP in WPDP by examining its file-level and statement-level accuracy compared to state-of-the-art methods, and by examining its cross-project prediction accuracy. The results of the experiment show that DIDP showed significant improvements in F1-score and Recall@Top20%LOC compared to existing methods, even with large software version changes. DIDP also performed well in cross-project SDP. Our study demonstrates that DIDP achieves impressive prediction results in WPDP, effectively mitigating data drift and accurately predicting defective files. Additionally, DIDP can rank the risk of statements in defective files, aiding developers and testers in identifying potential code issues.
基金supported by U.S.Office of Naval Research(ONR)Grant number G2A62826.
文摘Purpose:This research addresses the challenge of concept drift in AI-enabled software,particularly within autonomous vehicle systems where concept drift in object recognition(like pedestrian detection)can lead to misclassifications and safety risks.This study introduces a proactive framework to detect early signs of domain-specific concept drift by leveraging domain analysis and natural language processing techniques.This method is designed to help maintain the relevance of domain knowledge and prevent potential failures in AI systems due to evolving concept definitions.Design/methodology/approach:The proposed framework integrates natural language processing and image analysis to continuously update and monitor key domain concepts against evolving external data sources,such as social media and news.By identifying terms and features closely associated with core concepts,the system anticipates and flags significant changes.This was tested in the automotive domain on the pedestrian concept,where the framework was evaluated for its capacity to detect shifts in the recognition of pedestrians,particularly during events like Halloween and specific car accidents.Findings:The framework demonstrated an ability to detect shifts in the domain concept of pedestrians,as evidenced by contextual changes around major events.While it successfully identified pedestrian-related drift,the system’s accuracy varied when overlapping with larger social events.The results indicate the model’s potential to foresee relevant shifts before they impact autonomous systems,although further refinement is needed to handle high-impact concurrent events.Research limitations:This study focused on detecting concept drift in the pedestrian domain within autonomous vehicles,with results varying across domains.To assess generalizability,we tested the framework for airplane-related incidents and demonstrated adaptability.However,unpredictable events and data biases from social media and news may obscure domain-specific drifts.Further evaluation across diverse applications is needed to enhance robustness in evolving AI environments.Practical implications:The proactive detection of concept drift has significant implications for AI-driven domains,especially in safety-critical applications like autonomous driving.By identifying early signs of drift,this framework provides actionable insights for AI system updates,potentially reducing misclassification risks and enhancing public safety.Moreover,it enables timely interventions,reducing costly and labor-intensive retraining requirements by focusing only on the relevant aspects of evolving concepts.This method offers a streamlined approach for maintaining AI system performance in environments where domain knowledge rapidly changes.Originality/value:This study contributes a novel domain-agnostic framework that combines natural language processing with image analysis to predict concept drift early.This unique approach,which is focused on real-time data sources,offers an effective and scalable solution for addressing the evolving nature of domain-specific concepts in AI applications.
基金supported by Princess Nourah bint Abdulrahman University Researchers Supporting Project number(PNURSP2025R196)Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.
文摘Cardiovascular diseases(CVDs)continue to present a leading cause ofmortalityworldwide,emphasizing the importance of early and accurate prediction.Electrocardiogram(ECG)signals,central to cardiac monitoring,have increasingly been integratedwithDeep Learning(DL)for real-time prediction of CVDs.However,DL models are prone to performance degradation due to concept drift and to catastrophic forgetting.To address this issue,we propose a realtime CVDs prediction approach,referred to as ADWIN-GFR that combines Convolutional Neural Network(CNN)layers,for spatial feature extraction,with Gated Recurrent Units(GRU),for temporal modeling,alongside adaptive drift detection and mitigation mechanisms.The proposed approach integratesAdaptiveWindowing(ADWIN)for realtime concept drift detection,a fine-tuning strategy based on Generative Features Replay(GFR)to preserve previously acquired knowledge,and a dynamic replay buffer ensuring variance,diversity,and data distribution coverage.Extensive experiments conducted on the MIT-BIH arrhythmia dataset demonstrate that ADWIN-GFR outperforms standard fine-tuning techniques,achieving an average post-drift accuracy of 95.4%,amacro F1-score of 93.9%,and a remarkably low forgetting score of 0.9%.It also exhibits an average drift detection delay of 12 steps and achieves an adaptation gain of 17.2%.These findings underscore the potential of ADWIN-GFR for deployment in real-world cardiac monitoring systems,including wearable ECG devices and hospital-based patient monitoring platforms.
基金supported by the National Natural Science Foundation of China(Nos.11927901,11875301,11875302,U1867214,U1832105,U1832167)the Strategic Priority Research Program of Chinese Academy of Sciences(No.XDB34000000)+2 种基金the National Key R&D Program of China(No.2018YFE0205200)the CAS"Light of West China"Programthe Tsinghua University Initiative Scientific Research Program。
文摘A half-size prototype of the multi wire drift chamber for the cooling storage ring external-target experiment(CEE)was assembled and tested in the 350 MeV/u Kr+Fe reactions at the heavy-ion research facility in Lanzhou.The prototype consists of six sense layers,where the sense wires are stretched in three directions X,U,and V;meeting 0?,30?,and-30?,respectively,with respect to the vertical axis.The sensitive area of the prototype is 76 cm×76 cm.The amplified and shaped signals from the anode wires were digitized in a serial capacity array.When operating at a high voltage of 1500 V on the anode wires,the efficiency for each layer is greater than 95%.The tracking residual is approximately 301±2μm.This performance satisfies the requirements of CEE.
基金The Fundamental Research Fund Project of the First Institute of OceanographyMinistry of Natural Resources+1 种基金under contract No.GY022Y07the National Natural Science Foundation of China under contract No.42106232。
文摘During the 10th Chinese Arctic scientific expedition carried out in the summer of 2019,the surface current in the high-latitude areas of the Arctic Ocean was observed using a self-developed surface drifting buoy,which was initially deployed in the Chukchi Sea.The buoy traversed the Chukchi Sea,Chukchi Abyssal Plain,Mendeleev Ridge,Makarov Basin,and Canada Basin over a period of 632 d.After returning to the Mendeleev Ridge,it continued to drift toward the pole.Overall,the track of the buoy reflected the characteristics of the transpolar drift and Chukchi Slope Current,as well as the inertial flow,cross-ridge surface flow,and even the surface disorganized flow for some time intervals.The results showed that:(1)the transpolar drift mainly occurs in the Chukchi Abyssal Plain,Mendeleev Ridge,and western Canada Basin to the east of the ridge where sea ice concentration is high,and the average northward flow velocity in the region between 79.41°N and 86.32°N was 5.1 cm/s;(2)the average surface velocity of the Chukchi Slope Current was 13.5 cm/s,and while this current moves westward along the continental slope,it also extends northwestward across the continental slope and flows to the deep sea;and(3)when sea ice concentration was less than 50%,the inertial flow was more significant(the maximum observed inertial flow was 26 cm/s,and the radius of the inertia circle was 3.6 km).
基金supported in part by the National Natural Science Foundation of China(No.61203199)。
文摘Serious startup drift of the Ring Laser Gyroscope(RLG)is observed during cold startup process,which will dramatically degrade the performances of the corresponding Inertial Navigation System(INS).In this paper,correlation analysis method,which analyzes the relationship between the startup drift of the RLG and the temperature change,is used to determine the significant temperature-related terms during gyroscope startup.Based on the significant temperature-related terms and the startup time length,a startup drift compensation model for RLG based on monotonicity-constrained Radial Basis Function(RBF)neural network is proposed and validated.Compared with the raw RLG data without compensation,the standard deviation of the RLG output with the proposed constrained RBF network model is decreased by more than 46%,and the peak-to-peak value is decreased by more than 35%.Compared with the traditional multiple regression model,the standard deviation and peak-to-peak value of the RLG output are decreased by more than 10%and 6%,respectively.Compared with the common RBF network model,the standard deviation and peak-to-peak value of the RLG output are decreased by more than 8%and 3%,respectively.Navigation experiments also validate the effectiveness of the compensation model.
基金supported by the National Natural Science Foundation of China(No.42176020)the National Key Research and Development Program(No.2022 YFC3105002).
文摘The effect of Stokes drift production(SDP),which includes Coriolis-Stokes forcing,Langmuir circulation,and Craik-Lei-bovich vortexes,on the upper ocean during typhoon passage in the Bohai Sea(BS),China,is investigated by using a coupled wave-current model.The role of SDP in turbulent mixing and the further dynamics during the entire typhoon period are comprehensively stud-ied.Experimental results show that SDP greatly increases turbulent mixing at all depths under typhoon conditions by up to seven times that under normal weather conditions.SDP generally strengthens sea surface cooling by more than 0.4℃,with the maximum reduction in sea surface temperature(SST)at the during-typhoon stage exceeding 2℃,which is approximately seven times larger than that under normal weather conditions.The SDP-induced decrease in current speed can exceed 0.2ms^(-1),and the change in current direction is generally opposite the wind direction.These results suggest that Stokes drift depresses the effect of strong winds on currents by intensifying turbulent mixing.Mixed layer depth(MLD)is distinctly increased by O(1)during typhoons due to SDP and can deepen by more than 5m.In addition,the continuous effects of SDP on SST,current,and MLD at the after-typhoon stage indi-cate a hysteretic response between SDP and typhoon actions.
基金financially supported by the National Key Research and Development Program of China(Grant No.2021YFB2601100)the National Natural Science Foundation of China(Grant No.52171246)+4 种基金The Belt and Road Special Foundation of the State Key Laboratory of Hydrology-Water Resources and Hydraulic Engineering(Grant No.2019491911)the Open Research Foundation of the State Key Laboratory of Coastal and Offshore Engineering,Dalian University of Technology(Grant No.LP2005)the Science and Technology Innovation Program of Hunan Province(Grant No.2023RC3136)the Natural Science Foundation of Hunan Province(Grant No.2022JJ20041)Educational Science Foundation of Hunan Province(Grant No.23A0265)。
文摘Ocean waves and Stokes drift are generated by typhoons.This study investigated the characteristics of ocean waves and wave-induced Stokes drift and their effects during Typhoon Mangkhut using European Centre for MediumRange Weather Forecasts(ECMWF)ERA5 datasets and observational data.The results revealed that the typhoon generated intense cyclones and huge typhoon waves with a maximum wind speed of 45 m/s,a minimum pressure of955 h Pa,and a maximum significant wave height of 12 m.The Stokes drift caused by typhoon waves exceeded 0.6m/s,the Stokes depth scale exceeded 18 m,and the maximum Stokes transport reached 6 m^(2)/s.The spatial distribution of 10-m wind speed,typhoon wave height,Stokes drift,Stokes depth,and Stokes transport during the typhoon was highly correlated with the typhoon track.The distribution along the typhoon track showed significant zonal asymmetry,with greater intensity on the right side of the typhoon track than on the left side.These findings provide important insights into the impact of typhoons on ocean waves and Stokes drift,thus improving our understanding of the interactions between typhoons and the ocean environment.This study also investigated the contribution of Stokes transport to the total net transport during typhoons using Ekman-Stokes Numbers as a comparative measure.The results indicated that the ratio of Stokes transport to the total net transport reached up to 50%within the typhoon radius,while it was approximately 30%outside the radius.Strong Stokes transport induced by typhoon waves led to divergence in the transport direction,which resulted in upwelling of the lower ocean as a compensation current.Thus,Stokes transport played a crucial role in the vertical mixing of the ocean during typhoons.The findings suggested that Stokes transport should be paid more attention to,particularly in high latitude ocean regions,where strong winds can amplify its effects.
基金financially supported by the National Key Research and Development Program of China(2017YFD0200304)。
文摘Pesticide adjuvants,as crop protection products,have been widely used to reduce drift loss and improve utilization efficiency by regulating droplet spectrum.However,the coordinated regulation mechanisms of adjuvants and nozzles on droplet spectrum remain unclear.Here,we established the relationship between droplet spectrum evolution and liquid atomization by investigating the typical characteristics of droplet diameter distribution near the nozzle.Based on this,the regulation mechanisms of distinctive pesticide adjuvants on droplet spectrum were clarified,and the corresponding drift reduction performances were quantitively evaluated by wind tunnel experiments.It shows that the droplet diameter firstly shifts to the smaller due to the liquid sheet breakup and then prefers to increase caused by droplet interactions.Reducing the surface tension of sprayed liquid facilitates the uniform liquid breakup and increasing the viscosity inhibits the liquid deformation,which prolong the atomization process and effectively improve the droplet spectrum.As a result,the drift losses of flat-fan and hollow cone nozzles are reduced by about 50%after adding organosilicon and vegetable oil adjuvants.By contrast,the air induction nozzle shows a superior anti-drift ability,regardless of distinctive adjuvants.Our findings provide insights into rational adjuvant design and nozzle selection in the field application.
基金supported by the National Natural Science Foundation of China(NSFC)(Nos.12025502 and 12341504)。
文摘The circular electron-positron collider(CEPC)is designed to precisely measure the properties of the Higgs boson,study electroweak interactions at the Z-boson peak,and search for new physics beyond the Standard Model.As a component of the 4th conceptual CEPC detector,the drift chamber facilitates the measurement of charged particles.This study implemented a Geant4-based simulation and track reconstruction for the drift chamber.For the simulation,detector construction and response were implemented and added to the CEPC simulation chain.The development of track reconstruction involves track finding using the combinatorial Kalman filter method and track fitting using the tool of GenFit.Using the simulated data,the tracking performance was studied.The results showed that both the reconstruction resolution and tracking efficiency satisfied the requirements of the CEPC experiment.
基金supported by the Natural Resources Development Special Fund Project of Jiangsu Province(No.JSZRHYKJ202009)the Taishan Scholar Funds(No.tsqn 201812022)+2 种基金the Fundamental Research Funds for the Central Universities(No.202072001)the Guangxi Key Laboratory of Marine Disaster in the Beibu Gulf,Beibu Gulf University(No.2021KF03)the National Natural Science Foundation of China(No.42176020).
文摘An integral quality control(QC)procedure that integrates various QC methods and considers the design indexes and operational status of the instruments for the observations of drifting air-sea interface buoy was developed in the order of basic in-spection followed by targeted QC.The innovative method of combining a moving Hampel filter and local anomaly detection com-plies with statistical laws and physical processes,which guarantees the QC performance of meteorological variables.Two sets of observation data were used to verify the applicability and effectiveness of the QC procedure,and the effect was evaluated using the observations of the Kuroshio Extension Observatory buoy as the reference.The results showed that the outliers in the time series can be correctly identified and processed,and the quality of data improved significantly.The linear correlation between the quality-controlled observations and the reference increased,and the difference decreased.The correlation coefficient of wind speed before and after QC increased from 0.77 to 0.82,and the maximum absolute error decreased by approximately 2.8ms^(-1).In addition,air pressure and relative humidity were optimized by 10^(-3)–10^(-2) orders of magnitude.For the sea surface temperature,the weight of coefficients of the continuity test algorithm was optimized based on the sea area of data acquisition,which effectively expanded the applicability of the algorithm.
基金funded by the Basic Research on National Defense of China(No.JCKY2021603B033),which is gratefully acknowledged。
文摘In order to realize the thrust estimation of the Hall thruster during its flight mission,this study establishes an estimation method based on measurement of the Hall drift current.In this method,the Hall drift current is calculated from an inverse magnetostatic problem,which is formulated according to its induced magnetic flux density detected by sensors,and then the thrust is estimated by multiplying the Hall drift current with the characteristic magnetic flux density of the thruster itself.In addition,a three-wire torsion pendulum micro-thrust measurement system is utilized to verify the estimate values obtained from the proposed method.The errors were found to be less than 8%when the discharge voltage ranged from 250 V to 350 V and the anode flow rate ranged from 30 sccm to 50 sccm,indicating the possibility that the proposed thrust estimate method could be practically applied.Moreover,the measurement accuracy of the magnetic flux density is suggested to be lower than 0.015 mT and improvement on the inverse problem solution is required in the future.
基金Project supported by the National Natural Science Foundation of China (Grant Nos.11975062 and 11605021)the Fundamental Research Funds for the Central Universities (Grant No.3132023192)。
文摘The existence of a significant electron drift instability(EDI) in the Hall thruster is considered as one of the possible causes of the abnormal increase in axial electron mobility near the outlet of the channel. In recent years, extensive simulation research on the characteristics of EDI has been conducted, but the excitation mechanism and growth mechanism of EDI in linear stage and nonlinear stage remain unclear. In this work, a one-dimensional PIC model in the azimuthal direction of the thruster near-exit region is established to gain further insights into the mechanism of the EDI in detail, and the effects of different types of propellants on EDI characteristics are discussed. The changes in axial electron transport caused by EDI under different types of propellants and electromagnetic field strengths are also examined. The results indicate that EDI undergoes a short linear growth phase before transitioning to the nonlinear phase and finally reaching saturation through the ion Landau damping. The EDI drives a significant ion heating in the azimuthal direction through electron–ion friction before entering the quasi-steady state, which increases the axial mobility of the electrons. Using lighter atomic weight propellant can effectively suppress the oscillation amplitude of EDI, but it will increase the linear growth rate, frequency, and phase velocity of EDI. Compared with the classical mobility, the axial electron mobility under the EDI increases by three orders of magnitude, which is consistent with experimental phenomena. The change of propellant type is insufficient to significantly change the axial electron mobility. It is also found that the collisions between electrons and neutral gasescan significantly affect the axial electron mobility under the influence of EDI, and lead the strength of the electric field to increase and the strength of the magnetic field to decrease, thereby both effectively suppressing the axial transport of electrons.
基金financially supported by the National Natural Science Foundation of China(Grant No.62074089)the Natural Science Foundation of Ningbo City,China(Grant No.2022J072)+1 种基金the Youth Science and Technology Innovation Leading Talent Project of Ningbo City,China(Grant No.2023QL005)sponsored by the K.C.Wong Magna Fund in Ningbo University。
文摘The amorphous phase-change materials with spontaneous structural relaxation leads to the resistance drift with the time for phase-change neuron synaptic devices. Here, we modify the phase change properties of the conventional Ge_2Sb_2Te_5(GST) material by introducing an SnS phase. It is found that the resistance drift coefficient of SnS-doped GST was decreased from 0.06 to 0.01. It can be proposed that the origin originates from the precipitation of GST nanocrystals accompanied by the precipitation of SnS crystals compared to single-phase GST compound systems. We also found that the decrease in resistance drift can be attributed to the narrowed bandgap from 0.65 to 0.43 eV after SnS-doping. Thus, this study reveals the quantitative relationship between the resistance drift and the band gap and proposes a new idea for alleviating the resistance drift by composition optimization, which is of great significance for finding a promising phase change material.
