Jockusch and Ingrassia introduced notions of e-genericity, s-genericity and p-genericity for recursively enumerable sets in 1985 and 1980 respectively. It has been shown that there are many important properties of rec...Jockusch and Ingrassia introduced notions of e-genericity, s-genericity and p-genericity for recursively enumerable sets in 1985 and 1980 respectively. It has been shown that there are many important properties of recursively enumerable generic sets and degrees. We have investigated the structures of wtt-degrees inside recursively enumerable p-generic Turing degrees and proved that every r.e. p-generic degree is noncontiguous. In this note, we展开更多
Problems about density are remarkable in the theory of degrees of unsolvability. Owing to their difficulty few results have been obtained till now. Sacks 1964 showed that the r. e. degrees are dense; Fejer 1980 showed...Problems about density are remarkable in the theory of degrees of unsolvability. Owing to their difficulty few results have been obtained till now. Sacks 1964 showed that the r. e. degrees are dense; Fejer 1980 showed that nonbraching degrees are dense in the r.e. degrees, this is the first nontrivial definable subset of the degrees known to be dense.展开更多
A new reducibility between the recursive sets is defined,which is appropriate to be used in the study of the polynomial reducibility and the NP-problem.
A cable-driven redundant manipulator(CDRM)characterized by redundant degrees of freedom and a lightweight,slender design can perform tasks in confined and restricted spaces efficiently.However,the complex multistage c...A cable-driven redundant manipulator(CDRM)characterized by redundant degrees of freedom and a lightweight,slender design can perform tasks in confined and restricted spaces efficiently.However,the complex multistage coupling between drive cables and passive joints in CDRM leads to a challenging dynamic model with difficult parameter identification,complicating the efforts to achieve accurate modeling and control.To address these challenges,this paper proposes a dynamic modeling and adaptive control approach tailored for CDRM systems.A multilevel kinematic model of the cable-driven redundant manipulator is presented,and a screw theory is employed to represent the cable tension and cable contact forces as spatial wrenches,which are equivalently mapped to joint torque using the principle of virtual work.This approach simplifies the mapping process while maintaining the integrity of the dynamic model.A recursive method is used to compute cable tension section-by-section for enhancing the efficiency of inverse dynamics calculations and meeting the high-frequency demands of the controller,thereby avoiding large matrix operations.An adaptive control method is proposed building on this foundation,which involves the design of a dynamic parameter adaptive controller in the joint space to simplify the linearization process of the dynamic equations along with a closed-loop controller that incorporates motor parameters in the driving space.This approach improves the control accuracy and dynamic performance of the CDRM under dynamic uncertainties.The accuracy and computational efficiency of the dynamic model are validated through simulations,and the effectiveness of the proposed control method is demonstrated through control tests.This paper presents a dynamic modeling and adaptive control approach for CDRM to enhance accuracy and performance under dynamic uncertainties.展开更多
One of the most notable developments in the asset management industry in recent decades has been the growth of algorithmic trading.At the same time,significant structural changes in the industry have occurred,with pas...One of the most notable developments in the asset management industry in recent decades has been the growth of algorithmic trading.At the same time,significant structural changes in the industry have occurred,with passive investing gaining momentum.The intersection of these two major trends poses special challenges during market downturns,magnifying portfolio losses and leading to significant outflows.Emerging market(EM)investors have seen two major downturn events in the 2020s,namely the COVID-19 pandemic and the Russia-Ukraine conflict,both of which have strongly affected EM portfolios’risk-return profiles and increased their correlations with their developed market counterparts,eliminating much or all of EMs’diversification benefits.This has led to major capital outflows from EM countries,further destabilizing these fragile economies.Against this backdrop,we argue that capital need not exit these riskier markets during periods of turmoil and support this by developing a second-generation Automated Adaptive Trading System(AATS)back-tested on a relevant,diversified EM portfolio that tracks the Morgan Stanley Capital International(MSCI)Emerging Markets Index during a volatile period characterized by negative returns,high risk,and a high correlation with global markets for the buy-and-hold EM portfolio.The system incorporates an Autoregressive Moving Average-Generalized AutoRegressive Conditional Heteroskedasticity model that offers an interpretability advantage over machine-learning methods.The main strength of the AATS is its ability to allow the embedded hybrid forecasting model to adapt to the changing environments that characterize EMs.This is done by implementing a recursive window technique and running a user-specified fitness function to dynamically optimize the mean equation parameters throughout the lead time.Back-testing several configurations of the flexible AATS consistently reveals its superiority while assuring the robustness of the results.We conclude that with the right investment tools,EMs continue to offer compelling opportunities that should not be overlooked.The novel AATS proposed in this study is such a tool,providing active EM investors with substantial value-added through its ability to generate abnormal returns,and can help to enhance the resilience of EMs by mitigating the cost of crises for those countries.展开更多
This paper focuses on the problem of leaderfollowing consensus for nonlinear cascaded multi-agent systems.The control strategies for these systems are transformed into successive control problem schemes for lower-orde...This paper focuses on the problem of leaderfollowing consensus for nonlinear cascaded multi-agent systems.The control strategies for these systems are transformed into successive control problem schemes for lower-order error subsystems.A distributed consensus analysis for the corresponding error systems is conducted by employing recursive methods and virtual controllers,accompanied by a series of Lyapunov functions devised throughout the iterative process,which solves the leaderfollowing consensus problem of a class of nonlinear cascaded multi-agent systems.Specific simulation examples illustrate the effectiveness of the proposed control algorithm.展开更多
For nonlinear state estimation driven by non-Gaussian noise,the estimator is required to be updated iteratively.Since the iterative update approximates a linear process,it fails to capture the nonlinearity of observat...For nonlinear state estimation driven by non-Gaussian noise,the estimator is required to be updated iteratively.Since the iterative update approximates a linear process,it fails to capture the nonlinearity of observation models,and this further degrades filtering accuracy and consistency.Given the flaws of nonlinear iteration,this work incorporates a recursive strategy into generalized M-estimation rather than the iterative strategy.The proposed algorithm extends nonlinear recursion to nonlinear systems using the statistical linear regression method.The recursion allows for the gradual release of observation information and consequently enables the update to proceed along the nonlinear direction.Considering the correlated state and observation noise induced by recursions,a separately reweighting strategy is adopted to build a robust nonlinear system.Analogous to the nonlinear recursion,a robust nonlinear recursive update strategy is proposed,where the associated covariances and the observation noise statistics are updated recursively to ensure the consistency of observation noise statistics,thereby completing the nonlinear solution of the robust system.Compared with the iterative update strategies under non-Gaussian observation noise,the recursive update strategy can facilitate the estimator to achieve higher filtering accuracy,stronger robustness,and better consistency.Therefore,the proposed strategy is more suitable for the robust nonlinear filtering framework.展开更多
To obtain new integrable nonlinear differential equations there are some well-known methods such as Lax equations with different Lax representations.There are also some other methods that are based on integrable scala...To obtain new integrable nonlinear differential equations there are some well-known methods such as Lax equations with different Lax representations.There are also some other methods that are based on integrable scalar nonlinear partial differential equations.We show that some systems of integrable equations published recently are the M_(2)-extension of integrable such scalar equations.For illustration,we give Korteweg-de Vries,Kaup-Kupershmidt,and SawadaKotera equations as examples.By the use of such an extension of integrable scalar equations,we obtain some new integrable systems with recursion operators.We also give the soliton solutions of the systems and integrable standard nonlocal and shifted nonlocal reductions of these systems.展开更多
Intrusion detection systems play a vital role in cyberspace security.In this study,a network intrusion detection method based on the feature selection algorithm(FSA)and a deep learning model is developed using a fusio...Intrusion detection systems play a vital role in cyberspace security.In this study,a network intrusion detection method based on the feature selection algorithm(FSA)and a deep learning model is developed using a fusion of a recursive feature elimination(RFE)algorithm and a bidirectional gated recurrent unit(BGRU).Particularly,the RFE algorithm is employed to select features from high-dimensional data to reduce weak correlations between features and remove redundant features in the numerical feature space.Then,a neural network that combines the BGRU and multilayer perceptron(MLP)is adopted to extract deep intrusion behavior features.Finally,a support vector machine(SVM)classifier is used to classify intrusion behaviors.The proposed model is verified by experiments on the NSL-KDD dataset.The results indicate that the proposed model achieves a 90.25%accuracy and a 97.51%detection rate in binary classification and outperforms other machine learning and deep learning models in intrusion classification.The proposed method can provide new insight into network intrusion detection.展开更多
Software defect prediction aims to use measurement data of code and historical defects to predict potential problems,optimize testing resources and defect management.However,current methods face challenges:(1)Coarse-g...Software defect prediction aims to use measurement data of code and historical defects to predict potential problems,optimize testing resources and defect management.However,current methods face challenges:(1)Coarse-grained file level detection cannot accurately locate specific defects.(2)Fine-grained line-level defect prediction methods rely solely on local information of a single line of code,failing to deeply analyze the semantic context of the code line and ignoring the heuristic impact of line-level context on the code line,making it difficult to capture the interaction between global and local information.Therefore,this paper proposes a telecontext-enhanced recursive interactive attention fusion method for line-level defect prediction(TRIA-LineDP).Firstly,using a bidirectional hierarchical attention network to extract semantic features and contextual information from the original code lines as the basis.Then,the extracted contextual information is forwarded to the telecontext capture module to aggregate the global context,thereby enhancing the understanding of broader code dynamics.Finally,a recursive interaction model is used to simulate the interaction between code lines and line-level context,passing information layer by layer to enhance local and global information exchange,thereby achieving accurate defect localization.Experimental results from within-project defect prediction(WPDP)and cross-project defect prediction(CPDP)conducted on nine different projects(encompassing a total of 32 versions)demonstrated that,within the same project,the proposed methods will respectively recall at top 20%of lines of code(Recall@Top20%LOC)and effort at top 20%recall(Effort@Top20%Recall)has increased by 11%–52%and 23%–77%.In different projects,improvements of 9%–60%and 18%–77%have been achieved,which are superior to existing advanced methods and have good detection performance.展开更多
Aeromagnetic compensation is one of the key issues in high-precision geomagnetic fl ight carrier navigation, directly determining the accuracy and reliability of real-time magnetic measurement data. The accurate model...Aeromagnetic compensation is one of the key issues in high-precision geomagnetic fl ight carrier navigation, directly determining the accuracy and reliability of real-time magnetic measurement data. The accurate modeling and compensation of interference magnetic measurements on carriers are of great signifi cance for the construction of reference and real-time maps for geomagnetic navigation. Current research on aeromagnetic compensation algorithms mainly focuses on accurately modeling interference magnetic fields from model- and data-driven perspectives based on measured aeromagnetic data. Challenges in obtaining aeromagnetic data and low information complexity adversely aff ect the generalization performance of a constructed model. To address these issues, a recursive least square algorithm based on elastic weight consolidation is proposed, which eff ectively suppresses the occurrence of catastrophic forgetting by controlling the direction of parameter updates. Experimental verifi cation with publicly available aeromagnetic datasets shows that the proposed algorithm can eff ectively circumvent historical information loss caused by interference magnetic field models during parameter updates and improve the stability, robustness, and accuracy of interference magnetic fi eld models.展开更多
Accurate short-term photovoltaic(PV)output forecasting is beneficial for increasing grid stabil-ity and enhancing the capacity for photovoltaic power absorption.In response to the challenges faced by commonly used pho...Accurate short-term photovoltaic(PV)output forecasting is beneficial for increasing grid stabil-ity and enhancing the capacity for photovoltaic power absorption.In response to the challenges faced by commonly used photovoltaic forecasting methods,which struggle to handle issues such as non-u-niform lengths of time series data for power generation and meteorological conditions,overlapping photovoltaic characteristics,and nonlinear correlations,an improved method that utilizes spectral clustering and dynamic time warping(DTW)for selecting similar days is proposed to optimize the dataset along the temporal dimension.Furthermore,XGBoost is employed for recursive feature selec-tion.On this basis,to address the issue that single forecasting models excel at capturing different data characteristics and tend to exhibit significant prediction errors under adverse meteorological con-ditions,an improved forecasting model based on Stacking and weighted fusion is proposed to reduce the independent bias and variance of individual models and enhance the predictive accuracy.Final-ly,experimental validation is carried out using real data from a photovoltaic power station in the Xi-aoshan District of Hangzhou,China,demonstrating that the proposed method can still achieve accu-rate and robust forecasting results even under conditions of significant meteorological fluctuations.展开更多
Spartina alterniflora is now listed among the world’s 100 most dangerous invasive species,severely affecting the ecological balance of coastal wetlands.Remote sensing technologies based on deep learning enable large-...Spartina alterniflora is now listed among the world’s 100 most dangerous invasive species,severely affecting the ecological balance of coastal wetlands.Remote sensing technologies based on deep learning enable large-scale monitoring of Spartina alterniflora,but they require large datasets and have poor interpretability.A new method is proposed to detect Spartina alterniflora from Sentinel-2 imagery.Firstly,to get the high canopy cover and dense community characteristics of Spartina alterniflora,multi-dimensional shallow features are extracted from the imagery.Secondly,to detect different objects from satellite imagery,index features are extracted,and the statistical features of the Gray-Level Co-occurrence Matrix(GLCM)are derived using principal component analysis.Then,ensemble learning methods,including random forest,extreme gradient boosting,and light gradient boosting machine models,are employed for image classification.Meanwhile,Recursive Feature Elimination with Cross-Validation(RFECV)is used to select the best feature subset.Finally,to enhance the interpretability of the models,the best features are utilized to classify multi-temporal images and SHapley Additive exPlanations(SHAP)is combined with these classifications to explain the model prediction process.The method is validated by using Sentinel-2 imageries and previous observations of Spartina alterniflora in Chongming Island,it is found that the model combining image texture features such as GLCM covariance can significantly improve the detection accuracy of Spartina alterniflora by about 8%compared with the model without image texture features.Through multiple model comparisons and feature selection via RFECV,the selected model and eight features demonstrated good classification accuracy when applied to data from different time periods,proving that feature reduction can effectively enhance model generalization.Additionally,visualizing model decisions using SHAP revealed that the image texture feature component_1_GLCMVariance is particularly important for identifying each land cover type.展开更多
High-speed milling(HSM)is advantageous for machining high-quality complex-structure surface components with various materials.Identifying and estimating cutting force signals for characterizing HSM is of high signific...High-speed milling(HSM)is advantageous for machining high-quality complex-structure surface components with various materials.Identifying and estimating cutting force signals for characterizing HSM is of high significance.However,considering the tool runout and size effects,many proposed models focus on the material and mechanical characteristics.This study presents a novel approach for predicting micromilling cutting forces using a semianalytical multidimensional model that integrates experimental empirical data and a mechanical theoretical force model.A novel analytical optimization approach is provided to identify the cutting forces,classify the cutting states,and determine the tool runout using an adaptive algorithm that simplifies modeling and calculation.The instantaneous un-deformed chip thickness(IUCT)is determined from the trochoidal trajectories of each tool flute and optimized using the bisection method.Herein,the computational efficiency is improved,and the errors are clarified.The tool runout parameters are identified from the processed displacement signals and determined from the preprocessed vibration signals using an adaptive signal processing method.It is reliable and stable for determining tool runout and is an effective foundation for the force model.This approach is verified using HSM tests.Herein,the determination coefficients are stable above 0.9.It is convenient and efficient for achieving the key intermediate parameters(IUCT and tool runout),which can be generalized to various machining conditions and operations.展开更多
According to the road adaptive requirements for the vehicle longitudinal safety assistant system an estimation method of the road longitudinal friction coefficient is proposed.The method can simultaneously be applied ...According to the road adaptive requirements for the vehicle longitudinal safety assistant system an estimation method of the road longitudinal friction coefficient is proposed.The method can simultaneously be applied to both the high and the low slip ratio conditions. Based on the simplified magic formula tire model the road longitudinal friction coefficient is preliminarily estimated by the recursive least squares method.The estimated friction coefficient and the tires model parameters are considered as extended states. The extended Kalman filter algorithm is employed to filter out the noise and adaptively adjust the tire model parameters. Then the final road longitudinal friction coefficient is accurately and robustly estimated. The Carsim simulation results show that the proposed method is better than the conventional algorithm. The road longitudinal friction coefficient can be quickly and accurately estimated under both the high and the low slip ratio conditions.The error is less than 0.1 and the response time is less than 2 s which meets the requirements of the vehicle longitudinal safety assistant system.展开更多
基金Project supported by the National Natural Science Foundation of China.
文摘Jockusch and Ingrassia introduced notions of e-genericity, s-genericity and p-genericity for recursively enumerable sets in 1985 and 1980 respectively. It has been shown that there are many important properties of recursively enumerable generic sets and degrees. We have investigated the structures of wtt-degrees inside recursively enumerable p-generic Turing degrees and proved that every r.e. p-generic degree is noncontiguous. In this note, we
文摘Problems about density are remarkable in the theory of degrees of unsolvability. Owing to their difficulty few results have been obtained till now. Sacks 1964 showed that the r. e. degrees are dense; Fejer 1980 showed that nonbraching degrees are dense in the r.e. degrees, this is the first nontrivial definable subset of the degrees known to be dense.
基金Research partially supported by the Youth NSF grant of China.
文摘A new reducibility between the recursive sets is defined,which is appropriate to be used in the study of the polynomial reducibility and the NP-problem.
基金Supported by National Natural Science Foundation of China(Grant No.52405040)Research Project of State Key Laboratory of Mechanical System and Vibration(Grant No.MSV202514)。
文摘A cable-driven redundant manipulator(CDRM)characterized by redundant degrees of freedom and a lightweight,slender design can perform tasks in confined and restricted spaces efficiently.However,the complex multistage coupling between drive cables and passive joints in CDRM leads to a challenging dynamic model with difficult parameter identification,complicating the efforts to achieve accurate modeling and control.To address these challenges,this paper proposes a dynamic modeling and adaptive control approach tailored for CDRM systems.A multilevel kinematic model of the cable-driven redundant manipulator is presented,and a screw theory is employed to represent the cable tension and cable contact forces as spatial wrenches,which are equivalently mapped to joint torque using the principle of virtual work.This approach simplifies the mapping process while maintaining the integrity of the dynamic model.A recursive method is used to compute cable tension section-by-section for enhancing the efficiency of inverse dynamics calculations and meeting the high-frequency demands of the controller,thereby avoiding large matrix operations.An adaptive control method is proposed building on this foundation,which involves the design of a dynamic parameter adaptive controller in the joint space to simplify the linearization process of the dynamic equations along with a closed-loop controller that incorporates motor parameters in the driving space.This approach improves the control accuracy and dynamic performance of the CDRM under dynamic uncertainties.The accuracy and computational efficiency of the dynamic model are validated through simulations,and the effectiveness of the proposed control method is demonstrated through control tests.This paper presents a dynamic modeling and adaptive control approach for CDRM to enhance accuracy and performance under dynamic uncertainties.
基金funded by the EU’s NextGenerationEU instrument through the National Recovery and Resilience Plan of Romania-Pillar Ⅲ-C9-I8,managed by the Ministry of Research,Innovation and Digitalization,within the project entitled,Non-Gaussian self-similar processes:Enhancing mathematical tools and financial models for capturing complex market dynamics”,contract no.760243/28.12.2023,code CF 194/31.07.2023’.
文摘One of the most notable developments in the asset management industry in recent decades has been the growth of algorithmic trading.At the same time,significant structural changes in the industry have occurred,with passive investing gaining momentum.The intersection of these two major trends poses special challenges during market downturns,magnifying portfolio losses and leading to significant outflows.Emerging market(EM)investors have seen two major downturn events in the 2020s,namely the COVID-19 pandemic and the Russia-Ukraine conflict,both of which have strongly affected EM portfolios’risk-return profiles and increased their correlations with their developed market counterparts,eliminating much or all of EMs’diversification benefits.This has led to major capital outflows from EM countries,further destabilizing these fragile economies.Against this backdrop,we argue that capital need not exit these riskier markets during periods of turmoil and support this by developing a second-generation Automated Adaptive Trading System(AATS)back-tested on a relevant,diversified EM portfolio that tracks the Morgan Stanley Capital International(MSCI)Emerging Markets Index during a volatile period characterized by negative returns,high risk,and a high correlation with global markets for the buy-and-hold EM portfolio.The system incorporates an Autoregressive Moving Average-Generalized AutoRegressive Conditional Heteroskedasticity model that offers an interpretability advantage over machine-learning methods.The main strength of the AATS is its ability to allow the embedded hybrid forecasting model to adapt to the changing environments that characterize EMs.This is done by implementing a recursive window technique and running a user-specified fitness function to dynamically optimize the mean equation parameters throughout the lead time.Back-testing several configurations of the flexible AATS consistently reveals its superiority while assuring the robustness of the results.We conclude that with the right investment tools,EMs continue to offer compelling opportunities that should not be overlooked.The novel AATS proposed in this study is such a tool,providing active EM investors with substantial value-added through its ability to generate abnormal returns,and can help to enhance the resilience of EMs by mitigating the cost of crises for those countries.
基金National Natural Science Foundation of China(No.12071370)。
文摘This paper focuses on the problem of leaderfollowing consensus for nonlinear cascaded multi-agent systems.The control strategies for these systems are transformed into successive control problem schemes for lower-order error subsystems.A distributed consensus analysis for the corresponding error systems is conducted by employing recursive methods and virtual controllers,accompanied by a series of Lyapunov functions devised throughout the iterative process,which solves the leaderfollowing consensus problem of a class of nonlinear cascaded multi-agent systems.Specific simulation examples illustrate the effectiveness of the proposed control algorithm.
基金co-supported by the National Natural Science Foundation of China(No.62303246,No.62103204)the China Postdoctoral Science Foundation(No.2023M731788)。
文摘For nonlinear state estimation driven by non-Gaussian noise,the estimator is required to be updated iteratively.Since the iterative update approximates a linear process,it fails to capture the nonlinearity of observation models,and this further degrades filtering accuracy and consistency.Given the flaws of nonlinear iteration,this work incorporates a recursive strategy into generalized M-estimation rather than the iterative strategy.The proposed algorithm extends nonlinear recursion to nonlinear systems using the statistical linear regression method.The recursion allows for the gradual release of observation information and consequently enables the update to proceed along the nonlinear direction.Considering the correlated state and observation noise induced by recursions,a separately reweighting strategy is adopted to build a robust nonlinear system.Analogous to the nonlinear recursion,a robust nonlinear recursive update strategy is proposed,where the associated covariances and the observation noise statistics are updated recursively to ensure the consistency of observation noise statistics,thereby completing the nonlinear solution of the robust system.Compared with the iterative update strategies under non-Gaussian observation noise,the recursive update strategy can facilitate the estimator to achieve higher filtering accuracy,stronger robustness,and better consistency.Therefore,the proposed strategy is more suitable for the robust nonlinear filtering framework.
基金partially supported by the Scientific and Technological Research Council of Turkey(TüBITAK)。
文摘To obtain new integrable nonlinear differential equations there are some well-known methods such as Lax equations with different Lax representations.There are also some other methods that are based on integrable scalar nonlinear partial differential equations.We show that some systems of integrable equations published recently are the M_(2)-extension of integrable such scalar equations.For illustration,we give Korteweg-de Vries,Kaup-Kupershmidt,and SawadaKotera equations as examples.By the use of such an extension of integrable scalar equations,we obtain some new integrable systems with recursion operators.We also give the soliton solutions of the systems and integrable standard nonlocal and shifted nonlocal reductions of these systems.
基金supported in part by the National Natural Science Foundation of China(No.62001333)the Scientific Research Project of Education Department of Hubei Province(No.D20221702).
文摘Intrusion detection systems play a vital role in cyberspace security.In this study,a network intrusion detection method based on the feature selection algorithm(FSA)and a deep learning model is developed using a fusion of a recursive feature elimination(RFE)algorithm and a bidirectional gated recurrent unit(BGRU).Particularly,the RFE algorithm is employed to select features from high-dimensional data to reduce weak correlations between features and remove redundant features in the numerical feature space.Then,a neural network that combines the BGRU and multilayer perceptron(MLP)is adopted to extract deep intrusion behavior features.Finally,a support vector machine(SVM)classifier is used to classify intrusion behaviors.The proposed model is verified by experiments on the NSL-KDD dataset.The results indicate that the proposed model achieves a 90.25%accuracy and a 97.51%detection rate in binary classification and outperforms other machine learning and deep learning models in intrusion classification.The proposed method can provide new insight into network intrusion detection.
基金supported by National Natural Science Foundation of China(no.62376240).
文摘Software defect prediction aims to use measurement data of code and historical defects to predict potential problems,optimize testing resources and defect management.However,current methods face challenges:(1)Coarse-grained file level detection cannot accurately locate specific defects.(2)Fine-grained line-level defect prediction methods rely solely on local information of a single line of code,failing to deeply analyze the semantic context of the code line and ignoring the heuristic impact of line-level context on the code line,making it difficult to capture the interaction between global and local information.Therefore,this paper proposes a telecontext-enhanced recursive interactive attention fusion method for line-level defect prediction(TRIA-LineDP).Firstly,using a bidirectional hierarchical attention network to extract semantic features and contextual information from the original code lines as the basis.Then,the extracted contextual information is forwarded to the telecontext capture module to aggregate the global context,thereby enhancing the understanding of broader code dynamics.Finally,a recursive interaction model is used to simulate the interaction between code lines and line-level context,passing information layer by layer to enhance local and global information exchange,thereby achieving accurate defect localization.Experimental results from within-project defect prediction(WPDP)and cross-project defect prediction(CPDP)conducted on nine different projects(encompassing a total of 32 versions)demonstrated that,within the same project,the proposed methods will respectively recall at top 20%of lines of code(Recall@Top20%LOC)and effort at top 20%recall(Effort@Top20%Recall)has increased by 11%–52%and 23%–77%.In different projects,improvements of 9%–60%and 18%–77%have been achieved,which are superior to existing advanced methods and have good detection performance.
基金supported by the National Natural Science Foundation of China under Grant 61673017in part by the Science and Technology Department of Shaanxi Province under Grant 2024JC-YBQN-0657。
文摘Aeromagnetic compensation is one of the key issues in high-precision geomagnetic fl ight carrier navigation, directly determining the accuracy and reliability of real-time magnetic measurement data. The accurate modeling and compensation of interference magnetic measurements on carriers are of great signifi cance for the construction of reference and real-time maps for geomagnetic navigation. Current research on aeromagnetic compensation algorithms mainly focuses on accurately modeling interference magnetic fields from model- and data-driven perspectives based on measured aeromagnetic data. Challenges in obtaining aeromagnetic data and low information complexity adversely aff ect the generalization performance of a constructed model. To address these issues, a recursive least square algorithm based on elastic weight consolidation is proposed, which eff ectively suppresses the occurrence of catastrophic forgetting by controlling the direction of parameter updates. Experimental verifi cation with publicly available aeromagnetic datasets shows that the proposed algorithm can eff ectively circumvent historical information loss caused by interference magnetic field models during parameter updates and improve the stability, robustness, and accuracy of interference magnetic fi eld models.
基金Supported by the National Natural Science Foundation of China(No.52005442)the Technology Project of Zhejiang Huayun Information Technology Co.,Ltd.(No.HYJT/JS-2020-004).
文摘Accurate short-term photovoltaic(PV)output forecasting is beneficial for increasing grid stabil-ity and enhancing the capacity for photovoltaic power absorption.In response to the challenges faced by commonly used photovoltaic forecasting methods,which struggle to handle issues such as non-u-niform lengths of time series data for power generation and meteorological conditions,overlapping photovoltaic characteristics,and nonlinear correlations,an improved method that utilizes spectral clustering and dynamic time warping(DTW)for selecting similar days is proposed to optimize the dataset along the temporal dimension.Furthermore,XGBoost is employed for recursive feature selec-tion.On this basis,to address the issue that single forecasting models excel at capturing different data characteristics and tend to exhibit significant prediction errors under adverse meteorological con-ditions,an improved forecasting model based on Stacking and weighted fusion is proposed to reduce the independent bias and variance of individual models and enhance the predictive accuracy.Final-ly,experimental validation is carried out using real data from a photovoltaic power station in the Xi-aoshan District of Hangzhou,China,demonstrating that the proposed method can still achieve accu-rate and robust forecasting results even under conditions of significant meteorological fluctuations.
基金The National Key Research and Development Program of China under contract No.2023YFC3008204the National Natural Science Foundation of China under contract Nos 41977302 and 42476217.
文摘Spartina alterniflora is now listed among the world’s 100 most dangerous invasive species,severely affecting the ecological balance of coastal wetlands.Remote sensing technologies based on deep learning enable large-scale monitoring of Spartina alterniflora,but they require large datasets and have poor interpretability.A new method is proposed to detect Spartina alterniflora from Sentinel-2 imagery.Firstly,to get the high canopy cover and dense community characteristics of Spartina alterniflora,multi-dimensional shallow features are extracted from the imagery.Secondly,to detect different objects from satellite imagery,index features are extracted,and the statistical features of the Gray-Level Co-occurrence Matrix(GLCM)are derived using principal component analysis.Then,ensemble learning methods,including random forest,extreme gradient boosting,and light gradient boosting machine models,are employed for image classification.Meanwhile,Recursive Feature Elimination with Cross-Validation(RFECV)is used to select the best feature subset.Finally,to enhance the interpretability of the models,the best features are utilized to classify multi-temporal images and SHapley Additive exPlanations(SHAP)is combined with these classifications to explain the model prediction process.The method is validated by using Sentinel-2 imageries and previous observations of Spartina alterniflora in Chongming Island,it is found that the model combining image texture features such as GLCM covariance can significantly improve the detection accuracy of Spartina alterniflora by about 8%compared with the model without image texture features.Through multiple model comparisons and feature selection via RFECV,the selected model and eight features demonstrated good classification accuracy when applied to data from different time periods,proving that feature reduction can effectively enhance model generalization.Additionally,visualizing model decisions using SHAP revealed that the image texture feature component_1_GLCMVariance is particularly important for identifying each land cover type.
基金Supported by National Natural Science Foundation of China(Grant No.52175528).
文摘High-speed milling(HSM)is advantageous for machining high-quality complex-structure surface components with various materials.Identifying and estimating cutting force signals for characterizing HSM is of high significance.However,considering the tool runout and size effects,many proposed models focus on the material and mechanical characteristics.This study presents a novel approach for predicting micromilling cutting forces using a semianalytical multidimensional model that integrates experimental empirical data and a mechanical theoretical force model.A novel analytical optimization approach is provided to identify the cutting forces,classify the cutting states,and determine the tool runout using an adaptive algorithm that simplifies modeling and calculation.The instantaneous un-deformed chip thickness(IUCT)is determined from the trochoidal trajectories of each tool flute and optimized using the bisection method.Herein,the computational efficiency is improved,and the errors are clarified.The tool runout parameters are identified from the processed displacement signals and determined from the preprocessed vibration signals using an adaptive signal processing method.It is reliable and stable for determining tool runout and is an effective foundation for the force model.This approach is verified using HSM tests.Herein,the determination coefficients are stable above 0.9.It is convenient and efficient for achieving the key intermediate parameters(IUCT and tool runout),which can be generalized to various machining conditions and operations.
基金The National Natural Science Foundation of China(No.61273236)the Natural Science Foundation of Jiangsu Province(No.BK2010239)the Ph.D. Programs Foundation of Ministry of Education of China(No.200802861061)
文摘According to the road adaptive requirements for the vehicle longitudinal safety assistant system an estimation method of the road longitudinal friction coefficient is proposed.The method can simultaneously be applied to both the high and the low slip ratio conditions. Based on the simplified magic formula tire model the road longitudinal friction coefficient is preliminarily estimated by the recursive least squares method.The estimated friction coefficient and the tires model parameters are considered as extended states. The extended Kalman filter algorithm is employed to filter out the noise and adaptively adjust the tire model parameters. Then the final road longitudinal friction coefficient is accurately and robustly estimated. The Carsim simulation results show that the proposed method is better than the conventional algorithm. The road longitudinal friction coefficient can be quickly and accurately estimated under both the high and the low slip ratio conditions.The error is less than 0.1 and the response time is less than 2 s which meets the requirements of the vehicle longitudinal safety assistant system.
