Because of the features involved with their varied kernels,differential operators relying on convolution formulations have been acknowledged as effective mathematical resources for modeling real-world issues.In this p...Because of the features involved with their varied kernels,differential operators relying on convolution formulations have been acknowledged as effective mathematical resources for modeling real-world issues.In this paper,we constructed a stochastic fractional framework of measles spreading mechanisms with dual medication immunization considering the exponential decay and Mittag-Leffler kernels.In this approach,the overall population was separated into five cohorts.Furthermore,the descriptive behavior of the system was investigated,including prerequisites for the positivity of solutions,invariant domain of the solution,presence and stability of equilibrium points,and sensitivity analysis.We included a stochastic element in every cohort and employed linear growth and Lipschitz criteria to show the existence and uniqueness of solutions.Several numerical simulations for various fractional orders and randomization intensities are illustrated.展开更多
This study proposes a comprehensive,coupled thermomechanical model that replaces local spatial derivatives in classical differential thermomechanical equations with nonlocal integral forms derived from the peridynamic...This study proposes a comprehensive,coupled thermomechanical model that replaces local spatial derivatives in classical differential thermomechanical equations with nonlocal integral forms derived from the peridynamic differential operator(PDDO),eliminating the need for calibration procedures.The model employs a multi-rate explicit time integration scheme to handle varying time scales in multi-physics systems.Through simulations conducted on granite and ceramic materials,this model demonstrates its effectiveness.It successfully simulates thermal damage behavior in granite arising from incompatible mineral expansion and accurately calculates thermal crack propagation in ceramic slabs during quenching.To account for material heterogeneity,the model utilizes the Shuffle algorithm andWeibull distribution,yielding results that align with numerical simulations and experimental observations.This coupled thermomechanical model shows great promise for analyzing intricate thermomechanical phenomena in brittle materials.展开更多
The optimization of the rule base of a fuzzy logic system (FLS) based on evolutionary algorithm has achievednotable results. However, due to the diversity of the deep structure in the hierarchical fuzzy system (HFS) a...The optimization of the rule base of a fuzzy logic system (FLS) based on evolutionary algorithm has achievednotable results. However, due to the diversity of the deep structure in the hierarchical fuzzy system (HFS) and thecorrelation of each sub fuzzy system, the uncertainty of the HFS’s deep structure increases. For the HFS, a largenumber of studies mainly use fixed structures, which cannot be selected automatically. To solve this problem, thispaper proposes a novel approach for constructing the incremental HFS. During system design, the deep structureand the rule base of the HFS are encoded separately. Subsequently, the deep structure is adaptively mutated basedon the fitness value, so as to realize the diversity of deep structures while ensuring reasonable competition amongthe structures. Finally, the differential evolution (DE) is used to optimize the deep structure of HFS and theparameters of antecedent and consequent simultaneously. The simulation results confirm the effectiveness of themodel. Specifically, the root mean square errors in the Laser dataset and Friedman dataset are 0.0395 and 0.0725,respectively with rule counts of rules is 8 and 12, respectively.When compared to alternative methods, the resultsindicate that the proposed method offers improvements in accuracy and rule counts.展开更多
Background: Retinoblastoma, the most common intraocular pediatric cancer, presents complexities in its genetic landscape that necessitate a deeper understanding for improved therapeutic interventions. This study lever...Background: Retinoblastoma, the most common intraocular pediatric cancer, presents complexities in its genetic landscape that necessitate a deeper understanding for improved therapeutic interventions. This study leverages computational tools to dissect the differential gene expression profiles in retinoblastoma. Methods: Employing an in silico approach, we analyzed gene expression data from public repositories by applying rigorous statistical models, including limma and de seq 2, for identifying differentially expressed genes DEGs. Our findings were validated through cross-referencing with independent datasets and existing literature. We further employed functional annotation and pathway analysis to elucidate the biological significance of these DEGs. Results: Our computational analysis confirmed the dysregulation of key retinoblastoma-associated genes. In comparison to normal retinal tissue, RB1 exhibited a 2.5-fold increase in expression (adjusted p Conclusions: Our analysis reinforces the critical genetic alterations known in retinoblastoma and unveils new avenues for research into the disease’s molecular basis. The discovery of chemoresistance markers and immune-related genes opens potential pathways for personalized treatment strategies. The study’s outcomes emphasize the power of in silico analyses in unraveling complex cancer genomics.展开更多
As a distributed machine learning method,federated learning(FL)has the advantage of naturally protecting data privacy.It keeps data locally and trains local models through local data to protect the privacy of local da...As a distributed machine learning method,federated learning(FL)has the advantage of naturally protecting data privacy.It keeps data locally and trains local models through local data to protect the privacy of local data.The federated learning method effectively solves the problem of artificial Smart data islands and privacy protection issues.However,existing research shows that attackersmay still steal user information by analyzing the parameters in the federated learning training process and the aggregation parameters on the server side.To solve this problem,differential privacy(DP)techniques are widely used for privacy protection in federated learning.However,adding Gaussian noise perturbations to the data degrades the model learning performance.To address these issues,this paper proposes a differential privacy federated learning scheme based on adaptive Gaussian noise(DPFL-AGN).To protect the data privacy and security of the federated learning training process,adaptive Gaussian noise is specifically added in the training process to hide the real parameters uploaded by the client.In addition,this paper proposes an adaptive noise reduction method.With the convergence of the model,the Gaussian noise in the later stage of the federated learning training process is reduced adaptively.This paper conducts a series of simulation experiments on realMNIST and CIFAR-10 datasets,and the results show that the DPFL-AGN algorithmperforms better compared to the other algorithms.展开更多
Channel prediction is critical to address the channel aging issue in mobile scenarios.Existing channel prediction techniques are mainly designed for discrete channel prediction,which can only predict the future channe...Channel prediction is critical to address the channel aging issue in mobile scenarios.Existing channel prediction techniques are mainly designed for discrete channel prediction,which can only predict the future channel in a fixed time slot per frame,while the other intra-frame channels are usually recovered by interpolation.However,these approaches suffer from a serious interpolation loss,especially for mobile millimeter-wave communications.To solve this challenging problem,we propose a tensor neural ordinary differential equation(TN-ODE)based continuous-time channel prediction scheme to realize the direct prediction of intra-frame channels.Specifically,inspired by the recently developed continuous mapping model named neural ODE in the field of machine learning,we first utilize the neural ODE model to predict future continuous-time channels.To improve the channel prediction accuracy and reduce computational complexity,we then propose the TN-ODE scheme to learn the structural characteristics of the high-dimensional channel by low-dimensional learnable transform.Simulation results show that the proposed scheme is able to achieve higher intra-frame channel prediction accuracy than existing schemes.展开更多
We find the exact forms of meromorphic solutions of the nonlinear differential equations■,n≥3,k≥1,where q,Q are nonzero polynomials,Q■Const.,and p_(1),p_(2),α_(1),α_(2)are nonzero constants withα_(1)≠α_(2).Co...We find the exact forms of meromorphic solutions of the nonlinear differential equations■,n≥3,k≥1,where q,Q are nonzero polynomials,Q■Const.,and p_(1),p_(2),α_(1),α_(2)are nonzero constants withα_(1)≠α_(2).Compared with previous results on the equation p(z)f^(3)+q(z)f"=-sinα(z)with polynomial coefficients,our results show that the coefficient of the term f^((k))perturbed by multiplying an exponential function will affect the structure of its solutions.展开更多
An innovative complex lidar system deployed on an airborne rotorcraft platform for remote sensing of atmospheric pollution is proposed and demonstrated.The system incorporates integrated-path differential absorption l...An innovative complex lidar system deployed on an airborne rotorcraft platform for remote sensing of atmospheric pollution is proposed and demonstrated.The system incorporates integrated-path differential absorption lidar(DIAL) and coherent-doppler lidar(CDL) techniques using a dual tunable TEA CO_(2)laser in the 9—11 μm band and a 1.55 μm fiber laser.By combining the principles of differential absorption detection and pulsed coherent detection,the system enables agile and remote sensing of atmospheric pollution.Extensive static tests validate the system’s real-time detection capabilities,including the measurement of concentration-path-length product(CL),front distance,and path wind speed of air pollution plumes over long distances exceeding 4 km.Flight experiments is conducted with the helicopter.Scanning of the pollutant concentration and the wind field is carried out in an approximately 1 km slant range over scanning angle ranges from 45°to 65°,with a radial resolution of 30 m and10 s.The test results demonstrate the system’s ability to spatially map atmospheric pollution plumes and predict their motion and dispersion patterns,thereby ensuring the protection of public safety.展开更多
With the widespread data collection and processing,privacy-preserving machine learning has become increasingly important in addressing privacy risks related to individuals.Support vector machine(SVM)is one of the most...With the widespread data collection and processing,privacy-preserving machine learning has become increasingly important in addressing privacy risks related to individuals.Support vector machine(SVM)is one of the most elementary learning models of machine learning.Privacy issues surrounding SVM classifier training have attracted increasing attention.In this paper,we investigate Differential Privacy-compliant Federated Machine Learning with Dimensionality Reduction,called FedDPDR-DPML,which greatly improves data utility while providing strong privacy guarantees.Considering in distributed learning scenarios,multiple participants usually hold unbalanced or small amounts of data.Therefore,FedDPDR-DPML enables multiple participants to collaboratively learn a global model based on weighted model averaging and knowledge aggregation and then the server distributes the global model to each participant to improve local data utility.Aiming at high-dimensional data,we adopt differential privacy in both the principal component analysis(PCA)-based dimensionality reduction phase and SVM classifiers training phase,which improves model accuracy while achieving strict differential privacy protection.Besides,we train Differential privacy(DP)-compliant SVM classifiers by adding noise to the objective function itself,thus leading to better data utility.Extensive experiments on three high-dimensional datasets demonstrate that FedDPDR-DPML can achieve high accuracy while ensuring strong privacy protection.展开更多
In recent years,the research field of data collection under local differential privacy(LDP)has expanded its focus fromelementary data types to includemore complex structural data,such as set-value and graph data.Howev...In recent years,the research field of data collection under local differential privacy(LDP)has expanded its focus fromelementary data types to includemore complex structural data,such as set-value and graph data.However,our comprehensive review of existing literature reveals that there needs to be more studies that engage with key-value data collection.Such studies would simultaneously collect the frequencies of keys and the mean of values associated with each key.Additionally,the allocation of the privacy budget between the frequencies of keys and the means of values for each key does not yield an optimal utility tradeoff.Recognizing the importance of obtaining accurate key frequencies and mean estimations for key-value data collection,this paper presents a novel framework:the Key-Strategy Framework forKey-ValueDataCollection under LDP.Initially,theKey-StrategyUnary Encoding(KS-UE)strategy is proposed within non-interactive frameworks for the purpose of privacy budget allocation to achieve precise key frequencies;subsequently,the Key-Strategy Generalized Randomized Response(KS-GRR)strategy is introduced for interactive frameworks to enhance the efficiency of collecting frequent keys through group-anditeration methods.Both strategies are adapted for scenarios in which users possess either a single or multiple key-value pairs.Theoretically,we demonstrate that the variance of KS-UE is lower than that of existing methods.These claims are substantiated through extensive experimental evaluation on real-world datasets,confirming the effectiveness and efficiency of the KS-UE and KS-GRR strategies.展开更多
This paper presents a novel cooperative value iteration(VI)-based adaptive dynamic programming method for multi-player differential game models with a convergence proof.The players are divided into two groups in the l...This paper presents a novel cooperative value iteration(VI)-based adaptive dynamic programming method for multi-player differential game models with a convergence proof.The players are divided into two groups in the learning process and adapt their policies sequentially.Our method removes the dependence of admissible initial policies,which is one of the main drawbacks of the PI-based frameworks.Furthermore,this algorithm enables the players to adapt their control policies without full knowledge of others’ system parameters or control laws.The efficacy of our method is illustrated by three examples.展开更多
Concentrate copper grade(CCG)is one of the important production indicators of copper flotation processes,and keeping the CCG at the set value is of great significance to the economic benefit of copper flotation indust...Concentrate copper grade(CCG)is one of the important production indicators of copper flotation processes,and keeping the CCG at the set value is of great significance to the economic benefit of copper flotation industrial processes.This paper addresses the fluctuation problem of CCG through an operational optimization method.Firstly,a density-based affinity propagationalgorithm is proposed so that more ideal working condition categories can be obtained for the complex raw ore properties.Next,a Bayesian network(BN)is applied to explore the relationship between the operational variables and the CCG.Based on the analysis results of BN,a weighted Gaussian process regression model is constructed to predict the CCG that a higher prediction accuracy can be obtained.To ensure the predicted CCG is close to the set value with a smaller magnitude of the operation adjustments and a smaller uncertainty of the prediction results,an index-oriented adaptive differential evolution(IOADE)algorithm is proposed,and the convergence performance of IOADE is superior to the traditional differential evolution and adaptive differential evolution methods.Finally,the effectiveness and feasibility of the proposed methods are verified by the experiments on a copper flotation industrial process.展开更多
In this study,we aimto investigate certain triple integral transformand its application to a class of partial differentialequations.We discuss various properties of the new transformincluding inversion, linearity, exi...In this study,we aimto investigate certain triple integral transformand its application to a class of partial differentialequations.We discuss various properties of the new transformincluding inversion, linearity, existence, scaling andshifting, etc. Then,we derive several results enfolding partial derivatives and establish amulti-convolution theorem.Further, we apply the aforementioned transform to some classical functions and many types of partial differentialequations involving heat equations,wave equations, Laplace equations, and Poisson equations aswell.Moreover,wedraw some figures to illustrate 3-D contour plots for exact solutions of some selected examples involving differentvalues in their variables.展开更多
In the realm of large-scale machine learning,it is crucial to explore methods for reducing computational complexity and memory demands while maintaining generalization performance.Additionally,since the collected data...In the realm of large-scale machine learning,it is crucial to explore methods for reducing computational complexity and memory demands while maintaining generalization performance.Additionally,since the collected data may contain some sensitive information,it is also of great significance to study privacy-preserving machine learning algorithms.This paper focuses on the performance of the differentially private stochastic gradient descent(SGD)algorithm based on random features.To begin,the algorithm maps the original data into a lowdimensional space,thereby avoiding the traditional kernel method for large-scale data storage requirement.Subsequently,the algorithm iteratively optimizes parameters using the stochastic gradient descent approach.Lastly,the output perturbation mechanism is employed to introduce random noise,ensuring algorithmic privacy.We prove that the proposed algorithm satisfies the differential privacy while achieving fast convergence rates under some mild conditions.展开更多
Using Euler’s first-order explicit(EE)method and the peridynamic differential operator(PDDO)to discretize the time and internal crystal-size derivatives,respectively,the Euler’s first-order explicit method–peridyna...Using Euler’s first-order explicit(EE)method and the peridynamic differential operator(PDDO)to discretize the time and internal crystal-size derivatives,respectively,the Euler’s first-order explicit method–peridynamic differential operator(EE–PDDO)was obtained for solving the one-dimensional population balance equation in crystallization.Four different conditions during crystallization were studied:size-independent growth,sizedependent growth in a batch process,nucleation and size-independent growth,and nucleation and size-dependent growth in a continuous process.The high accuracy of the EE–PDDO method was confirmed by comparing it with the numerical results obtained using the second-order upwind and HR-van methods.The method is characterized by non-oscillation and high accuracy,especially in the discontinuous and sharp crystal size distribution.The stability of the EE–PDDO method,choice of weight function in the PDDO method,and optimal time step are also discussed.展开更多
The job shop scheduling problem is a classical combinatorial optimization challenge frequently encountered in manufacturing systems.It involves determining the optimal execution sequences for a set of jobs on various ...The job shop scheduling problem is a classical combinatorial optimization challenge frequently encountered in manufacturing systems.It involves determining the optimal execution sequences for a set of jobs on various machines to maximize production efficiency and meet multiple objectives.The Non-dominated Sorting Genetic Algorithm Ⅲ(NSGA-Ⅲ)is an effective approach for solving the multi-objective job shop scheduling problem.Nevertheless,it has some limitations in solving scheduling problems,including inadequate global search capability,susceptibility to premature convergence,and challenges in balancing convergence and diversity.To enhance its performance,this paper introduces a strengthened dominance relation NSGA-Ⅲ algorithm based on differential evolution(NSGA-Ⅲ-SD).By incorporating constrained differential evolution and simulated binary crossover genetic operators,this algorithm effectively improves NSGA-Ⅲ’s global search capability while mitigating pre-mature convergence issues.Furthermore,it introduces a reinforced dominance relation to address the trade-off between convergence and diversity in NSGA-Ⅲ.Additionally,effective encoding and decoding methods for discrete job shop scheduling are proposed,which can improve the overall performance of the algorithm without complex computation.To validate the algorithm’s effectiveness,NSGA-Ⅲ-SD is extensively compared with other advanced multi-objective optimization algorithms using 20 job shop scheduling test instances.The experimental results demonstrate that NSGA-Ⅲ-SD achieves better solution quality and diversity,proving its effectiveness in solving the multi-objective job shop scheduling problem.展开更多
BACKGROUND Crohn’s disease(CD)is often misdiagnosed as intestinal tuberculosis(ITB).However,the treatment and prognosis of these two diseases are dramatically different.Therefore,it is important to develop a method t...BACKGROUND Crohn’s disease(CD)is often misdiagnosed as intestinal tuberculosis(ITB).However,the treatment and prognosis of these two diseases are dramatically different.Therefore,it is important to develop a method to identify CD and ITB with high accuracy,specificity,and speed.AIM To develop a method to identify CD and ITB with high accuracy,specificity,and speed.METHODS A total of 72 paraffin wax-embedded tissue sections were pathologically and clinically diagnosed as CD or ITB.Paraffin wax-embedded tissue sections were attached to a metal coating and measured using attenuated total reflectance fourier transform infrared spectroscopy at mid-infrared wavelengths combined with XGBoost for differential diagnosis.RESULTS The results showed that the paraffin wax-embedded specimens of CD and ITB were significantly different in their spectral signals at 1074 cm^(-1) and 1234 cm^(-1) bands,and the differential diagnosis model based on spectral characteristics combined with machine learning showed accuracy,specificity,and sensitivity of 91.84%,92.59%,and 90.90%,respectively,for the differential diagnosis of CD and ITB.CONCLUSION Information on the mid-infrared region can reveal the different histological components of CD and ITB at the molecular level,and spectral analysis combined with machine learning to establish a diagnostic model is expected to become a new method for the differential diagnosis of CD and ITB.展开更多
Time based maintenance(TBM)and condition based maintenance(CBM)are widely applied in many large wind farms to optimize the maintenance issues of wind turbine gearboxes,however,these maintenance strategies do not take ...Time based maintenance(TBM)and condition based maintenance(CBM)are widely applied in many large wind farms to optimize the maintenance issues of wind turbine gearboxes,however,these maintenance strategies do not take into account environmental benefits during full life cycle such as carbon emissions issues.Hence,this article proposes a carbon emissions computing model for preventive maintenance activities of wind turbine gearboxes to solve the issue.Based on the change of the gearbox state during operation and the influence of external random factors on the gearbox state,a stochastic differential equation model(SDE)and corresponding carbon emission model are established,wherein SDE is applied to model the evolution of the device state,whereas carbon emission is used to implement carbon emissions computing.The simulation results indicate that the proposed preventive maintenance cannot ensure reliable operation of wind turbine gearboxes but reduce carbon emissions during their lifespan.Compared with TBM,CBM minimizes unit carbon emissions without influencing reliable operation,making it an effective maintenance method.展开更多
The proliferation of Large Language Models (LLMs) across various sectors underscored the urgency of addressing potential privacy breaches. Vulnerabilities, such as prompt injection attacks and other adversarial tactic...The proliferation of Large Language Models (LLMs) across various sectors underscored the urgency of addressing potential privacy breaches. Vulnerabilities, such as prompt injection attacks and other adversarial tactics, could make these models inadvertently disclose their training data. Such disclosures could compromise personal identifiable information, posing significant privacy risks. In this paper, we proposed a novel multi-faceted approach called Whispered Tuning to address privacy leaks in large language models (LLMs). We integrated a PII redaction model, differential privacy techniques, and an output filter into the LLM fine-tuning process to enhance confidentiality. Additionally, we introduced novel ideas like the Epsilon Dial for adjustable privacy budgeting for differentiated Training Phases per data handler role. Through empirical validation, including attacks on non-private models, we demonstrated the robustness of our proposed solution SecureNLP in safeguarding privacy without compromising utility. This pioneering methodology significantly fortified LLMs against privacy infringements, enabling responsible adoption across sectors.展开更多
Since 2016,community group buying has grown significantly in China,largely driven by its efficient logistics,supply chains,low prices,and convenience.This model has been further popularized during the COVID-19 pandemi...Since 2016,community group buying has grown significantly in China,largely driven by its efficient logistics,supply chains,low prices,and convenience.This model has been further popularized during the COVID-19 pandemic due to its effectiveness in meeting daily needs while minimizing human-to-human contact.A key component of this business model is the“group leaders”-influential individuals within a community responsible for managing group buying activities,which include order collection,supplier liaison,and goods distribution.Their primary task is to form and sustain a reliable community group buying consortium,a task that demands excellent organizational and interpersonal skills.This paper examines this phenomenon using the lens of the differential mode of association,a theoretical model explaining interpersonal relationships in traditional Chinese society.The research indicates that group leaders,through regular interaction with consumers,are able to alter their social network position,increase their influence,understand consumer needs,provide satisfying services,and enhance trust,thereby transforming consumers into loyal group buying participants.This transformation not only brings stability to group buying activities but also reinforces the community influence of group leaders,thus fostering the growth of community group buying.展开更多
文摘Because of the features involved with their varied kernels,differential operators relying on convolution formulations have been acknowledged as effective mathematical resources for modeling real-world issues.In this paper,we constructed a stochastic fractional framework of measles spreading mechanisms with dual medication immunization considering the exponential decay and Mittag-Leffler kernels.In this approach,the overall population was separated into five cohorts.Furthermore,the descriptive behavior of the system was investigated,including prerequisites for the positivity of solutions,invariant domain of the solution,presence and stability of equilibrium points,and sensitivity analysis.We included a stochastic element in every cohort and employed linear growth and Lipschitz criteria to show the existence and uniqueness of solutions.Several numerical simulations for various fractional orders and randomization intensities are illustrated.
基金supported by the University Natural Science Foundation of Jiangsu Province(Grant No.23KJB130004)the National Natural Science Foundation of China(Grant Nos.11932006,U1934206,12172121,12002118).
文摘This study proposes a comprehensive,coupled thermomechanical model that replaces local spatial derivatives in classical differential thermomechanical equations with nonlocal integral forms derived from the peridynamic differential operator(PDDO),eliminating the need for calibration procedures.The model employs a multi-rate explicit time integration scheme to handle varying time scales in multi-physics systems.Through simulations conducted on granite and ceramic materials,this model demonstrates its effectiveness.It successfully simulates thermal damage behavior in granite arising from incompatible mineral expansion and accurately calculates thermal crack propagation in ceramic slabs during quenching.To account for material heterogeneity,the model utilizes the Shuffle algorithm andWeibull distribution,yielding results that align with numerical simulations and experimental observations.This coupled thermomechanical model shows great promise for analyzing intricate thermomechanical phenomena in brittle materials.
基金the Sichuan Science and Technology Program(2021ZYD0016).
文摘The optimization of the rule base of a fuzzy logic system (FLS) based on evolutionary algorithm has achievednotable results. However, due to the diversity of the deep structure in the hierarchical fuzzy system (HFS) and thecorrelation of each sub fuzzy system, the uncertainty of the HFS’s deep structure increases. For the HFS, a largenumber of studies mainly use fixed structures, which cannot be selected automatically. To solve this problem, thispaper proposes a novel approach for constructing the incremental HFS. During system design, the deep structureand the rule base of the HFS are encoded separately. Subsequently, the deep structure is adaptively mutated basedon the fitness value, so as to realize the diversity of deep structures while ensuring reasonable competition amongthe structures. Finally, the differential evolution (DE) is used to optimize the deep structure of HFS and theparameters of antecedent and consequent simultaneously. The simulation results confirm the effectiveness of themodel. Specifically, the root mean square errors in the Laser dataset and Friedman dataset are 0.0395 and 0.0725,respectively with rule counts of rules is 8 and 12, respectively.When compared to alternative methods, the resultsindicate that the proposed method offers improvements in accuracy and rule counts.
文摘Background: Retinoblastoma, the most common intraocular pediatric cancer, presents complexities in its genetic landscape that necessitate a deeper understanding for improved therapeutic interventions. This study leverages computational tools to dissect the differential gene expression profiles in retinoblastoma. Methods: Employing an in silico approach, we analyzed gene expression data from public repositories by applying rigorous statistical models, including limma and de seq 2, for identifying differentially expressed genes DEGs. Our findings were validated through cross-referencing with independent datasets and existing literature. We further employed functional annotation and pathway analysis to elucidate the biological significance of these DEGs. Results: Our computational analysis confirmed the dysregulation of key retinoblastoma-associated genes. In comparison to normal retinal tissue, RB1 exhibited a 2.5-fold increase in expression (adjusted p Conclusions: Our analysis reinforces the critical genetic alterations known in retinoblastoma and unveils new avenues for research into the disease’s molecular basis. The discovery of chemoresistance markers and immune-related genes opens potential pathways for personalized treatment strategies. The study’s outcomes emphasize the power of in silico analyses in unraveling complex cancer genomics.
基金the Sichuan Provincial Science and Technology Department Project under Grant 2019YFN0104the Yibin Science and Technology Plan Project under Grant 2021GY008the Sichuan University of Science and Engineering Postgraduate Innovation Fund Project under Grant Y2022154.
文摘As a distributed machine learning method,federated learning(FL)has the advantage of naturally protecting data privacy.It keeps data locally and trains local models through local data to protect the privacy of local data.The federated learning method effectively solves the problem of artificial Smart data islands and privacy protection issues.However,existing research shows that attackersmay still steal user information by analyzing the parameters in the federated learning training process and the aggregation parameters on the server side.To solve this problem,differential privacy(DP)techniques are widely used for privacy protection in federated learning.However,adding Gaussian noise perturbations to the data degrades the model learning performance.To address these issues,this paper proposes a differential privacy federated learning scheme based on adaptive Gaussian noise(DPFL-AGN).To protect the data privacy and security of the federated learning training process,adaptive Gaussian noise is specifically added in the training process to hide the real parameters uploaded by the client.In addition,this paper proposes an adaptive noise reduction method.With the convergence of the model,the Gaussian noise in the later stage of the federated learning training process is reduced adaptively.This paper conducts a series of simulation experiments on realMNIST and CIFAR-10 datasets,and the results show that the DPFL-AGN algorithmperforms better compared to the other algorithms.
基金supported in part by the National Key Research and Development Program of China(Grant No.2020YFB1805005)in part by the National Natural Science Foundation of China(Grant No.62031019)in part by the European Commission through the H2020-MSCA-ITN META WIRELESS Research Project under Grant 956256。
文摘Channel prediction is critical to address the channel aging issue in mobile scenarios.Existing channel prediction techniques are mainly designed for discrete channel prediction,which can only predict the future channel in a fixed time slot per frame,while the other intra-frame channels are usually recovered by interpolation.However,these approaches suffer from a serious interpolation loss,especially for mobile millimeter-wave communications.To solve this challenging problem,we propose a tensor neural ordinary differential equation(TN-ODE)based continuous-time channel prediction scheme to realize the direct prediction of intra-frame channels.Specifically,inspired by the recently developed continuous mapping model named neural ODE in the field of machine learning,we first utilize the neural ODE model to predict future continuous-time channels.To improve the channel prediction accuracy and reduce computational complexity,we then propose the TN-ODE scheme to learn the structural characteristics of the high-dimensional channel by low-dimensional learnable transform.Simulation results show that the proposed scheme is able to achieve higher intra-frame channel prediction accuracy than existing schemes.
基金supported by the NSFC(12261044)the STP of Education Department of Jiangxi Province of China(GJJ210302)。
文摘We find the exact forms of meromorphic solutions of the nonlinear differential equations■,n≥3,k≥1,where q,Q are nonzero polynomials,Q■Const.,and p_(1),p_(2),α_(1),α_(2)are nonzero constants withα_(1)≠α_(2).Compared with previous results on the equation p(z)f^(3)+q(z)f"=-sinα(z)with polynomial coefficients,our results show that the coefficient of the term f^((k))perturbed by multiplying an exponential function will affect the structure of its solutions.
文摘An innovative complex lidar system deployed on an airborne rotorcraft platform for remote sensing of atmospheric pollution is proposed and demonstrated.The system incorporates integrated-path differential absorption lidar(DIAL) and coherent-doppler lidar(CDL) techniques using a dual tunable TEA CO_(2)laser in the 9—11 μm band and a 1.55 μm fiber laser.By combining the principles of differential absorption detection and pulsed coherent detection,the system enables agile and remote sensing of atmospheric pollution.Extensive static tests validate the system’s real-time detection capabilities,including the measurement of concentration-path-length product(CL),front distance,and path wind speed of air pollution plumes over long distances exceeding 4 km.Flight experiments is conducted with the helicopter.Scanning of the pollutant concentration and the wind field is carried out in an approximately 1 km slant range over scanning angle ranges from 45°to 65°,with a radial resolution of 30 m and10 s.The test results demonstrate the system’s ability to spatially map atmospheric pollution plumes and predict their motion and dispersion patterns,thereby ensuring the protection of public safety.
基金supported in part by National Natural Science Foundation of China(Nos.62102311,62202377,62272385)in part by Natural Science Basic Research Program of Shaanxi(Nos.2022JQ-600,2022JM-353,2023-JC-QN-0327)+2 种基金in part by Shaanxi Distinguished Youth Project(No.2022JC-47)in part by Scientific Research Program Funded by Shaanxi Provincial Education Department(No.22JK0560)in part by Distinguished Youth Talents of Shaanxi Universities,and in part by Youth Innovation Team of Shaanxi Universities.
文摘With the widespread data collection and processing,privacy-preserving machine learning has become increasingly important in addressing privacy risks related to individuals.Support vector machine(SVM)is one of the most elementary learning models of machine learning.Privacy issues surrounding SVM classifier training have attracted increasing attention.In this paper,we investigate Differential Privacy-compliant Federated Machine Learning with Dimensionality Reduction,called FedDPDR-DPML,which greatly improves data utility while providing strong privacy guarantees.Considering in distributed learning scenarios,multiple participants usually hold unbalanced or small amounts of data.Therefore,FedDPDR-DPML enables multiple participants to collaboratively learn a global model based on weighted model averaging and knowledge aggregation and then the server distributes the global model to each participant to improve local data utility.Aiming at high-dimensional data,we adopt differential privacy in both the principal component analysis(PCA)-based dimensionality reduction phase and SVM classifiers training phase,which improves model accuracy while achieving strict differential privacy protection.Besides,we train Differential privacy(DP)-compliant SVM classifiers by adding noise to the objective function itself,thus leading to better data utility.Extensive experiments on three high-dimensional datasets demonstrate that FedDPDR-DPML can achieve high accuracy while ensuring strong privacy protection.
基金supported by a grant fromthe National Key R&DProgram of China.
文摘In recent years,the research field of data collection under local differential privacy(LDP)has expanded its focus fromelementary data types to includemore complex structural data,such as set-value and graph data.However,our comprehensive review of existing literature reveals that there needs to be more studies that engage with key-value data collection.Such studies would simultaneously collect the frequencies of keys and the mean of values associated with each key.Additionally,the allocation of the privacy budget between the frequencies of keys and the means of values for each key does not yield an optimal utility tradeoff.Recognizing the importance of obtaining accurate key frequencies and mean estimations for key-value data collection,this paper presents a novel framework:the Key-Strategy Framework forKey-ValueDataCollection under LDP.Initially,theKey-StrategyUnary Encoding(KS-UE)strategy is proposed within non-interactive frameworks for the purpose of privacy budget allocation to achieve precise key frequencies;subsequently,the Key-Strategy Generalized Randomized Response(KS-GRR)strategy is introduced for interactive frameworks to enhance the efficiency of collecting frequent keys through group-anditeration methods.Both strategies are adapted for scenarios in which users possess either a single or multiple key-value pairs.Theoretically,we demonstrate that the variance of KS-UE is lower than that of existing methods.These claims are substantiated through extensive experimental evaluation on real-world datasets,confirming the effectiveness and efficiency of the KS-UE and KS-GRR strategies.
基金supported by the Industry-University-Research Cooperation Fund Project of the Eighth Research Institute of China Aerospace Science and Technology Corporation (USCAST2022-11)Aeronautical Science Foundation of China (20220001057001)。
文摘This paper presents a novel cooperative value iteration(VI)-based adaptive dynamic programming method for multi-player differential game models with a convergence proof.The players are divided into two groups in the learning process and adapt their policies sequentially.Our method removes the dependence of admissible initial policies,which is one of the main drawbacks of the PI-based frameworks.Furthermore,this algorithm enables the players to adapt their control policies without full knowledge of others’ system parameters or control laws.The efficacy of our method is illustrated by three examples.
基金supported in part by the National Key Research and Development Program of China(2021YFC2902703)the National Natural Science Foundation of China(62173078,61773105,61533007,61873049,61873053,61703085,61374147)。
文摘Concentrate copper grade(CCG)is one of the important production indicators of copper flotation processes,and keeping the CCG at the set value is of great significance to the economic benefit of copper flotation industrial processes.This paper addresses the fluctuation problem of CCG through an operational optimization method.Firstly,a density-based affinity propagationalgorithm is proposed so that more ideal working condition categories can be obtained for the complex raw ore properties.Next,a Bayesian network(BN)is applied to explore the relationship between the operational variables and the CCG.Based on the analysis results of BN,a weighted Gaussian process regression model is constructed to predict the CCG that a higher prediction accuracy can be obtained.To ensure the predicted CCG is close to the set value with a smaller magnitude of the operation adjustments and a smaller uncertainty of the prediction results,an index-oriented adaptive differential evolution(IOADE)algorithm is proposed,and the convergence performance of IOADE is superior to the traditional differential evolution and adaptive differential evolution methods.Finally,the effectiveness and feasibility of the proposed methods are verified by the experiments on a copper flotation industrial process.
文摘In this study,we aimto investigate certain triple integral transformand its application to a class of partial differentialequations.We discuss various properties of the new transformincluding inversion, linearity, existence, scaling andshifting, etc. Then,we derive several results enfolding partial derivatives and establish amulti-convolution theorem.Further, we apply the aforementioned transform to some classical functions and many types of partial differentialequations involving heat equations,wave equations, Laplace equations, and Poisson equations aswell.Moreover,wedraw some figures to illustrate 3-D contour plots for exact solutions of some selected examples involving differentvalues in their variables.
基金supported by Zhejiang Provincial Natural Science Foundation of China(LR20A010001)National Natural Science Foundation of China(12271473 and U21A20426)。
文摘In the realm of large-scale machine learning,it is crucial to explore methods for reducing computational complexity and memory demands while maintaining generalization performance.Additionally,since the collected data may contain some sensitive information,it is also of great significance to study privacy-preserving machine learning algorithms.This paper focuses on the performance of the differentially private stochastic gradient descent(SGD)algorithm based on random features.To begin,the algorithm maps the original data into a lowdimensional space,thereby avoiding the traditional kernel method for large-scale data storage requirement.Subsequently,the algorithm iteratively optimizes parameters using the stochastic gradient descent approach.Lastly,the output perturbation mechanism is employed to introduce random noise,ensuring algorithmic privacy.We prove that the proposed algorithm satisfies the differential privacy while achieving fast convergence rates under some mild conditions.
文摘Using Euler’s first-order explicit(EE)method and the peridynamic differential operator(PDDO)to discretize the time and internal crystal-size derivatives,respectively,the Euler’s first-order explicit method–peridynamic differential operator(EE–PDDO)was obtained for solving the one-dimensional population balance equation in crystallization.Four different conditions during crystallization were studied:size-independent growth,sizedependent growth in a batch process,nucleation and size-independent growth,and nucleation and size-dependent growth in a continuous process.The high accuracy of the EE–PDDO method was confirmed by comparing it with the numerical results obtained using the second-order upwind and HR-van methods.The method is characterized by non-oscillation and high accuracy,especially in the discontinuous and sharp crystal size distribution.The stability of the EE–PDDO method,choice of weight function in the PDDO method,and optimal time step are also discussed.
基金in part supported by the Key Research and Development Project of Hubei Province(Nos.2020BAB1141,2023BAB094)the Key Project of Science and Technology Research ProgramofHubei Educational Committee(No.D20211402)+1 种基金the Teaching Research Project of Hubei University of Technology(No.XIAO2018001)the Project of Xiangyang Industrial Research Institute of Hubei University of Technology(No.XYYJ2022C04).
文摘The job shop scheduling problem is a classical combinatorial optimization challenge frequently encountered in manufacturing systems.It involves determining the optimal execution sequences for a set of jobs on various machines to maximize production efficiency and meet multiple objectives.The Non-dominated Sorting Genetic Algorithm Ⅲ(NSGA-Ⅲ)is an effective approach for solving the multi-objective job shop scheduling problem.Nevertheless,it has some limitations in solving scheduling problems,including inadequate global search capability,susceptibility to premature convergence,and challenges in balancing convergence and diversity.To enhance its performance,this paper introduces a strengthened dominance relation NSGA-Ⅲ algorithm based on differential evolution(NSGA-Ⅲ-SD).By incorporating constrained differential evolution and simulated binary crossover genetic operators,this algorithm effectively improves NSGA-Ⅲ’s global search capability while mitigating pre-mature convergence issues.Furthermore,it introduces a reinforced dominance relation to address the trade-off between convergence and diversity in NSGA-Ⅲ.Additionally,effective encoding and decoding methods for discrete job shop scheduling are proposed,which can improve the overall performance of the algorithm without complex computation.To validate the algorithm’s effectiveness,NSGA-Ⅲ-SD is extensively compared with other advanced multi-objective optimization algorithms using 20 job shop scheduling test instances.The experimental results demonstrate that NSGA-Ⅲ-SD achieves better solution quality and diversity,proving its effectiveness in solving the multi-objective job shop scheduling problem.
基金the National Natural Science Foundation of China,No.61975069 and No.62005056Natural Science Foundation of Guangxi Province,No.2021JJB110003+2 种基金Natural Science Foundation of Guangdong Province,No.2018A0303131000Academician Workstation of Guangdong Province,No.2014B090905001Key Project of Scientific and Technological Projects of Guangzhou,No.201604040007 and No.201604020168.
文摘BACKGROUND Crohn’s disease(CD)is often misdiagnosed as intestinal tuberculosis(ITB).However,the treatment and prognosis of these two diseases are dramatically different.Therefore,it is important to develop a method to identify CD and ITB with high accuracy,specificity,and speed.AIM To develop a method to identify CD and ITB with high accuracy,specificity,and speed.METHODS A total of 72 paraffin wax-embedded tissue sections were pathologically and clinically diagnosed as CD or ITB.Paraffin wax-embedded tissue sections were attached to a metal coating and measured using attenuated total reflectance fourier transform infrared spectroscopy at mid-infrared wavelengths combined with XGBoost for differential diagnosis.RESULTS The results showed that the paraffin wax-embedded specimens of CD and ITB were significantly different in their spectral signals at 1074 cm^(-1) and 1234 cm^(-1) bands,and the differential diagnosis model based on spectral characteristics combined with machine learning showed accuracy,specificity,and sensitivity of 91.84%,92.59%,and 90.90%,respectively,for the differential diagnosis of CD and ITB.CONCLUSION Information on the mid-infrared region can reveal the different histological components of CD and ITB at the molecular level,and spectral analysis combined with machine learning to establish a diagnostic model is expected to become a new method for the differential diagnosis of CD and ITB.
基金supported by Basic Science Research Program through the National Natural Science Foundation of China(Grant No.61867003)Key Project of Science and Technology Research and Development Plan of China Railway Co.,Ltd.(N2022X009).
文摘Time based maintenance(TBM)and condition based maintenance(CBM)are widely applied in many large wind farms to optimize the maintenance issues of wind turbine gearboxes,however,these maintenance strategies do not take into account environmental benefits during full life cycle such as carbon emissions issues.Hence,this article proposes a carbon emissions computing model for preventive maintenance activities of wind turbine gearboxes to solve the issue.Based on the change of the gearbox state during operation and the influence of external random factors on the gearbox state,a stochastic differential equation model(SDE)and corresponding carbon emission model are established,wherein SDE is applied to model the evolution of the device state,whereas carbon emission is used to implement carbon emissions computing.The simulation results indicate that the proposed preventive maintenance cannot ensure reliable operation of wind turbine gearboxes but reduce carbon emissions during their lifespan.Compared with TBM,CBM minimizes unit carbon emissions without influencing reliable operation,making it an effective maintenance method.
文摘The proliferation of Large Language Models (LLMs) across various sectors underscored the urgency of addressing potential privacy breaches. Vulnerabilities, such as prompt injection attacks and other adversarial tactics, could make these models inadvertently disclose their training data. Such disclosures could compromise personal identifiable information, posing significant privacy risks. In this paper, we proposed a novel multi-faceted approach called Whispered Tuning to address privacy leaks in large language models (LLMs). We integrated a PII redaction model, differential privacy techniques, and an output filter into the LLM fine-tuning process to enhance confidentiality. Additionally, we introduced novel ideas like the Epsilon Dial for adjustable privacy budgeting for differentiated Training Phases per data handler role. Through empirical validation, including attacks on non-private models, we demonstrated the robustness of our proposed solution SecureNLP in safeguarding privacy without compromising utility. This pioneering methodology significantly fortified LLMs against privacy infringements, enabling responsible adoption across sectors.
文摘Since 2016,community group buying has grown significantly in China,largely driven by its efficient logistics,supply chains,low prices,and convenience.This model has been further popularized during the COVID-19 pandemic due to its effectiveness in meeting daily needs while minimizing human-to-human contact.A key component of this business model is the“group leaders”-influential individuals within a community responsible for managing group buying activities,which include order collection,supplier liaison,and goods distribution.Their primary task is to form and sustain a reliable community group buying consortium,a task that demands excellent organizational and interpersonal skills.This paper examines this phenomenon using the lens of the differential mode of association,a theoretical model explaining interpersonal relationships in traditional Chinese society.The research indicates that group leaders,through regular interaction with consumers,are able to alter their social network position,increase their influence,understand consumer needs,provide satisfying services,and enhance trust,thereby transforming consumers into loyal group buying participants.This transformation not only brings stability to group buying activities but also reinforces the community influence of group leaders,thus fostering the growth of community group buying.