Dear Editor, In order to accommodate the effects of false data injection attacks(FDIAs), the moving target defense(MTD) strategy is recently proposed to enhance the security of the smart grid by perturbing branch susc...Dear Editor, In order to accommodate the effects of false data injection attacks(FDIAs), the moving target defense(MTD) strategy is recently proposed to enhance the security of the smart grid by perturbing branch susceptances. However, most pioneer work only focus on the defending performance of MTD in terms of detecting FDIAs and the impact of MTD on the static factors such as the power and economic losses.展开更多
Dear Editor,Machine learning(ML) approaches have been widely employed to enable real-time ML-based stability assessment(MLSA) of largescale automated electricity grids. However, the vulnerability of MLSA to malicious ...Dear Editor,Machine learning(ML) approaches have been widely employed to enable real-time ML-based stability assessment(MLSA) of largescale automated electricity grids. However, the vulnerability of MLSA to malicious cyber-attacks may lead to wrong decisions in operating the physical grid if its resilience properties are not well understood before deployment. Unlike adversarial ML in prior domains such as image processing, specific constraints of power systems that the attacker must obey in constructing adversarial samples require new research on MLSA vulnerability analysis for power systems.展开更多
Dear Editor,Dummy attack(DA), a deep stealthy but impactful data integrity attack on power industrial control processes, is recently recognized as hiding the corrupted measurements in normal measurements. In this lett...Dear Editor,Dummy attack(DA), a deep stealthy but impactful data integrity attack on power industrial control processes, is recently recognized as hiding the corrupted measurements in normal measurements. In this letter, targeting a more practical case, we aim to detect the oneshot DA, with the purpose of revealing the DA once it is launched.Specifically, we first formulate an optimization problem to generate one-shot DAs. Then, an unsupervised data-driven approach based on a modified local outlier factor(MLOF) is proposed to detect them.展开更多
Dear Editor,This letter is concerned with visual perception closely related to heterogeneous images.Facing the huge challenge brought by different image modalities,we propose a visual perception framework based on het...Dear Editor,This letter is concerned with visual perception closely related to heterogeneous images.Facing the huge challenge brought by different image modalities,we propose a visual perception framework based on heterogeneous image knowledge,i.e.,the domain knowledge associated with specific vision tasks,to better address the corresponding visual perception problems.展开更多
In a crowd density estimation dataset,the annotation of crowd locations is an extremely laborious task,and they are not taken into the evaluation metrics.In this paper,we aim to reduce the annotation cost of crowd dat...In a crowd density estimation dataset,the annotation of crowd locations is an extremely laborious task,and they are not taken into the evaluation metrics.In this paper,we aim to reduce the annotation cost of crowd datasets,and propose a crowd density estimation method based on weakly-supervised learning,in the absence of crowd position supervision information,which directly reduces the number of crowds by using the number of pedestrians in the image as the supervised information.For this purpose,we design a new training method,which exploits the correlation between global and local image features by incremental learning to train the network.Specifically,we design a parent-child network(PC-Net)focusing on the global and local image respectively,and propose a linear feature calibration structure to train the PC-Net simultaneously,and the child network learns feature transfer factors and feature bias weights,and uses the transfer factors and bias weights to linearly feature calibrate the features extracted from the Parent network,to improve the convergence of the network by using local features hidden in the crowd images.In addition,we use the pyramid vision transformer as the backbone of the PC-Net to extract crowd features at different levels,and design a global-local feature loss function(L2).We combine it with a crowd counting loss(LC)to enhance the sensitivity of the network to crowd features during the training process,which effectively improves the accuracy of crowd density estimation.The experimental results show that the PC-Net significantly reduces the gap between fullysupervised and weakly-supervised crowd density estimation,and outperforms the comparison methods on five datasets of Shanghai Tech Part A,ShanghaiTech Part B,UCF_CC_50,UCF_QNRF and JHU-CROWD++.展开更多
Traditional clustering algorithms often struggle to produce satisfactory results when dealing with datasets withuneven density. Additionally, they incur substantial computational costs when applied to high-dimensional...Traditional clustering algorithms often struggle to produce satisfactory results when dealing with datasets withuneven density. Additionally, they incur substantial computational costs when applied to high-dimensional datadue to calculating similarity matrices. To alleviate these issues, we employ the KD-Tree to partition the dataset andcompute the K-nearest neighbors (KNN) density for each point, thereby avoiding the computation of similaritymatrices. Moreover, we apply the rules of voting elections, treating each data point as a voter and casting a votefor the point with the highest density among its KNN. By utilizing the vote counts of each point, we develop thestrategy for classifying noise points and potential cluster centers, allowing the algorithm to identify clusters withuneven density and complex shapes. Additionally, we define the concept of “adhesive points” between two clustersto merge adjacent clusters that have similar densities. This process helps us identify the optimal number of clustersautomatically. Experimental results indicate that our algorithm not only improves the efficiency of clustering butalso increases its accuracy.展开更多
Mobile Edge Computing(MEC)is a technology designed for the on-demand provisioning of computing and storage services,strategically positioned close to users.In the MEC environment,frequently accessed content can be dep...Mobile Edge Computing(MEC)is a technology designed for the on-demand provisioning of computing and storage services,strategically positioned close to users.In the MEC environment,frequently accessed content can be deployed and cached on edge servers to optimize the efficiency of content delivery,ultimately enhancing the quality of the user experience.However,due to the typical placement of edge devices and nodes at the network’s periphery,these components may face various potential fault tolerance challenges,including network instability,device failures,and resource constraints.Considering the dynamic nature ofMEC,making high-quality content caching decisions for real-time mobile applications,especially those sensitive to latency,by effectively utilizing mobility information,continues to be a significant challenge.In response to this challenge,this paper introduces FT-MAACC,a mobility-aware caching solution grounded in multi-agent deep reinforcement learning and equipped with fault tolerance mechanisms.This approach comprehensively integrates content adaptivity algorithms to evaluate the priority of highly user-adaptive cached content.Furthermore,it relies on collaborative caching strategies based onmulti-agent deep reinforcement learningmodels and establishes a fault-tolerancemodel to ensure the system’s reliability,availability,and persistence.Empirical results unequivocally demonstrate that FTMAACC outperforms its peer methods in cache hit rates and transmission latency.展开更多
Dear Editor,This letter proposes a symmetry-preserving dual-stream graph neural network(SDGNN) for precise representation learning to an undirected weighted graph(UWG). Although existing graph neural networks(GNNs) ar...Dear Editor,This letter proposes a symmetry-preserving dual-stream graph neural network(SDGNN) for precise representation learning to an undirected weighted graph(UWG). Although existing graph neural networks(GNNs) are influential instruments for representation learning to a UWG, they invariably adopt a unique node feature matrix for illustrating the sole node set of a UWG.展开更多
Traditional expert-designed branching rules in branch-and-bound(B&B) are static, often failing to adapt to diverse and evolving problem instances. Crafting these rules is labor-intensive, and may not scale well wi...Traditional expert-designed branching rules in branch-and-bound(B&B) are static, often failing to adapt to diverse and evolving problem instances. Crafting these rules is labor-intensive, and may not scale well with complex problems.Given the frequent need to solve varied combinatorial optimization problems, leveraging statistical learning to auto-tune B&B algorithms for specific problem classes becomes attractive. This paper proposes a graph pointer network model to learn the branch rules. Graph features, global features and historical features are designated to represent the solver state. The graph neural network processes graph features, while the pointer mechanism assimilates the global and historical features to finally determine the variable on which to branch. The model is trained to imitate the expert strong branching rule by a tailored top-k Kullback-Leibler divergence loss function. Experiments on a series of benchmark problems demonstrate that the proposed approach significantly outperforms the widely used expert-designed branching rules. It also outperforms state-of-the-art machine-learning-based branch-and-bound methods in terms of solving speed and search tree size on all the test instances. In addition, the model can generalize to unseen instances and scale to larger instances.展开更多
A global planning algorithm for intelligent vehicles is designed based on the A* algorithm, which provides intelligent vehicles with a global path towards their destinations. A distributed real-time multiple vehicle c...A global planning algorithm for intelligent vehicles is designed based on the A* algorithm, which provides intelligent vehicles with a global path towards their destinations. A distributed real-time multiple vehicle collision avoidance(MVCA)algorithm is proposed by extending the reciprocal n-body collision avoidance method. MVCA enables the intelligent vehicles to choose their destinations and control inputs independently,without needing to negotiate with each other or with the coordinator. Compared to the centralized trajectory-planning algorithm, MVCA reduces computation costs and greatly improves the robustness of the system. Because the destination of each intelligent vehicle can be regarded as private, which can be protected by MVCA, at the same time MVCA can provide a real-time trajectory planning for intelligent vehicles. Therefore,MVCA can better improve the safety of intelligent vehicles. The simulation was conducted in MATLAB, including crossroads scene simulation and circular exchange position simulation. The results show that MVCA behaves safely and reliably. The effects of latency and packet loss on MVCA are also statistically investigated through theoretically formulating broadcasting process based on one-dimensional Markov chain. The results uncover that the tolerant delay should not exceed the half of deciding cycle of trajectory planning, and shortening the sending interval could alleviate the negative effects caused by the packet loss to an extent. The cases of short delay(< 100100 ms) and low packet loss(< 5%) can bring little influence to those trajectory planning algorithms that only depend on V2 V to sense the context, but the unpredictable collision may occur if the delay and packet loss are further worsened. The MVCA was also tested by a real intelligent vehicle, the test results prove the operability of MVCA.展开更多
The quantum theory application is a hot research area in recent years, especially the theory of quantum mechanics. In this paper, we focus on the research of image segmentation based on quantum mechanics. Firstly,the ...The quantum theory application is a hot research area in recent years, especially the theory of quantum mechanics. In this paper, we focus on the research of image segmentation based on quantum mechanics. Firstly,the theory of quantum mechanics is introduced; afterwards, a review of image segmentation methods based on quantum mechanics is presented; and finally, the characteristics about the quantum mechanics applied to image processing are concluded. Two main research topics are discussed in this paper. One is to emphasize that quantum mechanics can be applied in different research areas, such as image segmentation, and the second is to conclude some methods in image segmentation and give some suggestions for possible novel methods by applying quantum mechanics theory. As a summary, this is a review paper which presents some methods based on the feasible theory in quantum mechanics aiming at achieving a better performance in image segmentation.展开更多
In the era of big data,there is an urgent need to establish data trading markets for effectively releasing the tremendous value of the drastically explosive data.Data security and data pricing,however,are still widely...In the era of big data,there is an urgent need to establish data trading markets for effectively releasing the tremendous value of the drastically explosive data.Data security and data pricing,however,are still widely regarded as major challenges in this respect,which motivate this research on the novel multi-blockchain based framework for data trading markets and their associated pricing mechanisms.In this context,data recording and trading are conducted separately within two separate blockchains:the data blockchain(DChain) and the value blockchain(VChain).This enables the establishment of two-layer data trading markets to manage initial data trading in the primary market and subsequent data resales in the secondary market.Moreover,pricing mechanisms are then proposed to protect these markets against strategic trading behaviors and balance the payoffs of both suppliers and users.Specifically,in regular data trading on VChain-S2D,two auction models are employed according to the demand scale,for dealing with users’ strategic bidding.The incentive-compatible Vickrey-Clarke-Groves(VCG)model is deployed to the low-demand trading scenario,while the nearly incentive-compatible monopolistic price(MP) model is utilized for the high-demand trading scenario.With temporary data trading on VChain-D2S,a reverse auction mechanism namely two-stage obscure selection(TSOS) is designed to regulate both suppliers’ quoting and users’ valuation strategies.Furthermore,experiments are carried out to demonstrate the strength of this research in enhancing data security and trading efficiency.展开更多
We introduce a novel method using a new generative model that automatically learns effective representations of the target and background appearance to detect,segment and track each instance in a video sequence.Differ...We introduce a novel method using a new generative model that automatically learns effective representations of the target and background appearance to detect,segment and track each instance in a video sequence.Differently from current discriminative tracking-by-detection solutions,our proposed hierarchical structural embedding learning can predict more highquality masks with accurate boundary details over spatio-temporal space via the normalizing flows.We formulate the instance inference procedure as a hierarchical spatio-temporal embedded learning across time and space.Given the video clip,our method first coarsely locates pixels belonging to a particular instance with Gaussian distribution and then builds a novel mixing distribution to promote the instance boundary by fusing hierarchical appearance embedding information in a coarse-to-fine manner.For the mixing distribution,we utilize a factorization condition normalized flow fashion to estimate the distribution parameters to improve the segmentation performance.Comprehensive qualitative,quantitative,and ablation experiments are performed on three representative video instance segmentation benchmarks(i.e.,YouTube-VIS19,YouTube-VIS21,and OVIS)and the effectiveness of the proposed method is demonstrated.More impressively,the superior performance of our model on an unsupervised video object segmentation dataset(i.e.,DAVIS19)proves its generalizability.Our algorithm implementations are publicly available at https://github.com/zyqin19/HEVis.展开更多
Business processes described by formal or semi-formal models are realized via information systems.Event logs generated from these systems are probably not consistent with the existing models due to insufficient design...Business processes described by formal or semi-formal models are realized via information systems.Event logs generated from these systems are probably not consistent with the existing models due to insufficient design of the information system or the system upgrade.By comparing an existing process model with event logs,we can detect inconsistencies called deviations,verify and extend the business process model,and accordingly improve the business process.In this paper,some abnormal activities in business processes are formally defined based on Petri nets.An efficient approach to detect deviations between the process model and event logs is proposed.Then,business process models are revised when abnormal activities exist.A clinical process in a healthcare information system is used as a case study to illustrate our work.Experimental results show the effectiveness and efficiency of the proposed approach.展开更多
This paper investigates the differentially private problem of the average consensus for a class of discrete-time multi-agent network systems(MANSs). Based on the MANSs,a new distributed differentially private consensu...This paper investigates the differentially private problem of the average consensus for a class of discrete-time multi-agent network systems(MANSs). Based on the MANSs,a new distributed differentially private consensus algorithm(DPCA) is developed. To avoid continuous communication between neighboring agents, a kind of intermittent communication strategy depending on an event-triggered function is established in our DPCA. Based on our algorithm, we carry out the detailed analysis including its convergence, its accuracy, its privacy and the trade-off between the accuracy and the privacy level, respectively. It is found that our algorithm preserves the privacy of initial states of all agents in the whole process of consensus computation. The trade-off motivates us to find the best achievable accuracy of our algorithm under the free parameters and the fixed privacy level. Finally, numerical experiment results testify the validity of our theoretical analysis.展开更多
Recently, Massive Open Online Courses(MOOCs) have become a major online learning methodology for millions of people worldwide. However, the dropout rates from several current MOOCs are high. Usually, dropout predictio...Recently, Massive Open Online Courses(MOOCs) have become a major online learning methodology for millions of people worldwide. However, the dropout rates from several current MOOCs are high. Usually, dropout prediction aims to predict whether a learner will exhibit learning behaviors during several consecutive days in the future. Therefore, the information related to the learning behaviors of a learner in several consecutive days should be considered. After in-depth analysis of the learning behavior patterns of the MOOC learners, this study reports that learners often exhibit similar learning behaviors on several consecutive days, i.e., the learning status of a learner for the subsequent day is likely to be similar to that for the previous day. Based on this characteristic of MOOC learning,this study proposes a new simple feature matrix for keeping information related to the local correlation of learning behaviors and a new Convolutional Neural Network(CNN) model for predicting the dropout. Extensive experimental validations illustrate that the local correlation of learning behaviors should not be neglected. The proposed CNN model considers this characteristic and improves the dropout prediction accuracy. Furthermore, the proposed model can be used to predict dropout temporally and early when sufficient data are collected.展开更多
In this paper,we develop a novel global-attentionbased neural network(GANN)for vision language intelligence,specifically,image captioning(language description of a given image).As many previous works,the encoder-decod...In this paper,we develop a novel global-attentionbased neural network(GANN)for vision language intelligence,specifically,image captioning(language description of a given image).As many previous works,the encoder-decoder framework is adopted in our proposed model,in which the encoder is responsible for encoding the region proposal features and extracting global caption feature based on a specially designed module of predicting the caption objects,and the decoder generates captions by taking the obtained global caption feature along with the encoded visual features as inputs for each attention head of the decoder layer.The global caption feature is introduced for the purpose of exploring the latent contributions of region proposals for image captioning,and further helping the decoder better focus on the most relevant proposals so as to extract more accurate visual feature in each time step of caption generation.Our GANN is implemented by incorporating the global caption feature into the attention weight calculation phase in the word predication process in each head of the decoder layer.In our experiments,we qualitatively analyzed the proposed model,and quantitatively evaluated several state-of-the-art schemes with GANN on the MS-COCO dataset.Experimental results demonstrate the effectiveness of the proposed global attention mechanism for image captioning.展开更多
Unmanned surface vehicles(USVs) are important autonomous marine robots that have been studied and gradually applied into practice. However, the autonomous navigation of USVs, especially the issue of obstacle avoidance...Unmanned surface vehicles(USVs) are important autonomous marine robots that have been studied and gradually applied into practice. However, the autonomous navigation of USVs, especially the issue of obstacle avoidance in complicated marine environment, is still a fundamental problem. After studying the characteristics of the complicated marine environment, we propose a novel adaptive obstacle avoidance algorithm for USVs,based on the Sarsa on-policy reinforcement learning algorithm.The proposed algorithm is composed of local avoidance module and adaptive learning module, which are organized by the “divide and conquer” strategy-based architecture. The course angle compensation strategy is proposed to offset the disturbances from sea wind and currents. In the design of payoff value function of the learning strategy, the course deviation angle and its tendency are introduced into action rewards and penalty policies. The validity of the proposed algorithm is verified by comparative experiments of simulations and sea trials in three sea-state marine environments. The results show that the algorithm can enhance the autonomous navigation capacity of USVs in complicated marine environments.展开更多
With the massive increase of wirelessly connected devices and the rapid development of the Internet, information is transmitted more and more frequently. Since the information transmissions over these networks are gre...With the massive increase of wirelessly connected devices and the rapid development of the Internet, information is transmitted more and more frequently. Since the information transmissions over these networks are greatly threatened not only by the imperfection of channels but also by the potential attackers or eavesdroppers, security and reliability become some of the crucial requirements for our future networks. Due to the complex dynamic behavior, ergodicity, wide spectrum and sensitivity to initial values, chaos signals show most required attributes of good cryptosystems and great potentials in optical fiber communications for desirable spatial accuracy and distance. In this context, it has become imperative to investigate and apply chaos theories to solve emerging secure communication problems in various networks. This includes leveraging chaos systems and signals to address a wide range of secure communication challenges in optical fiber communications, chaos cipher, image encryption, etc.展开更多
基金supported in part by the Guizhou Provincial Science and Technology Projects(ZK[2022]149)the Natural Science Foundation of Guizhou University([2021]47)+4 种基金the GZU Cultivation project of the National Natural Science Foundation of China(NSFC)([2020]80)NSFC(62073285,62061130220)the Natural Science Foundation of Zhejiang Province(LZ21F 020006)the Fundamental Research Funds for the Central Universities(226-2022-00120)the Key Laboratory of Collaborative Sensing and Autonomous Unmanned Systems of Zhejiang Province。
文摘Dear Editor, In order to accommodate the effects of false data injection attacks(FDIAs), the moving target defense(MTD) strategy is recently proposed to enhance the security of the smart grid by perturbing branch susceptances. However, most pioneer work only focus on the defending performance of MTD in terms of detecting FDIAs and the impact of MTD on the static factors such as the power and economic losses.
基金supported in part by the Guizhou Provincial Science and Technology Projects(ZK[2022]149)the Special Foundation of Guizhou University(GZU)([2021]47)+2 种基金the Guizhou Provincial Research Project for Universities([2022]104)the GZU cultivation project of the National Natural Science Foundation of China([2020]80)Shanghai Engineering Research Center of Big Data Management。
文摘Dear Editor,Machine learning(ML) approaches have been widely employed to enable real-time ML-based stability assessment(MLSA) of largescale automated electricity grids. However, the vulnerability of MLSA to malicious cyber-attacks may lead to wrong decisions in operating the physical grid if its resilience properties are not well understood before deployment. Unlike adversarial ML in prior domains such as image processing, specific constraints of power systems that the attacker must obey in constructing adversarial samples require new research on MLSA vulnerability analysis for power systems.
基金supported in part by the Guizhou Provincial Science and Technology Projects(ZK[2022]149)the Guizhou Provincial Research Project for Universities([2022]104)+2 种基金the Special Foundation of Guizhou University([2021]47)the GZU cultivation project of National Natural Science Foundation of China([2020]80)Shanghai Engineering Research Center of Big Data Management,and the National Natural Science Foundation of China(62073285,62061130220)。
文摘Dear Editor,Dummy attack(DA), a deep stealthy but impactful data integrity attack on power industrial control processes, is recently recognized as hiding the corrupted measurements in normal measurements. In this letter, targeting a more practical case, we aim to detect the oneshot DA, with the purpose of revealing the DA once it is launched.Specifically, we first formulate an optimization problem to generate one-shot DAs. Then, an unsupervised data-driven approach based on a modified local outlier factor(MLOF) is proposed to detect them.
基金supported in part by the National Natural Science Foundation of China(62302161,62303361)the Postdoctoral Innovative Talent Support Program of China(BX20230114)。
文摘Dear Editor,This letter is concerned with visual perception closely related to heterogeneous images.Facing the huge challenge brought by different image modalities,we propose a visual perception framework based on heterogeneous image knowledge,i.e.,the domain knowledge associated with specific vision tasks,to better address the corresponding visual perception problems.
基金the Humanities and Social Science Fund of the Ministry of Education of China(21YJAZH077)。
文摘In a crowd density estimation dataset,the annotation of crowd locations is an extremely laborious task,and they are not taken into the evaluation metrics.In this paper,we aim to reduce the annotation cost of crowd datasets,and propose a crowd density estimation method based on weakly-supervised learning,in the absence of crowd position supervision information,which directly reduces the number of crowds by using the number of pedestrians in the image as the supervised information.For this purpose,we design a new training method,which exploits the correlation between global and local image features by incremental learning to train the network.Specifically,we design a parent-child network(PC-Net)focusing on the global and local image respectively,and propose a linear feature calibration structure to train the PC-Net simultaneously,and the child network learns feature transfer factors and feature bias weights,and uses the transfer factors and bias weights to linearly feature calibrate the features extracted from the Parent network,to improve the convergence of the network by using local features hidden in the crowd images.In addition,we use the pyramid vision transformer as the backbone of the PC-Net to extract crowd features at different levels,and design a global-local feature loss function(L2).We combine it with a crowd counting loss(LC)to enhance the sensitivity of the network to crowd features during the training process,which effectively improves the accuracy of crowd density estimation.The experimental results show that the PC-Net significantly reduces the gap between fullysupervised and weakly-supervised crowd density estimation,and outperforms the comparison methods on five datasets of Shanghai Tech Part A,ShanghaiTech Part B,UCF_CC_50,UCF_QNRF and JHU-CROWD++.
基金National Natural Science Foundation of China Nos.61962054 and 62372353.
文摘Traditional clustering algorithms often struggle to produce satisfactory results when dealing with datasets withuneven density. Additionally, they incur substantial computational costs when applied to high-dimensional datadue to calculating similarity matrices. To alleviate these issues, we employ the KD-Tree to partition the dataset andcompute the K-nearest neighbors (KNN) density for each point, thereby avoiding the computation of similaritymatrices. Moreover, we apply the rules of voting elections, treating each data point as a voter and casting a votefor the point with the highest density among its KNN. By utilizing the vote counts of each point, we develop thestrategy for classifying noise points and potential cluster centers, allowing the algorithm to identify clusters withuneven density and complex shapes. Additionally, we define the concept of “adhesive points” between two clustersto merge adjacent clusters that have similar densities. This process helps us identify the optimal number of clustersautomatically. Experimental results indicate that our algorithm not only improves the efficiency of clustering butalso increases its accuracy.
基金supported by the Innovation Fund Project of Jiangxi Normal University(YJS2022065)the Domestic Visiting Program of Jiangxi Normal University.
文摘Mobile Edge Computing(MEC)is a technology designed for the on-demand provisioning of computing and storage services,strategically positioned close to users.In the MEC environment,frequently accessed content can be deployed and cached on edge servers to optimize the efficiency of content delivery,ultimately enhancing the quality of the user experience.However,due to the typical placement of edge devices and nodes at the network’s periphery,these components may face various potential fault tolerance challenges,including network instability,device failures,and resource constraints.Considering the dynamic nature ofMEC,making high-quality content caching decisions for real-time mobile applications,especially those sensitive to latency,by effectively utilizing mobility information,continues to be a significant challenge.In response to this challenge,this paper introduces FT-MAACC,a mobility-aware caching solution grounded in multi-agent deep reinforcement learning and equipped with fault tolerance mechanisms.This approach comprehensively integrates content adaptivity algorithms to evaluate the priority of highly user-adaptive cached content.Furthermore,it relies on collaborative caching strategies based onmulti-agent deep reinforcement learningmodels and establishes a fault-tolerancemodel to ensure the system’s reliability,availability,and persistence.Empirical results unequivocally demonstrate that FTMAACC outperforms its peer methods in cache hit rates and transmission latency.
基金supported in part by the National Natural Science Foundation of China (62372385,62002337)the Chongqing Natural Science Foundation (CSTB2022NSCQMSX1486,CSTB2023NSCQ-LZX0069)。
文摘Dear Editor,This letter proposes a symmetry-preserving dual-stream graph neural network(SDGNN) for precise representation learning to an undirected weighted graph(UWG). Although existing graph neural networks(GNNs) are influential instruments for representation learning to a UWG, they invariably adopt a unique node feature matrix for illustrating the sole node set of a UWG.
基金supported by the Open Project of Xiangjiang Laboratory (22XJ02003)Scientific Project of the National University of Defense Technology (NUDT)(ZK21-07, 23-ZZCX-JDZ-28)+1 种基金the National Science Fund for Outstanding Young Scholars (62122093)the National Natural Science Foundation of China (72071205)。
文摘Traditional expert-designed branching rules in branch-and-bound(B&B) are static, often failing to adapt to diverse and evolving problem instances. Crafting these rules is labor-intensive, and may not scale well with complex problems.Given the frequent need to solve varied combinatorial optimization problems, leveraging statistical learning to auto-tune B&B algorithms for specific problem classes becomes attractive. This paper proposes a graph pointer network model to learn the branch rules. Graph features, global features and historical features are designated to represent the solver state. The graph neural network processes graph features, while the pointer mechanism assimilates the global and historical features to finally determine the variable on which to branch. The model is trained to imitate the expert strong branching rule by a tailored top-k Kullback-Leibler divergence loss function. Experiments on a series of benchmark problems demonstrate that the proposed approach significantly outperforms the widely used expert-designed branching rules. It also outperforms state-of-the-art machine-learning-based branch-and-bound methods in terms of solving speed and search tree size on all the test instances. In addition, the model can generalize to unseen instances and scale to larger instances.
基金supported by the National Natural Science Foundation of China(61572229,6171101066)the Key Scientific and Technological Projects for Jilin Province Development Plan(20170204074GX,20180201068GX)Jilin Provincial International Cooperation Foundation(20180414015GH)。
文摘A global planning algorithm for intelligent vehicles is designed based on the A* algorithm, which provides intelligent vehicles with a global path towards their destinations. A distributed real-time multiple vehicle collision avoidance(MVCA)algorithm is proposed by extending the reciprocal n-body collision avoidance method. MVCA enables the intelligent vehicles to choose their destinations and control inputs independently,without needing to negotiate with each other or with the coordinator. Compared to the centralized trajectory-planning algorithm, MVCA reduces computation costs and greatly improves the robustness of the system. Because the destination of each intelligent vehicle can be regarded as private, which can be protected by MVCA, at the same time MVCA can provide a real-time trajectory planning for intelligent vehicles. Therefore,MVCA can better improve the safety of intelligent vehicles. The simulation was conducted in MATLAB, including crossroads scene simulation and circular exchange position simulation. The results show that MVCA behaves safely and reliably. The effects of latency and packet loss on MVCA are also statistically investigated through theoretically formulating broadcasting process based on one-dimensional Markov chain. The results uncover that the tolerant delay should not exceed the half of deciding cycle of trajectory planning, and shortening the sending interval could alleviate the negative effects caused by the packet loss to an extent. The cases of short delay(< 100100 ms) and low packet loss(< 5%) can bring little influence to those trajectory planning algorithms that only depend on V2 V to sense the context, but the unpredictable collision may occur if the delay and packet loss are further worsened. The MVCA was also tested by a real intelligent vehicle, the test results prove the operability of MVCA.
基金supported by the National Natural Science Foundation of China under Grant No.51679058the China Higher Specialized Research Fund(Ph.D.supervisor category) under Grant No.20132304110018
文摘The quantum theory application is a hot research area in recent years, especially the theory of quantum mechanics. In this paper, we focus on the research of image segmentation based on quantum mechanics. Firstly,the theory of quantum mechanics is introduced; afterwards, a review of image segmentation methods based on quantum mechanics is presented; and finally, the characteristics about the quantum mechanics applied to image processing are concluded. Two main research topics are discussed in this paper. One is to emphasize that quantum mechanics can be applied in different research areas, such as image segmentation, and the second is to conclude some methods in image segmentation and give some suggestions for possible novel methods by applying quantum mechanics theory. As a summary, this is a review paper which presents some methods based on the feasible theory in quantum mechanics aiming at achieving a better performance in image segmentation.
基金partially supported by the Science and Technology Development Fund,Macao SAR (0050/2020/A1)the National Natural Science Foundation of China (62103411, 72171230)。
文摘In the era of big data,there is an urgent need to establish data trading markets for effectively releasing the tremendous value of the drastically explosive data.Data security and data pricing,however,are still widely regarded as major challenges in this respect,which motivate this research on the novel multi-blockchain based framework for data trading markets and their associated pricing mechanisms.In this context,data recording and trading are conducted separately within two separate blockchains:the data blockchain(DChain) and the value blockchain(VChain).This enables the establishment of two-layer data trading markets to manage initial data trading in the primary market and subsequent data resales in the secondary market.Moreover,pricing mechanisms are then proposed to protect these markets against strategic trading behaviors and balance the payoffs of both suppliers and users.Specifically,in regular data trading on VChain-S2D,two auction models are employed according to the demand scale,for dealing with users’ strategic bidding.The incentive-compatible Vickrey-Clarke-Groves(VCG)model is deployed to the low-demand trading scenario,while the nearly incentive-compatible monopolistic price(MP) model is utilized for the high-demand trading scenario.With temporary data trading on VChain-D2S,a reverse auction mechanism namely two-stage obscure selection(TSOS) is designed to regulate both suppliers’ quoting and users’ valuation strategies.Furthermore,experiments are carried out to demonstrate the strength of this research in enhancing data security and trading efficiency.
基金supported in part by the National Natural Science Foundation of China(62176139,62106128,62176141)the Major Basic Research Project of Shandong Natural Science Foundation(ZR2021ZD15)+4 种基金the Natural Science Foundation of Shandong Province(ZR2021QF001)the Young Elite Scientists Sponsorship Program by CAST(2021QNRC001)the Open Project of Key Laboratory of Artificial Intelligence,Ministry of Educationthe Shandong Provincial Natural Science Foundation for Distinguished Young Scholars(ZR2021JQ26)the Taishan Scholar Project of Shandong Province(tsqn202103088)。
文摘We introduce a novel method using a new generative model that automatically learns effective representations of the target and background appearance to detect,segment and track each instance in a video sequence.Differently from current discriminative tracking-by-detection solutions,our proposed hierarchical structural embedding learning can predict more highquality masks with accurate boundary details over spatio-temporal space via the normalizing flows.We formulate the instance inference procedure as a hierarchical spatio-temporal embedded learning across time and space.Given the video clip,our method first coarsely locates pixels belonging to a particular instance with Gaussian distribution and then builds a novel mixing distribution to promote the instance boundary by fusing hierarchical appearance embedding information in a coarse-to-fine manner.For the mixing distribution,we utilize a factorization condition normalized flow fashion to estimate the distribution parameters to improve the segmentation performance.Comprehensive qualitative,quantitative,and ablation experiments are performed on three representative video instance segmentation benchmarks(i.e.,YouTube-VIS19,YouTube-VIS21,and OVIS)and the effectiveness of the proposed method is demonstrated.More impressively,the superior performance of our model on an unsupervised video object segmentation dataset(i.e.,DAVIS19)proves its generalizability.Our algorithm implementations are publicly available at https://github.com/zyqin19/HEVis.
基金supported by the National Natural Science Foundation of China(61170078,61472228,61903229,61902222)the “Taishan Scholar” Construction Project of Shandong Province,China,the Natural Science Foundation of Shandong Province(ZR2018MF001)+1 种基金the Scientific Research Foundation of Shandong University of Science and Technology for Recruited Talents(2017RCJJ044)the Key Research and Development Program of Shandong Province(2018GGX101011)
文摘Business processes described by formal or semi-formal models are realized via information systems.Event logs generated from these systems are probably not consistent with the existing models due to insufficient design of the information system or the system upgrade.By comparing an existing process model with event logs,we can detect inconsistencies called deviations,verify and extend the business process model,and accordingly improve the business process.In this paper,some abnormal activities in business processes are formally defined based on Petri nets.An efficient approach to detect deviations between the process model and event logs is proposed.Then,business process models are revised when abnormal activities exist.A clinical process in a healthcare information system is used as a case study to illustrate our work.Experimental results show the effectiveness and efficiency of the proposed approach.
基金supported in part by the National Key Research and Development Program of China (2016YFB0800601)
文摘This paper investigates the differentially private problem of the average consensus for a class of discrete-time multi-agent network systems(MANSs). Based on the MANSs,a new distributed differentially private consensus algorithm(DPCA) is developed. To avoid continuous communication between neighboring agents, a kind of intermittent communication strategy depending on an event-triggered function is established in our DPCA. Based on our algorithm, we carry out the detailed analysis including its convergence, its accuracy, its privacy and the trade-off between the accuracy and the privacy level, respectively. It is found that our algorithm preserves the privacy of initial states of all agents in the whole process of consensus computation. The trade-off motivates us to find the best achievable accuracy of our algorithm under the free parameters and the fixed privacy level. Finally, numerical experiment results testify the validity of our theoretical analysis.
基金partially supported by the National Natural Science Foundation of China (Nos. 61866007, 61363029, 61662014, 61763007, and U1811264)the Natural Science Foundation of Guangxi District (No. 2018GXNSFDA138006)+2 种基金Guangxi Key Laboratory of Trusted Software (No. KX201721)Humanities and Social Sciences Research Projects of the Ministry of Education (No. 17JDGC022)Chongqing Higher Education Reform Project (No. 183137)
文摘Recently, Massive Open Online Courses(MOOCs) have become a major online learning methodology for millions of people worldwide. However, the dropout rates from several current MOOCs are high. Usually, dropout prediction aims to predict whether a learner will exhibit learning behaviors during several consecutive days in the future. Therefore, the information related to the learning behaviors of a learner in several consecutive days should be considered. After in-depth analysis of the learning behavior patterns of the MOOC learners, this study reports that learners often exhibit similar learning behaviors on several consecutive days, i.e., the learning status of a learner for the subsequent day is likely to be similar to that for the previous day. Based on this characteristic of MOOC learning,this study proposes a new simple feature matrix for keeping information related to the local correlation of learning behaviors and a new Convolutional Neural Network(CNN) model for predicting the dropout. Extensive experimental validations illustrate that the local correlation of learning behaviors should not be neglected. The proposed CNN model considers this characteristic and improves the dropout prediction accuracy. Furthermore, the proposed model can be used to predict dropout temporally and early when sufficient data are collected.
基金the National Natural Science Foundation of China(61971296,U19A2078,61836011,61801315)the Ministry of Education and China Mobile Research Foundation Project(MCM20180405)Sichuan Science and Technology Planning Project(2019YFG0495,2021YFG0301,2021YFG0317,2020YFG0319,2020YFH0186)。
文摘In this paper,we develop a novel global-attentionbased neural network(GANN)for vision language intelligence,specifically,image captioning(language description of a given image).As many previous works,the encoder-decoder framework is adopted in our proposed model,in which the encoder is responsible for encoding the region proposal features and extracting global caption feature based on a specially designed module of predicting the caption objects,and the decoder generates captions by taking the obtained global caption feature along with the encoded visual features as inputs for each attention head of the decoder layer.The global caption feature is introduced for the purpose of exploring the latent contributions of region proposals for image captioning,and further helping the decoder better focus on the most relevant proposals so as to extract more accurate visual feature in each time step of caption generation.Our GANN is implemented by incorporating the global caption feature into the attention weight calculation phase in the word predication process in each head of the decoder layer.In our experiments,we qualitatively analyzed the proposed model,and quantitatively evaluated several state-of-the-art schemes with GANN on the MS-COCO dataset.Experimental results demonstrate the effectiveness of the proposed global attention mechanism for image captioning.
文摘Unmanned surface vehicles(USVs) are important autonomous marine robots that have been studied and gradually applied into practice. However, the autonomous navigation of USVs, especially the issue of obstacle avoidance in complicated marine environment, is still a fundamental problem. After studying the characteristics of the complicated marine environment, we propose a novel adaptive obstacle avoidance algorithm for USVs,based on the Sarsa on-policy reinforcement learning algorithm.The proposed algorithm is composed of local avoidance module and adaptive learning module, which are organized by the “divide and conquer” strategy-based architecture. The course angle compensation strategy is proposed to offset the disturbances from sea wind and currents. In the design of payoff value function of the learning strategy, the course deviation angle and its tendency are introduced into action rewards and penalty policies. The validity of the proposed algorithm is verified by comparative experiments of simulations and sea trials in three sea-state marine environments. The results show that the algorithm can enhance the autonomous navigation capacity of USVs in complicated marine environments.
文摘With the massive increase of wirelessly connected devices and the rapid development of the Internet, information is transmitted more and more frequently. Since the information transmissions over these networks are greatly threatened not only by the imperfection of channels but also by the potential attackers or eavesdroppers, security and reliability become some of the crucial requirements for our future networks. Due to the complex dynamic behavior, ergodicity, wide spectrum and sensitivity to initial values, chaos signals show most required attributes of good cryptosystems and great potentials in optical fiber communications for desirable spatial accuracy and distance. In this context, it has become imperative to investigate and apply chaos theories to solve emerging secure communication problems in various networks. This includes leveraging chaos systems and signals to address a wide range of secure communication challenges in optical fiber communications, chaos cipher, image encryption, etc.