Search

With the development of big data and the increase of encryption scenarios, it 's difficult to meet the requirements of encryption performance with only software-run encryption methods, and FPGA/ ASIC encryption systems implemented using Verilog/VHDL methods have poor flexibility and difficult maintenance and upgrades problem. In response to the above problems, this paper designed and implemented an AES algorithm encryption system based on heterogeneous reconfigurable computing, including three mainstream modes of AES algorithm ECB, CBC, CTR, each mode realized 128 bit, 192 bit, 256 bit encryption of three key sizes. This paper realized the hardware acceleration of the module based on FPGA, and realized the dynamic switching of different modes and different bit width encryption modules based on the hardware reconfigurable mechanism. By implementing and verifying the system on Intel Stratix 10, the experimental results show that the throughput rates of AES-ECB, AES-CTR and AES-CBC in the system are 116.43 Gbps,60. 34 Gbps, and 4. 32 Gbps, respectively. The ECB mode compared with Intel Xeon E5-2650 V2 CPU and NVIDIA GeForce GTX 1080 GPU achieves 23.18 times and 1.43 times acceleration ratios respectively. Compared with the method just calling the CPU,the overall system has a computational acceleration ratio of 4.72. [ABSTRACT FROM AUTHOR]

In edge computing switching strategy, aiming at the problems of high transmission delay a nd poor environmental adaptability of Markov decision process ( MDP), this paper proposed an edge computing switching strategy integrating fuzzy logic a nd Markov decision process. The method used fuzzy logic algorithm to fuzzify the system parameters, and introduced the fuzzy value into the fitness function to ensure the effective fusion of system parameters. The differential evolution algorithm solved the maximum problem of fitness function, which could select the optimal rules of the environment and improve the adaptability of edge computing to the environment. The algorithm introduced the fitness function into MDP, which improved the comprehensive performance of the system. The scheme took the mobile intelligent device as the initiator of task unloading and the edge server as the object of task unloading. This paper simulated the one -dimensional MDP switching strategy, one-dimensional delay only MDP switching strategy, two-dimensional MDP switching strategy,fuzzy logic MDP switching strategy, minimum distance switching algorithm and minimum delay switching algorithm. The simulation results show that the average task execution time of the edge computing switching strategy of fuzzy logic MDP is 608 . 8 s, which a re 27. 2%,8. 6 %,37 . 1 %,41 % and 22. 3% lower than one -dimensional MDP switching strategy, one-dimensional delay only MDP switching strategy, two-dimensional MDP switching strategy, minimum distance switching algorithm and minimum delay switching algorithm respectively. This scheme not only improves the environmental adaptability of the edge computing switching strategy based on MDP, but also greatly reduces the transmission delay of edge computing. [ABSTRACT FROM AUTHOR]

Targeting to the deficiency of sparrow search algorithm solved the multi-objective problems, and the problems can easily enter the partial optimization and inferior convergence in the counting process, this paper came up with a kind of improved multi-objective sparrow search algorithm. First of all, this paper used a new-type non-dominated sorting to find the Pareto front. Next, it integrated the polynomial mutation and cosine algorithm into species evolution strategy to strengthen its searching ability. It used the species selection method of competition mechanism to decrease the differentiation caused by partial optimized particle and overall optimized particle in the searching process. Finally, this paper compared the improved algorithm and various kinds of multi-objective algorithm in standard test function. The simulation results show that, the convergence and searching ability of the improved algorithm are all superior than other algorithm. Therefore, this algorithm can effectively address the multiple target optimization problem. [ABSTRACT FROM AUTHOR]

Under a large-scale and complex environment, for the path planning algorithm of JPS, the memory consumption is large, the smoothness of path result is low, and the path result is excessively close to obstacles. Aiming at these problems, this paper proposed an improved JPS algorithm that integrated a level function of safety potential field and an optimized Floyd algorithm. It firstly built the safety level function and reassigned the grid status in the grid map to build a safety level map. Then by introducing two bias functions of goal and cardinal direction, and by combining the safety level function, this paper further reduced the time consumption brought by symmetric search, which improved the safety level of the path planned. Besides, it also optimized Floyd algorithm by adding a flow of second smoothing algorithm. At last, the paper integrated B-spline interpolation, improving the smoothness of path planned by the improved algorithm. The simulation tests verify that there are significant improvements in memory consumption, path length, path smoothness and path safety level for the improved and optimized algorithm. [ABSTRACT FROM AUTHOR]

For the vehicle routing problem with time window, stochastic travel and service time, and customer classification, this paper constructed a chance constrained programming model, which considered two class customers (ordinary customers and priority customers) and adopted the chance constraint to guarantee the punctual service possibility of priority customers. Meanwhile, this paper designed a variable neighborhood iterated local search algorithm to solve the model, and proposed a minimum waiting time heuristic rule to generate initial solution. Based on Solomon benchmarks, it conducted series of simulation experiments. The results show that the initial solution generation method is valid, the given algorithm can get approximate optimal solutions for both of the deterministic and stochastic problems in a short time, and the customer ratio is positively relative to the number of vehicle usage . The results have a certain reference significance to solve the problem of low customer service level caused by the limited resources and uncertain factors. [ABSTRACT FROM AUTHOR]

Message propagation algorithms from statistical physics are widely used in various fields of artificial intelligence, especially in solving combinatorial optimization problems. According to the related literatures of message propagation algorithm, this paper summarized the history of message propagation algorithm and its related application. According to the development of message propagation algorithm, it introduced the concepts of information propagation algorithm for solving the satisfiability problem, which mainly involved the warning propagation algorithm, the belief propagation algorithm and the survey propagation algorithm. This paper described the convergence and effectiveness research of the three kind of algorithms, summarized the application of each algorithm in related fields, and summarized the research path and application direction of message propagation algorithm. [ABSTRACT FROM AUTHOR]

Interactive image segmentation uses a priori information to guide the acquisition of the people ' s interesting parts of an image, but existing algorithms cannot balance efficiency and accuracy. To solve this problem, this paper proposed a fast interactive segmentation algorithm based on superpixel and random walk (random walk on superpixel, SPRW) . Firstly, it presegmented the image into superpixel regions with local similarity and used pixel colour averages to represent the superpixel regions. Secondly, it built the F-B graph structure based on manually labelled a priori information and extended the range of the random walk, obtained the hard segmentation results using the random walk solution. Finally, this paper proposed the improved matting algorithm (fast robust matting, FRB ) for the unsmooth boundaries of segmentation results and performed the secondary process to obtain soft segmentation results. Experiments on the BSDSOO and MSRC datasets confirm that the proposed hard method is superior to other algorithms in terms of time and average intersection ratio, while experiments on the Alpha Matting dataset demonstrate that the proposed soft algorithm improves efficiency and accuracy. In addition, the experiment of replacing the background of a life photograph demonstrates the application value of the proposed algorithm. [ABSTRACT FROM AUTHOR]

To solve the problem that existing botnet detections targeted a single phase of the botnet lifecycle, this paper proposed an online botnet detection method based on ensemble learning. Firstly, this paper fine-grained labeled the traffic of multiple phases of botnet lifecycle to generate a botnet dataset. Secondly, this paper combined multiple feature selection algorithms to generate a significant feature set containing 23 features and a less significant feature set containing 28 features. It integrated multiple deep learning models based on stacking ensemble learning and provided different input feature sets for different primary class ifiers to obtain a botnet online detection model. Finally, this paper deployed the botnet online detection model to detect multiple botnets online at the network entrance. Experiment shows that the proposed botnet online detection method based on ensemble learning in this paper can effectively detect multiple stages of botnet traffic, and the malicious traffic detection rate can reach 96 . 47% . [ABSTRACT FROM AUTHOR]

Most of the existing virtual network mapping algorithms rely on manual rules to sort nod es and determine the sequence of node mapping so as to optimize node mapping and improve the success rate of virtual network requests . In the link mapping stage, it generally uses the breadth-first search algorithm, ignoring the strong correlation between node resources and link resources, so that it can only obtain local optimal mapping results. In response to the above problems, based on the SG multi-domain heterogeneous network environment, from the perspective of network survivability protection, this paper proposed a virtual network mapping algorithm using two-layer reinforcement learning. It applied reinforcement learning to both the node and link stages of network mapping, used the gradient strategy and back propagation method to train the network model of this paper, and used the training model of this paper to complete the mapping. The simulation results show that, compared with the comparison algorithms, the algorithm optimizes the link mapping while optimizing the node mapping, and achieves better results in the mapping success rate, long-term return rate, and node and link utilization rate. [ABSTRACT FROM AUTHOR]

In order to overcome the drawbacks of Archimedes optimization algorithm( AOA), such as weak global search ability, easily trapping into local optimum and prematurely converge, this paper put forward Archimedes optimization algorithm improved by multi-strategy collaborative( MAOA ) . Initially, it used the random Gaussian mutation strategy to increase the diversity of the population in the iterative process and strengthen the global search ability. Then, based on the randomness, ergodicity and diversity of multiple chaotic models, it introduced the local chaotic search strategy to expand the scope range of the chaotic space and enhance the local development capabilities of the algorithm. At the same time, it proposed a nonlinear dynamic density decreasing factor to coordinate the global exploration ability and local development ability of the algorithm. Finally, for the sake of increasing the diversity of the population during the iteration process, this paper adopted the golden sine strategy of the Levy flight guidance mechanism to perturb the population position and improve the ability of the algorithm to jump out of the local optimum. Through simulation experiments on 12 benchmark functions and part of the CEC2014 function set, the results show that the proposed algorithm can overcome the shortcomings of AOA' s weak global exploration ability and easy to fall into local optimality, and improve the accuracy and stability of AOA . In addition, the introduction of mechanical optimization design cases for testing and analysis will further verify the feasibility and applicability of MAOA on practical issues. [ABSTRACT FROM AUTHOR]

In order to fully mine nodes' features and better integrate these features simultaneously in the heterogeneous information network, this paper proposed a AMF L& GRec Firstly, AMFL & GRec used the Leader Rank algorithm to extract the target node' global sequence, and used a meta-path-bas ed heterogeneous information network embedding model to extract the node' local sequence,and used the skip-gram model to learn the node' global and local features. And then it used the self-attention mechanism to learn the preference of the target nodes' local and global features to obtain the feature representation of the target node in a single meta-path. Secondly, it used the self-attention mechanism to fuse the representation of the same node under different meta-paths to obtain the final feature representation. Finally, it utilized a multi-layer perceptron to achieve the task of rating prediction. This paper conducted a large number of experiments on two real datasets. The experimental results verify that the AMFL & GRec algorithm can not only capture the micro(local) structure of densely connected nodes, but also capture the global structure of the node in the network, and finally obtain nodes' overall (local +global) characteristics. At the same time, the experimental results also prove that the AMFL & GRec's rating prediction performance is better than the baselines. It proves that in the heterogeneous information network utilizing the self-attention mechanism to consider the nodes' preferences for local and global features and meta-paths can improve the accuracy of rating prediction. [ABSTRACT FROM AUTHOR]

Interactive image segmentation refers to bringing in a small number of user guidelines to segment the target object during the segmentation process and is one of the most fundamental tasks in image processing. Existing methods usually require the construction of non-quadratic energy functions and generally suffer from the lack of unique solutions and low segmentation accuracy. To further improve the segmentation quality, this paper proposed an interactive image segmentation algorithm combining local linear embedding and seed information（SILLE). The algorithm toke into account the local and a priori information of the pixel points and incorporated the information of the labeled seed points into the newly constructed energy function to obtain a unique and optimal solution of the energy function with an efficient and fast minimization scheme, thus obtaining more accurate segmentation results. Finally, comparison of different methods on different datasets verifies the effectiveness and feasibility of the algorithm. [ABSTRACT FROM AUTHOR]

With the continuous rise of federated learning, gradient boosting decision tree（GBDT）,as a traditional machine learning method, is gradually applied to federated learning to achieve ideal classification results.Aiming at the problems of the existing horizontal federated learning model of GBDT,such as the accuracy is greatly influenced by non-IID dataset, information leakage and high communication cost, the paper proposed a federated gradient boosting decision tree for non-IID dataset, called nFL-GBDT.Firstly, the algorithm calculated similar samples among the participants by utilizing the LSH,and using weighted gradient constructed the first tree.Secondly, a reliable third party calculated the global leaf weight that only needed one round of communication.Finally, the experimental analysis shows that the algorithm can protect the privacy of the original data, and its communication cost is lower than that of simFL and FederBoost.At the same time, the experiment divides three groups of public data sets according to the imbalance ratio.The results show that the accuracy of this algorithm is improved by 3.53%,5.46% and 4.43% respectively compared with Individual, TFL and F-GBDT-G. [ABSTRACT FROM AUTHOR]

The quality of traffic images obtained outdoors in foggy weather is poor, and the use of existing algorithms will misestimate the atmospheric light values and transmittance, resulting in color distortion and halo phenomenon in the sky region, so that this paper proposed an adaptive multi-state feature fusion algorithm to remove fog from traffic images. According to the characteristics of the sky area in the foggy traffic images, the method used a light-dark area detection model to divide the sky and non-sky regions, and separately estimated the corresponding atmospheric light values to eliminate color distortion. At the same time, it created a multi-scale image decomposition model to automatically discover multi-state features pixel by pixel, and further based adaptive feature fusion strategy to highlight locally significant features and recombining the features, refining the precise transmission diagram, to solve the halo effect. The experimental results show that the visual effect of the new algorithm is real, the objective evaluation index is better than other classical algorithms, and is the shortest compared to time. The algorithm effectively solves color distortion and halo effect, satisfies fast speed and high precision requirements, and has important application value in the field of intelligent traffic construction. [ABSTRACT FROM AUTHOR]

When UAVs are equipped with a deep neural network for power inspection, because the device computing power and battery capacity as well as the deep neural network computation load limit, it cannot independently process the massive amount of image data generated in the inspection task. To address this problem, this paper proposed an unloading strategy for UAV power inspection based on improved hybrid particle swarm algorithm and matching theory, which decomposed the system cost minimization problem into two sub-problems, such as cooperative partitioning of deep neural network computing tasks and edge server selection. For the collaborative partition problem, it proposed a staggered transmission method based on the execution process of deep neural network computational tasks, and an improved hybrid particle swarm algorithm solved the multi-UAV task collaborative partition layer. For the server selection problem, it defined the respective preference functions of the UAV and the server, and established a stable match between them through matching theory according to the preference functions to obtain the server selection policy. Simulation results show that the proposed strategy can effectively reduce the energy consumption and computational task processing delay of UAVs and promote the load balancing of edge servers compared with other offloading strategies. [ABSTRACT FROM AUTHOR]

Most existing traditional congestion control algorithms are difficult to adapt to the highly dynamic link environment of wireless Ad hoc network. In order to solve the above problem, this paper proposed a method of improving the performance of congestion control based on deep reinforcement learning, Enhanced-CC. It conducted a preliminary detection of the congestion window by using the traditional congestion control algorithm. On this basis, the method used deep reinforcement technology to learn the real-time optimal congestion window range of the link. When the congestion window calculated by the traditional congestion control algorithm was too large or too small, the method adjusted the congestion window, so that the sending rate could match the highly dynamic link bandwidth, and the method could improve the transmission performance of the traditional congestion control algorithm. The experimental results show that Enhanced-CC can significantly improve the performance of traditional congestion control algorithms such as BBR, CUBIC, Westwood, Reno, and is superior to the performance of fully learning based congestion control algorithms such as PCC and PCC Vivace, and the combination of deep reinforcement learning and traditional congestion control algorithms such as Orca and DeepCC. [ABSTRACT FROM AUTHOR]

In order to solve the failure of path planning with static or dynamic obstacles in the process of path planning, this paper proposed an artificial potential field based on POMDP-APF path planning for UAV（unmanned aerial vehicle）. Firstly, the obstacle information obtained by sensors was combined with POMDP model to predict the future locations of obstacles. Se-condly, it proposed a new circumscribed sphere of cube for obstacle to ensure the safety of UAV in path planning process. Finally, combined with the improved APF algorithm, it realized the path planning of UAV. Simulation results show that POMDP-APF strategy has good feasibility and effectiveness in the real-time path planning of UAV, so that UAV can effectively avoid obstacles with shorter path length and time. [ABSTRACT FROM AUTHOR]

Loop closure detection can eliminate the accumulated error of visual SLAM, which is of great significance to the SLAM system. Among them, the widely used visual bag-of-word model algorithm has the problem of visual word identity and ambiguity, which affects the loop closure detection effect. To improve these problems and loop back detection effect, this paper proposed a loop closure detection algorithm based on soft-assigned SIFT features. The algorithm allocated the SIFT feature points extracted from the image to several words with the closest Euclidean distance, according to the distance sorting and weighting, and removed the feature points that were far away from the words to generate more discriminating descriptors. In addition, when filtering candidates, the algorithm added the proportion constraint of the same word feature points and the stability constraint of word shift to filter out a few candidates. In the experimental results, the algorithm compared with the traditional visual bag-of-words model and several loop closure detection algorithms in recent years, the recall rate at 100% accuracy rate improved under three data sets, and the average image query time was about 40 ms. The results show that the algorithm can improve the loop detection effect and ensure the real-time performance. [ABSTRACT FROM AUTHOR]

Aiming at the shortcoming of salp swarm optimization algorithm such as low accuracy, slow convergence speed and easy to fall into local optimum, this paper proposed an adaptive t-distribution and dynamic weight salp swarm optimization algorithm. Firstly, the leader position update introduced the global search stage formula of butterfly optimization algorithm to enhance the global exploration ability. Secondly, the follower location update introduced an adaptive dynamic weighting factor to strengthen the guiding role of elite individuals, so as to enhance the local development ability. Finally, the adaptive t-distribution mutation strategy mutated the optimal individual in order to avoid the algorithm falling into local optimum. By solving 12 benchmark test functions, and according to comparison results of the mean value, standard deviation, solving success rate, Wilcoxon test and convergence curve, the proposed algorithm was superior to standard salp swarm algorithm, the compared other improved salp swarm algorithm and the compared other swarm intelligence algorithms. The results also show that it has a significant improvement in the optimization accuracy and convergence speed, and has the ability to jump out of local optimum. The experimental results verify the effectiveness of the proposed algorithm by applying it to find the lowest point of denitrification inlet concentration. [ABSTRACT FROM AUTHOR]

In order to fix the integer ambiguity quickly and accurately, this paper proposed a new ambiguity search algorithm based on measurement accuracy constraints to solve the problems of the LAMBDA algorithm, such as the wide search range of the integer ambiguity and the low search efficiency. When the least squares problem got optimally weighted, the algorithm took the carrier phase measurement accuracy as the constraint condition to test the fixed ambiguity solution on the basis of the stan-dard differential evolution （DE） algorithm. This algorithm solved the influence of different satellite altitude angles, and could achieve 99% success rate when solving 3D integer ambiguity. Compared with the MLAMBDA algorithm, the standard DE algorithm and the adaptive weighted differential evolution （AWDE） algorithm, the proposed algorithm further improves the efficiency and success rate of ambiguity resolution. [ABSTRACT FROM AUTHOR]

The rectangular layout problem with balance constraints is a combinatorial optimization problem, which is difficult to solve when the problem scale increases. To improve the performance, this paper designed a bee colony algorithm. By analyzing the distribution of solutions, it provided a greedy initialization scheme for the population, selected an effective mutation operator, and limited the search space around the optimal solution. In addition, it designed a local search module to further improve the quality of the solution. On 10 open test cases, the algorithm was compared with the best known existing algorithms, and the performance of the proposed algorithm exceeded the existing algorithms on 9 large-scale cases. The theoretical analysis and experimental results show that the proposed algorithm can significantly improve the efficiency of solution. [ABSTRACT FROM AUTHOR]

The method of market mechanism is rigorous in mathematical derivation, clear in theoretical explanation, small in algorithm computation, and less limited in network scale and topology structure. This paper reviewed the classical li-terature and recent studies about two methods based on market mechanism; auction and contract net, and introduced and summarized the basic principle, progress, application background and limitations of this method in detail. Finally, the summary presented the key issues and future research trends in the research of task allocation for unmanned swarm based on market mechanism. [ABSTRACT FROM AUTHOR]

Community search,as an important research content of social network analysis,aims to find densely connected subgraphs that highly relate to the query node given by users.Most community search methods currently available focus on homogeneous networks.However,in reality,information networks are often attribute-heterogeneous.This paper proposed P-distance and S-distance based on meta-path P and meta-structure S in heterogeneous networks,as well as (k,d,P) -truss and (k,d,S) -truss community models,to measure the structural cohesion of subgraphs.Additionally,it proposed a keyword attribute score function to measure the keyword attribute correlation of different subgraphs,and presented algorithms which could find communities with the highest keyword attribute score of (k,d,P) -truss and (k,d,S) -truss.Search algorithms could find a personalized community with both structural cohesion and keyword attribute correlation,and support to limit the maximum distance d between the query node and any node in the community to control the scope of community search.Compared with the related community search algorithms on real-world datasets,the experimental results prove the effectiveness and feasibility of the proposed algorithms. [ABSTRACT FROM AUTHOR]

In a cooperative Markov game, each intelligence not only has to achieve a common goal, but also needs to ensure that the joint actions can satisfy the set constraints. Therefore, this paper proposed a cooperative multi-agent TD3 algorithm（MACTD3） under security constraints. Firstly, it used the attention mechanism to coordinate the actions of individual intelligences with the decision process constraints. Then it constructed a modified cost function using Lagrange multipliers. Further, in order to ensure the convergence of the algorithm, it was ensured that each intelligent body could satisfy the pre-defined constraints with different time-scale sub-learning policies. The parameters of the Actor-Critic network perform gradient descent while Lagrangian parameters on the long time scale. Finally, experimental results in heterogeneous and homogeneous cooperative multi-intelligent environments show that the MACTD3 algorithm can always obtain the minimum penalty cost compared with other algorithms. The scalability experiments by number show that MACTD3 can still satisfy the constraints with different numbers of intelligences, proving the effectiveness and scalability of the algorithm. [ABSTRACT FROM AUTHOR]

Existing session-based recommendation algorithms mainly recommend by mining the item conversion relationship of a single target session, and take less account of the complex conversion information between items from other different sessions. This paper proposed a session-based recommendation algorithm fusing global and neighbor collaboration information（SFGN-GNN）, which simultaneously considered the collaboration information from neighbor and global sessions to fully exploit user preference. The algorithm expressed user preference by learning session representation. Firstly, it built the neighbor graph according to the pairwise item transfer relationship between the target session and neighbor session, and built the global graph according to the pairwise item transfer relationship in all sessions. Then, it used the graph neural network to obtain the neighbor-level and global-level item representations of the target session node. Next, it used the fusion gate to obtain the session-level item representation, and embedded the position information and time information of the item in the target session. Afterward, it obtained the final session representation by using the soft attention mechanism. Finally, it predicted the next possible interaction item by softmax function. Experiments on two datasets demonstrate the effectiveness of SFGN-GNN algorithm. [ABSTRACT FROM AUTHOR]

GIFT algorithm as an improved version of PRESENT algorithm, the structure is more concise and efficient, when it running on FPGA, the performance still has room for improvement. This paper proposed a new implementation scheme, by implemented the algorithm from a 40-round iterative computation to a 20-round iteration, and executed the encryption/decryption in parallel with the round key generation operations. After the proposed scheme used in xc6slx16 FPGA platform, frequency up to 194 MHz, throughput up to 1.2 Gbps, and it consumes 21 clock cycles. The results show that the proposed method has better performance and less clock cycle consumption compared to the existing work. It is practical to perform at high speed on FPGA. [ABSTRACT FROM AUTHOR]

This paper proposed an SFC (service function chaining） placement algorithm based on VNF (virtual network function） instance sharing to address the problem of difficult tradeoff between the deployment cost of VNF instances and forwarding cost in the process of SFC placement. Firstly, for multi-link SFC, it constructed the VNF and virtual link mapping model, and estimated the upper bound of the path deployment length to ensure the SFC delay. Secondly, within the limit of the path length, it maximized the number of the reused VNF instance as much as possible to balance the forwarding cost and the deployment cost of VNF. Finally, it obtained the SFC placement strategy. Compared with the existing SPH (shortest path heuristic） and GUS (greedy on used server） placement algorithms, the total operating expense of the proposed algorithm is 6.6% and 12.15% lower, and when the number of SFC increases, the service acceptance rate of this algorithm can reach 89.33%.The simulation experimental results show that this algorithm can effectively reduce the SFC placement cost while ensuring the quality of service. [ABSTRACT FROM AUTHOR]

How to deal with network faults efficiently and quickly is the basic requirement and main task of designing routing protocol. When dynamic routing protocols deal with network faults, a large number of packets are discarded during dynamic convergence. Therefore, at present, router manufacturers generally use routing protection methods to overcome network failures. Among many route protection methods, the DC (downstream criterion) rules is a generally recognized method. However, the time complexity of the existing DC rules algorithms is generally high, and the complexity increases rapidly with the increase of the average degree of network nodes. In order to deal with the above problems, this paper proposed a linear time complexity university routing protection scheme ERPLR (efficient routing protection method with linear time complexity). The method firstly proposed the backup next hop calculation rule, and then calculated the backup next hop for all source-destination node pairs based on the existing shortest path tree according to the backup next hop calculation rule. In the process of calculating the backup next hop, accessing each node and its neighbors at most once, so the time complexity of ERPLR is O（V+E). The experimental results show that, compared with the existing rules for implementing DC rules, ERPLR has similar results in four metrics: failure protection ratio and path stretch. Compared with DC rules, ERPLR reduces the computational overhead by about 74.93% and 78.91% in real topology and generated topology, respectively, this method can greatly reduce the calculation cost of DC rules. [ABSTRACT FROM AUTHOR]

In recent years, single device sound scene classification has achieved good results, however, progress in multi-device sound scene classification has been slow. To solve the problem of large differences in the number of multi-device samples, this paper proposed a pairwise feature fusion algorithm. By calculating the differences in the spectrogram for each pair of paired samples and averaging these differences after accumulation, obtaining the average spectral characteristics of each device for the conversion of device samples. The algorithm effectively improved the generalization ability of the model while increasing the number of device samples. Meanwhile, in order to obtain global information, it proposed a lightweight attention module, which could make the model focus on the training of the whole sound sequence information on the basis of reduced computation by performing self-attention operations on the input features after compression in the frequency domain. The experimental results show that the proposed algorithm has better advantages in terms of model size and classification accuracy compared with other methods. [ABSTRACT FROM AUTHOR]

Considering the functional characteristics of Android application virtualization technology, accurate detection of Android virtualization programs is the basis and necessary prerequisite for identifying hidden security risks. Therefore, this paper proposed a method to detect Android virtualization programs based on heterogeneous information networks, and implemented the prototype system Aiplugin. According to the characteristics of Android virtualization programs, the system extracted four types of static program features and mapped program features to heterogeneous information networks. Aiplugin associated different programs in the form of meta paths. It used heterogeneous graph attention network representation algorithm and OC-SVM algorithm and integrated program semantic information from different views to realize the representation and classification of Android virtualization programs. The experimental results show that Aiplugin can detect more types of Android virtuali-zation programs, including parallel space, compared with the current representative tool VAhunt. [ABSTRACT FROM AUTHOR]

As the growth of social network scale, so do challenges to the existing anomaly detection algorithms. Therefore, this paper proposed an anomaly detection method based on graph modularity clustering（GMC＿AD）, which could be applied to solve the problem of low detection efficiency caused by network size and complexity. Based on analyzing the network topology structure, the GMC＿AD method improved the efficiency of events detection by weighting mechanism on abnormal nodes and modularity clustering algorithm. The GMC＿AD processes could be described as follow: a)Since designing a quantization strategy for node evolution in the network, GMC＿AD get the set of abnormal nodes by recognizing nodes with abnormal evolutionary behaviors. b)The method used a modularity clustering algorithm to reduce the network size. c)During the calculation of network fluctuation value, it introduced a weighting mechanism for taking the influence of abnormal nodes into consideration, after that, the GMC＿AD method detected the abnormality by the changes of network fluctuation value. On real social network datasets VAST, EU＿E-mail and ENRON, the GMC＿AD method accurately detected the abnormal periods. The event detection sensibility of GMC＿AD method was increased by 50%～82% meanwhile the run-time efficiency increased by 30%～70%. The GMC＿AD method enhances not only the accuracy and sensitivity but also the efficiency of anomaly detections. [ABSTRACT FROM AUTHOR]

Aiming at the problem of slow search speed and insufficient solution quality of ant colony algorithm, this paper proposed an ant colony algorithm combining dynamic hierarchical clustering and neighborhood interval reorganization. In the ini-tial stage, the algorithm adjusted the hierarchical clustering threshold and iterated to the target cluster based on the principle of minimum inter-cluster distance merging, and then merged the clusters according to the pre-merging coefficient. In the next place it used ant colony system to generate subclass paths, disconnected and reorganized the initial paths to improve the overall convergence speed of the algorithm. Then the algorithm used ant colony system to optimize the solution space, and at the same time, carried out neighborhood interval diffusion reorganization between clusters to increase the diversity of solutions. Furthermore, if the quality of the reconstructed solution was better than the current optimization solution at a fixed number of iterations, the recommendation process would be carried out to improve the accuracy of the solution. When the algorithm stagnated, it introduced an adjustment factor to reduce the differences between pheromones of each path to enhance the ant search ability, which could help the algorithm jump out of the local optimal. The experiment result shows that the accuracy of the algorithm is about 3% when facing large-scale problems, which can effectively improve the accuracy and convergence rate of the solution. [ABSTRACT FROM AUTHOR]

The most existing deep text clustering methods only use traditional autoencoder to learn representation for clustering, and neglect the problems with over-reliance on raw data quality and loss of key semantic information during feature mapping. This paper proposed a deep document clustering method via key semantic information complementation (DCKSC) model. The DCKSC model firstly enriched the original text data by extracting keyword data. Secondly, this model designed a key semantic information complement module which used data enhancement representation to improve the traditional autoencoder, and compensated for the key semantic information lost in the mapping process. Finally, the algorithm synthesized the clustering loss and the reconstruction loss of the keyword semantic autoencoder, optimized the cluster label assignment and learned the presentation characteristics suitable for clustering. Experimental results show that DCKSC is superior to many mainstream deep document clustering algorithms. [ABSTRACT FROM AUTHOR]

The application of deep reinforcement learning technology for autonomous driving decision has become a research topic at domestic and overseas. The existing research on vehicle traffic flow lacks randomness and authenticity,and the effective exploration of autonomous vehicles in the environment has limitations. Therefore, this paper used the 1D3 algorithm to study the right turn driving decision of autonomous vehicles in signal-free intersections. Firstly, it developed the training and testing scenario of signal-free intersection in Carla simulation,and added the traffic flow management function to improve the randomness of system training and testing. Secondly,in order to improve the exploratory of autonomous vehicles, it added OU noise for the target action to improve the Actor network in TD3 algorithm. Finally, it used the success rate and average travel time to evaluate the autonomous driving behavior decisions. The results show that in different traffic flow scenarios, the traffic success rate of the improved 1D3 algorithm is 6. 2% higher than the DDPG algorithm controlled vehicles, and 23% higher than the rule-based AEB model. The improved TD3 algorithm not only can explore more possibilities, but also has a more prominent performance of prevailing decision. [ABSTRACT FROM AUTHOR]

In the field of visual simultaneous localization and mapping ( VSLAM ), the key-frame selection method is mostly heuristic threshold method. This method is prone to the problem of low positioning accuracy. This paper proposed the ORB-SLAM3 algorithm based on improved key-frame selection in response to this problem. Starting from the consideration of key-frame quality, the algorithm adopted the following three standards instead of the heuristic threshold method in ORBSLAM3. The first was an adaptive key-frame threshold based on geometric constraints to ensure a sufficient number of feature points. The second was the distribution standard based on the principle of image centroid to ensure that the feature points were evenly distributed. The last was the inertial measurement unit (IMU) acceleration state observation. Experimental results on the EuRoc dataset show that the improved algorithm improves the positioning accuracy of ORB-SLAM3 by 9% in monocular inertial and 6% in stereo inertial without using the heuristic threshold. This algorithm shows better robustness and composition ability than ORB-SLAM3. [ABSTRACT FROM AUTHOR]

LLP is a machine learning method that puts instances into packages. It only provides instance information and label proportional information in packages, but does not provide label information. Aiming at the LLP problem of multiple related tasks, this paper proposed a label proportion integrated learning model based on transfer learning, called AT-LLP for short. The model connected related tasks by constructing shared parameters between tasks, and migrated the knowledge learned in the source task to the target task, so as to improve the learning efficiency of the target task. At the same time, the algorithm introduced the ensemble learning algorithm, which continuously adjusted the weight coefficient of the training set in the multi-iteration learning process of the classifier, so as to further train the weak classifier into a strong classifier. Experiments show that the proposed AT-LLP model has better performance than the existing LLP method. [ABSTRACT FROM AUTHOR]

Local path planning for unmanned surface vehicle ( USV) plays an important role in maritime rescue and marine transportation. Existing local path planning algorithms achieve good results in simple scenarios, but have poor performance when facing complex obstacles and sea current disturbances present in the environment. To this end, this paper proposed a reinforcement learning algorithm based on spatial and temporal sensing-enhanced deep Q-network. Firstly, it introduced a multiscale spatial attention module to capture the multiscale spatial information of distance sensors, which enhanced the perception capability of complex obstacle environments. Secondly, it used the LSTM-based current sensing module to extract the temporal sequence features of the current disturbance environment, which enhanced the perception capability of the current disturbance. In addition, by simulating the sensor and motion model of USV, it designed the reinforcement learning state space, action space and direction-guided reward function, it improved the navigation performance and convergence speed of the algorithm. Simulation experiments in complex scenarios show that the proposed algorithm improves both success rate and average arrival time metrics comparing to the original algorithm, and the algorithm shows strong adaptability to complex environment. [ABSTRACT FROM AUTHOR]

In recommender systems, graph convolutional networks have stronger information extraction capabilities for graphstructured data. However, existing graph convolutional networks mainly focus on enhancing the model structure, ignoring the importance of improving the sampling quality of the original samples and mining the implicit relationship between users and items. Aiming at the above problems, this paper proposed a graph contrastive learning recommendation algorithm based on mixed sampling. Firstly, the algorithm used a mixed sampling method to extract part of the information in positive samples and injected them into negative samples, thereby generating new informative hard negative samples. Secondly, to extract features on hard negative samples, it used the light graph convolution network to obtain node representations of users and items. Finally, it carried out a multi-task strategy to jointly optimize the recommendation supervision task and the contrastive learning task. The experiments on real datasets Yelp2018 and Amazon-book demonstrate that the proposed algorithm improves performance compared with other recommendation algorithms in recall and NDCG evaluation indexes. [ABSTRACT FROM AUTHOR]

This paper proposed a natural language sentence matching method that combined high-level and low-level semantic information to solve the problems about current natural language sentence matching method fail to integrate common semantic information and it is difficult to capture deep-semantic information. First of all, the method used pre-trained word vector GloVe and character-level word vector to obtained the word embedding representation of sentence P and sentence Q. Secondly, this paper encode red P and Q with bidirectional LSTM, then it contained low-level semantic information through preliminary fusion of P and Q. Thirdly, this paper calculated bidirectional attention between P and Q, then spliced them together to get semantic representation, afterwards it calculated its self-attention to obtained high-level semantic information. Finally, this paper used a heuristic fusion function to fuse the low-level semantic information with the high-level semantic information to obtain the final semantic representation, and it used a convolutional neural network to prediction answers. This paper evaluated the proposed model on two tasks, such as recognition textual entailment, paraphrase recognition. This paper conducted experiments on the SNLI dataset and the Quora dataset. The results show that the accuracy of the proposed algorithm on the SNLI test set is 87. 1%, and the accuracy of the Quora test set is 86. 8%, which verifies the effectiveness of the algorithm in the task of natural language sentence matching. [ABSTRACT FROM AUTHOR]

Most of the existing multi-label learning techniques consider the correlation learning problem but ignore the inconsistency feature of structural properties, which can change the structural property of the label space obtained by function mapping and it can directly affect the classification performance. In order to deal with this problem, this paper proposed a multi-label classification algorithm based on structural property preserving policy and correlation learning policies. Firstly, the algorithm constructed a mapping function to realize the mapping between the feature space and the label space. Secondly, it used structural property preserving strategy based on feature data to reduce the difference between feature data caused by linear transformation. Finally, this paper introduced the correlation learning strategy based on label data to further optimize the parameters of the proposed algorithm to improve the classification performance. The experimental results through a group of benchmark instances show that compared with the other classical multi-label classification algorithm, the proposed algorithm is much superior in classification performance, and the algorithm has great effectiveness. [ABSTRACT FROM AUTHOR]

Due to low line extraction and matching accuracy, existing point-line fusion visual SLAM（simultaneous localization and mapping） methods have low localization accuracy. This paper improved existing point-line fusion stereo visual SLAM method from multiple dimensions. Firstly, this paper improved the LSD（line segment detection） extraction quality through internal parameters adjustment and length threshold filtering. Secondly, on the basis of geometric constraints, it abstracted the line feature matching as a sparse minimization problem to find best match of line segment. Thirdly, on the basis of image texture score and number of successfully matched features, this paper improved back-end point-line feature fusion strategy by assigning point-line feature weights. Compared with LSD algorithm and LBD（line binary descriptor） matching method, the number of short line segments decreased by 67% on average and matching accuracy increased by 18% on average. Compared with PL-SLAM, localization error dropped by about 15% and 45% respectively on the EuRoC and KITTI datasets. Experiments demonstrate that the proposed method enhances localization accuracy of SLAM system effectively by improving various modules performance of point-line SLAM method in multiple dimensions. [ABSTRACT FROM AUTHOR]

Aiming at the feature extraction problem of feature-based visual odometry, this paper proposed a feature selection algorithm based on mutual information and semantic segmentation uncertainty. Based on semantic and geometric information of features, the algorithm points extracted from potential static objects. It corrected the semantic uncertainty of features based on the semantic context, and selected the features based on the information entropy changes of features. Finally, this paper used the public KITTI visual odometry dataset to evaluate the algorithm and compared the experiment results with other algorithms. The results prove that the proposed algorithm has better accuracy of pose estimation, which verifies the effectiveness and feasibility of the algorithm. [ABSTRACT FROM AUTHOR]

The traditional algorithms have the low performance when applied to remote sensing images segmentation. Thus, this paper proposed a segmentation algorithm based on adaptive feature-reduction. Firstly, this algorithm divided the source image into super-pixels as the basic operation object. Then, it extracted the color, texture, edge and spatial features of images and used weighted pixel values to calculate the features of super-pixels. Furthermore, it added the fuzzy separation measure into the FRFCM model to construct own segmentation model. This model can automatically select useful features. Finally, this paper got the final segmentation result based on optimizing the segmentation model. Experiments on remote sensing images prove that this proposed algorithm has superior performance in terms of segmentation accuracy, running time and eliminate noise effects. [ABSTRACT FROM AUTHOR]

The genericity of existing data provenance sanitization mechanisms is very low. One mechanism is usually used to deal with one specific type of sensitive elements. It is still very difficult to deal with comprehensive sanitization requirements including multiple types of sensitive elements in a disciplined manner. To address this issue, this paper proposed a primitive-based generic framework of provenance sanitization. Firstly, this paper introduced the types of sensitive provenance elements and structural constraints that might be involved in data provenance sanitization. Secondly, it thoroughly analyzed existing provenance sanitization mechanisms and formally defined a set of provenance sanitization primitives. Each primitive was a minimal operation for editing a provenance graph. This paper divided the overall process of data provenance sanitization into three stages: hiding sensitive elements, recovering insensitive dependencies, and verifying constraints. Furthermore, it proposed a method for constructing the space of sanitization strategies by selecting and composing possible sanitization primitives stage by stage. Finally, this paper designed and implemented a primitive-based generic provenance sanitization algorithm. The experimental results in public provenance datasets verity the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

In indoor localization, PDR method is one of the most convenient localization methods, but the cumulative error will get larger as the distance traveled increases. The use of Bluetooth peak correction algorithm can effectively reduce the cumulative error of PDR, but the Bluetooth signal has the problem of pseudo-peak and mis-peak in multi-Bluetooth base stations. To address the above problems, this paper proposed a PDR-based Bluetooth peak detection method. The method first calculated the prediction probability based on the PDR position estimation information and Bluetooth distribution information to filter out the closest Bluetooth in the forward direction, thus reducing false peaks. Secondly, it calculated the adaptive threshold based on the change of the signal, thus outputting the switching sate to find the wave peak, to detect the true peak and reduce the false peak. Finally, this paper used an improved Bluetooth peak correction algorithm to correct the PDR position estimation. The experimental results show that the proposed method can achieve a correct peak detection rate of 82.1% on Android smartphones . Compared with the traditional sliding window peak detection method, it can effectively reduce the interference of pseudo-peaks and false peaks, and reduce the cumulative error of PDR. [ABSTRACT FROM AUTHOR]

Aiming at the shortcomings of arithmetic optimization algorithm (AOA) in the search process, such as local extreme points, slow convergence speed and low solution accuracy, this paper proposed a multi-strategy fusion arithmetic optimization algorithm (MFAOA). Firstly, the algorithm used the Sobol sequence to initialize the AOA population, which increased the diversity of the initial individuals and laid the foundation for the global optimization of the algorithm. Then, it reconstructed the mathematical optimizer acceleration function (MOA) to weigh the proportion of the global search and the local development process. Finally, it used the chaotic elite mutation strategy to improve the algorithm's over-dependence on the current optimal solution and enhanced the algorithm's ability to jump out of the local extremum. The paper used 12 general benchmark functions and part of CEC2014 test functions for experimental simulation, and the results show that MFAOA has a significant improvement in solution accuracy and convergence speed. Besides, the algorithm introduced two engineering examples for optimization, which verifies the feasibility of MFAOA in engineering optimization problems. [ABSTRACT FROM AUTHOR]

Aiming at the problems of the current semantic segmentation network's spatial and channel feature mismatch, as well as the pixel loss of small target objects, this paper designed a dual-path semantic segmentation algorithm based on spatial feature extraction and attention mechanism. The spatial information path used four times downsampling to retain high-resolution features, and introduced a spatial feature extraction module to fuse multi-scale spatial information, thereby strengthening the network's ability to recognize small target objects. In addition, it used a semantic context path combined with two-stage channel attention to extract discriminative features, so that deep features could guide shallow features to capture more accurate semantic information, thereby reducing accuracy loss. This paper verified the algorithm on the CamVid dataset and Aeroscapes dataset, the mean intersection over union can reach 70. 5% and 51. 8% respectively. Compared with the current mainstream dual-path semantic segmentation model, the results verify the effectiveness of the proposed algorithm. [ABSTRACT FROM AUTHOR]

Side channel analysis has seriously threatened the application security of cryptographic algorithms. In order to improve the ability of SM4 algorithm to resist side channel analysis, this paper proposed a threshold masking scheme for SM4 algorithm. Firstly, it decomposed the S-box of SM4 algorithm. Then this paper designed the threshold masking method based on two sharing pattern for SM4. According to the method, the schema split the S-box input into two shares by using random number, and rebuilt the circuit by composite field operation and the S-box threshold masking, and reduced the hardware cost by reusing S-boxes. After the linear layer operation, the schema carried out unmasked operation by XOR the two output results. The simulation results and security test results of FPGA implementation for SM4 threshold masking schema show that the mas-king scheme can effectively resist CPA attack, and its implementation area is lower. [ABSTRACT FROM AUTHOR]

The UAV Ad hoc network receives extensive attention in recent years due to its strong anti-interference ability, suitable for complex terrain, high degree of intelligence and low cost. The design and optimization of the routing protocol in this network are always the core research problem. Aiming at the problem that the node doesn't update the local route in time due to it's rapid movement in the UAV Ad hoc network, this paper proposed a dynamic sensor optimized link state routing protocol based on the Q-learning algorithm (dynamic sensor optimized link state routing based on Q-learning algorithm, DSQ-OLSR). Firstly, the proposed protocol fully considered the characteristics of the high-speed movement of nodes in the UAV Ad hoc network. When selected MPR (multi-point relay) nodes, this paper added two indicators of link stability and link existence time to make the selected MPR nodes set more stable and reasonable. In addition, this paper used the Q-learning algorithm to adjust the sending interval of TC messages adaptively. In order to reduce control overhead, the proposed algorithm increased the TC sending interval when the network topology changed slightly. In order to meet the requirements of rapid perception and construction of the network topology and further realize the timely routing of data, the algorithm reduced the TC sending interval when the topology changed greatly. The simulation results show that compared with the DT-OLSR (dynamic topology link state routing based on Q-learning algorithm) protocol, the proposed protocol improves the end-to-end delay, throughput, success rate and network lifetime performance by 12. 6 1%, 9. 28%, 7. 69% and 5. 86% respectively, which verifies the effectiveness of this protocol. [ABSTRACT FROM AUTHOR]

Traditional load balancing algorithms can't meet the demand of high concurrent requests and quick calling of public network digital trunk. This paper proposed a dynamic load balancing algorithm based on load feedback for distributed digital trunk to achieve load balancing and increase user capacity. Firstly, this paper established monitoring method and monitoring indexes for static and dynamic load of participating MCPTT server. Then, it used weighted round robin algorithm to allocate participating MCPTT server to users and got complex load parameters by dealing user requests. Finally, it updated the weight of participating MCPTT server based on load feedback to dynamically adjust server load. Simulation results show that the proposed algorithm has better load balancing effect, smaller load balancing degree and lower response delay compared with traditional algorithms and other dynamic feedback algorithms. [ABSTRACT FROM AUTHOR]