Search

MySQL used configuration parameters to adjust the linear pre-read threshold and the cold/hot ratio of the cold/hot LRU algorithm, resulting in a performance bottleneck in the buffer. Aiming at the above problems, this paper proposed an adaptive buffer management method, the method designed an adaptive threshold adjustment algorithm and an adaptive hot and cold cache replacement algorithm through the reinforcement online learning technology of regret minimization. First of all, this paper made an in-depth study of the pre-read algorithm and the hot and cold cache replacement algorithm in MySQL, and clarified the specific impact of the pre-read threshold and the hot and cold ratio on the two algorithms. Secondly, this paper designed a set of parameter evaluation process by FIFO history queue and adding auxiliary fields to evaluate whether the current parameter is large or small in real time. Finally, this paper designed a parameter adjustment model, which uses the performance monitoring indicators of MySQL’s native pre-read algorithm and cache replacement algorithm to achieve reasonable parameter adjustment. This paper conducted 900 simulation experiments on FIU datasets, the experimental results show that compared with MySQL’s native benchmark pre-read algorithm and hot and cold cache algorithm, the two adaptive algorithms could effectively reduce disk I/O by 8% and increase cache hit ratio by 24% without sacrificing algorithm speed. Compared with the latest cache replacement algorithm, the adaptive hot and cold cache replacement algorithm improved the speed to 1.6 times while ensuring the cache hit ratio. [ABSTRACT FROM AUTHOR]

Aiming at the differences in the contribution of feature data to the cluster centers in the clustering algorithm and the sensitivity of the algorithm to the initial cluster centers, this paper proposes a Weighted Knowledge Amountbased Intuitionistic Fuzzy C-means Method（WKAIFCM）. Firstly, this method fuzzed the original dataset intuitionistically and improved the latest intuitionistic fuzzy knowledge measure to calculate the knowledge amount which utilized in the feature weighting of dataset. Secondly, this method initialized the cluster centers to improve the calculation accuracy and clustering efficiency of high-dimensional feature dataset by kernel space density and kernel distance. Finally, based on the principle of sample distance between clusters and the principle of minimum knowledge amount, this method established a clustering optimization model to get the optimal iterative algorithm. The experimental results based on the UCI artificial dataset show that the proposed method can greatly improve the accuracy and iterative efficiency of clustering. The classification accuracy and execution efficiency are increased by 10.63% and 31.75% respectively, and this method has good universality and stability. This paper introduces a new theory of knowledge measure into fuzzy clustering for the first time and gets extraordinary results, which creates a new case for the potential application of this theory in other related fields. [ABSTRACT FROM AUTHOR]

Intelligently formulating the RPA execution path is conducive to saving labor costs and improving the promotion of RPA for enterprises. For the first time, this paper proposed based on improving DDQN algorithm for RPA path planning. First of all, the problem that the working environment of RPA was a Web page, which didn't meet the exploration conditions of the depth enhancement algorithm, with the help of the idea of metaphor map, it built the virtual environment to meet the requirements of the path planning experiment. At the same time, in order to improve the exploration efficiency of DDQN algorithm, this paper proposed to use the Jaccard coefficient of the location information between samples as a sample priority and combined it with rank-based prioritization to build new sampling methods. This paper randomly used task samples on the virtual environment to verify to demonstrate compliance with the experimental requirements. Further comparison of experimental results of the improved DDQN with DQN, DDQN, PPO and SAC-Discrete shows that the improved algorithm has fewer iterations, faster convergence speed, and higher return value, indicating the effectiveness and feasibility of the improving DDQN algorithm. [ABSTRACT FROM AUTHOR]

Blockchain technology can effectively solve the problem of trusted data sharing in the Internet of Things (IoT) scenario, but the main stream consensus algorithm may have a large delay, and it is difficult to process the mass heterogeneous data from multi-sources. To solve this problem, this paper proposed a dynamically multi-block double-round consensus algorithm (called DMDR). This algorithm split the two steps of transaction verification and packaging, and the way of transaction processing in advance and block generation in delay enabled the common node to take advantage of the waiting time to process the transaction and generate multiple blocks in a consensus, thus improving the data processing efficiency. This algorithm divided the nodes in the network into multiple clusters, and reduced the communication cost by the double-round consensus between each cluster and the whole system, and ensured the accuracy of the consensus results based on the mutual verification of the points in the cluster. The simulation results show that the throughput of the proposed algorithm is better than that of PoW and PBFT, and it still has a considerable transaction throughput in small delay. [ABSTRACT FROM AUTHOR]

Aiming at the problems of the existing Byzantine fault-tolerant consensus mechanism applied to alliance chain, such as insufficient scalability and difficulty to support efficient and secure consensus under large-scale network nodes, this paper proposed a practical Byzantine fault-tolerant consensus algorithm(called H-PBFT) based on Raft clustering grouping by node grouping strategy. Firstly, the shuffled frog leaping algorithm combined with K-medoids clustering strategy using to cluster nodes in the system into multiple groups participated. The central nodes of each cluster nodes in the PBFT consensus of the main consensus cluster and the Raft algorithm introduced the improved supervision node was used to achieve consensus in each cluster group. Intra-group consensus mechanism supervised the introduction of nodes to make Raft algorithm Byzantine-resistant. Experimental results show that, compared with PBFT and Raft, this algorithm can improve fault tolerance performance in large-scale network node environment, and can also cluster nodes quickly and efficiently, improve consensus efficiency, reduce consensus communication overhead and complexity. This algorithm has better scalability, which can be better applied in alliance chain scenarios. [ABSTRACT FROM AUTHOR]

To address the problem of unbalanced computational resource consumption and accuracy of semantic segmentation models using attention mechanism, this paper proposed a lightweight attention enhancement algorithm for semantic segmentation. Firstly, it designed a striped dimensional attention mechanism based on the shape characteristics of objects in driving scenes, used striped pooling instead of traditional square convolution, and combined dimensionality reduction operations to extract long-range semantic associations in each dimension to cut down the model computation. Then it fused the attention on channel domain and spatial domain to form a lightweight multidimensional attention fusion module that could be superimposed and disassembled to extract feature information in all directions and further improve the model accuracy. Finally, it inserted the module into the ResNet-101 backbone based encoding-decoding network to guide the semantic fusion of high and low layers, correct the feature map edge information, and supplement the prediction details. The experiments show that the module has strong robustness and generalization ability, cutting about 90% of the number of parameters and 80% of the computation compared with the same type of attention mechanism, and the segmentation accuracy still achieves a stable improvement. [ABSTRACT FROM AUTHOR]

To address the shortcomings of the object detection model in the training process, such as the allocation of positive and negative samples without considering the aspect ratio of the ground-truth box and the poor adaptability to different distributions of objects, this paper proposed the ratio-prior and loss-aware assignment（RLA） algorithm. RLA didn’t change the structure of the original detection model, firstly it selected an equal proportion of the central sampling area based on the aspect ratio of the ground-truth box, then calculated the integrated loss of the anchor points, considered the actual distribution of objects within the ground-truth box, and finally distinguished between positive and negative samples by means of a dynamic loss threshold. The algorithm solved the problems of poor adaptability and difficulty in selecting the best positive samples based on IoU allocation, and the sample allocation for eccentric objects and objects with different aspect ratios was more reasonable. Compared with existing sample allocation algorithms, the algorithm outperforms the MS COCO dataset by 1. 66% over the AP of the baseline FCOS, and 0. 76% and 0. 24% over the AP of the ATSS algorithm and the PAA algorithm respectively when the model structure is the same, demonstrating the effectiveness of the RLA algorithm. [ABSTRACT FROM AUTHOR]

To address the problem that the interval centroid-based watermarking lacks of error correction capability and is difficult to resist multi-flow attacks, this paper proposed a robust network flow watermarking algorithm based on dynamic interval compression. The method used coding and decoding technology to enhance the error correction capability of the interval centroid-based watermarking, and modulated the network traffic carrying the same watermark information into multiple modes by dynamic interval compression to resist multi-flow attacks. Meanwhile, it detected the watermark in layers at the detection side to reduce the waste of computational resources. The experimental results show that when the detection threshold is set to 0. 8,the false positive rate is lower than 5%,and the watermark detection rate can be higher than the original interval centroid-based method by about 10%,and there is no obvious silent interval after merging multiple watermarked flows. It can be seen that the algorithm has good robustness and concealment, and can effectively improve the usability of network flow watermarking. [ABSTRACT FROM AUTHOR]

Aiming at the problem that the existing social recommendation algorithms ignore the potential association of users and the collaborative relationship between items, this paper proposed a new algorithm model GATHGN. This model framework unified modeled of user association and item relationship. Firstly, users’ mined explicit social relations, potential association relations and user-item association relations, so as to extract users’ social high-order characteristics and potential interest high-order characteristics. Then, the above two high-level features were aggregated based on the graph attention mechanism, and the user fusion features were updated layer by layer. Finally, the final recommendation results were calculated according to the updated user fusion characteristics and project characteristics. Experimental results on Yelp and Flickr data show that the HR and NDCG of GATHGN are significantly improved compared with the baseline algorithm. [ABSTRACT FROM AUTHOR]

In the recommendation system, the user’s ratings are often affected by the rating context, that is, the user’s previous ratings of some items will affect the objectivity of his rating of the current item. Sparse linear method treats user ratings affected by context as the same as other ratings when calculating item similarity. However, this partial ratings cannot objectively reflect the similarity between items. To solve the above problems, this paper proposed a recommendation algorithm combining rating context and item similarity based on sparse linear method. It divided the algorithm into three stages.The first stage used weighted ratings to calculate the item’s nearest neighbor for feature selection.In the second stage, it used the rating error weight to reduce the fitting of the ratings affected by the context of the algorithm model, and trained the item similarity matrix. In the third stage, it predicted the ratings according to the user’s ratings and the item similarity, and finally sorted the predicted ratings to complete the item recommendation. Experiments were conducted on four datasets of MovieLens, it used mean average precision (MAP), mean reciprocal rank (MRR) and normalized discounted cumulative gain (NDCG) to evaluate the effectiveness of the algorithm. The experimental results show that the fusion rating context will further improve the accuracy of item similarity and thus improve the performance of recommendation. [ABSTRACT FROM AUTHOR]

In order to improve the optimization effect of traditional ant colony algorithm in solving traveling salesman problem, this paper developed a dual-ant colony optimization algorithm with dynamic differentiation and neighborhood induction mechanism. Firstly, the algorithm introduced chaotic random strategy, and changed the original greedy strategy in the initialization stage of the algorithm to chaotic distribute the initial pheromone, so as to maintain the diversity of the population and improve the accuracy of the solution. Secondly, the algorithm divided the isolated ants in the ant colony into isolated ant colony and normal ant colony, and the two groups of ants searched around the current optimal path and the outlier path respectively. It adopted the induction mechanism among the populations. Normal ants were responsible for searching the optimal path, and isolated ants released pheromones randomly in chaos to induce the normal ant colony to a new path, thus effectively balancing the contradiction between the convergence rate and the diversity of solutions. The simulation results of different scale TSP show the effectiveness of the proposed algorithm. [ABSTRACT FROM AUTHOR]

Road traffic accidents occur frequently and seriously in the accident-prone spots. In order to improve the safety and efficiency of road traffic, it is necessary to find the location of accident-prone points. The existing density clustering algorithm needed to set the number of center points and was easy to expand the clustering range when identifying traffic accident-prone points, this paper proposed the limit cluster expansion and adaptive search clustering by fast search and find of density peaks (LA-CFDP) algorithm to solve these problems. LA-CFDP algorithm automatically determined the number of center points by increasing the restriction condition of center points, and introduced the parameter expansion factor to limit the cluster expansion range, so as to improve the adaptability and accuracy of the algorithm for accident-prone point identification. The case analysis on the 2019 traffic accident data set of four cities in United Kingdom shows that the Sihouette coefficient of the clustering results of LA-CFDP algorithm reaches 0.72～0.92, and the Davies-Bouldin index (DBI) are all reduced to below 0.37. The clustering results accord with the definition and characteristics of accident-prone spots, and can provide reliable basis for the management of accident-prone spots. [ABSTRACT FROM AUTHOR]

To effectively incorporate knowledge into dialogue reasoning, this paper proposed a multi-domain end-to-end task-oriented dialogue system based on a double-layer memory network. Firstly, it used the form of knowledge rows instead of triples to represent knowledge, which improved the performance of knowledge location. Secondly, it used a double-layer memory network structure to model knowledge and dialogue history separately, which improved the reasoning ability of the model. Finally, it used a dynamic encoder to encode data in various fields to improve the generalization ability of the model. Through experimental analysis, the F1 and BLEU indicators of the model are improved through compared with the comparison algorithm on the InCar and CamRest datasets, which verifies the effectiveness and advancement of the model. [ABSTRACT FROM AUTHOR]

Aiming at the problems in the practical Byzantine fault tolerance（PBFT） consensus algorithm, such as large communication overhead, lack of reward and punishment mechanism and lack of enthusiasm of nodes, this paper proposed an improved PBFT consensus algorithm based on the node grouping reputation model（GR-PBFT）. Firstly, GR-PBFT algorithm introduced a reputation reward and punishment mechanism to ensure the security of the system, and then grouped by nodes reputation to select consensus nodes so that it could solve the reputation accumulation problem of nodes generated by consensus algorithms such as reputation mechanisms. Besides, it could also reduce the degree of system centralization and improve the enthusiasm of nodes to become consensus nodes. Then, this algorithm improved the election method of the master node to ensure the reliability of the master node. Meanwhile, it optimized the execution process of the consensus protocol and reduced the communication complexity in the preparation, confirmation and response stage to improve the consensus efficiency. Finally, the simulation experiments show that the GR-PBFT consensus algorithm has better performance than the PBFT consensus algorithm in terms of consensus delay, communication overhead, throughput and security and so on. [ABSTRACT FROM AUTHOR]

To address the defects of high complexity, large power consumption and poor practicability of current WBAN security schemes, this paper proposed a combined chaotic flow encryption scheme to meet the requirements of high security and low power consumption in WBAN. The algorithm consisted of three quantization accuracy, it firstly used tent map to interfere with the orbit of logistic map and generate chaotic sequences, then generated the key stream by combining the m sequences with good equilibrium and autocorrelation, and finally got the ciphertext after the XOR operation with the plaintext. This paper used Verilog hardware description language to describe the algorithm and implemented board level verification on FPGA. Through the security test of standard gray image, the information entropy of encrypted image reached 7. 999 4, and the correlation coefficient of adjacent pixels was close to 0. The results show that the algorithm has better correlation and higher information entropy compared with the existing algorithms. [ABSTRACT FROM AUTHOR]

When the meta-heuristic algorithm solves the joint resource allocation problem of multi-beam satellites, the computational complexity increases and the algorithm is difficult to converge due to the time delay constraint and capacity constraint. This paper introduced a penalty mechanism in the objective function, and added a penalty value to the objective function of the invalid solution, so that the optimized solution adaptively satisfied these two constraints. Based on this, this paper proposed a joint resource allocation algorithm based on quantum-behaved particle swarm optimization. Simulation results show that the introduction of the penalty strategy solves the problem of difficulty in handling the delay constraint and capacity constraint when applying the meta-heuristic algorithm. The quantum-behaved particle swarm optimization algorithm with penalty mechanism outperforms the existing joint allocation algorithm in terms of allocation fairness index and total system capacity. [ABSTRACT FROM AUTHOR]

In order to solve the path planning problem of multi-robots in static environment, the path length was used as the optimization target model, and this paper designed a multi-robot firefly algorithm (MR-FA) for this model. Firstly, considering the path security to expand the obstacles in the environment, MR-FA designed an initialization rule to improve the efficiency of generating the initial population. Secondly, according to the continuity principle and characteristics of the algorithm, it designed an individual isometric strategy to convert individuals with inconsistent dimensions into equal-dimensional individuals to facilitate the mobile update of fireflies, and designed initialization rules to improve the efficiency of generating initial populations. Then, it performed collision detection on the planned movement path of each robot, and designed corresponding collision avoidance strategies for different collision situations of robots: pause-fallback strategy, local path replanning strategy. Finally, this paper carried out the simulation experiments in three groups of environments and compared the effectiveness of MR-FA with the other three algorithms. It can be concluded that MR-FA has more advantages in solving multi-robot path planning. [ABSTRACT FROM AUTHOR]

Most existing NMF methods not only ignore the non-local structure of data, but also are difficult to deal with noise and outliers effectively. To address these issues, this paper proposed a novel robust structure regularized nonnegative matrix factorization (RSNMF) algorithm for clustering. The proposed RSNMF constructed a nearest neighbor graph and a maximum entropy graph to respect local and non-local structures of the data, respectively. Moreover, the L2,1-norm-based cost function tries to address noise and outliers. Therefore, RSNMF could learn robust compact and discriminative representations. This paper presented an optimal iterative algorithm to solve two nonnegative factors. The convergence of such an optimization scheme has been proved theoretically and empirically. Experimental clustering results on seven image datasets show that the proposed algorithm is superior to the state-of-the-art methods in both noiseless and noisy situations. [ABSTRACT FROM AUTHOR]

In order to solve the problems of low convergence accuracy and difficulty in jumping out of local optimum of traditional SSA, this paper proposed an improved salp swarm algorithm (ISSA) with multi-strategy fusion. Firstly, this paper proposed a new follower position update method integrating the convergence strategy of the midperpendicular algorithm to solve the shortcomings of the traditional SSA follower position update method. In order to improve the ability of SSA to jump out of the local optimum, this paper proposed a self perturbation strategy based on the convergence strategy of the midperpendicular algorithm. Secondly, by analyzing the shortcomings of the traditional SSA leader position update strategy, this paper proposed a new leader position update strategy, and for the fixed population order of SSA, this paper proposed a method to reconstruct the arrangement order of the salp population with the index of fitness to improve the performance of the algorithm. Finally, simulation experiments prove the effectiveness of the ISSA, and the experiments results show that ISSA solves the problems of low convergence accuracy and difficulty in jumping out of local optimum, and improves the convergence speed and stability of SSA. The superiority of ISSA is proved by comparison experiments with other improved SSA. [ABSTRACT FROM AUTHOR]

With the aim of satisfaction of demand response, this paper proposed an improved polar bear optimization based approach for cost optimization on multi-tenant colocation data centers. This paper used a one-to-many reverse auction model to reveal the relationship between tenants and operator, and encouraged tenants to voluntarily participate in the auction and submit their energy-saving plans and expected rewards. Then, this algorithm adopted the improved polar bear algorithm to solve the optimal tenant combination and minimize the cost. In detail, this method leveraged the sigmoid function to process the discretize problem. Meanwhile, to enhance the ability of jumping out of the local optimum, it integrated a mutation strategy into the algorithm. To further improve the searching ability in a global view, the method designed an adaptive field of view strategy instead of fixed field of view to dynamically adjust the scope of the local search, and reduced the probability of the algorithm trapping into the local optimal solution. Finally, the paper compared the proposed algorithm with several classical algorithms. The experimental results show that the proposed algorithm not only gains the least cost alone, but also improves the efficiency. [ABSTRACT FROM AUTHOR]

Multimodal fusion algorithm is one of the solutions to the problem of urban road video caption which only considers visual information and ignores the equally important audio information. Existing multimodal fusion algorithms based on Transformer all have the problem of low fusion performance between modes and high computational complexity. In order to improve the interaction between multimodal information, This paper recently proposed a new Transformer based model called Multimodal Attention Bottleneck for Video Captioning (MABVC). Firstly, this paper uses pre-trained I3 D and VGGish networks to extract visual and audio features of video and input the extracted features into Transformer model. Then, the decoder part will train the information of the two modes respectively and perform multimodal fusion. Finally, the model processes the results of the decoder and generates text captions that people can understand. This paper conducted a comparison experiments using data sets MSR-VTT, MSVD and self-built data sets BUUISE, and validated model results using evaluation metrics the model. The experimental results show that the video caption model based on multimodal attention fusion has obvious improvement in all indicators. The model can still achieve good results on traffic scene data sets, and has great application prospects/can be promoted and applied in intelligent driving industry. [ABSTRACT FROM AUTHOR]

This paper considers the physical-layer security of information transmission in an unmanned aerial vehicle (UAV) multi-user communication system, where a UAV communicates with multiple users on the ground, with the presence of an eavesdropper on the ground trying to intercept the confidential information sent from the UAV to the users. The channels between the UAV and all ground nodes are modeled as more accurate probabilistic LoS (line-of-sight) channels. This paper studies maximizing the minimum average secrecy rate of all users by jointly designing the three-dimensional (3D) trajectory of the UAV and the user scheduling, under the constraints of UAV fight conditions and the discrete user scheduling parameters. To solve the optimization design problem for the UAV secure communication system under the probabilistic LoS channel model, it first decoupled it into three sub-problem, then solved the three sub-problems one by one, by using the integer relaxation and successive convex approximation methods, and finally obtained the 3D flight trajectory of UAV by using the block coordinate descent method. Based on the instantaneous channel state information obtained during the UAV’s flight, it further proposed a real-time optimization algorithm for UAV speed and user scheduling. This algorithm formulated the optimization problem into a linear programming problem and solved it by using the interior point method. Simulation results show that compared to the existing benchmark algorithms, the trajectory optimization of UAV based on the probabilistic LoS channel model can significantly improve the secrecy rate of the system, and the proposed real-time optimization algorithm for speed and user scheduling can further improve the secrecy rate performance. [ABSTRACT FROM AUTHOR]

High-quality community detection for large-scale complex networks usually depends on the topology of the graph, which used to divide the node set. However, real-world networks usually have noisy and cluster-independent links, which may cause the model to divide the nodes from different clusters together. This paper proposed a algorithm called graph reconstruction based community detection (GRCD). This method could handle community detection in large-scale complex networks. GRCD firstly deleted the connected edges between communities to reconstruct the community structure of the original graph. Subsequently, GRCD regarded the network as a social system, aiming to reveal the community in a more intuitive way. This paper proposed an efficient community detection strategy : a community organization generation strategy based on discourse power. Extensive experiments were performed on datasets of different sizes. The results show that GRCD can not only deal with large-scale networks, but also has strong competitiveness in the quality of its community division compared with several existing benchmark algorithms while maintaining high stability. [ABSTRACT FROM AUTHOR]

To improve the local mining and global search ability of quantum-behaved particle swarm optimization algorithm ( QPSO), this paper proposed an improved QPSO algorithm( DSQPSO). DSQPSO algorithm introduced the double strategies co-evolution to adjust the particle position update formula. Firstly, in order to fully reflect the advantage of individual exploration and the characteristic of collective guidance, this paper put forward two kinds of ideas of attraction points to achieve better integration of individuals and the swarm as well as information exchange. Secondly, it redefined the search scope of the particle through considering the relationship between the optimal average position and the global optimum and individual's historical optimum respectively. Moreover, in the iterative process, DSQPSO used the random perturbation mechanism to adjust the global optimal position in order to help the diversity of the swarm to be preserved. Based on 18 test functions, this paper compared DSQPSO with PSO, QPSO, RQPSO and LQPSO in convergence accuracy and robustness. Furthermore, in terms of the optimization results, it compared the improved algorithm with eight intelligent algorithms on two practical engineering optimization problems. Experiments indicate that whether in benchmarking or in engineering application, DSQPSO has obvious advantages in calculation precision and convergence effect. [ABSTRACT FROM AUTHOR]

Aiming at the problems that the sparrow search algorithm (SSA) is prone to fall into local optimum and the optimization accuracy is low in the optimization process, this paper proposed a hybrid strategy improved sparrow search algorithm (MSSA). Firstly, in order to enable individual sparrows to fully search in the search space and increase the accuracy of algorithm optimization, it introduced an archiving stage in the algorithm optimization process to receive the residual position information that might be captured by sparrow producers when they moved to the safe area. Secondly, in the iterative process of the algorithm, it performed an adaptive neighborhood search operation on the current optimal individual, and fully explored the location information around the high-quality individual to enhance the algorithm's ability to jump out of the local optimum. This paper used 9 benchmark functions to evaluate the MSSA with SSA, and other four improved SSA, which were chaotic sparrow search optimization algorithm (CSSOA), mixed strategy improved sparrow search algorithm (MSSSA), improved sparrow search algorithm(ISSA), and enhanced sparrow search algorithm (ESSA). Experiment result illustrates that MSSA can achieve better convergence accuracy and stability on nearly 80% of the benchmark functions, and MSSA is also ranked first in the Friedman test. This paper also applied MSSA to optimize wireless sensor network( WSN) coverage in an obstacle environment. Compared with other five compared algorithms, MSSA can increase the coverage rates of WSN up 9. 77%, 4. 25%, 6. 62%, 3. 02%, and 7. 38%, respectively. [ABSTRACT FROM AUTHOR]

Aiming at the problem of production imbalance caused by experience-based equipment purchase strategy in hybrid flow shop, this paper proposed a barrel-greedy algorithm. Under the constraint of fixed equipment cost, this algorithm took the fastest production cycle of the production line as the goal, and used the short board idea of barrel effect to identify the bottleneck process, and on this basis, it introduced the greedy idea for the inconsistent characteristics of the bottleneck processes of multiple products in the production line. Then, comparing the solution results of different algorithms based on the actual production line case, the barrel-greedy algorithm has certain advantages in solving quality and efficiency compared with exhaustive search algorithm and improved genetic algorithm. Finally, taking the actual production line as the background, this paper used Plant Simulation to compare the production line before and after transformation, and verifies the feasibility and effectiveness of the algorithm in practical production. [ABSTRACT FROM AUTHOR]

The basic marine predators algorithm ( MP A) has some drawbacks such as slow convergence speed, low precision, and easy to fall into local optima when solving complex optimization problems. In order to overcome these shortcomings, this paper proposed a planar-mirror reflection imaging learning-based MPA ( PRIL-MPA). In the early stage of the iteration, the PRIL-MPA introduced the strategy that the current global optimal individual guides other individuals in the group to search, so as to accelerate the convergence speed of the algorithm. In the later stage of the iteration, the PRIL-MPA introduced the planar mirror reflection imaging strategy to escape from the local optimization and improve the accuracy of the solution. On the one hand, a comparison of PRIL-MPA with four other algorithms on 12 benchmark test functions shows that the proposed algorithm achieves significant improvement in terms of the solution precision and convergence speed. On the other hand, this paper applied PRIL-MPA to solve 21 feature selection problems, which shows that the proposed algorithm can effectively remove redundant features and improve the accuracy of data classification. Compared with other algorithms, the performance of the proposed algorithm is more competitive. [ABSTRACT FROM AUTHOR]

Whale optimization algorithm is a new swarm intelligence optimization algorithm inspired by humpback whale hunting behavior, and its performance is far better than the traditional algorithms. In order to track the latest research results and promote the research in the field of swarm intelligence optimization algorithm, this paper firstly introduced the basic principle of whale optimization algorithm, briefly described its implementation steps, and compared and analyzed its pe1formance characteristics. In view of its shortcomings of slow convergence speed and low convergence accuracy, this paper summarized and analyzed the improved methods including other intelligent optimization algorithms, Levy flight strategy, chaos strategy, as well as their advantages and limitations. Then, it described its applications and effect in combinatorial optimization, image segmentation, data prediction, and so on. Finally, this paper summarized and prospected the future development trend. [ABSTRACT FROM AUTHOR]

Consensus algorithm based on credit has significant advantages in consensus efficiency and security, which has received great attention from academy and industry in recent years. This paper made a comparative analysis of the current consensus algorithms based on credit to provide reference for researchers to study in depth. Firstly, this paper systematically reviewed the state-of-the-art consensus algorithms based on credit, gave its development history, classification and core working principle, and summarized its credit calculation model and performance evaluation indicators. Secondly, it analyzed the creditbased consensus algorithms qualitatively and quantitatively, and pointed out their advantages and disadvantages. Finally, aiming at the problems of insufficient credit incentive and low integration with the consensus process in the state-of-the-art consensus algorithms, this paper proposed to optimize from the credit incentive based on game theory and designing efficient communication topology, and gave the future research direction. [ABSTRACT FROM AUTHOR]

SWIPT can effectively deal with the energy limitation problem of communication terminals, and IRS can assist in enhancing the efficiency of SWIPT. Therefore, to overcome the shortcoming of limited coverage of deploying a single IRS and further improve the time and spectrum resource utilization efficiency of SWIPT, this paper studied a double-IRS-assisted NOMA SWIPT system, where the beamforming vector of the transmitter, the phase shifts of each IRS, and the power splitting coefficients of the receivers were jointly optimized to maximize the minimum user rate. To solve the above non-convex optimization problem with highly coupled variables, this paper proposed an AO algorithm based on SDR and SCA techniques to solve it efficiently. The simulation results show that the double-IRS-assisted system can achieve a higher minimum rate than that of its single-IRS, which reveals the superiority of deploying double IRS, the effectiveness of the proposed algorithm, and the importance of jointly optimizing IRS phase shifts and power splitting coefficients in improving the user rate performance. [ABSTRACT FROM AUTHOR]

Aiming at the fully-connected single user millimeter-wave massive MIMO system, this paper proposed a hybrid precoding scheme based on an improved orthogonal matching pursuit algorithm with the goal of maximizing the achievable sum rate of the system. On the basis of the existing hybrid precoding based on the OMP algorithm, firstly, in view of the problem of too many iterations, with the inspiring of the idea of multi-step length, this paper obtained an analog precoding matrix by extracted from the array response set’s top columns equal to the number of RF chains. Secondly, in view of the high complexity of the inversion operation, this paper obtained the optimal digital precoding matrix by exploiting Hölder inequality and Schatten norm to approximate the formulated objective function. The simulation results show that the proposed modified OMP scheme effectively reduces the computational complexity, and the system performance is better when the gap between the number of data streams and the number of RF chains is small. [ABSTRACT FROM AUTHOR]

When applying the LANDMARC algorithm based on RFID for vehicle location in an indoor parking lot, the accuracy of vehicle positioning cannot be improved by increasing the number of reference tags or deploying reference tags uniformly and regularly, because the complex structure of the indoor parking lot and the influence of multi-path effects of wireless. This paper proposed a location algorithm based on virtual tag (LAVT). The algorithm got the neighbor region of the vehicle through location of the nearest neighbor tags, to finding the center of the circumcircle and calculate the circumcenter of the neighbor region as the insertion point of the virtual tag. This paper replaced the original nearest neighbor tag with the virtual tag, to reduce the size of the neighbor region, and made the new nearest neighbor tag closer to the vehicle to be located, and to calculate the position vehicle more accurately. The simulation experiments and results show that LAVT improves the location accuracy by 19.03% compared to the traditional algorithm. The LAVT algorithm has better applicability for vehicle positioning in indoor parking lot environment, meeting the basic requirement of vehicle positioning in indoor parking lot. [ABSTRACT FROM AUTHOR]

Aiming at the deficiency that K2 algorithm depends on the maximum number of parent nodes and node of order, this paper proposed an improved Bayesian network structure learning algorithm (MWST-CS-K2). The algorithm firstly obtained the maximum number of parent nodes by constructing the maximum support tree (MWST). Then it used the correlation degree and updated coefficient between variables to set rules for adding, subtracting and reversing edges. The paper used improved cuckoo algorithm to optimize the nest location, and applied the breadth first search strategy to search and traverse to get the node order. Finally, the paper used maximum number of parent nodes and the order of nodes as the input of K2 algorithm to get the final network. Experiments show that in the standard ASIA,SACHS and CHILD network data tests, the average correct edge ratio of MWST-CS-K2 algorithm reaches 97.3%, 87.7 % and 95.6% respectively. The learning effect is better than other corresponding comparison algorithms, and the network structure obtains the most similar to the standard network structure. [ABSTRACT FROM AUTHOR]

Aiming at the problems of too many traversed nodes and large turning angles in the path planning of the A“ algorithm, this paper proposed an improved A~ algorithm that could adapt to the scene map. By quantifying the map scene information and the distribution of obstacles introducing the influence of the parent node on the current node and increasing the weight of the heuristic function of the obstacle distribution rate,this paper further reduced the number of traversed nodes and improved the search speed. By adding turning penalty function, extended neighborhood priority search and redundant node smoothing strategy further optimized the path, it avoided redundant turns on the path and reduced the possibility of local optimal solutions on the path. Finally, the simulation test in the same map scene shows that the proposed algorithm can effectively reduce the number of traversed nodes, re- duce the total turning angle,improve the search speed,shorten the path distance and obtain the global optimal path. [ABSTRACT FROM AUTHOR]

AGV can execute material handling flexibly, accurately, and efficiently, and have been widely applied in flexible manufacturing workshops. A multi-load AGV can transport multiple workpieces at the same time and owns strong handling flexibility. When performing multiple transport tasks, the solution to the path planning problem is more difficult due to the increasing complexity and constraints. Aiming at the energy-efficient path planning problem for a multi-load AGV in a flexible manufacturing workshop, this paper established an AGV energy-efficient path planning model with energy consumption and transport distance as the optimization objectives. Furthermore, this paper proposed a model solution method integrating the modified Dijkstra algorithm and the non-dominated sorting genetic algorithm-Ⅱ (NSGA-Ⅱ). Finally, the case study verifies the energy-saving effect of the model and the validity of the solution method. [ABSTRACT FROM AUTHOR]

Aiming at the problems of large sampling area, small effective area, many redundant nodes and long pruning time when applying rapidly exploring random trees (RRT) algorithm to manipulator path planning, this paper proposed an efficient RRT path planning algorithm based on partitioned dynamic sampling strategy and repeated area node rejection mechanism. Firstly, this paper used PS-RRT to quickly plan the initial path of the manipulator end. Secondly, it detected the collision of the links when the manipulator followed the path in sections, and carried out the secondary planning of the collision section with arm constraints. Finally, it spliced the initial path and the second planned path, and then pruned the path. The simulation results show that the obstacle avoidance path planning strategy of the manipulator based on PS-RRT algorithm greatly reduces the number of invalid nodes and can efficiently plan the collision free path of the manipulator, which verifies the feasibility of the algorithm. [ABSTRACT FROM AUTHOR]

Although reinforcement learning shows good performance in game playing, system control and other fields, how to use a small number of samples to learn new tasks quickly is an urgent problem to be solved in reinforcement learning. At present, applying meta learning to reinforcement learning has been one of the most effective solutions, and the generated meta reinforcement learning has increasingly become a research hotspot in the field of reinforcement learning. To help researchers understand the field of meta reinforcement learning quickly, this paper sorted out the algorithms according to the literatures of meta reinforcement learning in recent years, summarized them into CNN-based meta-RL, context-based meta-RL, gradient-based meta-RL, hierarchical-based meta-RL and offline meta-RL and compared five types of algorithms. In addition, it briefly described the basic theories and challenges of meta reinforcement learning. Finally, this paper also discussed the future development of meta reinforcement learning based on the current research status. [ABSTRACT FROM AUTHOR]

The purpose of image stitching is to obtain a high-definition, seamless panoramic image. Existing methods rely on the accuracy of feature matching, which will misalign images and produce errors such as artifacts and distortions.This paper proposed a new unsupervised real scene image stitching network that can adapt to real scene stitching in the presence of moving targets, ensuring no loss of accuracy in the panorama. It included two networks of alignment and reconstruction, excluding the negative influence of moving targets and misleading regions on the transformation matrix through content branching, and optimizing image details by constraining the reconstruction process through edge branching to achieve high-definition and artifact-free stitching effects. The experimental results show that the method’s RMSE, PSNR, and SSIM reached 1.81, 26.56, and 0.85, respectively. The objective evaluation indexes are better than other classical algorithms overall, and the user research results also indicate that the method obtains higher definition of panoramic images. The method effectively accomplishes unsupervised image stitching in real scenes and can be generalized to stitching tasks in other scenes. [ABSTRACT FROM AUTHOR]

The method of detecting the whole tampered image increases many unnecessary calculations. In order to reduce the computational complexity and further improve the detection accuracy, this paper proposed a copy-move forgery detection method based on improved saliency map and local feature matching. Firstly, it combined the gradient of image to improve the saliency map, and separated the local salient regions containing high texture information of the image. Secondly, it only used SIFT（Scale Invariant Feature Transform） algorithm to extract feature points in this local area. Then, it adopted density clustering and two-stage matching strategy for images with low saliency, and adopted the strategy of superpixel segmentation and salient block feature matching for images with high saliency. Finally, it combined PSNR and morphological operations to locate the tampered area. Experiments on two public datasets show that the average detection time of this method is less than 10s, and the average detection accuracy is greater than 97%,which are better than the compared methods. The experimental results show that this method can greatly reduce the detection time, effectively improve the detection accuracy, and has good robustness to geometric transformation and post-processing operations. [ABSTRACT FROM AUTHOR]

Dynamic economic emission dispatch（DEED） problem in power system is a kind of high-dimensional multiobjective optimization problem with large-scale constraints. The traditional evolutionary algorithm is easy to fall into local optimization, and the distribution and convergence of the obtained Pareto frontier are poor. In this paper, it fully explore the clonal selection principle of immune system, and propose a hybrid immune multi-objective optimization algorithm（HIMOA）. The proposed algorithm takes the traditional evolutionary algorithm as the basic framework.Since the deficiency of falling local optimization for the high-dimensional decision variables optimization, the external archive update mechanism is improved to preserve the excellent individuals from previous generations, and the cloning and Gaussian mutation strategy is adopted to strengthen the local exploitation ability, forcing effectively the HIMOA to jump out of the stagnant search state. In order to cope with the large-scale constraints, designing the fine-turning output power step by step to improve the feasibility of the evolutionary population. In the numerical simulation experiment, taking a 10-unit system as a test example, and compares HIMOA with the famous algorithms MODE,NSGAII, IMOEA/D-CH, ADEA, MOHDE＿SAT, MONNDE. The results show that HIMOA can provide a better Pareto solution to the 10-unit system of the DEED problem, and the convergence and distribution of the Pareto frontier obtained are better than other algorithms. The box diagram of each evaluation metric shows that HIMOA has better statistical characteristics than other algorithms. [ABSTRACT FROM AUTHOR]

The spread of epidemics poses a significant threat to the entire human community. Therefore, it is critical to identify the sources of transmission quickly and take timely control measures. However, the diversity of epidemic transmission processes and information uncertainty makes it challenging to identify the sources of transmission quickly and accurately. This paper proposed a new algorithm for identifying transmission sources in a metapopulation network by combining the reverse infection algorithm and Markov chain theory. The algorithm first uses a Markov chain to initially estimate the time when a subpopulation is infected, and the infected subpopulation obtains its own identity information based on the infection time. Then, it traverses all subpopulations that obtain the identity information of the infected subpopulation and spreads the collected identity information of the infected subpopulation to all its neighbors. Finally, the spreading source of the metapopulation network can be inferred based on the temporal order in which all the identity information of the infected subpopulation is obtained. Simulation experiments conducted on real airports networks and artificial networks show that the accuracy of this algorithm is significantly improved compared to other algorithms, regardless of whether all or partial of the infection snapshots are known. This algorithm is well-suited for metapopulation networks such as aviation networks and is also useful for real-world epidemic transmission tracing and control. [ABSTRACT FROM AUTHOR]

Increased number of Automated Guided Vehicles (AGVs) on automated container terminals leads to more frequent conflicts. This paper proposed an improved Conflict Based Search (CBS) algorithm. The bottom layer used the A* algorithm based on Manhattan distance, and the top layer combined the binary tree principle to build conflict trees to avoid conflicts between AGVs. With the objective of minimizing the total path length of AGVs between the shore bridge and the yard, the grid method used to developed the AGVs road network mode. Considering the point conflict and edge conflict among AGVs, the multi-AGVs conflict-free path planning problem in automated terminals statuted as a multi-agent path planning problem. The experimental results show that the proposed algorithm shortens the total path length and increases the computational speed with a guaranteed blockage rate of 0%, which verifies the effectiveness of the algorithm. [ABSTRACT FROM AUTHOR]

Aiming at the rescheduling problems of hybrid flow shop with rush order insertion, this paper proposed a hyper-heuristic genetic algorithm based on the two-layer coding. Aiming at the double-decision characteristics of order sort and machine selection in the hybrid flow shop, this algorithm designed a two-layer coding scheme in the low level. Each individual represented both order sort and machine selection information, and corresponded to a unique scheduling solution. Then the low level proposed 12 kinds of sorting and selection heuristics for iterative optimization of individuals. The high level of the algorithm used an adaptive genetic algorithm to determine the operation combination of order sort heuristic and machine selection heuristic and the sort of execution of each combination. And it designed an adaptive mutation operator to optimize the effectiveness of the algorithm. The results of large-scale data experiments show that the proposed algorithm has good solving quality and efficiency. [ABSTRACT FROM AUTHOR]

This paper proposed an improved RRT（Rapidly-Explorative Random Tree） algorithm to solve the problem that the traditional target offset RRT was easy to fall into local optimum in the environment where there were many obstacles such as yarn racks, placing platforms and other packages during the package handling process. The collision detection model was established by geometric envelope method, and the distance coefficient g was added to keep a safe distance between the end of the manipulator and the obstacle; A random action selection strategy was proposed to select the expansion action before each expansion of the tree; A weakening target offset strategy was proposed to offset the extension direction according to the position of Xgoal relative to the Xnear and Xrand line; According to the vertical distance limit method and cubic spline interpolation, the initial path was optimized, and finally a smooth path was obtained. Through simulation comparison with RRT algorithm, M-RRT algorithm, RRT algorithm with added gravity coefficient and Improved RRT * algorithm, the maximum decrease in path length was 23.3%, the maximum decrease in time was 82.5%, and the distance from obstacles was always more than 50 mm. The results show that the algorithm improves the efficiency and safety of the manipulator handling. [ABSTRACT FROM AUTHOR]

Weakly supervised temporal action localization (WTAL) aims to locate the start and end boundaries of action instances and identify the corresponding actions. Although the existing methods have made great progress, there are still problems of incomplete localization and missing detection of shorter motions. To this end, this paper proposed a localization method of feature mining and region enhancement (FMRE) Firstly it calculated the similarity score between video segments through the base branch, and aggregated the context information with this score to obtain a more differentiated segment classification score, further realizing the complete positioning of the action. Then, it added a enhance branch to dynamically up-sample action proposals with a shorter duration in the initial localization along the temporal dimension, and then utilized the multi-head self-attention mechanism to explicitly model the temporal structure between action proposals, which facilitated action localization with temporal dependencies and prevented missing detection of short actions. Finally, it constructed pseudo-labels of mutual supervision between the two branches to gradually improve the quality of action proposals during the training process. The algorithm achieves mAP of 70.3% and 40.7% detection performances on the THUMOS14 and ActivityNet1.3 datasets respectively, which proves the effectiveness of the proposed algorithm. [ABSTRACT FROM AUTHOR]

Aiming at the problems of blurring edge contours and loss of texture details after fusion of conventional CT and MRI medical images, this paper proposed an image fusion method based on non-subsampled contourlet transform domain combined with phase consistent rolling guidance filtering (PCRGF) and improved parameter-adaptive dual channel pulse coupled neural network (PCNN) .Firstly, it used PCRGF to enhance the CT source images to improve the definition of bone contour structure. Then, it applied NSCT to decompose enhanced CT and MRI source images to obtain the high and low frequency sub-bands.Fusion of low frequency sub-band used an improved parameter-adaptive dual channel pulse coupled neural network, which significantly improved the blurring of texture details in soft tissue.It used a weighted summation modified Laplace (WSML) algorithm to fuse the high frequency sub-bands, which enhanced the fused image with more details, textures and other information in the source images. Finally, it used the inverse NSCT transformation to reconstruct the fused image.The results of five groups of comparison experiments show that the objective evaluation indexes of AG,CC,SF,MSE and CEN are improved by 13.30%,6.71%,4.40%,40.23% and 19.16%,indicate that this method performs better in enhancing the texture details, edge contours, structural similarity and image pixels of the source image. [ABSTRACT FROM AUTHOR]

Energy efficiency is a very important issue in wireless sensor networks. To address the problem of increasing energy consumption caused by repeating clustering, this paper proposed a novel energy-efficient routing algorithm for wireless sensor networks, uneven clustering routing algorithm based on cluster tree (UCCT), which is a two-stage algorithm. In the first stage, the algorithm divided network area into two regions with different size. For each region, the algorithm used K-medoids to compute the center nodes in its node set, set each center node obtained as an initial cluster, and calculated the relay energy consumption for each cluster. Determine the routing of inter-cluster communication. In the second stage, the algorithm used linear programming method to add non-center nodes to the initial clusters for forming corresponding new clusters, and selected the node with highest residual energy as the cluster head in its corresponding cluster. The trait of the algorithm is that it does not need to repeat clustering. The simulation results show that for a given wireless sensor network, the network lifetime and the throughout obtained by Algorithm UCCT are 10.97% and 13.09% more than those obtained by the state-of-the-art existing algorithm ANRB, respectively. [ABSTRACT FROM AUTHOR]

This algorithm considers the tap delay channel model in 5G protocol, and does not consider the influence of SNR on the log-likelihood ratio of the received sequence for the segmented cyclic redundancy bit adaptive (SCADSCL) polarization decoding algorithm. This paper proposes the post-processing (PSCAD-SCL) decoding algorithm for SCAD-SCL. The algorithm determines the number of constant and unreliable log-likelihood ratio used to improve the reliability setting through simulation, and flips and appropriately enlarges the unreliable log-likelihood ratio to improve the bit error rate performance. The simulation results show that the bit error rate of PSCAD-SCL is better than the original SCAD-SCL decoding algorithm in the signal-to-noise ratio of 1～3dB. When the bit error rate is 10-4, the performance of PSCAD-SCL algorithm is about 0.3dB higher than that of SCAD-SCL algorithm. The proposed algorithm can improve 5G transmission performance. [ABSTRACT FROM AUTHOR]

Aiming at the problem of low accuracy and poor robustness of Visual Simultaneous Localization and Mapping (VSLAM） in dynamic environment, This paper proposed an adaptive Dynamic SLAM（AD-SLAM）. The scene dynamic classification front-end based on epipolar geometry constraint perceives the dynamic changes of the working environment in real time. The dynamic feature culling in low dynamic environment based on geometric constraints and moving probability and the dynamic target processing in high dynamic environment based on semantic segmentation eliminates moving objects. Experimental verification on the computer vision dataset TUM shows that the proposed method can improve the accuracy and robustness of localization in the mapping process of mobile robots while ensuring the real-time performance of the algorithm. [ABSTRACT FROM AUTHOR]

Aiming at the problem of instability caused by the randomness of node starting order and updating labels in the label propagation algorithm, this paper proposed a new label propagation algorithm for detection of complex network community (Density Peaks and Node Similarity, DPNS-LPA）. It includes the determination of community center and label propagation of peripheral nodes. Firstly, the method defined the local similarity index of nodes which was characterized by the hub depressed index, Jaccard index and the structural characteristics of nodes with degree 1,and this index was used to measure the distance between nodes and solve the random selection of the same maximum label. Then introduced the improved density peak clustering algorithm to find community centers and determined the number of communities. Finally, obtained the final community division result based on the label propagation of the community center and peripheral nodes. Experimental results on artificial networks and real networks show that the standardized mutual information, modularity and D-Score index values are superior to the comparison algorithms. The proposed algorithm can effectively discover community structure in complex networks, and has higher robustness. [ABSTRACT FROM AUTHOR]