Search

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]

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]

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]

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 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]

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]

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]

Copyright of Application Research of Computers / Jisuanji Yingyong Yanjiu is the property of Application Research of Computers Edition and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Application Research of Computers / Jisuanji Yingyong Yanjiu is the property of Application Research of Computers Edition and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Most of the existing image tampering detection methods are only for a certain tampering method, and there is a problem that the detection accuracy of the tampered area boundary is not high. In this regard, this paper proposed a U-shaped network based on dual-stream encoder-decoder architecture for image tampering. Firstly, the method used the skip connection between the encoder and the decoder to fuse the low-level and high-level features in the tampered image, and used the atrous convolution and CBAM attention mechanism to fuse the features output by the encoder, so that the network had better localization performance for tampered regions of different scales; Secondly, in order to improve the network’s detection accuracy of the boundary of the tampered area, this algorithm used the image morphological method to make a tampered boundary dataset; Finally, it used multiple loss functions to optimize the performance of the network simultaneously, namely it used cross-entropy and root-mean-square loss functions to measure the tampered region loss and tampered boundary loss of the prediction graph respectively. The experimental results on 4 public datasets: CASIA, Columbia, NIST16, Coverage show that the method proposed in this paper can effectively detect the tampering area of the fake image with splicing and copy-paste tampering methods, and output pixel-level tampering region location map. Compared with other mainstream tampering detection methods, the proposed method achieves the highest AUC values on the CASIA and Columbia dataset and the highest F1 values on the Columbia dataset. [ABSTRACT FROM AUTHOR]

Aiming at the problems of small key space and low security of single chaotic system in encryption, this paper pro-posed a dynamic audio encryption algorithm for image carrier and multi-chaotic system. Firstly,it blocked the plaintext audio to improve the efficiency of the algorithm, generated advanced keys from initial keys and plaintext audio feature values, significantly increasing the key space. This paper designed a random number generator that combined various chaotic systems, and verified its randomness through the NIST sp800_22 randomness test. It transferred the plaintext audio information to the feature matrix P to obtain the audio image. Finally, it obtained the encrypted audio image and encrypted audio through the cyclic remainder scrambling algorithm and diffusion. Simulation experiments and performance tests show that the encryption algorithm has large key space, strong key sensitivity, and uniforms distribution of encrypted audio energy. It has strong anti-attack performance,robustness and efficient encryption efficiency. [ABSTRACT FROM AUTHOR]

To address the issues to jointly represent the global and local information and refine the boundary in the salient object detection, this paper proposed a hierarchical boundary guided multi-scale Transformer for salient object detection. Specifically, it first utilized Transformer to jointly represent the global information, while the local feature was obtained via self-attention mechanism in the shallow layers. Then, it introduced Tokens-to-Token to extract the multi-scale features, smoothing the process of alternating the scale features simultaneously. Furthermore, this paper proposde a strategy of hierarchical boundary learning to guide the refinement of salient object boundary, improving the precise prediction of salient object boundary. The experimental results demonstrated that the proposed algorithm outperforms the eight popular salient object detection algorithms on the four public benchmarks. It evaluated the effectiveness of the proposed model and boundary guided strategy via ablation studies. [ABSTRACT FROM AUTHOR]

In order to solve the problem of low accuracy of 6D pose estimation for textured models under occlusion, this paper proposes an end-to-end 6D pose estimation algorithm based on local feature representation. Firstly, this paper proposes a Spatial and Coordinate Attention mechanism to obtain accurate localization information. A YOLOv5-CBE detection network forms by adding the attention mechanism to the backbone network and introducing a weighted Bidirectional Feature Pyramid Network in the detection layer. The Precision, Recall and mAP@0.5 of YOLOV5-CBE algorithm rise by 3.6%, 2.8% and 2.5% respectively, and the coordinate error of local feature center point decreases by 25% at most. Secondly, the YOLOv5-CBE network detects the local feature key points and calculates 6D pose of the model with 3 D Harris key points by Singular Value Decomposition, and the algorithm can guarantee 2D reprojection Accuracy and ADD Accuracy above 95% with 70% occlusion, which has a strong robustness. [ABSTRACT FROM AUTHOR]

Existing task offloading strategy usually makes offloading decision within one time slot without considering the internal relationship between multiple offload time slots, so they cannot be offloaded according to the actual needs of tasks. To solve this problem, this paper proposed a task secondary application offloading strategy based on deep Q network（DQN-TSAO）. Firstly, this paper introduced a three-layer of cloud-edge-end architecture that supports task secondary application offloading, and established priority model, delay model and energy consumption model for task offloading. Second, aiming at minimizing system energy consumption, the energy consumption optimization problem is transformed into a Markov decision process problem of maximum cumulative offloading reward. Finally, DQNTSAO algorithm can extract the task offload characteristics of each time slot, which enabled the task to obtain the optimal offloading decision of multiple time slots in the continuous interaction with the environment. Simulation results validated that DQN-TSAO algorithm can effectively reduce the total energy consumption of the system in a period of time. [ABSTRACT FROM AUTHOR]

After an emergency outbreak, it is extremely hard to obtain reasonable solutions for emergency decisions facing information asymmetries. This paper aims at the problem of simultaneous deciding locations of emergency resource centers and the delivery paths in a scenario with uncertain demand. Firstly, the paper introduced the triangular fuzzy number to depict the fuzzy demand and proposed an emergency resource center location-routing model based on the fuzzy demand; then the algorithm formed the high-level strategy by defining the states, actions, and rewards in Q learning; finally, the paper presented a Q-learning based hyper-heuristic by encapsulating the low-level heuristic operators with a new architecture. The numerical experiments verify the effectiveness of the algorithm, meanwhile showing the feasibility of the model and algorithm in practical applications by a case study. [ABSTRACT FROM AUTHOR]

In reality, the data generated in many fields usually have multiple classes and are imbalanced. In multi-class imbalance classification, problems such as class overlap, noise and multiple minority classes reduce the capability of classifiers, and effective solution of multi-class imbalance problem has become an important research topic in the field of machine learning and data mining. Based on the recent literature on multi-class imbalance classification methods, this paper analyzed and summarized both data preprocessing and algorithm-level classification methods, and conducted a detailed analysis of all algorithms in terms of advantages, disadvantages and data sets. The data preprocessing methods introduced oversampling, under-sampling, hybrid sampling and feature selection methods to compare the performance of the algorithms using the same datasets. In addition, the algorithm-level classification methods described and analyzed base classifier optimization, ensemble learning and multi-class decomposition techniques. Finally, this paper summarizes the future development directions of the multi-class imbalanced data classification research field. [ABSTRACT FROM AUTHOR]

Copyright of Application Research of Computers / Jisuanji Yingyong Yanjiu is the property of Application Research of Computers Edition and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

At present, the research on combining deep learning with Visual SLAM(Simultaneous Localization And Mapping) to construct indoor 3 D pointcloud semantic map is in full swing. In order to solve the problems that traditional Visual SLAM networks have low accuracy and poor speed and lack semantic information, this paper proposed a novel RGB-D semantic segmentation network. The network uses the depth information which less affected by the light in indoor scenes to improve the accuracy of segmentation, and meanwhile designs the lightweight multi-scale residual module(MRAM) and Atrous Spatial Pyramid Pooling(ASPP) module to lightweight the segmentation network and improve the segmentation accuracy. Firstly, ORB-SLAM2 network screens the input image sequences to obtain keyframes. Then, the keyframes go into the proposed semantic segmentation network to get the 2 D semantic label, and then map the 2 D semantic information to 3 D pointcloud space. Finally, the method uses the Bayesian algorithm to update the 3 D map to obtain the globally consistent 3 D pointcloud semantic map. The experiments adopt NYUv2 dataset to verify the performance of semantic segmentation network, and adopt TUM dataset construct pointcloud semantic map. The results show that the performance and speed of the semantic segmentation network in this paper are better than the existing models, and the combination of semantic segmentation network with visual SLAM can meet the requirements of constructing 3 D dense semantic pointcloud map accurately and quickly. [ABSTRACT FROM AUTHOR]

Aiming at the problems of low detection accuracy in massive unbalanced data and poor model generalization ability caused by data heterogeneity in traditional anomaly detection methods in IoT scenarios, this paper proposed an adversarial dual-coding anomaly detection network based on federated learning(GB-AEnet-FL). Firstly, this paper proposed an active feature distribution learning algorithm based on abnormal data, which actively learns the potential feature distribution of data, expands abnormal data through data reconstruction, and balances the proportion of positive and negative samples. Secondly, this paper introduced an adversarial training mechanism in the latent feature layer adding consistency enhancement constraints and shrinkage constraints to improve the accuracy of feature extraction. Finally, this paper designed a federated learning algorithm based on dynamic model selection which compares the confidence scores of the local model and the global model, dynamically selects part of the federated bodies to participate, accelerates the aggregation of models, and protects user privacy to a certain extent. Validated on four different datasets, the results show that the proposed algorithm is better than the traditional algorithm in detection accuracy, and the generalization ability is improved accordingly. [ABSTRACT FROM AUTHOR]

To solve the problems of low convergence accuracy, slow convergence speed and easy to fall into local optimum of traditional particle swarm algorithm, this paper proposed an improved particle swarm algorithm with multistrategy fusion. Firstly, in order to accelerate the convergence speed of free particles, the improved algorithm used a method of updating the position of free particles based on the midperpendicular algorithm. secondly, the improved algorithm designed a strategy of generating exploding particles near the optimal particles to enhance the optimizationseeking accuracy and optimization-seeking speed of the algorithm, and the improved algorithm also designed a particle velocity updating strategy relying only on the global optimal particle position to accommodate the first two strategies. Finally, The algorithm also used the inertia weights and particle position update methods of the simplified particle swarm optimization algorithm based on probabilistic hierarchy. This paper designed a few comparison experiments with other five improved particle swarm algorithms, and the results show that the improved algorithm in this paper has a greater advantage and better performance whether dealing with low-dimensional problems or high-dimensional problems. [ABSTRACT FROM AUTHOR]

Multiple random empirical kernel learning machine(MREKLM) selects a small number of samples to construct the empirical feature space, but does not take into account the distribution of data when projecting, and takes a long time to select samples. In order to utilize the distribution information of samples, this paper introduced the intraclass dispersion matrix, and proposed an intra-class variance based multiple empirical kernel learning(ICVMEKL), which enabled samples to take into account the intra-class information when projecting. The method enhanced the classification boundary and improved the classification accuracy. Further, in order to reduce the selection time of samples, this paper proposed an improved ICVMEKL(ICVMEKL＿I) based on locality-sensitive hashing algorithm by using the border point extraction based on locality-sensitive hashing(BPLSH) to select samples, so that the samples for constructing the empirical kernel no longer need to be obtained from the candidate set, and the method reduced the training time. Experiments on multiple datasets show that ICVMEKL can effectively improve the accuracy, ICVMEKL＿I can significantly reduce the training time, both of which show good generalization performance. [ABSTRACT FROM AUTHOR]

The shortest path tour problem(SPTP) aims to determine the shortest path between two nodes. In addition, the path must pass through multiple disjoint node subsets in a given order. This paper proposed the specific decomposition method for the ripple-spreading algorithm(RSA) to solve the SPTP. The RSA simulates ripple propagation patterns on the water surface and establishes connections among subproblems, which reduces computational redundancy compared to other decomposition methods. This paper adapted the RSA to make it solve the SPTP with multiple sources and destinations while maintaining time complexity. Comparative experiments on various network topologies show that the RSA ensures optimality and outperforms other algorithms in computational efficiency. The efficiency of the RSA when solving the SPTP with multiple sources and destinations makes it can provide solutions to real-world problems efficiently and demonstrates its application values. [ABSTRACT FROM AUTHOR]

The immutability of traditional blockchain limits the development of blockchain technology, research on modifiable blockchain is still in its infancy, many schemes still have many deficiencies in system efficiency and security. To deal with these problems, firstly, this paper proposes an improved blockchain data structure to make it suitable for modifiable functions; Secondly, a master private key synthesis algorithm is designed using homomorphic encryption technology to ensure the security of the private key used for data modification on the chain during the synthesis process; At the same time, a matching mechanism is designed to reduce the communication amount in the private key synthesis process; Finally, an auditing method for modification requests is designed to ensure the rationality and security of auditing modification requests. The experimental results show that the scheme in this paper not only has the characteristics of decentralization, but also improves the system security and communication efficiency compared with other schemes. [ABSTRACT FROM AUTHOR]

In order to improve the accuracy and efficiency of the feature point matching, this paper proposed a novel feature point matching algorithm in terms of vision and inertial measurement unit（IMU） fusion. Firstly, the algorithm calculated the point diffusion function using the motion information of IMU to remove motion blur, and improved the feature point matching rate. Secondly, based on LK（Lucas-Kanade） optical flow method, this paper introduced gradient error and uses L1 parametric to simulate sparse noise. Furthermore, the feature point position by using IMU is the initial value of the algorithm, and then this paper used BB（Barzilar-Borwein） step to improve the efficiency of the algorithm. Finally, the comparison experiments show that the efficiency and accuracy of the algorithm are better than the LK optical flow method. Especially, the algorithm improves the localization accuracy and robustness of the VINS-Mono framework on the dataset EuRoC. [ABSTRACT FROM AUTHOR]

Aiming at the shortcomings of the basic Gravity search algorithm（GSA）, such as prone to premature maturity, easy to fall into local optimum, and lack an effective acceleration mechanism, this paper proposed a GSA（IABHGSA） based on the improved adaptive black hole mechanism. The algorithm used the improved Tent mapping to initialize the population, which makes the distribution of the initial population more random, uniform and traversal, and it enhanced the global exploration capability of the algorithm; The algorithm introduced an improved adaptive black hole mechanism and selected the position update strategy, according to the evolution of the particles, which makes the position update more reasonable, Effectively reduce the possibility of particles falling into local optima; Through the optimal and worst particle update strategy based on learning ideas, enhanced the algorithm’s ability to escape from local optima and improved the algorithm’s optimization speed; The algorithm introduced group migration to provide effective accelerated convergence mechanism for the algorithm. Finally, this paper selected 8 benchmark functions to test IABHGSA and compared with the experimental results of related algorithms, the results show that IABHGSA has better optimization performance. [ABSTRACT FROM AUTHOR]

The problem of ineffective coordination between adjacent intersections of urban trunk roads due to the lack of information interaction, which leads to inefficient operation of trunk roads, this paper proposed a multi-objective collaborative optimization model of adjacent intersections of urban trunk roads under V2 X environment. The entry point was to obtain traffic volume and speed characteristics in real-time with V2 X technology. This paper took the traffic load as the key parameter. Weighting measurement based on different lane functions. At the same time, this paper introduced comfort and travel time as the synergistic regional optimization parameters, and used their weighted amounts as the comprehensive evaluation indexes of the model. Then this paper constructed a multi-objective collaborative optimization model for adjacent intersections of urban trunk roads. Finally, in order to verify the effectiveness of the model, using the NSGA-II algorithm simulated the examples to obtain the Pareto frontier of the optimization objective. The analysis results show that: The combined traffic load of key areas is reduced by about 19.9%, and the speed variation rate of synergistic regional trunk road traffic is reduced by about 28.37% and the travel time is reduced by about 3.46%, which can effectively improve the efficiency of urban trunk road traffic. [ABSTRACT FROM AUTHOR]

This paper proposed an end-to-end deep reinforcement learning framework to improve the efficiency of solving the Multi-Depot Vehicle Routing Problem（MDVRP）. There is a novel formulation of the Markov Decision Process（MDP） for the MDVRP, including the definitions of its state, action, and reward. Then, this paper exploited an improved Graph Attention Network（GAT） as the encoder to perform feature embedding on the graph representation of MDVRP, and designed a Transformer-based decoder. Meanwhile, this paper used the improved REINFORCE algorithm to train the proposed encoderdecoder model. Furthermore, the designed encoder-decoder model is not bounded by the size of the graph. That is, once the framework is trained, it can be used to solve MDVRP instances with different scales. Finally, the results on randomly generated and published standard instances verify the feasibility and effectiveness of the proposed framework. Significantly, even on solving MDVRP with 100 customer nodes, the trained model takes only two milliseconds on average to obtain a very competitive solution compared with existing methods. [ABSTRACT FROM AUTHOR]

In order to overcome the challenges of policy learning in Multi-Agents Systems（MASs）, such as the unstable environment and the interaction of agent decisions, this paper proposes a method named Observation Relation Extraction（ORE）, which uses a complete graph to model the relationship between different parts of each agent’s observation, and takes advantage of the attention mechanism to calculate the importance of the relationship between different parts of each agent’s observation. By applying the above method to multi-agent reinforcement learning algorithms based on value decomposition, this paper proposes multi-agent reinforcement learning algorithms based on observation relation extraction. Experimental results on StarCraft Multi-Agent Challenge（SMAC） show the proposed algorithms with ORE leads to better performance than the original algorithms in terms of both convergence speed and final performance [ABSTRACT FROM AUTHOR]

The homology analysis of diffusion results aims to identify which historical diffusion results were produced by the same set of diffusion sources. This paper uses Bernoulli Mixture Model to solve this problem: The diffusion results generated by the same group of sources correspond to the same Bernoulli component, and the parameters of the corresponding Bernoulli component reflects the arrival probability of the sources’ influence at each point. Then the log-likelihood function is constructed based on the model and the observed data. To determine the results of homology analysis, the Bernoulli parameters in the log-likelihood function are calculated through using the EM algorithm. A large number of experimental results verify that compared with the traditional clustering algorithm, the algorithm in this paper can get higher accuracy of the homologous clustering. That is to say, the algorithm in this paper can perform homology analysis on the propagation result data more efficiently and accurately. [ABSTRACT FROM AUTHOR]

Aiming at the problem that it is difficult to take into account both obstacle avoidance and formation when multi-AUV system plans path in unknown environment, this paper proposed a multi-AUV cooperative obstacle avoidance method based on leader-follower and behavior. First, this paper designed a local path planning method for AUV by constructing the evaluation function of collision risk and deviation from the target; on this basis, combined with formation control method, this paper designed different behaviors and behavior selection patterns for leader and followers respectively. The semi-physical simulation experiment results show that the algorithm can realize the cooperative obstacle avoidance of multi-AUV system in unknown environment, and the formation deviation and recovery time are better than traditional multi-robot obstacle avoidance algorithms. Experimental results verify the feasibility and effectiveness of the algorithm. [ABSTRACT FROM AUTHOR]

This paper investigated the fault detection problem in finite-frequency domain for nonlinear networked systems under stochastic cyber-attacks. To save limited network resource, this paper introduced a novel dynamic event-triggered scheme. Firstly, under the consideration of fault sensitivity and disturbance robustness, the paper converted the addressed fault detection problem into an auxiliary H-/Ｈ∞ filtering problem by augmenting the states of the original system and the fault detection filter. Taking sector bounded nonlinearity and stochastic cyber-attacks into consideration, the design of Hperformance index included the frequency characteristics of fault signals. Combined with finite-frequency input characteristics, the paper proposed the joint design algorithm for fault detection filter and dynamic event-triggered scheme under the finite-frequency fault input. Finally, a simulation example of stirred tank reactor system verified the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

Aiming at the problems that the Raft algorithm cannot resist the attacks of Byzantine nodes and the logs are easy to tamper with, this paper proposes an RB-Raft (Resist Byzantine-Raft) algorithm that resists Byzantine nodes. Firstly, this paper uses the method of hash chain to iteratively hash each log. At the same time, verification of the log through the dynamic verification mechanism, so that the malicious behavior of the leader node has a certain fault tolerance rate, which solves the problem of log forgery and verification. Secondly, this paper proposes a "Legacy" mechanism based on threshold encryption, which makes it legal for Candidate nodes to pull votes. This mechanism can prevent Byzantine nodes from randomly the attack of pulling votes to replace leader nodes, and solves the problem that Byzantine nodes affect the system consistency. The experimental results show that the proposed RB-Raft algorithm has the ability to resist Byzantine nodes, and its log recognition rate can reach 100%. At the same time, compared with PBFT, the consensus latency of the algorithm in this paper is reduced by 53.3%, and the throughput is increased by 61.8%. The algorithm proposed in this paper is suitable for consensus in untrusted consortium chains. [ABSTRACT FROM AUTHOR]

Copyright of Application Research of Computers / Jisuanji Yingyong Yanjiu is the property of Application Research of Computers Edition and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Application Research of Computers / Jisuanji Yingyong Yanjiu is the property of Application Research of Computers Edition and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Application Research of Computers / Jisuanji Yingyong Yanjiu is the property of Application Research of Computers Edition and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Application Research of Computers / Jisuanji Yingyong Yanjiu is the property of Application Research of Computers Edition and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Application Research of Computers / Jisuanji Yingyong Yanjiu is the property of Application Research of Computers Edition and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

In unmanned aerial vehicle Ad hoc network (UANET), increasing the network size will increase the average number of hops between nodes, making network management and routing protocol operation more difficult. Clustering structure can be used to optimize network management and improve network scalability. This paper proposed a fast and stable weighted clustering algorithm to address the instability and poor robustness of cluster structures caused by the high mobility of drones. Compared with existing weighted clustering algorithms, this algorithm improved the selection of four indicators: link retention rate, node degree and relative speed. It proposed an efficient cluster maintenance mechanism to address the cluster oscillation caused by cluster head node disconnection in battlefield and emergency scenarios. Finally, it verified the performance of this algorithm through simulation. The results show that compared with existing improved weighted clustering algorithms, this algorithm can effectively reduce clustering time, and quickly recover in the event of cluster head nodes dropping, making it more suitable for network deployment in complex environments. [ABSTRACT FROM AUTHOR]

This paper proposed a parallel deep forest algorithm based on Spark and NRSCA strategy (PDF-SNRSCA), aiming to address several issues encountered by parallel deep forest algorithms in big data environments, such as excessive redundancy and irrelevant features, low utilization rate of features at both ends, slow model convergence speed, and low parallel efficiency of cascading forests. Firstly, the algorithm proposes a feature selection strategy (FSNRS) based on neighborhood rough sets and fisher score, which measures the correlation and redundancy of features to effectively reduce the number of redundant and irrelevant features. Secondly, it proposed a scanning strategy based on random selection and equidistant extraction (S-RSEE) to ensure that all features are utilized with the same probability and solve the problem of low utilization rate of two ends in multi-scanning. Finally, combining with the Spark framework, the algorithm realized the parallel training of cascading forests, and it proposed a feature filtering mechanism based on the importance index (FFM-II) to balance the dimensions of enhanced class vectors and original class vectors, thereby accelerating the model convergence speed. Meanwhile, the algorithm designed a task scheduling mechanism based on SCA (TSM-SCA) to redistribute tasks and ensure load balancing in the cluster, which solves the problem of low parallel efficiency of cascading forests. Experiments show that the PDF-SNRSCA algorithm can effectively improve the classification performance of deep forests and greatly enhance the efficiency of parallel training of deep forests. [ABSTRACT FROM AUTHOR]

In order to solve the problems of large number of parameters and high GPU resource cost in binocular vision stereo matching method based on neural network in robot and unmanned driving fields, this paper proposed a multi-scale aggregation stereo matching method. Firstly, this paper proposed a multi-scale feature extraction network to obtain richer features without changing the resolution by using dilated convolution, and introduced the attention mechanism was. Then, features at different resolutions were cross-fused to improve the feature information. Secondly, the acquisition method of cost volume was changed, the cost volume was obtained by aggregation at low scale, and continuously combined the high-scale similar information to update iteratively, and cross fused multiple cost volumes to obtain the final cost volume. Finally, combined with the refinement module of attention mechanism, the outliers and discontinuous regions in the initial disparity map are corrected to obtain the final disparity map. Experimental results show that the algorithm can run under low parameter number and low cost GPU resources, and obtain good matching accuracy. [ABSTRACT FROM AUTHOR]

Rain streaks can seriously degrade the quality of captured images and affect subsequent computer vision tasks. In order to improve the quality of rainy images, this paper proposed a single-image deraining algorithm based on Transformer. First, the algorithm obtains a wide range of receptive fields through the Transformer with window mechanism, and then obtains the contextual information of rain streak features to improve the ability of the model to extract rain streak features; secondly, the algorithm extracts and fuses different kinds and levels of features through multi-branch modules to improve the model’s ability to characterize complex rain streaks information; finally, this paper fuses the shallow features and deep features through residual connections to complete the missing details in the deep features, which enhances the expression ability of the network. The experimental results on the public datasets Rain100 L, Rain100 H and the private dataset Rain3000 show that the method is more effective in removing rain streaks compared to existing algorithms while better recovering the lost background texture information in the images. PSNR and SSIM have respectively reached 38.33/0.9855, 28.42/0.9000 and 34.51/0.9643. Rain streaks can seriously degrade the quality of captured images and affect subsequent computer vision tasks. In order to improve the quality of rainy images, this paper proposed a single-image deraining algorithm based on Transformer. First, the algorithm obtains a wide range of receptive fields through the Transformer with window mechanism, and then obtains the contextual information of rain streak features to improve the ability of the model to extract rain streak features; secondly, the algorithm extracts and fuses different kinds and levels of features through multi-branch modules to improve the model’s ability to characterize complex rain streaks information; finally, this paper fuses the shallow features and deep features through residual connections to complete the missing details in the deep features, which enhances the expression ability of the network. The experimental results on the public datasets Rain100 L, Rain100 H and the private dataset Rain3000 show that the method is more effective in removing rain streaks compared to existing algorithms while better recovering the lost background texture information in the images. PSNR and SSIM have respectively reached 38.33/0.9855, 28.42/0.9000 and 34.51/0.9643. [ABSTRACT FROM AUTHOR]

At present, with the rapid development of AI, people can efficiently deploy excellent neural network algorithms on FPGA accelerators by exploring the hardware design space. However, due to the large amount of parameters and complex operation, it is difficult to match the algorithm with the hardware, and the acceleration efficiency is low. In order to better match the algorithm and hardware, this paper proposed a multi-level co-exploration method, adopted SPOS search strategy, aimed at accuracy and latency, to obtain the optimal neural network architecture, quantization method and hardware design combination. It applied the method to hourglass network which have high accuracy in pose estimation. While obtained the accuracy before and after quantization of candidate sub networks, it used traversal method to search hardware design parameters and obtain the estimated latency, and then got the optimal combination with the highest score according to the target function. In order to ensure the effectiveness of the obtained data, it retrained the sub network, then quantified and inferenced again to obtain the accuracy. It simulated the obtained hardware design parameters to get the testing latency, using the accelerator template designed based on Spinal HDL. On average, Co-exploration method reduced the parameters by 83.3% and with only 0.69 accuracy loss compared with the original structure; reduced the parameters by 33.2%, with only 0.46 accuracy loss, reduced the total testing latency of network inference by 22.1% and reduced the testing latency in hourglass block by 67.8% compared with the traditional acceleration method. Overall, the co-exploration method in this paper has a certain effect on the optimization of hourglass network, and it has more advantages than the traditional acceleration method. [ABSTRACT FROM AUTHOR]

Motor imagery EEG signals requires a high cost for recording, and there is a large difference for individual’s signals. Cross-subject motor imagery EEG signals recognition task belongs to a typical cross-domain learning problem with a small samples set. To solve this problem, this paper proposed a cross-domain feature learning method for motor imagery EEG signals to improve the recognition performance. The proposed method first selected the optimal measurement to align the covariance of EEG signals, and then extracted common spatial patterns（CSP） from the aligned EEG trials. Second, based on the CSP features, an optimal domain adaptation algorithm was selected to learn the optimal cross-domain features for the target domain. To validate the feasibility and effectiveness of the learned cross-domain features, a classical model was adopted to recognize the learned cross-domain features, and the comparative experiments were conducted on two public datasets. Experimental results show that the learned cross-domain features are obviously better than state-of-the-arts methods in recognition performance. In addition, this paper also compared the parameters setting, performance and efficiency for the proposed method. [ABSTRACT FROM AUTHOR]