Search

Traditional federated learning faces challenges such as high communication costs, structural heterogeneity,and insufficient privacy protection. To address these issues, this paper proposes a federated learning evolutionary algorithm that applies sparse evolutionary training algorithm to reduce communication costs and integrates local differential privacy protection for participants’ privacy. Additionally, it utilizes the NSGA-Ⅲ algorithm to optimize the network structure and sparsity of the global federated learning model, adjusting the relationship between data availability and privacy protection. This achieves a balance between the effectiveness, communication costs, and privacy of the global federated learning model. Experimental results under unstable communication environments demonstrate that, on the MNIST and CIFAR-10 datasets, compared to the solution with the lowest error rate using the FNSGA-Ⅲ algorithm, the proposed algorithm improves communication efficiency by 57. 19% and 52. 17%, respectively. The participants also achieved（3. 46, 10-4） and（6. 52, 10-4）-local differential privacy. This algorithm can effectively reduce communication costs and protect participant privacy without significantly compromising the accuracy of the global model. [ABSTRACT FROM AUTHOR]

In view of the problems of data sparsity and the diversity in academic paper recom-mender systems,based on CONVNCF, this paper proposed an algorithm of convolution with word and heterogeneous information network for academic paper recommendation ( WN -APR) . Firstly, WN -APR algorithm learned user and paper' s diverse features from different semantics to alleviate the sparsity problem. Then it designed an outer product fusing way to seamlessly combine user features with paper features. Replacing of 2D CNN, this algorithm applied 3 D convolution to mine the influence of different features on the performance. Finally, it modified the BPR loss function to enhance diversity in recommendations. Experimental results on CiteULike-a and CiteULike-t datasets show that WN-APR improves the performance of accuracy and diversity over the baseline models. [ABSTRACT FROM AUTHOR]

In order to solve the problems of the current art circulation information is not transparent and the centralized trading authority is asymmetric, this paper proposed a art blockchain certificate traceability model based on three chains. First, in view of the large amount of data in a single piece of artwork information, this paper proposed a blockchain-based symmetric searchable encryption algorithm, and used the interplanetary file system to securely store artwork circulation records on-chain and off-chain. Secondly, for the characteristics of the increasing effective data of artwork information, this paper proposed a blockchain-based inverted fast query and traceability algorithm to help data users realize fast traceability and positioning. At the same time, this paper proposed for the first time that the false information alliance chain stores false art circulation records to realize the processing of false information. Finally, experiments verify the feasibility of the model for big data security storage and fast query traceability. Experiments show that the model is feasible and the query method is efficient. [ABSTRACT FROM AUTHOR]

In view of the problem of fuzziness of rating and tag in traditional collaborative filtering algorithms,this paper used trapezoidal fuzzy number to describe the mapping relationship between rating and satisfaction.The algorithm considered the impact of sparseness of the rating,constructed a new trapezoidal fuzzy rating model to determine the similarity based on fuzzy rating,analyzed the degree of membership between the tag and the item,and constructed a fuzzy item-tag matrix to measure the similarity based on the degree of tag membership.Finally,it used the improved scoring prediction strategy to estimate the score.The experimental results on the MovieLens dataset show that the proposed algorithm improves the prediction accuracy while suppressing the cold start of the project,alleviating the problems of fuzziness and sparseness,which indicates the effectiveness of the proposed algorithm. [ABSTRACT FROM AUTHOR]

Screen-space ambient occlusion (AO) is a popular global illumination technique which can be used to achieve a better understanding of complex 3D streamtubes scenes. This paper proposed an anisotropic screen-space AO method to visualize complex 3D streamtubes. The basic idea is to utilize the characteristics of 3D streamtubes to design two anisotropic filters to guide screen-space sampling as well as spatial reusing. More specifically, this paper proposed to anisotropically generate samples perpendicular to the direction of streamtube to calculate AO. This mechanism can reduce the number of samples required to generate satisfactory results. In order to further improve the performance of the algorithm, this paper proposed to anisotropically reuse AO results from nearby pixels along the streamtube direction. The experimental results indicate that the proposed algorithm outperforms the existing solutions both in rendering quality and performance. [ABSTRACT FROM AUTHOR]

In the process of researching tree-based in-memory indexes, traditional on-chip prefetching cannot adapt to the locality of index accesses, resulting in memory accesses becoming a performance bottleneck of this type of memory index. This paper proposed a path prefetching scheme at the software level to accelerate memory index accesses by prefetching, and enabled the algorithm to be quickly deployed on real machines. Based on the analysis of the tree-based indexes memory access process, this algorithm used a prefetch table to save the relationship between keys and index access paths, and matched data in the prefetch table through a matching algorithm based on key slice hashing. This paper implemented and evaluated the algorithm on current advanced tree-based memory indexes. The results indicate that it maintains stable performance improvement under different data scale and read-write-mixed workloads. Therefore, the algorithm based on path prefetching can effectively accelerate the memory access speed of tree-based in-memory index and improve index performance. [ABSTRACT FROM AUTHOR]

This paper proposed an electronic voting scheme based on one-time ring signature and blockchain to solve the problems of the current e-voting system in terms of anonymity, transparency and open vote-counting. This paper introduced one-time ring signature, blockchain and stealth address technology. The one-time ring signature technology solved the problem of voter anonymity, repeated voting and public verification. The blockchain technology could ensure the openness and transparency of the e-voting system. The one-time ring signature technology could ensure no one or institution could obtain the voting intermediate result before the voting ends. In order to improve the efficiency of vote-counting,it used the method of key sharing to improve the vote-counting algorithm. Through security and performance analysis, the scheme conforms to the basic security standards of an electronic voting system. [ABSTRACT FROM AUTHOR]

The digital trunking system has the characteristics that the calling mode is mainly group calling and the communication mode is mostly half duplex. For the problem that the traditional user classification method couldn't meet the classification requirements of digital cluster users, this paper proposed a digital cluster user classification method based on improved RFM model. Firstly, it introduced the average speech duration attribute to establish the recency vitality speak (RVS) model. Then, it used the analytic hierarchy process to determine the weight of each parameter in the model. Finally, it used the K-means + + clustering algorithm to classify digital cluster users. The simulation result shows that, by using the user classification method proposed in this paper, the accuracy of digital cluster user classification can reach more than 87. 9% . [ABSTRACT FROM AUTHOR]

Aiming at the problem that the positioning accuracy of traditional SLAM algorithm decreases due to the influence of dynamic feature points in dynamic environment, this paper proposed SF-VINS which fused semantic information. Firstly, it incorporated the PP-LiteSeg semantic segmentation network into the front-end of system based on the VINS-Mono algorithm and removed the dynamic feature points according to the results of semantic segmentation. Then, it constructed the semantic probability error constraint with the pixel semantic probabilities and employed adaptive weights for feature points in the backend. Based on these modifications, this paper proposed a new BA cost function and an optimization strategy for camera extrinsic parameters to improve the accuracy of state estimation. Finally, this paper conducted experiments on the VIODE and NTU VIRAL datasets to validate its effectiveness. The experimental results show that the proposed algorithm has advantages in terms of positioning accuracy and robustness in both dynamic and static scenes compared with state-of-the-art visual-inertial SLAM algorithms. [ABSTRACT FROM AUTHOR]

Existing cost allocation methods for adaptive video steganography mainly focus on specific transform coefficients, resulting in lower capacity. Moreover, distortion drift is a significant challenge for steganography in HEVC videos. Therefore, this paper proposed a cost allocation method that combined the intra-frame and inter-frame processes of HEVC video coding to achieve high-capacity, low-distortion transmission in high-performance adaptive video steganography. Firstly, the method investigated the discrete sine transform features in HEVC video coding, analyzing the error propagation patterns of these coefficients under disturbance. During the embedding processed, it conducted a detailed analysis on the intra-block distortion, interblock distortion, and inter-frame distortion caused by modifying transform coefficients. The algorithm also took into account the differentiation in inter-block distortion resulting from steganography in different blocks, leading to the classification of blocks. This paper maximized the utilization of all non-zero transform coefficients, allocating distinct distortion costs for various carrier coefficients. The covert information was then embedded into frames that minimally impacted video quality. Experimental results indicate that, compared to existing HEVC video coefficient domain steganography methods, the proposed algorithm demonstrates advantages in terms of video bitrate, video quality, and embedding capacity. [ABSTRACT FROM AUTHOR]

Most of the existing MAPF methods based on communication learning have poor scalability or aggregate too much redundant information, resulting in inefficient communication. To solve these problems, this paper proposed disruptor identifiable communication (DIC), which learned concise communication excluding non-disruptors by judging whether the agent in the center of the field of view would change its decision-making due to the presence of neighbors, and successfully filtered out redundant information. At the same time, this paper further instantiated DIC and developed a new highly scalable distributed MAPF solver: disruptor identifiable communication based on reinforcement and imitation learning algorithm (DICRIA). Firstly, the disruptor discriminator and the policy output layer of DICRIA identified the disruptor. Secondly, the algorithm updated the information of the disruptor and the communication wish sender in two rounds of communication respectively. Finally, DICRIA output the final policy according to the coding results of each module. Experimental results show that DICRIA S performance is better than other similar solvers in almost all environment settings, and the algorithm increases the success rate by 5.2% on average compared to the baseline solver. Especially in dense problem instances with large-size maps, the algorithm even increases the success rate of DICRIA by 44.5% compared to the baseline solver. [ABSTRACT FROM AUTHOR]

To solve the flexible job shop dynamic scheduling problem with fuzzy quality control time, which is more realistic, this paper established two rescheduling models for machine breakdown and urgent order insertion with the objective of minimizing completion time. Two models were for three failure scenarios: emergency order insertion, machine failure during no-load operation, and machine failure during work-piece processing. To solve this model, this paper designed a novel genetic-neighborhood search algorithm that integrated cellular-automata-based neighborhood search and random restart hill-climbing. Aiming at the characteristics of dual sub-decisions involving order sequencing and machine selection, this paper designed a two-layer coding scheme including process code and machine code, and designed corresponding genetic operations such as crossover and mutation for them. After that, this paper applied the genetic operations into the framework of cellular-automata-based neighborhood search to enhance the algorithm's global search capability, and integrated the random restart hill-climbing algorithm based on key operations to improve the algorithms local development capability. Experiments tested 10 flexible job shop scheduling instances and one flexible job shop scheduling instance with fuzzy quality control time to verify the effectiveness of the proposed algorithm and models. In addition, the test results under different failure scenarios show the proposed method outperforms the backward-based scheduling strategy used in practice. [ABSTRACT FROM AUTHOR]

Maintaining population diversity and improving algorithm search efficiency are two major problems that need to be solved urgently in the multimodal multi-objective optimization. To address the above problems, this paper proposed a multimodal multi-objective brain storm optimization algorithm based on zoning search and reinforcement learning (MMBSO-ZSRL). In the MMBSO-ZSRL, the decision space was first decomposed into multiple subspaces to reduce the search difficulty and maintain the population diversity. Subsequently, the proposed algorithm used SARSA algorithm to balance the global exploration and local exploitation capabilities of the brain storm optimization algorithm. Additionally, the MMBSO-ZSRL utilized the special crowding distance to select individuals for guiding the population evolution. To verify the performance of the proposed algorithm, this paper selected six advanced multimodal multi-objective optimization algorithms and the IEEE CEC2019 multimodal multi-objective problem benchmark test suite for experiments. Experimental results demonstrate that the overall performance of the MMBSO-ZSRL is significantly better than that of compared algorithms. The proposed MMBSO-ZSRL can not only find the Pareto front with better diversity and approximation, but also find more Pareto optimal solutions in the decision space. [ABSTRACT FROM AUTHOR]

In order to improve the delivery efficiency of logistics, this paper proposed a vehicle routing problem with drone and time window considered by the time window, UAV (unmanned aerial vehicle) power change and multi-point continuous delivery of UAV. Then, this paper proposed a hybrid particle swarm optimization algorithm with local search to solve it. Based on the hybrid particle swarm optimization algorithm, the proposed algorithm transformed the problem solution space into the algorithm search space by constructing an efficient encoding and decoding strategy. Further, the proposed algorithm combined a single point insertion strategy, a vehicle replacement strategy and a UAV replacement strategy to form a local search strategy to improve the optimization ability. The experimental results show that the proposed model is more efficient than the model of pure vehicle distribution and saves 31.51% of the cost. The proposed algorithm is better than the four comparison algorithms, and its highest optimization rate is 82.08%. [ABSTRACT FROM AUTHOR]

In order to address the limitations of the neighborhood rough set model caused by neighborhood parameters and inadequate sample information representation, this paper proposed a rough set model based on the maximum coalition theory. By normalizing the neighborhood information system and utilizing the maximum coalition set to describe neighborhood granular information, the proposed model enabled finer information division and significant reduction of uncertainty in the boundary region. Combining the model with three-way clustering, this paper designed a three-way clustering algorithm based on maximum coalition rough set. Comparative experiments on six UCI public data sets show that the proposed algorithm has better clustering quality than the comparison algorithms, and has higher comparison accuracy when dealing with boundary region samples. [ABSTRACT FROM AUTHOR]

For the security problem of the spread of digital image and the digital image encryption from plaintext and too depend on the chaotic systems, this paper proposed a digital image encryption and monitoring algorithm combined with plaintext-related chaotic mapping and SHA-256. The algorithm used the SHA-256 algorithm to calculate the hash value as record to monitor the spread of digital image. Lorenz chaotic mapping generated the corresponding cryptogram by using forward diffusion, associated plaintext scrambling and backward diffusion to encrypt the digital image. The results show that the algorithm can resist many attacks and achieve the security and concealment of image propagation. [ABSTRACT FROM AUTHOR]

In the field of digital printing, accurately reproducing the color of computer images is a prerequisite for high-quality printing, where color characterization is a key step. Traditional polynomial regression models tend to amplify outliers in the characterization sample set due to high-order terms, causing model oscillation and affecting the accuracy of color characterization. Color characterization algorithms based on neural network have higher precision but significantly increase in algorithmic complexity, making them unsuitable for the efficiency requirements in industrial production. To address these issues, this paper proposed a color characterization method based on weighted polynomial regression algorithm with residual correction. This algorithm employed the Huber loss function, known for its strong robustness against outliers, as a substitute for mean squared error. It determined the weight of each sample through an adaptive mechanism and iteratively optimizes the residual values to obtain the optimal weight matrix, effectively reducing the impact of outlier samples on the system. Additionally, the correction module captured nonlinear scenarios that the initial model might miss, significantly improving the adjustment of the transformation results and thereby enhanced characterization precision. The results show that compared to conventional polynomial regression, this algorithm reduces the average color difference by 1.2. It achieves a precision close to that of deep belief network algorithms but with more than 99.37% reduction in inference time. [ABSTRACT FROM AUTHOR]

This paper proposed an aggregate signature scheme based on the SM9 algorithm to address the issue of excessive storage space occupied by the signatures of n messages generated by the conventional SM9 signature scheme. This scheme reduced the time cost of verifying multiple signatures compared to the original SM9 scheme, with a space cost of about 66.7% of the original SM9 scheme. Furthermore, the scheme introduced a locally verifiable approach based on the SM9 aggregate signature to tackle the problem where validators need only verify the correctness of specific messages when verifying signatures in current aggregate signature algorithms but still require knowledge of the complete message list. For the aggregated signatures S of a messages generated by a single user, the signer generated verification tags for a specific message m, enabling the verifier to verify the correctness of the message's signature without knowledge of the complete message list. Theoretical and experimental analysis confirm that the proposed scheme achieves a time complexity of O(1) for verifying specific messages given an aggregated signature. [ABSTRACT FROM AUTHOR]

This paper proposed a scheme to assist communication for vehicles undergoing uniform motion with variable speed, addressing issues such as Doppler spread, time delay spread, and received signal-to-noise ratio (SNR) through the utilization of a multi-intelligent RIS. Unlike traditional channel estimation, this scheme utilized channel gains and optimized RIS phase to minimize Doppler and delay spreads while maximizing instantaneous signal-to-noise ratio (SNR) for the moving object. The scheme studied the impact of RIS placement on the received signal by optimizing the RIS phase, exploring the distance between RIS units and the optimal positioning of RIS units when the distance between them was fixed to maintain a low range of reception SNR and delay spreading. It introduced relative motion theory for this problem and proposed respective algorithms to address both issues. Simulations show around a 10 dB power gain for vehicular communication receivers with multiple RIS assistance. Optimal RIS deployment suggests placing the first RIS near the base station and minimizing inter-RIS distances as much as practically feasible, showcasing the broad applicability of this multi-RIS communication approach in vehicular scenarios. [ABSTRACT FROM AUTHOR]

Extremely large-scale massive MIMO (XL-MIMO) emerges as a crucial technology for future 6G communication. Existing XL-MIMO hybrid-field channel models primarily model channels between uniform linear arrays and single-antenna users, employing the last-hop model of scatterers. However, if both transmitter and receiver are equipped with linear arrays, existing hybrid-field channel estimation schemes become inadequate. To address this, this paper proposed a channel modeling approach for XL-MIMO scenarios with both transmitter and receiver equipped with large-scale linear arrays, utilizing the SalehValenzuela model. Additionally, it introduced a hybrid-field channel estimation algorithm based on orthogonal matching pursuit (OMP). This algorithm initially estimated far-field components using the angle-domain transformation matrix, followed by estimating near-field components using the polar-domain transformation matrix. Furthermore, it introduced the Cramer-Rao lower bound (CRLB) to evaluate the proposed algorithm. Simulation results demonstrate approximately 0. 6 dB improvement in channel estimation performance compared to algorithms considering only far-field and near-field components. [ABSTRACT FROM AUTHOR]

In order to investigate vulnerabilities in stateful protocols, AFL-NET has put forward stateful protocol fuzz testing. In such fuzz testing, the selection of seeds makes a major contribution to the exploration of paths. However, current stateful protocol fuzz testers often repeatedly execute the same several seeds, resulting in an inability to effectively explore more paths. To alleviate this problem, starting from the gain of seeds, this paper proposed an effective seed dynamic scheduling algorithm based on stateful protocols. The algorithm utilized the potential gain, actual gain, and cost of seeds as the gain, using this gain to dynamically schedule seeds and allocate the number of times seeds. Experiments show that this method significantly improves the number of vulnerabilities found and also has a certain degree of improvement in increasing coverage, indicating that the definition of this gain and the seed scheduling algorithm can effectively select seeds and explore more paths and vulnerabilities. [ABSTRACT FROM AUTHOR]

To address the issue of calculation errors in neural network matrix-vector multiplication caused by manufacturing processes of RRAM cells, this paper modeled the characteristics of multiple faults in RRAM crossbar arrays and proposed a multi-fault tolerant algorithm. Firstly, it modeled the impacts of common transition fault and stuck at fault in RRAM crossbar arrays on the accuracy of neural network computations. Secondly, it partitioned the neural network and conducted partitioned training based on an improved knowledge distillation method. Lastly, it further optimized the algorithm by selecting an appro priate loss function and incorporating normalization layers. Experimental results on the MNIST and Cifar-10 datasets demonstrate that the proposed method can achieve a recovery rate of over 98% across multiple neural networks, indicating its effeetiveness in mitigating the impact of multiple faults in RRAM crossbar arrays on the accuracy of neural network computations. [ABSTRACT FROM AUTHOR]

Zero-knowledge succinct non-interactive proofs (zk-SNARK) have found extensive applications in various fields, including cryptocurrencies, due to their swift and efficient proof verification process. However, the computational intensity of the proof generation process poses a significant challenge, particularly at the number theoretic transform (NTT) stage. This paper proposed a GPU-based acceleration method for NTT computations, named PreNTT, to address this bottleneck. The method employed precomputation and optimization of twiddle factor powers to reduce the parallel computation overhead in NTT. It also introduced dynamic precomputation to enhance the efficiency of these computations. The algorithm made use of dynamic adaptive kernel scheduling, which allocated GPU resources on-chip according to the NTT input size, thereby boosting the computational efficiency for large-scale tasks. Additionally, the approach combined external global data shuffling with internal local data shuffling to avoid memory access conflicts. The use of CUDA multi-stream technology allowed for effective concealment of precomputation times during data transfer and computation processes. Experimental results indicate that the zk-SNARK system utilizing PreNTT achieves a speed-up ratio ranging from 1.7x to 9x in NTT module running times compared to Bellperson, the industryleading system. PreNTT effectively increases the parallelism of the NTT algorithm and reduces the computational overhead in zk-SNARK operations. [ABSTRACT FROM AUTHOR]

When dealing with dynamic economic dispatch problems involving electric vehicles (EVDED), HBO suffers from slow convergence and low accuracy. This paper proposed an improved heap-based optimizer algorithm called RDHBO. RDHBO adopted the optimal member region search and dual population interaction strategies. The former guided the optimal members to move to more promising regions, improving the convergence accuracy and convergence speed. The latter made full use of the climinated inferior individuals, enriching the diversity of the population, avoiding the algorithm falling into the local optimum. It investigated a 10-unit EVDED problem with four charging scenarios. The simulation results show that RDHBO is highly compe titive in generating low fuel cost and high stability compared with the existing representative methods. Finally, two improved strategies of RDHBO were subjected to ablation experiments, and the results show that combining the two strategies are effective. [ABSTRACT FROM AUTHOR]

This paper proposed an improved ant colony optimization named TSACO and an enhanced velocity obstacle (VO) to solve the UAV path planning problem. The TSACO incorporated non-uniform initial pheromone distribution, a turning heuristic function, and an elite ant system to improve the convergence speed and reduce the number of path corners during global planning. The enhanced VO integrated the UAV's dynamic equation, adaptive collision radius and emergency collision cone, along with an optimal velocity selection approach to increase real-time and safe local obstacle avoidance during local planning. Simulation experiments demonstrate that the proposed algorithms have better effectiveness in terms of path length, number of turns, and dynamic obstacle avoidance compared to other algorithms. [ABSTRACT FROM AUTHOR]

This paper introduced a real-time SLAM algorithm designed for mobile robots operating in environments characterized by low illumination and low texture. The algorithm leveraged the fusion of visual point-line features and IMU characteristics. It enhanced the EDlines algorithm by incorporating a leapfrog routing strategy and an adaptive threshold strategy, thereby improving the quality of line feature extraction and consequently enhancing feature tracking effectiveness. It established tight coupling constraints between visual and inertial features and employed a sliding window, along with a marginalization model, for nonlinear optimization. This enabled high-precision and real-time state estimation. Experimental results show that the proposed algorithm is superior effectiveness in online feature extraction when compared to traditional line segment extraction methods. Concurrently, the SLAM system achieves enhanced localization accuracy and robustness. [ABSTRACT FROM AUTHOR]

This paper proposed a new algorithm of the credibility evaluation concerning microblog users, based on their multiple interactive relationships and emotional tendencies. Firstly, the algorithm calculated the interaction degree and participation degree of users by analyzing the types and frequency of interactions among users. Secondly, this algorithm made the emotional scores of the textual contents including comments and replied among users by using a sentiment dictionary, and assessed users' emotional tendencies. Thirdly, based on the PageRank algorithm, the new algorithm extracted the features from user profiles and blog posts in order to compute the initial PageRank value for representing individual user credibility, adjusted the distribution of PageRank weights by integrating the user interaction degree and emotional tendencies, and modified the damping factor in accordance with the participation degree. Finally, the proposed algorithm made the credibility of the evaluated users after the iterative stabilization. The experimental results show that, compared to methods that overlook multi-interaction relationships and emotional tendencies, the new algorithm achieves better results with an improvement of up to 13.86% in terms of AUC value, precision, recall, and F₁-measure. The method that considers multiple interaction relationships and emotional tendencies can enhance the effectiveness of microblog user credibility evaluation with respect to microblog users. [ABSTRACT FROM AUTHOR]

To address the high throughput and resistance to Byzantine node attacks in the microgrid trading scenario of consortium chains, this paper proposed a multi-leader Byzantine fault tolerance consensus algorithm based on Raft, named MLBRaft. The algorithm first utilized the VRF to select a group of leader nodes, increasing throughput by allowing multiple leaders to submit blocks in parallel. A coordinator role was then introduced, responsible for the election and management of leaders and system consensus. During the block replication process between leaders and followers, the consensus process of the practical Byzantine fault tolerance (PBFT) algorithm was integrated and simplified to achieve the Byzantine resilience of this algorithm. Experimental results show that, under a large-scale network node environment, compared to the Raft algorithm, this algorithm improves throughput and consensus efficiency at the cost of some communication overhead. Compared to the PBFT algorithm, this algorithm enhances Byzantine fault tolerance and reduces communication overhead. In summary, this algorithm can effectively ensure the timeliness and security of alliance chain microgrid transactions. [ABSTRACT FROM AUTHOR]

Aiming at the problem of insufficient representation capability for details and frequency information in traditional infrared and visible image fusion methods, this paper proposed a fusion algorithm based on spectral feature hybrid Transformer. The algorithm utilized the Fourier transform to map image domain features to the frequency domain. Then the novel complex Transformer extracted deep-frequency information from the source images and mixed them with the features of the image domain to enhance the representation capability for edges and details. Additionally, the algorithm used a token replacement module to evaluate the saliency of Transformer tokens and eliminate the tokens with lower scores to prevent the presence of artifacts in the fused image. Qualitative and quantitative experiments conducted on the MSRS dataset demonstrate that the proposed algorithm exhibits superior fusion performance compared to nine state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Addressing the issues of redundant exploration and inapplicability in dynamic environments inherent in fast marching tree algorithm (FMT), this paper proposed the APF-Dynamic FMT algorithm, which integrated artificial potential field method. This algorithm designed a sampling point guidance function based on artificial potential field method, which could dynamically adjust the sampling point generation range according to the environment information to reduce redundant exploration. Additionally, this algorithm designed a dynamic path tree adjustment mechanism, when the existing path was affected by the environment change, it could re-plan a new excellent path on the basis of the remaining path tree that is not affected, which was suitable for solving the path planning problem in dynamic environment. The results verify that the APF-Dynamic FMT algorithm can significantly improve the success rate and path quality of path planning while consuming the same computational resources, and when the existing path is affected by the dynamic environment, it can efficiently re-plan the passable excellent path. [ABSTRACT FROM AUTHOR]

The conventional cloud-end MCS system currently faces problems of excessive load, leading to a significant increase in delay and energy consumption during the data aggregation process, inevitably causing a decrease in data aggregation efficiency. To tackle this issue, this paper proposed a cloud-edge-end MCS computation offloading algorithm based on APDQN. Firstly, it established a utility function considering the balanced optimization of delay and energy consumption, with the maximization of system utility as an optimized goal. Secondly, improving the P-DQN algorithm, it proposed a computational offloading algorithm AP-DQN for combining resource allocation. This algorithm, leveraging the advantages of MCS, designated idle users as one of the offloading devices. Finally, the problem was solved using the proposed method. Experimental results show that, compared to existing algorithms, the proposed method significantly improves data aggregation efficiency and maintains excellent system stability. [ABSTRACT FROM AUTHOR]

In the deep reinforcement learning method, the intrinsic curiosity model (ICM) guides the agent to obtain the opportunity to learn unknown strategies in the sparse reward environment, but the curiosity reward is a state difference value, which will make the agent pay too much attention to the exploration of new states, then could be the problem of blind exploration arises. To solve the above problem, this paper proposed an intrinsic curiosity model algorithm based on knowledge distillation (KD-ICM). Firstly, it introduced the method of knowledge distillation to make the agent acquire more abundant environmental information and strategy knowledge in a short time and accelerate the learning process. Secondly, by pre-training teachers' neural network model to guide the forward network to obtain a forward network model with higher accuracy and performance, reduced the blind exploration of agents. It designed two different simulation experiments on the Unity simulation platform for comparison. The experiments show that in the complex simulation task environment, the average reward of KDICM algorithm is 136% higher than that of ICM, and the optimal action probability is 13.47% higher than that of ICM. Both the exploration performance of the agent and the exploration quality can be improved, and it verifies the feasibility of the algorithm. [ABSTRACT FROM AUTHOR]

The existing ship object detection algorithms mostly rely on optimized improvements based on traditional object detection algorithms, without considering the scale and aspect ratio characteristics of ships, leading to issues such as missed detections and false detections in multi-scale object detection. To address this, the paper proposed a scale-adaptive receptive field ship detection method (SAF-YOLOX) based on YOLOXs. Firstly, it extracted different feature layers by the backbone network, which were fused by constructing a bidirectional feature pyramid, improving feature representation at various scales. Simultaneously, it designed an adaptive feature enhancement module to suppress redundant information introduced by the fusion of features at different scales, thereby attenuating background information. During the prediction phase, it employed a multi-branch parallel receptive field detection head, utilizing receptive fields adapted to target sizes and proportions for extracting scale-adaptive feature information. Additionally, it implemented a convergence-aware strategy, dynamically selecting and allocating samples based on the network s convergence state. This strategy ensured improved detection accuracy while maintaining detection speed. Experimental results demonstrate that the proposed method achieves an average detection accuracy of 93. 21% on the SeaShips dataset and 92.34% on the MCShips dataset. When compared to traditional YOLOXs, the method exhibits an improvement of 1.01% and 1.09%, respectively. The experimental results confirm that the proposed method, utilizing scale-adaptive receptive fields, can achieve high-precision detection of multi-scale ship targets. [ABSTRACT FROM AUTHOR]

In consideration of the superior performance of the wolf pack algorithm on single-objective optimization problems, combining with the biological habits of wolves to apply it to multi-objective optimization problems, this paper proposed a multiobjective wolf pack algorithm with elite guidance and information interaction (MOWPA-EGII). Firstly, MOWPA-EGII proposed an elite guidance strategy, using the elite wolf in the external file and the head wolf of the current sub-population to jointly guide the population movement, so that the artificial wolves uniformly distributed in the whole search space, and the strategy enhanced the global search ability of the algorithm; Secondly, it designed the information interaction mechanism to simulate the information transfer in the wolf hunting process, so that individuals with different advantages could transfer information to each other to ensure the hunting efficiency of the wolves and improved the ability of the algorithm to explore the optimal solution of the Pareto; Finally, it added the mutation operator to perturb the moving direction of the artificial wolves, so as to let the algorithm jump out of the local optimum and enhance the local search ability of the algorithm. In order to verify the effectiveness of MOWPA-EGII, comparing it with 5 classical algorithms and 10 recent algorithms, and the results show that MOWPA-EGII possesses good convergence and diversity, which proves that the present algorithm has a better optimization performance. [ABSTRACT FROM AUTHOR]

Existing studies based on convolutional neural networks mainly focus on the accuracy of image reconstruction, ignoring problems such as excessive parameters, insufficient feature extraction, and resource waste. In response to the above, this paper proposed multi-frequency feature extraction network (MFEN), which designed a lightweight lattice information interaction structure and used channel segmentation with multi-mode convolution combination to reduce the number of parameters. By separating the low-frequency, mid-frequency, and high-frequency information of the image and extracting the feature heterogeneity, it improved the expressiveness and feature differentiation of the network, made the network pay more attention to the restoration of texture detail features, and reasonably allocated the computational resources. In addition, it integrated the local binary pattern (LBP) algorithm into the network to enhance texture sensitivity, which further improved the network s ability to extract details. It experimentally verifies that the proposed method balances complexity and performance well. In the 2X zooming experiments on the Set5 dataset, compared to the conventional image super-resolution algorithm (SRCNN) based on convolutional neural network and the newer algorithm (MADNet), the peak signal-to-noise ratio (PSNR) of the proposed method is improved by 1.31 dB and 0. 12 dB respectively, and the number of parameters is reduced by 55% compared to MADNet. [ABSTRACT FROM AUTHOR]

Path-coverage oriented testing is a crucial method in software testing, and the rapid generation of high-quality test data to satisfy path coverage requirements has been a persistent research challenge. To address issues such as long running times, unstable exploration processes, and the generation of redundant test cases in existing intelligent optimization methods, this paper proposed a selection strategy based on the reinforcement learning paradigm applied to test data generation with path coverage as the criterion. By defining executable paths as the state of the intelligent agent, it defined the data selection after each iteration update as the agent's action. It associated the reward function with state changes, and employed a greedy strategy during the state update process to guide input data towards continuous variations in unexplored states. This iterative selection process aimed to continuously choose data that covered new executable paths, thereby achieving the goal of covering all execution paths of the target program. Experimental results demonstrate that compared to other algorithms, the proposed strategy significantly reduces running times and iteration counts while achieving notable improvements in coverage. Theoretical analysis supports the conclusion that the proposed strategy effectively realizes path coverage and enhances the efficiency of test data generation in practical applications. [ABSTRACT FROM AUTHOR]

In the current research on multi-view clustering, the majority of methods have not adequately considered the diversity of multiple views nor focused on the high-order neighborhood information of the data, which leds to clustering results that lack accuracy and struggle to uncover the underlying information in datasets. To address these issues, this paper proposed a multi-view clustering method based on diversity constraints and high-order information mining(MVCDCHO). Firstly, it designed a method for measuring diversity between views, utilizing diversity constraints to preserve the intersection features of the data while eliminating differing features across multiple views. Subsequently, it introduced a method for mining high-order information in views, requiring the intersection features of multiple views to approximate a mixed similarity graph, thereby extracting high-order information in data correlations that has been overlooked. Finally, it fused the intersection features of multiple views into a consensus graph and employ spectral clustering to obtain the clustering target graph. Additionally, it designed an alternating iterative method, iteratively learning to optimize the objective function. The experimental results show that MVCDCHO has excellent performance on the normalized mutual information (NMI), the adjusted Rand index (ARI), and the clustering accuracy (ACC). Theoretical analysis and experimental study underscore the crucial role of multi-view diversity and high-order information in the MVCDCHO algorithm, providing evidence for its superiority. [ABSTRACT FROM AUTHOR]

NeRF is a deep learning model aimed at modeling three-dimensional implicit spaces, and it holds significant value in the representation and rendering of 3D scenes. However, due to the complex training process, substantial computational resources, and time requirements, the usability and practicality of the NeRF algorithm are somewhat limited. Addressing the pain points of NeRF optimization has become a hot topic in the field of computer vision. This paper aimed to provide a comprehensive review of the optimization and application of NeRF. Firstly, it delved into the basic principles of NeRF and outlined the current optimization status from the perspectives of rendering quality, computational complexity, and pose. Secondly, it enumerated the application scenarios of NeRF to provide references for future, more efficient and practical algorithmic optimizations. Finally, it summarized the strengths and limitations of NeRF and proposed potential future directions tailored to harness the tremendous potential of NeRF in 3D rendering, scene synthesis, and beyond. [ABSTRACT FROM AUTHOR]

Aiming at the path planning problem of mobile robot in dynamic environment, this paper proposes a fusion algorithm (IHHO-IDWA) of Improved Harris Hawk Algorithm (IHHO) and Improved Dynamic Window Algorithm (IDWA）. First of all, this paper proposed a fusion adaptive chaos and core population dynamic division strategy, a fusion golden sine strategy and a dynamic cloud optimal disturbance resolution strategy to improve the performance of and solve the lack of search performance in the late stage of the Harris Eagle algorithm. In addition, in view of the problems that the dynamic window algorithm has a long planned path and easy to fall into deadlock, it proposed three improvement strategies to solve them: Firstly, add sub-functions to ensure that the algorithm can plan a shorter path; secondly, propose an adaptive weight strategy, balance the local obstacle avoidance ability and global search performance of the algorithm; thirdly, set the initial heading angle to avoid path redundancy. Finally, through numerical experiments of test functions, CEC2014 functions, and static and dynamic path planning experiments, it is verified that the performance of IHHO and IDWA in this paper has been significantly improved; through the 50×50 large-scale dynamic map, it is verified that the path planned by the fusion algorithm is shorter than that planned by the control group algorithm. 11.51%, proving the superiority of the method in this paper. [ABSTRACT FROM AUTHOR]

In the era of e-commerce, accurately predicting user purchase intentions has become a crucial factor for enhancing sales efficiency and optimizing the customer experience. Addressing the limitations of traditional ensemble strategies, which often suffer from subjective biases during the model design phase, this paper introduced an adaptive evolutionary ensemble learning model to predict user purchase intentions. This model adaptively selected the optimal base learners and meta-learners, incorporating both the predictive information from the base learners and the differential information between features to expand the feature dimensions, enhancing prediction accuracy. Moreover, to further refine the predictive capabilities of the model, this paper designed a binary adaptive differential evolution algorithm for feature selection, aiming to identify features that significantly influence the prediction outcome. Research results show that the binary adaptive differential evolution algorithm outperforms traditional optimization algorithms in global searches and feature selection. Compared to six common ensemble models and the DeepForest model, the proposed evolutionary ensemble model achieves a 2.76% and 2.72% increase in AUC value, respectively, and effectively mitigates the impacts of data imbalance [ABSTRACT FROM AUTHOR]

TANGRAM block cipher algorithm employs a bit-slice approach and is compatible with multiple software and hardware platforms. In response to TANGRAM-128/128 algorithm, this paper proposed a design plan which used Verilog HDL for FPGA implementation. This paper firstly provided an introduction to the characteristics and processed of TANGRAM algorithm and presented a scheme for reducing resource consumption using a finite-state machine for 44 rounds of encryption and decryption computation. Secondly, the engineering implementation of the FPGA algorithm was completed by the domestic Gaoyun platform and subjected to functional simulation and data correctness validation. Furthermore, relevant tests were performed on Quartus II 13.1.0 platform for comparison. Test results show that, based on Cyclone IV E EP4CE40F29C6 chip from Altera, TANGRAM block cipher algorithm has a maximum clock frequency of 138. 64 MHz and an encryption/decryption speed of 403.30 Mbps. While based on the GW2A-55 chip from Gaoyun, the maximum clock frequency is 96.537 MHz and the encryption/decryption speed is 280. 80 Mbps. [ABSTRACT FROM AUTHOR]

In order to better cope with large-scale high-dimensional sparse data sets in today’s era, this paper combines the advantages of BB method, mini-batch algorithm and stochastic variance reduced gradient（SVRG）, and proposes a mini-batch sparse stochastic variance reduced gradient method（MSSVRG-R2BB） with randomly improved BarzilaiBorwein step size. First, on the basis of calculating the total gradient in the outer loop of SVRG, this article adds the subgradient of L1 norm, designs a sparse approximate gradient for the inner loop of SVRG, and obtains a sparse SVRG algorithm（SSVRG）. On this basis, this paper propose to use the improved BB method of random selection to automatically calculate and update the step size in the mini-batch sparse stochastic variance reduced gradient method, which solves the step size selection problem of the mini-batch algorithm, and expands the MSSVRG-R2BB algorithm. Numerical experiments show that MSSVRG-R2BB algorithm can not only reduce the operation cost and reach the convergence upper bound faster, but also achieve the same optimization level of other advanced small-batch algorithms, and perform stably and well for different initial parameter selection. [ABSTRACT FROM AUTHOR]

This paper introduced a novel approach for image retrieval, the scene-aware object saliency ranking algorithm（SASR）,which addressed the issue of traditional image retrieval techniques relying on semantic similarity and neglecting the crucial importance of object relationships within a scene. SASR consisted of two stages. In the first stage, this paper proposed a viewpoint data-based method called the “combined threshold” to annotate true value labels for object-level saliency ranking, simplifying the annotation of ranking labels. In the second stage, this paper presented an object-level saliency ranking network based on graph convolutional networks that resolved several specific difficulties encountered in sorting objects. The proposed algorithm improved on the current saliency ranking label generation methods and was tested via a large number of comparative experiments. The experimental results on the SALICON dataset show that the SASR algorithm enhances saliency ranking perfor-mance significantly. Moreover, the results from the NUS-WIDE dataset indicate that, when supported by the proposed algorithm, image retrieval performance increases by an average of 2%,which solidifies the efficacy of the proposed algorithm [ABSTRACT FROM AUTHOR]

Regular path query is a technique of using regular expressions to query graph data, usually uses finite state automata to achieve query matching. The matching result of the existing regular path query method is a sequence of vertex pairs, and the structure of the graph is not fully preserved. In order to solve this problem, this paper proposed a method of structured regular path query for graph data. By structuring constraints between different sequences, the query results could be transformed from paths to subgraphs. For this purpose, the method firstly defined a structured regular path query language, and then designed a structured query parsing and a matching algorithm based on this structure. Experimental results on simulated and real datasets verify the influence of network size on query speed. This paper compared the proposed method with the control group. Experimental results show that the proposed method can realize structured query under the premise of satisfying regular expression constraints. [ABSTRACT FROM AUTHOR]

This paper proposed a robust peer-to-peer optimization method in the context of uncertain environments to address the uncertainty in closed-loop supply chain networks while considering demand uncertainty and facility disruption risk. This paper formulated a robust optimization model to minimize the total cost of the closed-loop supply chain network. Additionally, this paper proposed a Prim-DMGA that firstly identified high-quality initial solutions using the Prim algorithm and then optimized the routing and facility selection solutions in a two-layer adaptive GA feedback loop. The experimental results demonstrate that the Prim-DMGA generates better objective function values than the single-layer Prim-MGA and traditional GA with less computational time. Further, the results obtained from the algorithm are superior to those obtained by using the CPLEX software in solving large-scale scenarios. It concludes that the proposed robust optimization model effectively reduces the adverse effects caused by uncertainty and improves the robustness of closed-loop supply chain networks. Moreover, the Prim-DMGA generates better solutions with less computational time. [ABSTRACT FROM AUTHOR]

Task scheduling algorithms are the core method for resource allocation and deployment in cloud computing. To meet the current task demand of cloud computing while the amount of data grows exponentially, the paper focused on systematically sorting and summarizing of task scheduling algorithms. Categorized by cloud environment, it studied and analyzed four types of scheduling algorithms, namely single cloud, federated cloud, hybrid cloud, and multi-cloud. For single cloud environment, the paper elaborated from the perspectives of traditional heuristics, meta heuristics, and hybrid task scheduling algorithms. For federated cloud, hybrid cloud, and multi-cloud environments, the paper elaborate from the perspectives of workflow and independent task scheduling algorithms. Through comparisons, this paper summarized the advantages, disadvantages, and optimization performance of existing algorithms, and formed conclusive opinions and open questions, laying the foundation for future research on container clouds, data clouds, and algorithms that balanced resource allocation and task scheduling. [ABSTRACT FROM AUTHOR]

In reinforcement learning, the policy gradient algorithm often needs to model the continuous-time process as a discrete-time process through sampling. To model the problem more accurately, it improves the sampling frequency. However, the excessive sampling frequency may reduce the training efficiency. To solve this problem, this paper proposed action stable updating algorithm. This method calculated the probability of action repetition using the change of the output of the policy function, and randomly repeated or changed the action based on this probability. This paper theoretically analyzed the performance of this method. This paper evaluated the performance of this method in nine different environments and compared it with the existing methods. This method surpassed existing methods in six of these environments. The experimental results show that this method can improve the training efficiency of the policy gradient algorithm in continuous-time problems. [ABSTRACT FROM AUTHOR]

Aiming at the problem that feature extraction is inaccurate and the reconstruction image is not natural enough in blind super-resolution reconstruction, this paper proposed an image blind super-resolution reconstruction based on degradation aware and sequence residuals. This paper proposed a mini-residual group combined degeneration aware and sequence residuals as the backbone network. Then the method constructed a symmetrical enhanced multi-scale residual block. In the image reconstruction part, this paper used the bottleneck attention module and the sub-pixel convolutional module to emphasize the multi-dimensional elements of the image. Finally, the method made a global residual connection. Compared with the current representative algorithm DASR, experiments show that the PSNR and SSIM of the proposed algorithm are improved 0.145dB and 0.0014 on Set14×2, and the PSNR of the proposed algorithm is improved 1.898dB and 0.252dB on Set14×3/4, respectively. The proposed algorithm achieves better performance than several current image super-resolution algorithms on five standard test sets. [ABSTRACT FROM AUTHOR]

The existing one-class support vector machine algorithms are based on the idea of "minimum margin". They consider only the noise close to the space origin and are sensitive to noise. The purpose of this paper is to improve the anti-noise ability of the one-class support vector machine through the idea of "optimal margin distribution", which considers both of the noise close to the space origin and that far from the space origin. This paper proposes a novel One-Class Optimal Margin Distribution Machine (OCODM) method. This method maximizes the margin and minimizes the margin variance to optimize the margin distribution. The experimental results have shown that compared to the existing one-class support vector machine algorithms, this method has better robustness. The conclusion is that this method is a supplement of the existing one-class support vector machine algorithms and can enhance the anti-noise ability of existing methods. [ABSTRACT FROM AUTHOR]

In order to alleviate the problems of frequent I/O of storage and space waste caused by dense graph data generated by hot topics in social networks, it propose a cache replacement algorithm based on topic heat evolution acceleration (THEA-CR) according to the evolution and update law of topic generation and death. Firstly, this algorithm divided the social network data into some topic clusters to identify anchor targets. Secondly, this paper calculated the topic heat evolution acceleration to evaluate and judge the priority of hot data. Finally, this paper designed a dual queue cache replacement strategy to replace and update the cache space according to topic concern and access frequency. Massive comparative experiments verify the feasibility and effectiveness of the proposed algorithm in Sina Weibo dataset with the baselines cache replacement algorithms. The results show that the proposed THEA-CR can improve the cache hit rate by about 31.4% on average and shorten the query response time by about 27.1% in different query operations of social network dense graph data. [ABSTRACT FROM AUTHOR]