Search

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]

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]

Aiming at the distributed unrelated parallel machine scheduling problem with machining constraints, this paper proposed an extended empire competition algorithm to solve the problem, which took the total transportation cost, evaluation function for simultaneous shutdown of parallel machines among factories and equilibrium evaluation function for average switching frequency of workpiece types among factories as optimization objectives. Based on the original empire competition algorithm, this algorithm added an initial factory-workpiece sequence group suitable for factory assignment. According to the shortcoming of the traditional empire competition algorithm that it was easy to fall into the local optimum, this paper divided the inferior sequence assimilation into the external assimilation mechanism and the internal assimilation mechanism. The extended empire competition algorithm combined local and global search methods to realize the intelligent search behavior. This paper used the partial matching crossover and single point mutation to update the factory-workpiece sequence group and ensure the diversity of the factory-workpiece sequence. Finally, this paper designed three different scales of 12 examples and verified the effectiveness of the proposed algorithm through simulation experiments. At the same time, this paper verified the advantages of the proposed algorithm in solving the distributed multi-objective unrelated parallel machine scheduling problem by comparing the research results in related fields. [ABSTRACT FROM AUTHOR]

To solve the problems of low recognition accuracy and poor generalization performance of existing face anti-spoofing models in different application scenarios, this paper adopted the idea of disentangled representation learning and proposed a face anti-spoofing method based on disentangled representation learning. This method adopted U-Net architecture and ResNet18 as the encoder-decoder. In the first stage of training, it inputted real samples so that the encoder only learned information related to real samples. In the second stage, this paper built an adversarial learning network, inputted samples without labels, feature fusion of the pre-trained encoder output and the new encoder output, reconstructed the image by the decoder, and performed adversarial training with the original image in the discriminator to achieve feature decoupling. Compared with some classic face anti-spoofing methods, the model paper achieved better detection performance. The lowest detection error rate in several experiments on the OULU-NPU data set is only 0.8%, which is better than classic detection methods such as STDN. The face anti-spoofing method used staged training to enable the model to obtain a more discriminative feature representation than the end-to-end model in adversarial training. It adopted a multi-classification strategy in the deception feature map output stage to reduce the impact of different image noises on classification results, and experiments on public data sets verified the effectiveness of the algorithm. [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]

The combination processing of molds and electronic product joint inspection introduce the mandatory concurrent operations on the same machine (MCDSM), which breaks the constraint that the same machine cannot process different jobs at the same time in the job shop scheduling (JSP) To solve this type of job shop scheduling problem, this paper proposed an adaptive hybrid initialization genetic algorithm (AHIGA). Firstly, this paper defined the problem as a generalized JSP considering mandatory concurrent operations on the same machine (GJSPMCO) problem, and established an optimization model using mixed integer programming with the objective of minimizing the maximum completion time. Next, it designed corresponding encoding and decoding techniques to support the representation and resolution of feasible scheduling plans within the constraints of MCOSM. Meanwhile, it established a population hybrid initialization method to generate high-quality feasible solutions. This paper also designed novel crossover and mutation operation methods to ensure the feasibility of newly generated solutions under the constraint of MCOSM. Additionally, it constructed an adaptive crossover and mutation operators to enable the adaptive updating of offspring, thereby enhancing the algorithms global search capability. Finally, it constructed 40 test cases based on JSP benchmark, and used these test cases and an example of joint inspection of electronic products for experiments. The results show that the proposed model and algorithm can effectively solve GJSPMCO problem, and the improvement strategies can enhance the quality of solutions, demonstrating the feasibility of the model and the superiority of AHIGA. [ABSTRACT FROM AUTHOR]

Periodic high utility sequential pattern mining (PHUSPM) has attracted much attention because it can find more practical regular patterns in time series. However, existing PHUSPM algorithms struggle to effectively handle incremental updates and overlook the downward closure property and complexity of the algorithm in large-scale data. To solve this problem, this paper proposed an IncPUS-Miner algorithm, which effectively realized the incremental mining of periodic high-utility sequential patterns (PHUSPs). IncPUS-Miner introduced a novel data structure called pu-tree. Each tree node corresponded to an updated utility list(UUL) to store the auxiliary information of the corresponding sequence. When incremental data was added, this structure allowed flexible updates to project information, thereby enhancing the dynamic adaptability and scalability of the algorithm. In addition, this paper proposed two new upper bounds of sequence utility, PUB and EUB, and two corresponding pruning strategies, which effectively reduced the computational burden. The experimental results show that the IncPUS-Miner algorithm effectively realizes the incremental mining of PHUSPs on real data, and shows superior performance compared with other algorithms. [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]

To solve the decision problem in which the evaluations are multi-granular intuitionistic linguistic sets, this paper proposed a TODIM method based on relative entropy and binary entropy. Firstly, this method defined relative entropy and binary entropy of the intuitionistic linguistic sets to measure the difference and uncertainty of decision information. Secondly, it built an expert weighting model on the basis of relative entropy and binary entropy, and proposed attribute weighting models under the scenarios where the subjective weight was completely known, partially known and completely unknown. Finally, in order to gather the information of multi-granularity group decision information, this paper developed a multi-granular intuitionistic linguistic weighted arithmetic average (MIL-WAA) operator. The example analysis shows that this method can better measure the uncertainty and difference of decision information, and it considers the limited rationality behavior of decision-makers, so it is reasonable and effective. [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]

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.)

Threshold private set intersection (TPSI) is a special case of secure multi-party computation, which is widely used in many fields such as machine learning, ride-sharing, and fingerprint recognition. However, currently existing solutions are all based on algorithms with high computational complexity and are only implemented under a semi-honest model, resulting in high computational overhead and inability to resist attacks by malicious adversaries. In order to solve the above problems, this paper first proposed a vector oblivious match test(VOMT) protocol and designed an efficient semi-honest TPSI protocol based on VOMT and cuckoo hashing. In addition, it combined VOMT and symmetric key encryption schemes to construct the vector oblivious decryption matching test(VODMT) protocol and designed a TPSI protocol based on VODMT and oblivious pseudorandom functions that could resist malicious adversaries. Subsequently, it proved the security of the protocol under the semihonest model and the malicious model respectively, and analyzed that the computational complexity and communication complexity of the two protocols were linear. When the set size is 4 096, the online running time of the two proposed protocols is 0.81 s and 1.81 s respectively, while the previous work required 5 627 s, so both protocols are efficient. [ABSTRACT FROM AUTHOR]

Aiming at the problem of difficulty in allocating channels efficiently for secondary users (SU) in complex and variable cognitive radio systems, this paper proposed a high throughput channel allocation protocol, TKMA protocol. The protocol constructed an utility matrix of user and channel based on primary user (PU) activities, SU real-time service demands, and channel conditions, etc., allocated channels with the objective of maximizing the total utility value of the SU system under the premise of guaranteeing the communication quality of the PUs, and solved the problem by using the improved Kuhn-Munkras algorithm and polling scheduling. To evaluate the performance of the protocol, it established a universal multi-user multi-channel cognitive radio system model, described the packet transmission process using queuing theory, and derived the performance indicators of SU through Markov steady-state solution. The experimental results show that the use of TKMA protocol yields better results in terms of total SU system throughput, average delay, average queue length, rejection rate and other metrics compared with the previously proposed simplification algorithm and the traditional equitable random assignment protocol, which proves the effectiveness of the proposed protocol and system model. [ABSTRACT FROM AUTHOR]

Aiming at the shortcomings of node connection and energy limitation in wireless sensor networks, this paper proposed a clustering routing algorithm based on AHC (HACCRA) to prolong the network lifetime. The algorithm firstly applied the aggregated hierarchical clustering to cluster network nodes, and then defined appropriate decision objective functions for cluster head (CH) selection, cluster formation, and path construction respectively, it used the energy threshold, proposed the distance threshold, and took priority of the one-to-one connection between CHs during the process of nodes' data transmission, effectively solving the unconnected problem of clustering and routing in algorithms. The simulation results show that compared with JCR, ICR, and DCK-LEACH, HACCRA can better achieve nodes' balanced energy-consumption, and ensure effective connection of data transmission in the network, so as to prolong the network lifetime. [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 single domain generalization (SDG) based on meta-learning has emerged as an effective technique for solving the domain-shift problem. However, the inconsistent semantic information between source and augmented domains and difficult separation of domain-invariant features from domain-related features make SDG model hard to achieve great generalization. To address the above problems, this paper proposed a novel meta-learning method based on domain enhancement and feature alignment (MetaDefa) to improve the model generalization performance. This method utilized background replacement and visual damage techniques to generate diverse and effective augmented images for each image, ensuring the consistency of semantic information between the source domain and the enhanced domains. The multi-channel feature alignment module fully mines image information by focusing on similar target regions between the source and enhanced domains feature spaces and suppressing feature representations of non-target areas, thereby effectively extracting sufficient transferable knowledge. Through experimental evaluation, MetaDefa achieved 88.87%, 73.06% and 57.06% accuracy on office-Caltech-10, office31 and PACS datasets, respectively. The results show that the MetaDefa method successfully achieves semantic consistency between the source and augmented images and adequate extraction of domain-invariant features, which significantly improves the generalization performance of single domain generalization models. [ABSTRACT FROM AUTHOR]

Aiming at solving the problem that rapid increase of time delay in data synchronization within existing mimic storage architecture, which led to the performance degradation during system security scheduling. This paper proposed a pre-synchronization model that enabled standby executors to utilize checkpoints in heterogeneous pools for data pre-synchronization, thereby reducing the time required for the executor to go online. Furthermore, according to the synchronization characteristics of the pre-synchronization model and the switching scheduling situation, this paper designed an execution cycle maximum efficiency checkpointing (CMEC) method. This method can determine the optimal checkpoint interval by maximizing the effective work rate of each execution cycle, balancing checkpoint overhead and rollback overhead. The experiments show that, compared with the existing full-volume synchronization strategy, this method shortens the synchronization time required for the executor to go online, improves the synchronization efficiency and ensures the stability and continuity of the system under increasingly heavy business loads [ABSTRACT FROM AUTHOR]

Aiming at the shortcomings of whale optimization algorithm (WOA) when solving problems such as high dimension, multi-peak and non-origin of optimal value, such as low convergence accuracy and easy to be captured by local optimum, this paper proposed a whale optimization algorithm based on multi-dimensional variation learning and distributed optimization (MLDOWOA) . Firstly, this algorithm introduced adaptive weights and dominant individual interference to dynamically adjust the direction of individual spiral surround, which improved the global search ability and convergence accuracy of the algorithm. Then, in order to further expand the search range of the algorithm, the improved algorithm used a multi-dimensional variation learning mechanism to adaptively plan the direction of population variation. Finally, it put forward the distributed optimization mechanism to coordinate the step size of search, so as to help the population break through the limitation of search stagnation in the middle and late stage. The test results on 8 high dimensional benchmark functions and 4 fixed dimensional benchmark functions show that, compared with the basic WOA, SSA and the improved WOA algorithms ACWOA, AWOA, MSIWOA, ADWOA, the proposed algorithm has significant advantages in convergence accuracy and ability to cope with high dimensional functions. This paper used the algorithm to tune the parameters of the FOPID controller, and compared the control results with the research results of this engineering problem in recent years, which prove the excellent performance of the proposed algorithm in FOPID parameter tuning problems. [ABSTRACT FROM AUTHOR]

In order to solve the problems of inadequate global search and easy to fall into local extremum, this paper proposed a multi-strategy fusion improved adaptive tunicate swarm algorithm（MITSA）. Firstly, this paper used the best point set strategy to improve population diversity during initialization. Secondly, it offered a multi-elite cooperative guidance mechanism to optimize the tunicates’ location information, and enhance the global exploration ability of the algorithm by increasing the exploration possibility of unknown search area. Then, the algorithm achieved dynamic global and local search balance by introducing adaptive weight factors into the group behavior stage. Meanwhile, probabilistic wavelet variation strategy promoted individual dynamic fine-tuning to enhance the anti-stagnation ability of the algorithm, while using the greedy principle to retain excellent information to help the population to the food source. Finally, this paper proved the global convergence of the improved algorithm based on Markov chain theory. Through the numerical simulation of the benchmark test function and CEC2014 complex function, the experimental results and Wilcoxon rank sum test results comprehensively verify MITSA’s excellent convergence accuracy, robust robustness and high-dimensional scalability. [ABSTRACT FROM AUTHOR]

In order to solve the problems of poor anti-interference and invasion of user privacy in traditional methods of using cameras for human activity recognition, this paper proposed a human activity recognition network based on spatiotemporal attention of millimeter wave radar 3D point cloud data to achieve accurate perception of intelligent application context. The network firstly used a secondary sliding time window to accumulate and separate the point cloud data generated by human activities as the input of the classifier, then used the PointLSTM unit to aggregate point features and states according to the point cloud coordinate relationship to extract the time sequence features of human activities, and then spliced temporal-spatial features, reduced the overall network computation and enhanced the network’s aggregation ability for local featured through sampling grouping modules, and finally used a stacked attention module to deeply fuse global and local features in temporal-spatial point cloud data to complete the accurate classification of human activities. This paper used millimeter wave radar to collect point cloud datasets of various human activities, the experimental results show that the average accuracy of the proposed spatiotemporal attention network can reach 98.64%,which can effectively identify complex and small-difference human activities, and meet the requirements of the human activity recognition system. [ABSTRACT FROM AUTHOR]

To solve the problems of video freezes and low quality of experience (QoE) in panoramic video transmission, this paper proposed a bitrate adaptive strategy based on viewpoint prediction (VPBAS) by studying the current popular viewpoint adaptive transmission scheme.Firstly, this paper constructed a viewpoint prediction model based on long short-term memory network and full convolutional network.The model concatenated the viewpoint data and video saliency information to realize the mutual complement and correction of different modal data, so as to improve the accuracy of viewpoint prediction.Secondly, the client used the random forest algorithm to predict the current available bandwidth, and selected the bitrate for video segments according to the prediction results and available bandwidth information.Finally, the client sent the selected bitrate information to the server regularly, and the server pushed the panoramic video stream of the best bitrate to the client according to the feedback information.It repeated this interactive process continuously during the video playback until the client finished watching.Experimental results show that VPBAS can effectively improve the user’s viewing experience under bandwidth limitation compared with other schemes. [ABSTRACT FROM AUTHOR]

In order to solve the problem that the current three-dimensional segmentation methods ignored the effective use of geometric features when mining point cloud features, this paper proposed the point cloud instance segmentation network 3D-BSNet with bilateral features and similarity measure. The network mainly consisted of two parts, such as bilateral feature learning and lightweight similarity measurement. Firstly, this paper proposed the bilateral feature extraction module with 3D-UNet based on submanifold sparse convolution and multi-layer perceptron. This module could extract semantic and geometric features of point cloud data after voxelization. Secondly, this paper designed the bilateral attention mechanism combining channel dimension and spatial dimension. This module could reduce the information loss in the process of bilateral feature aggregation. Finally, this paper developed the lightweight similarity measurement module. This module could obtain the similarity between neighboring point clouds in the high-dimensional embedded feature space and even generate the segmentation results of fine-grained instances. Experiments show that 3D-BSNet performs well on S3DIS and Scannet（v2） dataset, and the average accuracy rate on Scannet (v2) is 3.3% higher than that of SSTNet, which effectively improves the precision of 3D instance segmentation. [ABSTRACT FROM AUTHOR]

Privacy protection technologies mainly include attribute-based encryption, homomorphic encryption, multiparty security computing, etc. Among them, in the access control of attribute-based encryption, bilinear mapping is time-consuming, homomorphic encryption is difficult to verify the results of plaintext computation in a non-public way,and multi-party security computation requires a trusted third party. To solve these problems, this paper proposed a batch zero knowledge identity authentication scheme based on attribute access strategy. This proposed scheme is based on the Aurora protocol and has good computing potential against quantum attacks. The proposed scheme introduces a synthetic prover to synthesize a proof of the proof generated by each user and reduce the computational cost of the prover and the verifier, and designs a search algorithm to find out unauthenticated users. Finally, this paper carries out safety analysis, feasibility analysis, and comparative analysis with other schemes. After analysis, the verification time in this scheme can be maintained in o (n). [ABSTRACT FROM AUTHOR]

Current bitmap collaboration models suffer from issues such as large volume of data transmission, poor flexibility, overlapping conflicts and storage pressure. To solve these problems, this paper proposes a collaborative editing model for complex bitmaps. Collaborative operation that sends only the coordinates and color change, featuring low data volume, multi-dimensional granularity, and overlap able. Adds a four-dimensional bitmap collaborative architecture with spatiotemporal relationship, and only saves the edited pixel data, which can save more storage space; A replica state control algorithm based on rollback that ensures operations are executed on correct replica. An algorithm that can dynamically generate branch versions according to the current state and policy configuration, solving the problem of too many branch versions. Finally, inferring model correctness based on the CCI model, develop a prototype collaborative editor “Co-Pixel”, execute experiments based on randomly generated operation sets, simulation of actual editing behavior against Adobe Lightroom. Results show that this model can avoid conflicts between independent operations to a greater extent, can reduce the algorithmic overhead in the consistency maintenance process, can flexibly adjust the intent retention policy, and can generate a version of the result that reduces the user’s intent maintenance effort. The model in this paper provides a good solution for collaborative bitmap editing. [ABSTRACT FROM AUTHOR]

After the outbreak of the epidemic, the distribution of living supplies in residential areas under closed management become one of the focal issues to be solved urgently, and this problem can be abstracted as the the location problem of distribution points for living supplies during the epidemic, whose essence is the NP-Hard problem in combinational optimization. This paper studied the exact algorithm of the location problem of distribution points for living supplies during the lockdown period. Firstly, the paper researched some mathematical properties and corresponding proof of the problem, and these properties could be used to reduce the size of the given problem, thereby reducing the difficulty of the problem solving. Then the paper designed allocation sub-algorithm, upper and lower bound sub-algorithms and the reduced order sub-algorithm. Based on these sub-algorithms, the paper proposed a backtracking algorithm with reduction which can reduce the size of the problem and get the optimal solution. Finally,the paper analyzed and solved several examples to further illustrate the principle and execution process of the proposed algorithm. The results show that the proposed algorithm can reduce the difficulty of solving the problem by reducing the size of the problem. [ABSTRACT FROM AUTHOR]

The level of face recognition technology continues to improve, and has achieved an ideal recognition rate in identity authentication, human-computer interaction and other industrial applications, and the market scale keeps growing. However, the occlusion problem in real scenes has not been completely solved. How to restrain or eliminate the negative impact of occlusion on key facial feature, is one of the hot spots in the field of face recognition. Aiming at the problem of lack of face structure information caused by occlusion, this paper reviews the occluded face recognition datasets and the occluded face recognition methods. Firstly, this paper introduces and analyzes some important new occluded face recognition datasets; Secondly, this paper summarizes the traditional learning methods and deep learning based methods to solve occlusion problems, and emphasizes the deep learning based robustness feature extraction and occluded facial information recovery. Finally, this paper summarizes and analyzes the advantages and disadvantages of relevant methods, points out the problems and challenges of occluded face recognition, and prospects the future research directions. [ABSTRACT FROM AUTHOR]

In order to achieve a fair distribution of benefits in federated learning, an indicator that quantifies the contribution of each data provider to the global model is critical. Aiming at the problems of privacy leakage, opacity and dependence on central server in existing contribution evaluation schemes, this paper proposed a transparent federated learning contribution evaluation scheme based on blockchain. Firstly, this paper proposed an improved Paillier secure aggregation algorithm, which avoided the inference of user local data in the model aggregation stage by joint decryption. Secondly, this paper proposed a method to approximate the contribution based on the gradient of user cumulative submission, which solved the problem of privacy leakage in the existing contribution evaluation scheme. In addition, it integrated the evaluation of the contribution into the consensus process of the blockchain, making the evaluation results auditable. Finally, experiments based on MNIST dataset show that the proposed method can effectively evaluate the contribution. [ABSTRACT FROM AUTHOR]

In order to solve the problem that the existing text guided image inpainting models lack efficient fusion of information between modes when dealing with text image fusion, resulting in unreal repair results and poor semantic consistency, this paper proposed a text guided image inpainting model BATF, which integrated image text features through conditional batch normalization. Firstly, it normalized the damaged and undamaged regions respectively by the spatial region normalization encoder to reduce the influence of direct feature normalization on the mean variance shift. Secondly, through the depth affine transformation, it fused the extracted image features and the text feature vectors to enhance the visual semantic embedding of the generator network feature map, so that the image and the features could be fused more effectively. Finally, it designed an efficient discriminator and introduced a target perception discriminator in this paper to enhance the texture authenticity and semantic consistency of the repaired image. Quantitative and qualitative experiments on CUB bird, a text-labeled dataset, show that the proposed model achieves 20.86,0.836,and 23.832 for PSNR, SSIM, and MAE, respectively. BATF model is better than the existing models MMFL and ALMR, and the repaired images both meet the requirements of given text attributes and have high semantic consistency. [ABSTRACT FROM AUTHOR]

This paper proposed a self-supervised training method based on inter-frame consistency to solve the problem that the current inverse rendering supervised learning method is challenging to obtain labels and has poor generalization ability. Due to the ill-posed nature of the inverse rendering problem, this paper introduced additional albedo consistency loss and cross-rendering loss to strengthen the self-supervised network, the main idea of which was to enforce inter-frame consistency constraints on image sequences with continuous illumination changes. The method performed image projection and warping between adjacent frames through pose maps and depth maps between image frames. This method established constraints between adjacent frames and used Siamese training to ensure photometric invariance consensus estimate. This paper used a fully convolutional neural network to recover geometry, reflectivity, and illumination from indoor video sequences. The method trained the self-supervised network using a collection of unlabeled consecutive frame images and incorporating a differentiable renderer, making the network learn in a self-supervised manner. Compared with other mainstream methods, quantitative and qualitative experimental results show that the proposed method performs better on multiple benchmarks. [ABSTRACT FROM AUTHOR]

It is difficult to label the label proportions data contaminated by noise in practical applications. This paper applied multi-view learning to uncertain learning with label proportions to improve classifier both performance and stability. Firstly, the proposed method introduced kernel function and super instance label for the representation of multi-view knowledge and label proportions information respectively, and considered the limitation of uncertain label proportions data to construct the model of uncertain label proportions information-based multi-view learning. Then, it transformed the model to its dual forms by the Lagrange method for solving the problem and introduced an iterative framework to obtain the classifiers of multiple views. Finally, this paper applied the proposed method to datasets of text categorization. Extensive experiments show that the proposed method outperforms the existing single-view learning with label proportions methods in accuracy and noise sensitivity. [ABSTRACT FROM AUTHOR]

Knowledge graph embedding designs to map the entities and relations into low-dimensional and dense vector spaces. The existing embedded models still have the following two defects: most of the existing models only focus on the semantic information of knowledge graph, but ignore plentiful hidden information of triples; the existing models only concern the unidirectional information of the entity, but ignore the bidirectional potential information. This paper proposed the knowledge graph embedding model Bi-HTGAT to solve these problems. The model designed a hierarchical type attention mechanism, considered the contribution of different entities of each type to the central entity under different relations. At the same time, this paper introduced the directional attention mechanism of the relations, fused the neighbor information in different directions to update the entities and relations embedding, and finally aggregated the two parts of information to obtain the final embedding of the entity. The experimental results show that Bi-HTGAT performs better than other baseline models in link prediction, which fully proves that Bi-HTGAT can further improve the accuracy of embedding results. [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.)

In order to address the shortcomings of the facial landmarks detection models, which cannot model the relations between long-distance landmarks, this paper proposed a parallel multi-branch architecture combining with convolution and Transformer for facial landmarks tasks, called MCTN, it utilized the dynamic attention mechanism to model the long-distance relations between facial landmarks. The multi-branch parallel structure designing allowed MCTN to include shared weights, global information fusion and other merits. What’s more, this paper proposed the novel Transformer structure, Deformer, which could make the MCTN focused attention weights faster on sparse and meaningful locations and solved the problem of slow convergence of Transformer. MCTN reached 4.33%,3.12% and 3.15% normalized average error respectively on the WFLW,300W and COFW datasets, the results show that MCTN utilizes Transformer with CNN multi-branch parallel structure and Deformer structure to dramatically outperform other facial landmarks localization algorithms based on convolution network. [ABSTRACT FROM AUTHOR]

Current knowledge distillation algorithms only distill between the corresponding layers. In order to solve the problem and improve the performance of knowledge distillation, this paper first analyzed the inference of the low-level features of the teacher model on the high-level features of the student model. On this basis, this paper proposed a knowledge distillation method for object detectors, which is based on knowledge review and feature decouple. Firstly, it aligned and fused the high-level feature maps of the student model, then extracted attention maps on spatial and channel dimensions separately, so that the high level features of students could learn the low-level and high-level knowledge of teachers progressively. Afterwards, it decoupled and distilled the foreground and background separately. Finally, it used a pyramid pooling to calculate the similarity between the features of the teacher model at different scales. This paper conducted experiments on different object detectors. Experiments show that the proposed method is simple but effective, and can be applied to a variety of different object detectors. RetinaNet and FCOS with backbone networks of ResNet-50 obtained 39. 8% and 42. 8% mAP on the COCO2017 dataset, respectively, which are 2. 4% and 2. 3% higher than the benchmark. [ABSTRACT FROM AUTHOR]

In order lo meet the fine-grained security isolation requirements of 5 G vertical users for network slicing deployment, while taking into account the isolation requirements of users and improving resource utilization, this paper proposed a network slicing security deployment method based on the improved BN model. Firstly, this paper proposed a dual-layer BN model network slicing deployment architecture, and designed a dual-layer virtualization architecture of virtual machine container based on SBA . It assigned conflict of interest labels to the network slicing according to the isolation requirements of users. It determined the isolation deployment strategy of network slice based on the improved BN model deployment rules. Then, it established the deployment method as an integer linear programming model, and took the deployment cost as the objective function. This model realized the low-cost deployment network slices by minimizing the objective function. Finally, this paper used genetic algorithm to solve the problem. The experimental results show that the proposed security deployment method can reduce the deployment cost on the premise of meeting the requirements of network slice security isolation. [ABSTRACT FROM AUTHOR]

A variety of factors will affect the combination and distribution of the molds used in the production of prefabricated components on the mold table, and will produce many combination and distribution results. In order to solve such problems and quickly find the best distribution results of the molds on the mold table, this paper proposed a mold combination method based on the combination of backtracking method and improved Eclat algorithm. Firstly, it built a binary tree model based on the mold combination relationship in the historical data, searched the binary tree through the backtracking method, and obtained all theoretically feasible mold combination results. Then it pre-placed these combination results by using the improved BL positioning algorithm on the mold table with a fixed area, and screened out the mold combination results that met the actual placement conditions. It used Eclat algorithm to obtain the optimal combination set of mold adaptation from the selected combination results, determined the association rules between different types of molds,and used the rules to guide the allocation process of molds on the mold table in the new component production task. At the same time, this paper improved the Eclat algorithm by introducing the partition idea and the priori constraint idea based on probability, so as to improve its operation efficiency when dealing with large-scale data. Finally, through the simulation test of the case data in the prefabricated component manufacturing enterprise, it verified the effectiveness of the method to quickly solve the problem of mold table combination allocation. The results show that the mold combination allocation based on backtracking and DEclat algorithm method has a good effect on the utilization of the mold area, the reduction of the mold changing time and the reduction of the total completion time. [ABSTRACT FROM AUTHOR]

Accurately estimating the critical operations that affect the quality of customized printed circuit board (PCB) can better guide enterprises in lean management of product quality. However, the common methods of enterprises are difficult to use the deep semantics between operation-related entities. To solve this problem, this paper constructed a knowledge graph of operation-related entities and proposed GENI-SD to estimate the importance of PCB operation. Firstly, this paper employed the knowledge graph to represent the relationship between operation-related entities, and utilized the graph neural network model GENI to estimate the importance of operation nodes. Secondly, this paper improved GENI and established a novel model called as GENI-SD by introducing a sampling module based on an improved predicate-aware attention mechanism and a score aggregation considering the direction of adjacent edges, thus to resolve noisy neighbors and non-direction aggregation shortcoming of GENI. Finally, it conducted experiments on the real data of PCB workshop. The results demonstrate that GENI-SD outperforms SOTA and obtains 6. 78% and 0. 71 % improvement in Spearman and NDCG@ 10 metrics comparing to that of GEN! respectively. This study provides a novel and effective method for estimating the importance of operation. [ABSTRACT FROM AUTHOR]

Continual learning, as a special machine learning paradigm that continuously learns new tasks in non-stationary data streams and can maintain the performance of old tasks, is a hot research topic in fields such as visual computing and autonomous robotics, but at this stage, the catastrophic forgetting problem is still a great challenge for continuous learning. This paper conducted a review study on the catastrophic forgetting problem of continual learning, analyzed the mechanism of catastrophic forgetting problem mitigation and explored the catastrophic forgetting problem solving strategies at three levels, included regularization strategy, replay strategy, dynamic architecture strategy and joint strategy, in terms of model parameters, training data and network architecture. According to the existing literature, this paper condensed the evaluation index of the catastrophic forgetting method and compared the performance of solving strategies for different catastrophic forgetting problems. Finally, it pointed out the future research direction of continual learning, to provide references for the study of continuous learning catastrophic forgetting problems. [ABSTRACT FROM AUTHOR]

Local feature information plays an important role in image segmentation, however, the referring image segmentation task is dependent on the text expression, so it is impossible to extract local feature information directly from the original reference image. In order to solve this problem, this paper proposes a specific noun-guided local feature extraction deep neural network model（NgLFNet). The NgLFNet model can automatically mine the local feature information of the object to be segmented according to the key nouns in the input text expression. Specifically, the model first obtains key nouns in text through sentence analysis; secondly, extracting corresponding features through text and image encoders, and using the key nouns to obtain local features of high-interest regions through the multihead attention mechanism; then the multi-modal features are gradually fused to learn; Finally, the decoding and correction module uses the obtained local features to perform more detailed corrections on the prediction mask to obtain the final result. The method in this paper is compared with a variety of mainstream referring segmentation methods and the experimental results show that the proposed method improves the accuracy of text-based instance segmentation task. [ABSTRACT FROM AUTHOR]

Entity linking studies are mainly focused on the fields of medical care, biology and news, but less on the field of civil aviation. Therefore, this paper carried out a research on entity linking task in civil aviation domain, and found that there were many entity variants and less ambiguity in entity linking. To solve these problems, this paper proposed an entity linking framework based on semantic inference and a negative sampling strategy for enhancing the robustness of the framework. This paper conducted comparative experiments on the civil aviation field dataset. Experimental results show that the performance of the proposed framework is better than the existing benchmark frameworks, and the effectiveness of the negative sampling strategy is verified through ablation experiments. With the negative sampling strategy, the Acc@ top1 of the proposed framework is as high as 0. 875. [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.)

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

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

Generative adversarial network (GAN), as an emerging generative model, has been gradually developed and applied in the fields of image generation, 3D reconstruction, cross-modal conversion, etc. It effectively solves the problem of inefficiency of conventional convolutional neural networks in image-generating tasks and fills the shortage of deep learning in the field of image generation. In order to help subsequent researchers quickly and comprehensively understand GAN, this paper sorted out the improved model of GAN based on the literature in recent years. It firstly introduced the basic principles of GAN from two perspectives of network structure and objective function, then elaborated and summarized various derivative models of GAN from two major perspectives of improvement and application types. Secondly it summarized and analyzed the quality and diversity of generated images from the perspectives of subjective qualitative, objective quantitative and task-specific evaluation. Finally, this paper discussed some core issues and latest research progress of GAN series models in recent years and analyzed the future development trend. [ABSTRACT FROM AUTHOR]

In recent years, the deep learning network model based on UNet and GAN (generative adversarial network) has shown unique advantages in the field of image restoration. But, there are still artifacts, blurring, degradation of texture details, difficult to repair large-area damage, and the repaired holes are incompatible with the background image. In order to solve the problems that the current existing models are not friendly to the repair of large-area damaged images and the degraded images after repair, this paper improved the Shift-UNet model by studying the existing methods. On the basis of U-Net and GAN, this paper added an improved attention mechanism Attention-UNet between each layer of encoder and decoder and integrated it into the Shift-UNet to form Attention-Shift-UNet. And through research, it changed the activation function of the original down-sampling part from Leaky＿ ReLU to SiLU. The improved model not only achieved good results on the 64×64 central cover, but also realized the random cover, and the cover area increased from 20 % to 80 %. The experimental results show that the repair effect of the proposed model is better, especially for the repair of large-area damaged images. After testing on CelebA, Paris Architecture and Paris Stree View datasets, the evaluation indexes have been significantly improved, and SSIM has increased from 0.944 5 to 0.947 1. PSNR is increased from 27.992 7 to 28.553 6. L2 loss is decreased from 0.001 7 to 0.001 5. [ABSTRACT FROM AUTHOR]

Most of the commonly used trace clustering methods use a relatively single standard, such as using the activity sequence relationship, while ignoring the activity behavior relationship, time or resource attributes, which is unfavorable for some flexibly configured business process systems, as it hard to improve the quality of process mining. In order to solve such problems, this paper proposed a multi-perspective trace clustering method based on activity behavior relationship and association time. Firstly, this method constructed the control flow code according to the behavior relationship between activities. At the same time, in terms of time attributes, it used a group of nearest association activity pairs and their time differences to represent traces. Secondly, it used weighted aggregation to integrate the trace similarity under the two perspectives, and then adjusted the clustering results. Finally, the paper applied this method in the login system scenario and compared with other clustering methods on five real logs. The experimental results show that the method can find process scenarios from complex login systems, and verify the superiority of the method from three metrics of fitness, precision and Fl score. [ABSTRACT FROM AUTHOR]

In order to further mine the changelog information, this paper proposed a siamese Bi-lSTM network model based on the attention mechanism to classify the changelog to realize topic annotation and assist in locating the location of code defects. The model proposed a word segmentation tool with security features to realize changelog preprocessing, used Bi-lSTM network to learn changelog contextual semantic information, and solved the problem of overfilling mode existing in changelog itself through siamese neural network and expanded the data set with high quality to improve generalization ability. It carried out serialization training for the changelog composed of multiple sentences, and the influence of sentences was distinguished through the attention mechanism. For some changelogs of the defect repair class, this paper improved the LLVM tool, generated a mapping table to search the log content, and located the location of the defect module in the source code. A large number of experimental results show that the classification effect of the model in this paper has strong generalization ability, and is nearly 10% higher than the general methods in text classification methods in terms of accuracy, F, value and other indicators, has ideal log classification effect and topic learning effect. [ABSTRACT FROM AUTHOR]