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]

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

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

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

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

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

Aiming at the problems of inaccurate semantic segmentation results and rough saliency maps of indoor scene images, this paper proposed a network architecture (feature regulator and dual-path guidance, FG-Net) based on multi-modal feature optimization extraction and dual-path guided decoding. Specifically, the feature regulator sequentially performed noise filtering, re-weighted representation, differential complementation and interactive fusion on the multi-modal features at each stage, and optimized multi-modal feature representation in the feature extraction process by strengthening RGB and depth feature aggregation. Then, the dual-path guidance component introduced rich cross-modal cues after feature interactive fusion in the decoding stage to further take advantage of multi-modal features. The dual-path cooperative guidance structure outputted a more detailed saliency map by integrating multi-scale and multi-level feature information in the decoding stage. This paper conducted experiments on the public datasets NYUD-v2 and SUN RGB-D, and achieved 48.5% in the main evaluation metric mIoU, which is better than other state-of-the-art algorithms. The results show that the algorithm achieves more refined semantic segmentation of indoor scene images, and has good generalization and robustness. [ABSTRACT FROM AUTHOR]

Emerging network architectures and technical service requirements for B5G and 6G will enable MEC with CF-mMIMO, helping to handle compute-intensive and latency-sensitive tasks in distributed IoT. For CF-mMIMO-assisted MEC systems, this paper aimed to minimize the delay in completing computational tasks of different task types under energy constraint. In order to solve the above goals, this paper designed a task offloading strategy based on UEs, multiple APs and CPU (central processing unit) for cloud-edge-end collaboration. Specifically, according to the different data types of each UE and AP service, this paper firstly used the convex optimization and graph matching methods to alternately iterate to optimize the offload association and task ratio. Then, under the limitation of the backhaul link, this paper used an improved binary whale optimization algorithm to further offload the tasks of unallocated terminals and associated access points to the cloud with efficient processing. Compared with other meta-heuristics such as ant colony optimization algorithm and hybrid gray wolf optimization algorithm, the proposed algorithm has better performance on discrete offload optimization problems, which can provide a good offload optimization strategy for distributed systems and greatly reduce the average delay of the whole network. [ABSTRACT FROM AUTHOR]

To address the issues of low efficiency and frequent security vulnerabilities in smart contract development, this paper proposed a smart contract auto-generation method based on code comment optimization. Firstly, it constructed a smart contract clustering analysis model based on the semantic information of smart contract code associated annotations to achieve fast and accurate clustering of functions similar to smart contracts. Then, it divided the smart contract knowledge base into different levels such as the contract layer, function layer, and interface layer associated with the annotation. And based on the clustered code and annotation information, it constructed a diversified Prompt feature prompt statement dataset. Finally, it achieved automatic generation of smart contracts with specific needs based on the large language model ChatGLM2-6B and with the help of P-Tuning v2 fine-tuning technology. In order to test the effectiveness of this method, this paper conducted comparative experiments with existing methods using the bilingual translation quality assessment assistant tool BLEU and the code security detection tools Mythril and VaaS. Experimental results show that the average BLEU of the code generated by this method is increased by about 13%, and the code security is improved by about 6%. This method integrates code annotation information into the automatic generation of smart contracts, effectively improves the quality of smart contracts, and provides a new method for the efficient development of safe and reliable smart contracts. [ABSTRACT FROM AUTHOR]

Currently, researchers are focusing on efficient applications and resource scheduling strategies in vehicular edge computing (VEC) environments, however, the real-world validation of these applications and strategies is often limited by cost and time and cannot be performed quickly and efficiently. The emergence of edge/fog computing simulators such as iFogSim2 reduces the cost of experiments. However, the connection switching and resource allocation requirements of high-speed moving vehicles pose challenges to the application of edge/fog computing simulators under VEC. Therefore, this paper improved iFogSim2 by designing VECSim, a VEC environment simulator that supported high-speed mobility. It integrated open-source base station data and constructed vehicle trajectory datasets so that researchers can focus on resource allocation strategies. Firstly, to simplify the experimental steps, this paper improved the mobile trajectory data parsing module and adapted the vehicle trajectory data generated by Simulation of Urban Mobility (SUMO), a microscopic transportation simulation software. Secondly, this paper modeled distributed applications under VEC based on the distributed data flow model and provided a service migration benchmark policy algorithm. In addition, VECSim introduced a time-performance optimization method to accelerate the simulation event processing by parallelizing the operation, which improved the time performance of the simulation tool. Experiments show that compared with similar service migration algorithms in iFogSim2, the proposed service migration algorithm exhibits good stability under the validation of large-scale motor vehicle trajectory dataset, and the time-performance optimization method achieves a 5.3% performance improvement in execution time. [ABSTRACT FROM AUTHOR]

In order to further optimize the overlapping community detection algorithm, this paper proposed a new definition of node importance based on degree and node clustering coefficient, and the nodes were updated in descending order of node importance, and the node update strategy was fixed to improve the stability of community detection. On this basis, this paper proposed an OCD-GEMPA. The algorithm combined the node2vec model to represent the nodes in a low-dimensional vector, constructed a matrix of weight values between nodes, calculated the label attribution coefficient according to the weight values, and selected labels accordingly, avoiding the problem of random selection. Experimental verification of the algorithm on real data sets and synthetic data sets shows that compared to other overlapping community detection algorithms, the OCD-GEMPA algorithm has significant improvements in both EQ and NMI indicators, with better accuracy and stability. [ABSTRACT FROM AUTHOR]

Knowledge tracing aims to model the state of knowledge and ultimately predict the future performance of learners by describing exercises through the representation of concepts. However, in terms of the representation of concepts, the current research doesn’t model the influence of historical knowledge concepts on the temporal relationship of the current concepts, nor does it describe the role of the spatial relationship between various concepts in the exercise. In order to solve these problems, this paper proposed a knowledge tracing model characterized by temporal and spatial correlation fusion. First of all, based on the degree of temporal correlation between concepts, it modelled the temporal effect of historical concepts from current concepts. Secondly, it modelled the spatial interaction between several concepts contained in the exercise to obtain the representation of knowledge points containing temporal and spatial information through the graph attention network. Finally, it used the above representation of concepts to derive the representation of the exercises, and generated the current state of knowledge through the self-attention mechanism. In the experimental stage, this paper compared the performance of the proposed model with the five relevant knowledge tracing models on four real datasets. The results show that the proposed model has better performance. In particular, compared to the five comparative models on the ASSISTments2017 dataset, the AUC and ACC are improved by 1.7%～7.7% and 7.3%～12.1%, respectively. At the same time, the ablation experiment proves the effectiveness of modeling the temporal and spatial correlation between concepts, and the training process experiment shows that the proposed model has certain advantages in the representation of concepts and the modeling of their interaction relationships. The application examples can also show that the model has better practical results than other knowledge tracing models. [ABSTRACT FROM AUTHOR]

Spatial co-location pattern mining aims to discover the association between spatial features and has been an important research direction in spatial data mining. Spatial co-location pattern mining method based on column calculation (CPM-Col algorithm) avoids the most time-consuming operation of generating table instances and directly searches for participating instances. This method has become one of the most efficient approaches. However, backtracking search for participating instances remains a bottleneck, especially in dense datasets and long pattern mining. To accelerate the search for participating instances, this paper proposed two improvements to the CPM-Col algorithm with less extra computations. Firstly, the row instances found by CPM-Col algorithm were stored as partial table instances, for avoiding backtracking calculations of many instances. Secondly, after successfully finding a row instance, some instances of the first feature were obtained by the sub-clique reaction of the row instance. Based on these improvements, this paper proposed a co-location pattern mining method based on improved column calculation (CPM-iCol algorithm) and discussed complexity, correctness, and completeness. Experiments were conducted on synthetic and real datasets. Comparing to a classical algorithm join-less and CPM-Col, the CPM-iCol algorithm significantly reduces mining time and backtracking times. The results show that the proposed algorithm has better performance and scalability than CPM-Col algorithm, especially in dense datasets. [ABSTRACT FROM AUTHOR]

In order to solve the problem that it is difficult for the model to perceive implicit information due to the lack of external knowledge in rumor detection, which limits the ability of the model to mine deep information, this paper proposed knowledge graph based multi-feature fusion rumor detection (KGMRD) method. Firstly, for each event, it constructed posts and comments together into a text sequence and used a classifier to extract the emotional features. This paper constructed a knowledge graph based on text using ConceptNet and aggregated the entity representation in the knowledge graph with the semantic features of text using the attention mechanism, so as to obtain the enhanced semantic feature representation. Secondly, in terms of communication structure, for each event, this paper built its communication structure diagram based on the propagation and forwarding relationship of the post, and used DropEdge to prune the communication structure diagram, so as to obtain more effective communication structure characteristics. Finally, it fused the obtained features to get a new representation and compared seven models including SVM-RBF on three real datasets of Weibo, Twitter15 and Twitter16. The experimental results show that compared with the current baseline with the best effect, the KGMRD method has the best ACC on the Weibo dataset and improves the ACC by 1.1%, and there is a 2.2% improvement on Twitter15 and Twitter16 dataset in ACC. The experiment proves that the KGMRD method is reasonable and effective. [ABSTRACT FROM AUTHOR]

Floating car GPS data serves as the foundation for processing traffic information, with the rapid increase in the number of monitored vehicles, a massive amount of GPS data is generated, posing great challenges to map matching. To address the shortcomings of traditional matching methods in terms of matching efficiency and accuracy, this paper proposed a real time parallel map matching algorithm for massive GPS data that ensured both high matching accuracy and computational efficiency. This paper firstly reconstructed an efficient and accurate real-time map matching algorithm for streaming data by introducing a comprehensive weight factor that considered velocity and direction to enhance the offline map matching algorithm that relied on historical trajectories. Then, it introduced the Spark Streaming distributed computing framework to achieve real-time and parallel computation of the map matching algorithm, significantly improving the efficiency of real-time map matching. Experimental results demonstrate that the proposed algorithm achieves more than a 10% increase in matching accuracy compared to conventional topological matching algorithms on complex road sections, with an overall matching accuracy of over 95%. In terms of matching efficiency, it achieves approximately a fourfold improvement compared to an equivalent number of standalone servers. The experimental results show that the proposed algorithm achieves real-time map matching of 80 million GPS data points on a computing cluster composed of 11 machines, proving that the proposed algorithm can achieve real-time vehicle matching in urban areas. [ABSTRACT FROM AUTHOR]

Blockchain technology has great potentiality in the secure sharing of electronic health records. However, current solutions face issues such as large storage space and low consensus efficiency. This paper proposed a novel scheme based on blockchain and friend and relative nodes. Firstly, this paper adopted a distributed file system to store users’ complete electronic health records on offline servers, and constructed a set of user’s friend and relative nodes. Each user’s data was stored redundantly by its friend and relative nodes, and only the block’s header information was stored on the chain, reducing storage space. Then, this paper designed a data access mechanism based on multi-signature technology, using Shamir secret sharing mechanism to distribute user’s private keys to their relatives and friends. More than half of the relatives and friends could use their own private keys to reconstruct users’ private keys, solving data access problems in emergency situations. Finally, this paper proposed a credit based Byzantine fault-tolerant consensus mechanism, which used the top 10% nodes with credit values as the leader node set and utilized a random algorithm to generate the master node in the leader node set. And it improved consensus security. The experimental results show that compared with existing methods, the proposed scheme reduces the on-chain storage space by 1/7, improves data access efficiency by 15 times, and has higher consensus security while ensuring good latency and throughput. The proposed scheme can achieve secure and efficient sharing of electronic health records, providing a case for the application of blockchain in the medical field. [ABSTRACT FROM AUTHOR]

The wide application of deep learning techniques has strongly promoted the development of the medical image analysis field. Most deep learning methods usually assume that the training and test sets are independent and identically distributed. However, the assumption is problematic to guarantee when the model. Resulting in the dilemma of model performance degradation and poor scene generalization ability. Deep learning-based domain adaptation techniques are the mainstream methods for improving model migration ability, which aims to enable the model trained on one dataset to obtain better results on another dataset with no or only a small amount of labels. Due to the difficulties in sample acquisition and labelling, unique image properties and modal differences in medical images, it brings many practical challenges to domain adaptive technology. This paper firstly introduced the definition and primary challenges of the domain adaptation and then classified and summarized related algorithms in recent years from a technical point of view, compared and analyzed their advantages and disadvantages, and then introduced the medical image datasets commonly used in domain adaptation and related algorithm results in detail. Finally, this paper prospected the future research direction of domain adaptation for medical image analysis regarding development bottlenecks, technical means, and cross-cutting areas. [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.)

To solve the problem of privacy leakage and multi-task allocation in crowdsensing, this paper proposed an edge assisted crowdsensing location privacy protection(EALP) multi-task allocation mechanism. Firstly, considering the geography of tasks, this paper used improved fuzzy clustering(FCM) algorithm to cluster tasks locations, improved the clustering index, and enhanced the rationality of multi-task allocation. Secondly, to prevent collusion between the cloud and perceived users, it proposed a location privacy protection protocol in the task allocation phase. It deployed homomorphic encryption among the perceived users, cloud and edge nodes. The cloud could safely calculate the mobile distance of the perceived users without knowing their locations and the location of the task cluster center. Finally, it proposed a multi-task allocation optimization scheme based on ant colony algorithm, it balanced the interests of both platform and perceptive users by optimizing the path of execute tasks. Experiment results show that compared with similar methods, the proposed mechanism improves task completion rate while protecting location privacy, and reduces system perception costs and user mobility costs. [ABSTRACT FROM AUTHOR]

U-Net has achieved great success in the field of image segmentation. However, some of the position information is lost in the process of convolution and downsampling, model is difficult to learn global and long-range semantic interaction information and lacks the ability to integrate global and local information. To extract rich local detail and contextual information, this paper proposed an image segmentation network called MLFCNet, combining a convolutional module and a capsule encoder. Based on the U-Net, this paper introduced a capsule network module to learn target positional information and the relationships between local and global information. At the same time, the proposed attention mechanism could retain the information discarded by the network pooling layer. This paper designed a new attention mechanism so that multi-scale features could be fused, where global information was captured and background noise was suppressed. In addition, it proposed a new local feature co-occurrence algorithm to better learn the relationship between local features. The proposed method was compared with nine methods on two public datasets, mIoU improves 4.7% and Dice coefficient improves 1.7% in liver medical images compared to the second highest performing model. Experimental results on the dataset of liver and dataset of human show that under the same experimental conditions, the proposed network is superior to U-Net and other mainstream image segmentation networks. [ABSTRACT FROM AUTHOR]

With the increasing popularity of IoT applications, the number of IoT device terminals is proliferating, the types are diverse, the levels are complex, and they are often in an uncontrollable environment, so it is critical to ensure the security and privacy of the data transmission process. This paper explored smart home services based on IoT architecture. Enabling smart home applications involved multiple parties, such as users, the cloud, ISH and smart devices, which required multi-party authentication for secure communication. This paper proposed a lattice-based multi-party authenticated key agreement protocol for smart home applications and proved that it was secure under the eCK model, and its security could be attributed to the difficulty of RLWE problem, which was resistant to quantum computing attacks. The proposed protocol is converted from an identity-based encryption scheme on lattice, does not require a public key certificate and avoids the deployment of a large PKI, achieves explicit authentication through message interaction, and can have a certain anonymity. Compared with other related post-quantum lattice-based multi-party authenticated key agreement protocol schemes, the proposed protocol is more advantageous in terms of security and execution efficiency. [ABSTRACT FROM AUTHOR]

At present, the mainstream solution of edge computing offloading is to model it as a multi-objective optimization problem to minimize energy consumption and delay. Different from the existing research, this paper mainly considered that tasks in different unloading areas had certain similarity in edge computing, which could be used to accelerate the convergence speed and solution effect of the algorithm. Based on this, this paper proposed an evolutionary multi-task multi-objective optimization algorithm to solve task offloading problems in different regions based on evolutionary multi-task optimization. This algorithm considered multiple independent regions to be optimized. It modeled the task offloading system model for each region as a multi-objective optimization problem, dynamically adjusting the communication level of the population by learning the user distribution in different regions and the similarity of the tasks to be processed, accelerating convergence speed, and achieving optimization for two different regions through one evolution. The experimental results show that the proposed algorithm has achieved good results in convergence speed and the uniformity of the optimal solution distribution, and can obtain the unloading deployment optimization scheme under edge computing. [ABSTRACT FROM AUTHOR]

For the channel estimation of broadband OFDM system assisted by IRS, most of the current researches are based on the full pilot setting on a single symbol, and excessive cascaded channel coefficients will lead to large pilot overhead. This paper proposed a two-stage channel estimation scheme based on block sparse in time-angle domain. Firstly, by analyzing the common sparse characteristics of the channel in the time domain and the angular domain, this paper transformed the cascaded channel matrix into a block sparse representation in the time domain-angular domain, and converted the channel estimation problem into a block sparse matrix recovery problem. Secondly, this paper proposed a two-stage sparse channel estimation scheme to sparsely recover the cascaded channel considering the transmission pilot limitation and the time-angle domain block sparse characteristics. Simulation results show that compared to the other three benchmark schemes, the proposed scheme can achieve better channel estimation performance with fewer pilots, effectively reducing the pilot overhead and achieving higher estimation accuracy. [ABSTRACT FROM AUTHOR]

Aiming at the problem that speech enhancement networks have difficulty in extracting global speech-related features and are ineffective in capturing local contextual information of speech. This paper proposed a two-branch attention and U-Net-based time-domain speech enhancement method, which used a U-Net encoder-decoder structure and took the high-dimensional time-domain features obtained from a single-channel noisy speech after one-dimensional convolution as input. Firstly, this paper designed Conformer-based residual convolution to enhance the noise reduction ability of network by utilizing residual connection. Secondly, this paper designed a two-branch attention mechanism structure, which utilized global and local attention to obtain richer contextual information in the noisy speech, and at the same time, to effectively represent the long sequence features and extract more diverse feature information. Finally, this paper constructed a weighted loss function by combining the loss function in the time domain and frequency domain to train the network and improve the performance in speech enhancement. This paper used several metrics to evaluate the quality and intelligibility of the enhanced speech, the enhanced speech perceptual evaluation of speech quality(PESQ) on the public datasets Voice Bank+DEMAND is 3.11, the short-time objective intelligibility(STOI) is 95%, the composite measure for predicting signal rating(CSIG) is 4.44, the composite measure for predicting background noise(CBAK) is 3.60, and the composite measure for predicting overall processed speech quality(COVL) is 3.81, in which the PESQ is improved by 7.6% compared to SE-Conformer, and improved by 5.1% compared to TSTNN improved by 5.1%. Experimental results show that the proposed method achieves better results in various metrics of speech denoising and meets the requirements for speech enhancement tasks. [ABSTRACT FROM AUTHOR]

Because of China's rapid urbanization and economic growth, the amount of waste generated from production and city life is increasing daily. Establishing effective recycling and transfer facilities is a critical problem in today's society. This paper studied the problem of finding locations for secondary waste recycling facilities, the essence of which was the NP-hard problem in combinatorial optimization. Firstly, to solve the problem, the paper made a mathematical model based on the actual situation and then studied the problem's mathematical properties to provide a proof and simplify the problem, reducing its scale and difficulty. Then, this paper designed the allocation sub-algorithm and the upper and lower bound sub-algorithms for the problem. Based on the above algorithms, it proposed a reduced-order backtracking algorithm to obtain an accurate solution while still reducing the problem size. Finally, the algorithm's principles and execution process were further elaborated through analyzing and simulating several examples. The results show that the algorithm successfully reduces the problem's difficulty by reducing the problem size. [ABSTRACT FROM AUTHOR]

Aiming at the problems of insufficient diversity of whale optimization algorithm(WOA), inefficient and unbalanced information exchange between the two search phases, this paper proposed an improved WOA based on the armed forces collaborative warfare mechanism for community discovery. In order to solve the problem of insufficient diversity in the encircling predation stage, this paper developed a "neighbor potential" learning model to improve the global search capability and learn breadth of WOA. To solve the problem of inefficient information exchange during the two-predation phase, this paper proposed bubble net predation based on whale commanders, which could ensure effective utilization of search information. To address the imbalance between the two predation mechanisms, this paper proposed an improved learning automaton, which could guide whale populations toward promising areas. Meanwhile, because community discovery in complex networks is a discrete problem, this paper proposed a new coded discrete evolution rule based on topological properties. Finally, this paper tested the proposed algorithms on real data sets and compared them with other algorithms, and simulation experiments show that the proposed algorithm has better optimization ability than the comparison algorithm, verifying the effectiveness of the improved strategy. [ABSTRACT FROM AUTHOR]

Aiming at overcoming drawbacks of lower accuracy and being trapped easily into local optimums of the sparrow search algorithm(SSA), this paper proposed an enhanced sparrow search algorithm by integrating niche mechanism(NSSA). Firstly, NSSA adopted an adaptive niche mechanism based on producers' similarity to automatically partition the whole sparrow population into several producer-centered speciation, and to move scroungers inside the speciation towards to the producer inside the same speciation, in order to maintaining the diversity of the whole population. Secondly, NSSA applied a fuzzy logic based differential mutation operation to further mutate sparrow producers to raise the probability to jump out of local optimums. It used 12 functions selected from the CEC2017 benchmark function as the testbed to evaluate NSSA with CSSOA, ISSA, MSSSA, SHSSA, and MSWOA. Experimental results show that NSSA even can raise convergence accuracy up by 10% compared with the second ranked evaluated algorithm on most of multimodal objective test functions. This paper also conducted ablation experiments for each improved strategy proposed in NSSA. Experimental results show NSSA can achieve supreme performance by applying all 3 strategies simultaneously. At last, NSSA is applied to solve the pressure vessel design problem. Experimental results illustrate that NSSA has the ability to find the best solutions compared to other evaluated algorithms. [ABSTRACT FROM AUTHOR]

In order to solve the problem that the existing log anomaly detection methods tend to focus only on the single feature of the quantitative relationship mode or the sequential mode, ignoring the relationship of the log time structure and the interrelation between different features, resulting in a high error detection rate and false positive rate, this paper proposed a log anomaly detection method based on the log time graph attention network. Firstly, this paper constructed a log time graph by designing a joint feature extraction module of log semantics and time structure, which effectively integrated the time structure relationship and semantic information of log. Secondly, it constructed the time relationship graph attention network, and used the graph structure to describe the time structure relationship between logs, which could adaptively learn the importance of different logs and carry out anomaly detection. Finally, it used three public datasets to verify the effectiveness of the model. Extensive experiments results indicate that the proposed method is able to effectively capture the temporal structure relationships in the logs, thereby improving the accuracy of anomaly detection. [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.)

Aiming at the problem of small scale and difficulty in taking into account multiple indexes in the design of frequency-hopping sequences, this paper proposed a frequency-hopping sequence design method based on large-scale multi-objective optimization. Firstly, considering the multiple performance indexes of frequency-hopping sequence,this paper established a multi-objective optimization model of frequency-hopping sequence. Then, this paper introduced a large-scale multi-objective optimization algorithm, and proposed the decision variable shuffling strategy and the opposition-based differential evolution, which could form a diverse non-dominated set by redistributing the position of decision variables and provide an effective direction for subsequent evolution by enabling reverse individuals to participate in differential evolution and provides an effective direction for subsequent evolution. Finally, this method used the proposed algorithm to optimize the model to obtain a frequency-hopping sequence set. The experimental results show that the proposed algorithm has stronger optimization ability than other multi-objective optimization algorithms,and the performance indexes of the frequency-hopping sequence set has obvious advantages. In different interference environments, the proposed design method has lower bit error rate than other methods, which verifies the effectiveness and superiority of the proposed method. [ABSTRACT FROM AUTHOR]

Federated learning enables different clients to collaborate and train a shared model while preserving user privacy. Motivating high-quality clients to participate in federated learning is crucial. In online federated learning environments, where clients join and leave training dynamically, evaluating and selecting clients in real-time poses a challenge. To address this challenge, this paper proposed an online federated learning incentive algorithm to optimize client selection and budget allocation, thereby enhancing the performance of federated learning under budget constraints.The proposed algorithm divided the budget into stages and computed optimal quality density thresholds based on historical sample information. The main idea was to dynamically assess the quality of client models and employ a quality threshold admission mechanism while limiting the number of participating clients. In theory, this paper proved that the incentive algorithm satisfied incentive compatibility, budget feasibility, and individual rationality. Experimental results demonstrate that the proposed online incentive algorithm achieves good performance in scenarios with different proportions of free-riding clients. Specifically, compared to existing methods, it achieves approximately 4% and 10%improvements on the EMNIST-B and CIFAR-10 datasets, respectively, under sufficient budget and in the presence of free-riding and mislabeled clients. [ABSTRACT FROM AUTHOR]

In order to solve the problem of limited channel resources of the Internet of Things (IoT) and improve the information timeliness of the IoT system, this paper considered a multi-access Cognitive Radio (CR) IoT system model including one Primary User (PU) and two Secondary User (SU) nodes. Under the constraint of PU working state and SU data queue stability, the paper analyzed the average Age of Information (AoI) of the First Secondary User node in the First Come First Served (FCFS), Last Come Last Served (LCLS) and the packet dropping queue, and derived the average AoI of the second SU node in the threshold strategy. Then, the paper proposed an optimization problem to minimize the average AoI of the first user and lower the average AoI of the second user below the given threshold. The constraint condition of the problem was convex, but the objective function was non-convex, so the paper introduced a suboptimal technique and obtained the optimal solution by double convex optimization algorithm. Simulation results show the performance of the proposed algorithm under different system parameters, and the algorithm performs well under the influence of different system parameters and multiple antennas. Subsequent work can consider extending CR IoT system to more than two SUs. [ABSTRACT FROM AUTHOR]

To study the evolution process and community structure of e-commerce networks, this paper uses AN improved stochastic block model (sbm) link prediction algorithm. since the degree distribution among blocks in the original sbm model is binomial, to make the degree distribution among blocks follow the power law distribution in the stochastic block model, this paper introduces the degree attenuation parameter. aiming AT the assumption that the connection between nodes depends only on the block to which nodes belong in the original sbm model, to make the degree distribution closer to the real network, the paper introduces the degree control parameter. based on this, the paper proposes AN optimized random block model, and use the alibaba taobao data set to verify the proposed algorithm. the results show that the accuracy of the proposed algorithm is higher than the sbm, the degree-corrected stochastic block model (dcsbm) and the hierarchical structure model (hbm). it shows that the improved algorithm can describe the community structure of the e-commerce network well and find the missing link in the network accurately. [ABSTRACT FROM AUTHOR]

The storage of massive point cloud data has great significance to the real-time 3D collaborative perception of autonomous driving. However, due to the requirements of data security and confidentiality, some data owners are unwilling to share their private point cloud data, which limits the improvement of model training accuracy. Federated learning is a computing paradigm that focuses on data privacy and security. This paper proposed a novel approach based on federated learning to address the challenge of large-scale point cloud semantic segmentation in collaborative vehicle perception scenarios. It integrated position encoding with inter-point angle information and geometric diffraction of neighboring points to enhance the feature extraction capability of the model. Finally, it dynamically adjusted the aggregation weights of the global model according to the generation quality of the local model to improve the ability to maintain the local geometric structure of the data. This paper applied the proposed method on three datasets, such as Semantic KITTI, SemanticPOSS and Toronto3D. The results show that the proposed approach significantly outperforms the single training data and the FedAvg-based method, and fully exploits the value of the point cloud data while taking into account the privacy sensitivity of each party's data. [ABSTRACT FROM AUTHOR]

Flexible modal face presentation attack detection can break through the limitations of traditional multi-modal methods on modal consistency in model training and deployment, and it can deploy the unified model flexibly to real scenarios of multiple modals on demand. However, there are still issues with improved model performance and high demand for computing resources. Therefore, this paper proposes a single stream flexible modal face presentation attack detection network based on Vision Transformer. Furthermore, this paper proposes the atrous patch embedding module to address the operational redundancy problem and reduce the input vector dimension, designs the modal encoding token to distinguish different modal features, and adopts a non-padding strategy to solve the modal absence problem essentially. The experimental results on publicly available multi-modal datasets show that the method proposed in this paper can obtain the best ACER averages of 2.69% and 33.81% in the intra-domain and cross-domain evaluations,respectively, and has excellent in-domain and out-of-domain generalization performance, and balanced performance across different sub-protocols compared to the existing three methods. It significantly reduces the quantities of calculations and parameters compared with multi-stream methods, and is more suitable for flexible and efficient deployment in modal absence scenarios. [ABSTRACT FROM AUTHOR]

Most existing deviation detection methods are capable of identifying deviations from process activities and data attributes, but they fail to address the issue of how changes in data during process execution impact the process,especially in cases involving interactions among multiple objects. To address this issue, this paper proposed a business process deviation detection method based on data impact in the context of multi-object interactions. Firstly, this method identified potential deviant activities based on control flow and data information. Then, it defined impact sets based on the impact of data changes on activities. Next, it introduced the concept of object-centric into the deviation detection process and formalized the object-centric Petri net model. On this basis, by analyzing whether the object has execution privilege on the data it modified, this paper classified and defined four types of data impacts and their calculation criteria,from which the results of deviation detection based on data impacts were obtained. Finally, compared with other deviation detection methods, the results show that the deviation detection results obtained by applying the method are improved and are able to handle process deviations for multi-object interactions. This method can effectively capture the process activities affected by data changes in multi-object interaction processes and improve the rationality and accuracy of deviation detection. [ABSTRACT FROM AUTHOR]

Most of the existing knowledge tracing research uses implicit information such as concepts contained in exercises or explicit information such as historical interaction data to model exercises, and does not pay attention to the heterogeneity of internal and external information, and lacks heterogeneous integration of internal and external information. To address these issues, this paper proposed a knowledge tracing model that integrates heterogeneous internal and external information. Firstly, based on implicit information like concepts, it calculated the relevance between historical concepts and current concepts, depicting the influence of historical concepts on the current ones and modeling the exercise’s implicit representation. Secondly, leveraging explicit information like interaction data, it computed the relevance between historical exercises and current exercises, capturing the impact of historical exercises on the current ones and establishing the exercise’s explicit representation. Furthermore, by utilizing the channel attention mechanism on the aforementioned internal and external exercise representations, this paper achieved a fusion of heterogeneous information to create the exercise’s heterogeneous representation, enabling the prediction of learners’ performance. To validate the performance and effectiveness of the proposed model, this paper conducted comparative experiments on three real-world datasets using four relevant baseline models. The experimental results demonstrate that our model achieves superior performance on multiple evaluation metrics. Additionally, ablation experiments confirm the effectiveness of our proposed model in better modeling exercise representations by incorporating both internal and external information. In the terms of applications, a smart learning environment is designed to prove the advantages of the proposed model in actual teaching scenarios. [ABSTRACT FROM AUTHOR]

In view of the current semantic segmentation can not accurately identify image edges and small objects, and simple fusion of multi-stage features will cause information redundancy, confusion and other problems, this paper proposed a Pre-guidanced multi-stage feature fusion network (PGMFFNet). PGMFFNet employed a encoder-decoder structure, at the encoder stage, which used a pre-guidance module to guide the information in each stage. Strengthened the relationship between the features of each stage, and solved the semantic confounding problems in the subsequent fusion process of the features of each stage. At the decoder stage, which used the multi-path up-pyramid sampling module to fuse high-level semantic features, and then used the improved dense void space pyramid pool module to further expand the sensory field of the fused features, and finally fused the feature information of high and low levels to make the segmentation effect of small objects better. This paper verified PGMFFNet on CityScapes open data set,and the mean intersection over union (MIoU) obtained to 78.38%, showing good segmentation effect. [ABSTRACT FROM AUTHOR]

With the rapid development of science and technology and the impact of the novel coronavirus epidemic in recent years, medical delivery robots have gradually appeared in major medical institutions. However, traditional medical delivery robots have local optimal solution problems and target unreachable problems when using artificial potential field algorithms for path planning. Therefore, for the local optimal solution problem, this paper proposes a method of designing virtual target points to rescue the robot from the local optimal state. In this paper, the target distance function is introduced into obstacle repulsion potential field function to limit obstacle repulsion, to solve the problem of target unreachable. Finally, the proposed method is compared with the traditional algorithm in a variety of complex environments. The results show that the improved algorithm can solve the local optimal solution and target unreachable problems existing in the traditional algorithm, and the efficiency of the algorithm is also increased by 5%-9% and can be effectively applied to practical scenarios. [ABSTRACT FROM AUTHOR]

Federated learning is a framework for obtaining machine learning models without centralized data training,reducing the risk of privacy leakage while also obtaining optimized training models locally. However, the identity,behavior, environment, etc. between nodes are different, resulting in unbalanced data distribution, which may cause a large deviation in the performance of the model on different devices, resulting in data heterogeneity. Aiming at the above problems, this paper proposes a Federated learning algorithm for data sharing clustering based on node optimization method that applies clustering and data sharing to federated learning system at the same time, which can effectively reduce the impact of data heterogeneity on federated learning and accelerate the convergence of local models.At the same time, a method to assess the convergence of the global shared model is designed to determine the timing of node clustering nodes. Finally, in this paper, the datasets EMNIST and CIFAR-10 were used for experiments and performance analysis to compare the effects of the size of the shared scale on the convergence speed and accuracy of each node, and to compare the accuracy of clustering and data sharing before and after the application of federated learning. Experimental results show that the convergence speed and accuracy of each node are improved when data sharing is introduced, and the accuracy is increased by about 10-15% when clustering and data sharing are introduced into federated learning training at the same time, indicating that this method has a good effect on the heterogeneous problem of federated learning data. [ABSTRACT FROM AUTHOR]

Addressing the shortcomings of existing knowledge completion models based on graph neural networks in handling the heterogeneity of knowledge graphs and the limitations posed by most models’ adoption of a single static entity representation, this paper introduces a model based on the graph attention mechanism for disentangled neighborhood information aggregation. Initially, this paper learns the disentangled representation of each entity,providing a multi-component representation for the latent influential factors of entities. Using the attention mechanism,the model selects the most influential latent factors as connection elements for two connected entities. Subsequently,by leveraging a relation-aware attention mechanism, the model adaptively aggregates neighborhood messages at the entity factor level, effectively reducing interference from irrelevant information during aggregation and significantly enhancing the model’s semantic representation capability. Moreover, to focus on the most relevant entity component in the scoring process with a given relation, this paper introduces an adaptive scoring coefficient, enabling the model to perceive the relevance between the given relationship and various entity components adaptively. Experimental results on the WN18RR and FB15K-237 datasets indicate that the proposed model outperforms other advanced baseline models in knowledge graph completion tasks, substantially enhancing the model’s expressive power. [ABSTRACT FROM AUTHOR]

Diabetic retinopathy (Diabetic Retinopathy, DR) is the symptom of diabetes affecting the retina during the onset of diabetes. Aiming at the problem of information loss of lesion areas such as microimages during model downsampling, this paper proposes a module of DenseNet fusion residual structure. This module first connects two consecutive Dense block, then sums the feature information using the residual structure, and processes the feature image information in parallel to prevent the loss of effective feature information. Finally, finally, the residual connects the two convolution blocks containing drop out to suppress the overfitting phenomenon. To solve the problem of the channel weighting of the feature graphs of lesion areas in previous convolution operations, the paper proposes a module of SeNet fusion residue structure. This module first connects SeNet, adds the feature information of global average pooling and global maximum pooling to improve the utilization of effective channel information, and then ensures the integrity of feature graph information through the residual mode of conv1x1. Based on the design of the above two modules, the paper proposes a DR classification method of DenseNet and SeNet fusion residue structures. The model achieves 89.8%precision and 97.0% specificity on the APTOS2019 dataset, 78.8% accuracy and 91.9% specificity on the Messidor-2dataset, which can effectively improve the classification ability of the degree of retinal lesions. [ABSTRACT FROM AUTHOR]

Finger vein recognition methods based on deep learning usually require a large amount of computing resources, it limits their promotion and popularization on embedded devices. The adoption of lightweight network faces the problem of decreasing accuracy due to the reduction of model parameters. Therefore, this paper proposed a lightweight recognition algorithm based on key features of finger vein and Adaface loss. In the Micronet network framework, firstly, this paper proposed FMixconv convolution to replace the deep convolution in the original network,which could obtain multi-scale information of vein features while reducing parameters. Secondly, the method used a lightweight attention module, CA module, to focus on key information of venous characteristics from space and channel.Finally, the algorithm added Adaface loss into the loss function, through the characteristics of the norm to evaluate image quality, to reduce the impact of image quality degradation on training. The recognition accuracy of the proposed algorithm on SDUMLA-HMT, FV-USM and self-built datasets reached 99.84%, 99.39% and 99.42%, while the number of parameters was only 0.82M. Experimental results show that the proposed network is ahead of other methods in accuracy and parameter size. [ABSTRACT FROM AUTHOR]

With the development of deep learning, object detection has gradually replaced manual quality inspection as the primary direction for industrial quality control. However, in the complex texture of the tile surface, there are more lowvisibility small defects, and the interference from the complex textured background is serious. This results in a high false detection and false alarm rate using traditional object detection methods. To enhance the efficiency of defect detection, this paper proposed a defect detection approach on complex textured tile surfaces based on the joint attention mechanisms of channels and spatial. Firstly, to enhance the feature expression of small defects, it proposed a selective feature fusion method by modeling the relationship between deep and shallow feature channels. Secondly, it designed a joint channel and spatial attention module that selects key feature channels and suppresses texture regions through channel and spatial attention,enabling the model to focus on learning defect features and enhancing its ability to discriminate between defects and texture.Finally, it validated the approach on a dataset of complexly textured ceramic tile surface defects. The experimental results demonstrate that compared to the AFF and CBAM methods, the selective feature fusion method and channel ＆ spatial joint attention achieved improvements of 5.3AP and 6.32AP, respectively. In addition, this paper compared the overall approach with the existing tile detection method YOLOv5 and texture fabric defect detection method AFAM, showing that it outperformed these methods, with respective improvements of 1.32AP and 2.12AP. [ABSTRACT FROM AUTHOR]

In order to realize the independent and controllable simulation software of urban energy pipeline network, this paper proposed a universal urban energy pipe network simulation calculation model based on the domestic heterogeneous high-performance computer "Songshan" supercomputing platform. It enhanced the adaptability to domestic heterogeneous parallel computer systems by optimizing the model of the non-pipe component and simplifying its input and output parameters. Then, it encapsulated the calculation process of different pipe network components, which could reduce the computational dependency of each connected component in the simulation calculation process and improve the parallelism of the engineering implementation of the calculation model. Finally, it also proposed a parallel system solution for energy pipe network simulation with this simulation calculation model. The generality of the suggested computational model had been proved by simulation tests of three separate real pipeline networks for urban water, gas, and heat. The simulated pressure has an error rate of less than 4% and its temperature has an error rate of less than 2%, according to comparisons between the actual network measurements and the simulated data in the network simulation model. These results also show that the proposed pipe network simulation model in the paper provides excellent computational versatility on domestic supercomputing platforms. [ABSTRACT FROM AUTHOR]

The concept drift and imbalance problems in complex data streams reduced the performance of classifiers.Traditional batch learning algorithms need to consider factors such as memory and runtime, but their performance is not outstanding in rapidly arriving massive data streams, and they also contain a large number of drift and class imbalance phenomena. Utilizing online ensemble algorithms to handle complex data stream problems has become an important research topic in the field of data mining. Firstly, this paper introduced and summarized the online versions of bagging, boosting, and stacking ensemble methods from the perspective of ensemble strategies, and compared the performance of different models. Secondly, this paper conducted a detailed summary and analysis of online ensemble classification algorithms for complex data streams for the first time. This paper introduced conceptual drift data stream detection and classification algorithms from two aspects: active detection and passive adaptation. This paper introduced unbalanced data streams from two aspects: data preprocessing and cost sensitivity. This paper analyzed the spatiotemporal efficiency of representative algorithms, and then it compared the performance of algorithms using the same dataset. Finally, this paper proposed the next research direction in response to the challenges in the field of online ensemble classification of complex data streams. [ABSTRACT FROM AUTHOR]

Aiming at the problem of multi-type tree division structure in coding unit (CU) division in versatile video coding (VVC), this paper proposed a fast division algorithm based on the orientation characteristics and spatial complexity of CU subblocks. Firstly, this paper used the overall texture complexity of CU to classify the current CU and filtered out the CU that is not divided. Then, this method used the difference in the characteristics of different division directions of subblocks to decide the CU division direction in advance. Finally, the algorithm used the complexity difference feature between the middle region and the edge region of CU to determine whether to skip the ternary tree (TT) division, which further reduces the number of candidate list division patterns. The experimental results show that compared with the official test platform VTM10.0, the encoder reduces the encoding time by 40.25% at the cost of increasing the average output bit rate by 1.12%, indicating that the algorithm can achieve shorter encoding time with less quality loss in versatile video coding. [ABSTRACT FROM AUTHOR]

To address the weaknesses of the honey badger algorithm, specifically its limited capacity for local search and susceptibility to local optima, this paper proposed an enhanced version based on coevolution with two populations. This approach used Cubic chaotic mapping to initialize the population, thereby expanding the search space and improving its distribution. Moreover, it introduced a dual-population optimization mechanism that combined the slime mold algorithm with the honey badger algorithm. By leveraging the strengths of both methods, the individuals could more effectively hone-in on the target location, resulting in improved search efficiency and optimization performance. To further improve the algorithm's ability to escape local optima, it employed a Cauchy random reverse perturbation strategy to disturb the optimal position of the honey badger population. By means of the experiment of improving the effectiveness of a single strategy, different high-dimensional experiments with seven other algorithms and Wilcoxon rank-sum tests, experimental results demonstrate that the proposed algorithm has high convergence accuracy and fast solving times. Finally, this paper applied the improved algorithm to the design of compression springs and pressure vessels, which further confirmed the efficacy of improved strategy and the practical utility of the algorithm. [ABSTRACT FROM AUTHOR]