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]

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

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

Objectives: Curve simplification is of importance in automated map generalization; nevertheless, the Douglas-Peucker (DP) algorithm popularly used in map generalization is not automatic, because a key parameter called distance tolerance (ε) must be given by experienced cartographers and needs to be input before execution of the algorithm. Methods: To solve the problem, this paper proposed a method to automatically calculate ε and by which the automation of the DP algorithm is achieved. The method consists of the following steps: (1) A formula is constructed by the Hausdorff distance for calculating the similarity degree (Ssim) between a curve at a larger scale and its simplified counterpart at a smaller scale. (2) 15 linear rivers are selected, and each of them is manually simplified to get their counterparts at seven different scales. The Ssim of each original river and each of its simplified counterpart at a smaller scale can be obtained using the formula constructed by the Hausdorff distance, and 15×7=105 coordinate pairs consisting of (S,Ssim) can be got, and a function between Ssim and S are constructed by the curve fitting using the coordinates. (3) In the meanwhile, the 15 rivers are simplified using a number of ε, and the Ssim of each original river and each of its simplified counterpart at a smaller scale can be calculated using the formula constructed by the Hausdorff distance. In this way, a number of coordinate pairs (ε,Ssim) are got, and a function between ε and Ssim is constructed by the curve fitting. (4) By the function between Ssim and S and that between ε and Ssim, a formula between ε and S can be deducted. Using the formula ε can be calculated automatically, because in a map generalization task S is usually known. After this step, automation of the DP algorithm is achieved. Results: The experiment results show that (1) The proposed DP algorithm can automatically simplify the rivers in a specific geographical area to get the results at different scales; and (2) the resulting river curves generated by the proposed DP algorithm have a high degree of similarity with the ones made by experienced cartographers. Their average similarity degree is 0.927. Conclusion: The proposed DP algorithm can simplify curve features on maps automatically, and the results are highly intelligent and credible. Although only river data is tested in this paper, the principle of the proposed method can be extended to other linear features on maps. Our future work will be on improving the accuracy of the proposed DP algorithm using more river data so that the algorithm can be used in practical map generalization engineering. [ABSTRACT FROM AUTHOR]

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

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

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