An improved matrix factorization based model for many-objective optimization recommendation

Research on Singular Value Decomposition Recommendation Algorithm Based on Data Filling

In the era of big data, the problem of information overload has become increasingly prominent. Recommendation systems are widely studied due to the problem. Due to the sparseness of data, the recommendation effect is not always ideal. To alleviate the problem of data sparsity, a singular value decomposition recommendation algorithm based on data filling is proposed. First, an improved Tanimoto similarity coefficient calculation method is proposed to calculate the similarity, and effective interpolation data is generated for the singular value decomposition model according to the proposed prediction formula. The experimental results show that when using the same dataset MovieLens100K, compared with several commonly used recommendation algorithms, the improved algorithm improves the prediction accuracy of the model, In the best case, RMSE is 10.1% lower than KNNBasic, 7.8% lower than Slope One algorithm, 6.9% lower than SVD algorithm, and 4.8% lower than SVD++ algorithm, verifying that this method can improve the recommendation quality.

A survey on federated learning: challenges and applications

Federated learning (FL) is a secure distributed machine learning paradigm that addresses the issue of data silos in building a joint model. Its unique distributed training mode and the advantages of security aggregation mechanism are very suitable for various practical applications with strict privacy requirements. However, with the deployment of FL mode into practical application, some bottlenecks appear in the FL training process, which affects the performance and efficiency of the FL model in practical applications. Therefore, more researchers have paid attention to the challenges of FL and sought for various effective research methods to solve these current bottlenecks. And various research achievements of FL have been made to promote the intelligent development of all application areas with privacy restriction. This paper systematically introduces the current researches in FL from five aspects: the basics knowledge of FL, privacy and security protection mechanisms in FL, communication overhead challenges and heterogeneity problems of FL. Furthermore, we make a comprehensive summary of the research in practical applications and prospect the future research directions of FL.

Application of an improved Discrete Salp Swarm Algorithm to the wireless rechargeable sensor network problem

This paper presents an improved Discrete Salp Swarm Algorithm based on the Ant Colony System (DSSACS). Firstly, we use the Ant Colony System (ACS) to optimize the initialization of the salp colony and discretize the algorithm, then use the crossover operator and mutation operator to simulate the foraging behavior of the followers in the salp colony. We tested DSSACS with several algorithms on the TSP dataset. For TSP files of different sizes, the error of DSSACS is generally between 0.78% and 2.95%, while other algorithms are generally higher than 2.03%, or even 6.43%. The experiments show that our algorithm has a faster convergence speed, better positive feedback mechanism, and higher accuracy. We also apply the new algorithm for the Wireless rechargeable sensor network (WRSN) problem. For the selection of the optimal path, the path selected by DSSACS is always about 20% shorter than the path selected by ACS. Results show that DSSACS has obvious advantages over other algorithms in MCV’s multi-path planning and saves more time and economic cost than other swarm intelligence algorithms in the wireless rechargeable sensor network.

Precise Supervision of Enterprise Environmental Protection Behavior Based on Boolean Matrix Factorization under Low Carbon Background

Supervising the environmental protection behavior of enterprises is a key strategy to achieve “carbon peaking and carbon neutrality”. This research innovatively proposes the concept of precise supervision, aiming to implement differentiated supervision measures for different types of enterprises, and realize the precise supervision method of enterprise environmental protection, which is different from the traditional supervision mode. Firstly, this paper proposes a novel MEBF+ method based on the benchmark algorithm MEBF, and obtains MEBF++ after incorporating the model bias. Secondly, based on the dataset of environmental supervision and certification of listed Chinese companies, the accuracy and robustness of the proposed method are verified by using multiple evaluation indicators. Finally, based on the analysis of the experimental results, two precise supervision concepts, narrow and broad, are proposed under the low-carbon background. The results show that compared with the benchmark method, the accuracy of the proposed method has been improved to a large extent. In addition, the precise supervision proposed in this paper can help reduce the consumption of manpower and resources as well as unite the public to monitor the environmental protection behavior of enterprises.