scispace - formally typeset
Search or ask a question
Author

Zhijian Li

Bio: Zhijian Li is an academic researcher from Hebei Normal University. The author has contributed to research in topics: Recurrent neural network & Network security. The author has co-authored 1 publications.

Papers
More filters
Journal ArticleDOI
TL;DR: In this paper, a situation prediction method based on feature separation and dual attention mechanism is presented in order to improve the safety of smart cities, which can alleviate the overfitting problem and reduce cost of model training by keeping the dimension unchanged.
Abstract: With the development of smart cities, network security has become more and more important. In order to improve the safety of smart cities, a situation prediction method based on feature separation and dual attention mechanism is presented in this paper. Firstly, according to the fact that the intrusion activity is a time series event, recurrent neural network (RNN) or RNN variant is used to stack the model. Then, we propose a feature separation method, which can alleviate the overfitting problem and reduce cost of model training by keeping the dimension unchanged. Finally, limited attention is proposed according to global attention. We sum the outputs of the two attention modules to form a dual attention mechanism, which can improve feature representation. Experiments have proved that compared with other existing prediction algorithms, the method has higher accuracy in network security situation prediction. In other words, the technology can help smart cities predict network attacks more accurately.

1 citations


Cited by
More filters
Proceedings ArticleDOI
04 May 2022
TL;DR: In this paper , a network security situation prediction method based on Attention-CNN-BiGRU is proposed, which combines CNN and BiGRU for extraction and understanding of situation time series.
Abstract: To improve the accuracy and efficiency of network security situation prediction, a network security situation prediction method based on Attention-CNN-BiGRU is proposed. It combined Convolutional Neural Network(CNN) and bidirectional Gated Recurrent Unit(BiGRU), The structure of the proposed model is more accurate for extraction and understanding of situation time series; besides, to improve the performance of proposed model, the Attention mechanism is utilized to optimize the model; particle swarm optimization(PSO) is applied to optimize varieties of hyperparameters of the model. The optimal combination of hyperparameters selected by PSO is used for training of the model. Finally, the method proposed in this paper was verified in experiment and compared with other models. The results shows that the method can acomplish the task of situation prediction with better capability.

1 citations