Classification and Early Warning Model of Terrorist Attacks Based on Optimal GCN

FENG Yong; GAI Ming; WANG Fuhai; WANG Rongbing; XU Xiaowei

doi:10.1049/cje.2020.10.005

Volume 29 Issue 6

Dec. 2020

Turn off MathJax

Article Contents

Article Navigation > Chinese Journal of Electronics > 2020 > 29(6): 1193-1200

FENG Yong, GAI Ming, WANG Fuhai, et al., “Classification and Early Warning Model of Terrorist Attacks Based on Optimal GCN,” Chinese Journal of Electronics, vol. 29, no. 6, pp. 1193-1200, 2020, doi: 10.1049/cje.2020.10.005

Citation:

FENG Yong, GAI Ming, WANG Fuhai, et al., “Classification and Early Warning Model of Terrorist Attacks Based on Optimal GCN,” Chinese Journal of Electronics, vol. 29, no. 6, pp. 1193-1200, 2020, doi: 10.1049/cje.2020.10.005

Citation:

PDF( 1093 KB)

Classification and Early Warning Model of Terrorist Attacks Based on Optimal GCN

doi: 10.1049/cje.2020.10.005

1.
College of Information, Liaoning University, Shenyang 110036, China;
2.
Department of Information Science, University of Arkansas at Little Rock, Little Rock, Arkansas 72204-1099, USA

Funds: This work is supported by the National Nature Science Foundation of China under Grant No.71771110, the Social science planning foundation of Liaoning province of China under Grant No. L18AGL007, the Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University under Grant No.93K172018K01, the project of Liaoning Provincial Engineering Laboratory of Big Data System of Public Opinion and Network Security under Grant No.2016-294, the Foundation of China Scholarship Council.

More Information

Corresponding author: WANG Rongbing (corresponding author) was born in1979. He received the Ph.D. degree in business management from Liaoning University. He is an associate professor at Liaoning University. He is a visiting scholar of Edinburgh University. His research interests include data mining, cloud computing and machine learning. (Email:wrb@lnu.edu.cn)
Received Date: 2019-07-19
Publish Date: 2020-12-25

Abstract

Abstract

Aiming at the lack of effective quantitative model to support the analysis of terrorist attacks, a multilayer depth Neural network (NN) Graph convolutional networks (GCN) model (NNGCN) was put forward to realize the classification and early warning of terrorist attacks. The proposed model optimized the traditional GCN with the help of complex NN. The concept of link index was introduced into the NNGCN model. It is combined with the important information between event nodes. The information includes the similarity of events and link probability. Compared with the original unoptimized model, the improved model increased the classification accuracy of terrorist attacks. Because the model uses the node's feature information and the link relationship of graph structure, it can also warn the sudden terrorist attacks effectively.
- Terrorist attack,
- Correlation analysis,
- Classification,
- Early warning,
- Link index,
- GCN

FullText(HTML)

References(28)

References

Jane, et al., "Analysis of open source information of terrorist attacks in 2017", available at https://www.sohu.com/a/218396332_389790, 2018-01-23.

P. Katona, M.D. Intriligator and J.P. Sullivan, Countering Terrorism and WMD:Creating a Global Counter-terrorism Network,Routledge, London, England, pp.100-328, 2006.

J. Jones, R. Chang, and T. Butkiewicz, "Visualizing uncertainty for geographical information in the global terrorism database", Proceeding of SPIE-The International Society for Optical Engineering, Vol.15, No.9, pp.1396-1407, 2008.

Z.Y. Fu, R.Z. Xu and W.Q. Liu, "Research on terrorist attack warning model based on bayesian network", Journal of Catastrophology, Vol. 31, No.3, pp.184-189, 2016.

H.W. Mo, "Application of data mining in anti-terrorism early warning", M.S. Thesis, Beijing University of Technology, Beijing, China, 2017. (in Chinese)

T.N. Kipf, and M. Welling, "Semi-supervised classification with graph convolutional networks", available at https://arxiv.org/abs/1609.02907, 2017-2-22.

B. Perozzi, R. Al-Rfou R and S. Skiena., "DeepWalk:Online learning of social representations", Proc. of KDD' 14 Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, New York, NY, USA, pp.701-710, 2014.

J. Tang, et al., "LINE:Large-scale information network embedding",Proc. of International Conference on World Wide Web, Florence, Italy, pp.1067-1077, 2015.

A. Grover and J. Leskovec, "node2vec:Scalable feature learning for networks", Proc. of KDD' 16 Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, California, USA, pp.855-864, 2016.

Z. Marinka, A. Monica and L. Jure, "Modeling polypharmacy side effects with graph convolutional networks", Bioinformatics, Vol.34, No.13, pp.i457-i466, 2018.

R. Berg, T. Kipf and M. Welling, "Graph convolutional matrix completion", available at https://arxiv.org/abs/1706.02263, 2017-10-25.

J.Bruna, et al., "Spectral networks and locally connected networks on graphs", Proc. of ICLR 2013:International Conference on Learning Representations, Scottsdale, Arizona, USA, pp.1-14, 2013.

M. Defferrard, X. Bresson and P. Vandergheynst, "Convolutional neural networks on graphs with fast localized spectral filtering", Proc. of NIPS 2016:The 30th Annual Conference on Neural Information Processing Systems, Barcelona, Spain, pp.1-9, 2016.

D.K. Hammond, P. Vandergheynst and Rémi Gribonval, "Wavelets on graphs via spectral graph theory", Applied and Computational Harmonic Analysis, Vol.30, No.2, pp.129-150, 2011.

K. Balasubramaniam, "Hybrid fuzzy-ontology design using FCA based clustering for information retrieval in semantic web", Procedia Computer Science, Vol.50, No.21, pp.135-142, 2015.

F. Amato, et al., "Detecting anomalies in Twitter stream for public security issues", Proc. of the IEEE International Forum on Research & Technologies for Society & Industry Leveraging A Better Tomorrow, Bologna, Italy, pp.154-158, 2016.

F. Zhu and X.Z. Pan, "Application research of naive bayes algorithm in anti-terrorism intelligence classification", Intelligence Exploration, Vol.2019, No.10, pp.78-81, 2019.

Y. Xiang, "Early warning system of terrorist attack risk based on improved neural network", Disaster science, Vol.33, No.1, pp.183-189, 2018.

B. Bader and T. Schuste, "Expatriate social networks in terrorism-endangered countries:An empirical analysis in Afghanistan, India, Pakistan, and Saudi Arabia", Journal of International Management, Vol.21, No.1,pp.63-77, 2015.

A. Catherine,et al., "An evolutionary algorithm approach to link prediction in dynamic social networks", Journal of Computational Science, Vol.5, No.5, pp.750-764, 2014.

X.S. Wang, Y.T. Ma and Y.H. Chen, "Domain adaptation network based on autoencoder", Chinese Journal of Electronics, Vol.27, No.6, pp.1258-1264, 2018.

Z. Yang, W.W. Cohen and R. Salakhutdinov, "Revisiting semi-supervised learning with graph embeddings", Proc. of ICML' 16 Proceedings of the 33rd International Conference on Machine Learning, New York, NY, USA, pp.40-48, 2016.

S. Zhu, J. Du and N. Ren, "A novel simple visual tracking algorithm based on hashing and deep learning", Chinese Journal of Electronics, Vol.26, No.5, pp.1073-1078, 2017.

M. Schlichtkrull, et al., "Modeling relational data with graph convolutional networks", Proc. of ESWC 2018:European Semantic Web Conference, Heraklion, Crete, Greece, pp.593-607, 2018.

T.N. Kipf and M. Welling, "Variational graph auto-encoders", available at https://arxiv.org/abs/1611.07308, 2016-11-21.

S. Jian, X.P. Zhang, L.L. Liu, et al. "Multi-nodes link prediction method based on deep convolution neural networks", Chinese Journal of Electronics, Vol.46,No.12,pp.2970-2977,2018.

Y. Zhang, "Link prediction based on local path algorithm removing duplicate paths", M.S. Thesis, Xidian University at Xian, China, 2015.

S. Liu, et al., "Link prediction algorithm based on network representation learning and random walk", Journal of Computer Applications, Vol.37, No.8, pp.2234-2239, 2017.

Relative Articles

Supplements(0)

Cited By

Proportional views