Deep Multi-view Spatio-Temporal Network for Urban Crime Prediction
Pages 50 - 61
Abstract
Crimes sabotage various societal aspects, such as social stability, public safety, economic development, and individuals’ quality of life. To accurately predict crime occurrences can not only bring the peace of mind to individuals but also help distribute and manage police resources effectively by authorities. We aim to take into account plenty of environmental factors, such as data collected from Internet of Things (IoT) devices and social networks to predict crimes at city or a finer level. To this end, we propose a deep-learning-based spatio-temporal multi-view model, which explores the relationship between tweets, weather (a type of sensory data) and crime rate, for effective crime prediction. Our extensive experiments on a four-month crime dataset (covering 77 communities, 22 crime types, and 120 days) of Chicago city show that our model can achieve improvement over 19 out of 22 crime types (up to 6.7% in homicide). We also collect the corresponding weather information for different regions of Chicago city to support the crime prediction. Our experiments demonstrate that weather information can improve the performance of the proposed method.
References
[1]
Al Boni, M., Gerber, M.S.: Predicting crime with routine activity patterns inferred from social media. In: 2016 IEEE International Conference on Systems, Man, and Cybernetics (SMC), pp. 001233–001238. IEEE (2016)
[2]
Bai, L., Yao, L., Kanhere, S.S., Wang, X., Liu, W., Yang, Z.: Spatio-temporal graph convolutional and recurrent networks for citywide passenger demand prediction. In: Proceedings of the 28th ACM International Conference on Information and Knowledge Management, pp. 2293–2296 (2019)
[3]
Batista GE, Prati RC, and Monard MC A study of the behavior of several methods for balancing machine learning training data ACM SIGKDD Explor. Newsl. 2004 6 1 20-29
[4]
Chawla NV, Bowyer KW, Hall LO, and Kegelmeyer WP SMOTE: synthetic minority over-sampling technique J. Artif. Intell. Res. 2002 16 321-357
[5]
Chen X, Huang C, Zhang X, Wang X, Liu W, and Yao L Li J, Wang S, Qin S, Li X, and Wang S Expert2Vec: distributed expert representation learning in question answering community Advanced Data Mining and Applications 2019 Cham Springer 288-301
[6]
Cho, K., et al.: Learning phrase representations using rnn encoder-decoder for statistical machine translation. arXiv preprint arXiv:1406.1078 (2014)
[7]
Ding, X., Liu, T., Duan, J., Nie, J.Y.: Mining user consumption intention from social media using domain adaptive convolutional neural network. In: AAAI, vol. 15, pp. 2389–2395 (2015)
[8]
Fast, E., Chen, B., Bernstein, M.S.: Empath: understanding topic signals in large-scale text. In: Proceedings of the 2016 CHI Conference on Human Factors in Computing Systems, pp. 4647–4657 (2016)
[9]
Gerber MS Predicting crime using twitter and kernel density estimation Decis. Support Syst. 2014 61 115-125
[10]
Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, pp. 2672–2680 (2014)
[11]
Gorman DM, Speer PW, Gruenewald PJ, and Labouvie EW Spatial dynamics of alcohol availability, neighborhood structure and violent crime J. Stud. Alcohol. 2001 62 5 628-636
[12]
Kadar C and Pletikosa I Mining large-scale human mobility data for long-term crime prediction EPJ Data Sci. 2018 7 1 1-27
[13]
Kenrick DT and MacFarlane SW Ambient temperature and horn honking: a field study of the heat/aggression relationship Environ. Behav. 1986 18 2 179-191
[14]
Li, Y., Liu, Z., Yao, L., He, Z.: Non-local self-attentive autoencoder for genetic functionality prediction. In: Proceedings of the 29th ACM International Conference on Information & Knowledge Management, pp. 2117–2120 (2020)
[15]
Ning X, Yao L, Benatallah B, Zhang Y, Sheng QZ, and Kanhere SS Source-aware crisis-relevant tweet identification and key information summarization ACM Trans. Internet Technol. (TOIT) 2019 19 3 1-20
[16]
Ning X, Yao L, Wang X, and Benatallah B Cong G, Peng W-C, Zhang WE, Li C, and Sun A Calling for response: automatically distinguishing situation-aware tweets during crises Advanced Data Mining and Applications 2017 Cham Springer 195-208
[17]
Ning, X., Yao, L., Wang, X., Benatallah, B., Salim, F., Haghighi, P.D.: Predicting citywide passenger demand via reinforcement learning from spatio-temporal dynamics. In: Proceedings of the 15th EAI International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services, pp. 19–28 (2018)
[18]
Tomek, I., et al.: An experiment with the edited nearest-nieghbor rule (1976)
[19]
Wang, H., Kifer, D., Graif, C., Li, Z.: Crime rate inference with big data. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 635–644 (2016)
[20]
Yan, X., Guo, J., Lan, Y., Cheng, X.: A biterm topic model for short texts. In: Proceedings of the 22nd International Conference on World Wide Web, pp. 1445–1456 (2013)
[21]
Yoon, J., Jarrett, D., van der Schaar, M.: Time-series generative adversarial networks. In: Advances in Neural Information Processing Systems, pp. 5508–5518 (2019)
[22]
Zhao, X., Tang, J.: Modeling temporal-spatial correlations for crime prediction. In: Proceedings of the 2017 ACM on Conference on Information and Knowledge Management, pp. 497–506 (2017)
Recommendations
Modeling Temporal-Spatial Correlations for Crime Prediction
CIKM '17: Proceedings of the 2017 ACM on Conference on Information and Knowledge ManagementCrime prediction plays a crucial role in improving public security and reducing the financial loss of crimes. The vast majority of traditional algorithms performed the prediction by leveraging demographic data, which could fail to capture the dynamics ...
Dynamic road crime risk prediction with urban open data
AbstractCrime risk prediction is helpful for urban safety and citizens’ life quality. However, existing crime studies focused on coarse-grained prediction, and usually failed to capture the dynamics of urban crimes. The key challenge is data sparsity, ...
Predictability Comparison of Three Kinds of Robbery Crime Events Using LSTM
DSDE '19: Proceedings of the 2019 2nd International Conference on Data Storage and Data EngineeringPrediction of crime occurrences is of great significance for underlying criminal risk reduction and public security improvement. In all kinds of crime events, robbery is a more serious and noticeable one that threatens our everyday life. Different kinds ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
Jan 2021
230 pages
ISBN:978-3-030-69376-3
DOI:10.1007/978-3-030-69377-0
- Editors:
- Miao Qiao,
- Gottfried Vossen,
- Sen Wang,
- Lei Li
© Springer Nature Switzerland AG 2021.
Publisher
Springer-Verlag
Berlin, Heidelberg
Publication History
Published: 29 January 2021
Author Tags
Qualifiers
- Article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 14 Dec 2024