Deep Learning-Based Data Completion and Prediction Model for Burglary Cases

Enqi Cao; Fanliang Bu; Zhuxuan Han

doi:10.6919/ICJE.202408_10(8).0004

Authors

Enqi Cao
Fanliang Bu
Zhuxuan Han

DOI:

https://doi.org/10.6919/ICJE.202408_10(8).0004

Keywords:

Deep Learning; Data Completion; Crime Prediction.

Abstract

To address the problem of data completion and prediction for burglary cases, a data completion and prediction model for burglary cases is proposed. The model first constructs a Conv-BiGRU-AE data completion module to effectively fill in the missing data in burglary cases. Then, a Trans-CrimeNet crime prediction module is established to use the completed burglary data for crime prediction. Experimental results show that, under a 20% missing rate, the MAE and RMSE of burglary crime prediction by Trans-CrimeNet after completion by Conv-BiGRU-AE decreased by 17.14% and 11.68%, respectively. Under a 30% missing rate, the MAE and RMSE decreased by 13.77% and 13.17%, respectively.

Downloads

Download data is not yet available.

References

Taleb I, Serhani M A, Dssouli R. Big Data Quality: A Survey. 2018 IEEE International Congress on Big Data (BigData Congress). IEEE, 2018: 166-173.

Dong Y, Peng C Y J. Principled missing data methods for researchers. SpringerPlus, 2013, 2: 222.

Laranjeiro N, Soydemir S N, Bernardino J. A Survey on Data Quality: Classifying Poor Data. 2015 IEEE 21st Pacific Rim International Symposium on Dependable Computing (PRDC). IEEE, 2015: 179-188.

Alzubaidi L, Zhang J, Humaidi A J, et al. Review of deep learning: concepts, CNN architectures, challenges, applications, future directions. Journal of big Data, 2021, 8: 53.

Wang S, Shao C, Zhang J, et al. Traffic flow prediction using bi-directional gated recurrent unit method. Urban informatics, 2022, 1(1): 16.

Vaswani A, Shazeer N, Parmar N, et al. Attention is All you Need. Advances in Neural Information Processing Systems 30 (NIPS 2017). Curran Associates, 2017: 5998-6008.