CrimeAlarm: Towards Intensive Intent Dynamics in Fine-Grained Crime Prediction
Conference or Workshop item
Hu, Kaixi, Li, Lin, Xie, Qing, Tao, Xiaohui and Xu, Guandong. 2024. "CrimeAlarm: Towards Intensive Intent Dynamics in Fine-Grained Crime Prediction." H.V., Onizuka M.Lee J.-G.Tong Y.Xiao C.Ishikawa Y.Lu K.Amer-Yahia S.Jagadish (ed.) 29th International Conference on Database Systems for Advanced Applications (DASFAA 2024). Gifu, Japan 02 - 05 Jul 2024 Singapore . Springer. https://doi.org/10.1007/978-981-97-5575-2_7
| Paper/Presentation Title | CrimeAlarm: Towards Intensive Intent Dynamics in Fine-Grained Crime Prediction |
|---|---|
| Authors | Hu, Kaixi, Li, Lin, Xie, Qing, Tao, Xiaohui and Xu, Guandong |
| Editors | H.V., Onizuka M.Lee J.-G.Tong Y.Xiao C.Ishikawa Y.Lu K.Amer-Yahia S.Jagadish |
| Journal or Proceedings Title | Proceedings of 29th International Conference on Database Systems for Advanced Applications (DASFAA 2024) |
| Journal Citation | 14856, pp. 104-120 |
| Number of Pages | 17 |
| Year | 2024 |
| Publisher | Springer |
| Place of Publication | Singapore |
| ISBN | 9789819755745 |
| 9789819755752 | |
| Digital Object Identifier (DOI) | https://doi.org/10.1007/978-981-97-5575-2_7 |
| Web Address (URL) of Paper | https://link.springer.com/chapter/10.1007/978-981-97-5575-2_7 |
| Web Address (URL) of Conference Proceedings | https://link.springer.com/book/10.1007/978-981-97-5575-2 |
| Conference/Event | 29th International Conference on Database Systems for Advanced Applications (DASFAA 2024) |
| Event Details | 29th International Conference on Database Systems for Advanced Applications (DASFAA 2024) Parent International Conference on Database Systems for Advanced Applications Delivery In person Event Date 02 to end of 05 Jul 2024 Event Location Gifu, Japan |
| Abstract | Granularity and accuracy are two crucial factors for crime event prediction. Within fine-grained event classification, multiple criminal intents may alternately exhibit in preceding sequential events, and progress differently in next. Such intensive intent dynamics makes training models hard to capture unobserved intents, and thus leads to sub-optimal generalization performance, especially in the intertwining of numerous potential events. To capture comprehensive criminal intents, this paper proposes a fine-grained sequential crime prediction framework, CrimeAlarm, that equips with a novel mutual distillation strategy inspired by curriculum learning. During the early training phase, spot-shared criminal intents are captured through high-confidence sequence samples. In the later phase, spot-specific intents are gradually learned by increasing the contribution of low-confidence sequences. Meanwhile, the output probability distributions are reciprocally learned between prediction networks to model unobserved criminal intents. Extensive experiments show that CrimeAlarm outperforms state-of-the-art methods in terms of NDCG@5, with improvements of 4.51% for the NYC16 and 7.73% for the CHI18 in accuracy measures. |
| Keywords | Intent dynamics; Sequential crime predict; Knowledge distillation |
| Contains Sensitive Content | Does not contain sensitive content |
| ANZSRC Field of Research 2020 | 460502. Data mining and knowledge discovery |
| Public Notes | Files associated with this item cannot be displayed due to copyright restrictions. |
| Series | Lecture Notes in Computer Science |
| Byline Affiliations | Wuhan University of Technology, China |
| University of Southern Queensland | |
| University of Technology Sydney | |
| Education University of Hong Kong, China |
Permalink -
https://research.usq.edu.au/item/z995q/crimealarm-towards-intensive-intent-dynamics-in-fine-grained-crime-prediction
26
total views0
total downloads9
views this month0
downloads this month