EUVIMEDEUVIMED entdecken
Crossref

Addressing Long-Tailed Spatial and Category Imbalances in Citywide Incident Prediction

Bhumika, Debasis Das

IEEE Transactions on Big Data · 2026-08 · 12 (4) · 1358-1369

DOI: 10.1109/tbdata.2026.3679574 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Big Data, 2026-08. Verfasst von Bhumika und 1 weiteren Autor:innen. Die Arbeit nennt 43 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Citywide incidents such as crimes, accidents, and public safety threats contribute to substantial societal disruption and economic loss. Accurate prediction of such incidents can significantly aid city administrators in proactive response planning. Existing approaches model the incident prediction as a spatio-temporaltask, but often neglect the inter-region spatial long-tailed distribution of incidents. This uneven distribution introduces spatial bias in learning which causes models to overfit regions with frequent incidents (head regions) while underfit the regions with occasional incidents (tail regions). Furthermore, model learning is hindered by intra-region category imbalance, where certain incident types (e.g., theft) dominate over rarer categories (e.g., robbery) within the same region. To address inter and intra region challenges, we propose an approach named SLIP (Spatial Long-tail Incident Prediction). Specifically, for inter-region skewness, SLIP adopts a multi-expert design comprising a common feature extraction backbone followed by three expert branches. In addition, to mitigate the intra-region category imbalance, we utilizes a variant of focal loss, particularly for positive-negative imbalance. SLIP outperforms spatio-temporal state-of-the-art methods by 2–11% in Macro F1, 4–11% in Micro F1, and 1–11% in Severity Weighted F1 across Los Angeles and Chicago cities for the urban crime dataset. Additionally, we incorporate fairness metrics into the evaluation and present a comprehensive comparison of spatio-temporal incident prediction.

Zitieren

APA

Bhumika, & Das, D. (2026). Addressing Long-Tailed Spatial and Category Imbalances in Citywide Incident Prediction. IEEE Transactions on Big Data, 12(4), 1358-1369. https://doi.org/10.1109/tbdata.2026.3679574

Vancouver

Bhumika, Das D. Addressing Long-Tailed Spatial and Category Imbalances in Citywide Incident Prediction. IEEE Transactions on Big Data. 2026;12(4):1358-1369. doi:10.1109/tbdata.2026.3679574

BibTeX
@article{Bhumika2026,
  author = {Bhumika and Das, Debasis},
  title = {Addressing Long-Tailed Spatial and Category Imbalances in Citywide Incident Prediction},
  journal = {IEEE Transactions on Big Data},
  year = {2026},
  volume = {12},
  number = {4},
  pages = {1358--1369},
  doi = {10.1109/tbdata.2026.3679574}
}
Kostenlos starten →