Spatio-temporal prediction of terrorist attacks based on GCN-LSTM
Terrorist attacks represent a significant threat to national order, social stability, and economic security. Accurate prediction of such attacks is a critical task for casualty reduction, enhanced decision-making, and optimal resource distribution in counter-terrorism efforts. This paper introduces...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
KeAi Communications Co., Ltd.
2025-06-01
|
| Series: | Journal of Safety Science and Resilience |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2666449625000301 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849434497622212608 |
|---|---|
| author | Yingjie Du Ning Ding Hongyu Lv |
| author_facet | Yingjie Du Ning Ding Hongyu Lv |
| author_sort | Yingjie Du |
| collection | DOAJ |
| description | Terrorist attacks represent a significant threat to national order, social stability, and economic security. Accurate prediction of such attacks is a critical task for casualty reduction, enhanced decision-making, and optimal resource distribution in counter-terrorism efforts. This paper introduces an innovative spatio-temporal fusion framework that combines graph convolutional network (GCN) with long short-term memory (LSTM) models. By capturing and merging spatio-temporal features from relevant events, the proposed GCN-LSTM model achieves remarkable accuracy in predicting terrorist attacks. The experimental results demonstrate outstanding performance, with the model attaining minimal RMSE and MAE values of 0.037 and 0.031, respectively, surpassing all baseline models (LSTM, GCN, and CNN-LSTM-Transformer). Through its effective interpretation of complex spatio-temporal patterns underlying terrorist attacks, our model substantially enhances the predictive accuracy across diverse time horizons. These findings carry crucial implications for enhancing counter-terrorism strategies. |
| format | Article |
| id | doaj-art-b8ffd0209f14460e8431738d4707b055 |
| institution | Kabale University |
| issn | 2666-4496 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | KeAi Communications Co., Ltd. |
| record_format | Article |
| series | Journal of Safety Science and Resilience |
| spelling | doaj-art-b8ffd0209f14460e8431738d4707b0552025-08-20T03:26:38ZengKeAi Communications Co., Ltd.Journal of Safety Science and Resilience2666-44962025-06-016218619510.1016/j.jnlssr.2025.02.005Spatio-temporal prediction of terrorist attacks based on GCN-LSTMYingjie Du0Ning Ding1Hongyu Lv2Public Security Behavioral Science Lab, People's Public Security University of China, Beijing, 100038, China; College of Investigation, People's Public Security University of China, Beijing, 100038, ChinaPublic Security Behavioral Science Lab, People's Public Security University of China, Beijing, 100038, China; Corresponding author.Public Security Behavioral Science Lab, People's Public Security University of China, Beijing, 100038, China; College of Investigation, People's Public Security University of China, Beijing, 100038, ChinaTerrorist attacks represent a significant threat to national order, social stability, and economic security. Accurate prediction of such attacks is a critical task for casualty reduction, enhanced decision-making, and optimal resource distribution in counter-terrorism efforts. This paper introduces an innovative spatio-temporal fusion framework that combines graph convolutional network (GCN) with long short-term memory (LSTM) models. By capturing and merging spatio-temporal features from relevant events, the proposed GCN-LSTM model achieves remarkable accuracy in predicting terrorist attacks. The experimental results demonstrate outstanding performance, with the model attaining minimal RMSE and MAE values of 0.037 and 0.031, respectively, surpassing all baseline models (LSTM, GCN, and CNN-LSTM-Transformer). Through its effective interpretation of complex spatio-temporal patterns underlying terrorist attacks, our model substantially enhances the predictive accuracy across diverse time horizons. These findings carry crucial implications for enhancing counter-terrorism strategies.http://www.sciencedirect.com/science/article/pii/S2666449625000301Terrorist attacksSpatio-temporal predictionGraph convolutional networksLong short-term memoryCounter-terrorism |
| spellingShingle | Yingjie Du Ning Ding Hongyu Lv Spatio-temporal prediction of terrorist attacks based on GCN-LSTM Journal of Safety Science and Resilience Terrorist attacks Spatio-temporal prediction Graph convolutional networks Long short-term memory Counter-terrorism |
| title | Spatio-temporal prediction of terrorist attacks based on GCN-LSTM |
| title_full | Spatio-temporal prediction of terrorist attacks based on GCN-LSTM |
| title_fullStr | Spatio-temporal prediction of terrorist attacks based on GCN-LSTM |
| title_full_unstemmed | Spatio-temporal prediction of terrorist attacks based on GCN-LSTM |
| title_short | Spatio-temporal prediction of terrorist attacks based on GCN-LSTM |
| title_sort | spatio temporal prediction of terrorist attacks based on gcn lstm |
| topic | Terrorist attacks Spatio-temporal prediction Graph convolutional networks Long short-term memory Counter-terrorism |
| url | http://www.sciencedirect.com/science/article/pii/S2666449625000301 |
| work_keys_str_mv | AT yingjiedu spatiotemporalpredictionofterroristattacksbasedongcnlstm AT ningding spatiotemporalpredictionofterroristattacksbasedongcnlstm AT hongyulv spatiotemporalpredictionofterroristattacksbasedongcnlstm |