Hybrid of deep learning and exponential smoothing for enhancing crime forecasting accuracy
The continued urbanization poses several challenges for law enforcement agencies to ensure a safe and secure environment. Countries are spending a substantial amount of their budgets to control and prevent crime. However, limited efforts have been made in the crime prediction area due to the deficie...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Published: |
Public Library of Science (PLoS)
2022
|
| _version_ | 1811137590493970432 |
|---|---|
| author | Butt, Umair Muneer Letchmunan, Sukumar Hassan, Fadratul Hafinaz Koh, Tieng Wei |
| author_facet | Butt, Umair Muneer Letchmunan, Sukumar Hassan, Fadratul Hafinaz Koh, Tieng Wei |
| author_sort | Butt, Umair Muneer |
| collection | UPM |
| description | The continued urbanization poses several challenges for law enforcement agencies to ensure a safe and secure environment. Countries are spending a substantial amount of their budgets to control and prevent crime. However, limited efforts have been made in the crime prediction area due to the deficiency of spatiotemporal crime data. Several machine learning, deep learning, and time series analysis techniques are exploited, but accuracy issues prevail. Thus, this study proposed a Bidirectional Long Short Term Memory (BiLSTM) and Exponential Smoothing (ES) hybrid for crime forecasting. The proposed technique is evaluated using New York City crime data from 2010-2017. The proposed approach outperformed as compared to state-of-the-art Seasonal Autoregressive Integrated Moving Averages (SARIMA) with low Mean Absolute Percentage Error (MAPE) (0.3738, 0.3891, 0.3433, 0.3964), Root Mean Square Error (RMSE)(13.146, 13.669, 13.104, 13.77), and Mean Absolute Error (MAE) (9.837, 10.896, 10.598, 10.721). Therefore, the proposed technique can help law enforcement agencies to prevent and control crime by forecasting crime patterns. |
| first_indexed | 2024-09-25T03:36:43Z |
| format | Article |
| id | upm.eprints-101753 |
| institution | Universiti Putra Malaysia |
| last_indexed | 2024-09-25T03:36:43Z |
| publishDate | 2022 |
| publisher | Public Library of Science (PLoS) |
| record_format | dspace |
| spelling | upm.eprints-1017532024-05-02T06:50:46Z http://psasir.upm.edu.my/id/eprint/101753/ Hybrid of deep learning and exponential smoothing for enhancing crime forecasting accuracy Butt, Umair Muneer Letchmunan, Sukumar Hassan, Fadratul Hafinaz Koh, Tieng Wei The continued urbanization poses several challenges for law enforcement agencies to ensure a safe and secure environment. Countries are spending a substantial amount of their budgets to control and prevent crime. However, limited efforts have been made in the crime prediction area due to the deficiency of spatiotemporal crime data. Several machine learning, deep learning, and time series analysis techniques are exploited, but accuracy issues prevail. Thus, this study proposed a Bidirectional Long Short Term Memory (BiLSTM) and Exponential Smoothing (ES) hybrid for crime forecasting. The proposed technique is evaluated using New York City crime data from 2010-2017. The proposed approach outperformed as compared to state-of-the-art Seasonal Autoregressive Integrated Moving Averages (SARIMA) with low Mean Absolute Percentage Error (MAPE) (0.3738, 0.3891, 0.3433, 0.3964), Root Mean Square Error (RMSE)(13.146, 13.669, 13.104, 13.77), and Mean Absolute Error (MAE) (9.837, 10.896, 10.598, 10.721). Therefore, the proposed technique can help law enforcement agencies to prevent and control crime by forecasting crime patterns. Public Library of Science (PLoS) 2022 Article PeerReviewed Butt, Umair Muneer and Letchmunan, Sukumar and Hassan, Fadratul Hafinaz and Koh, Tieng Wei (2022) Hybrid of deep learning and exponential smoothing for enhancing crime forecasting accuracy. Public Library of Science, 17 (9). art. no. 274172. pp. 1-22. ISSN 1932-6203 https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0274172 10.1371/journal.pone.0274172 |
| spellingShingle | Butt, Umair Muneer Letchmunan, Sukumar Hassan, Fadratul Hafinaz Koh, Tieng Wei Hybrid of deep learning and exponential smoothing for enhancing crime forecasting accuracy |
| title | Hybrid of deep learning and exponential smoothing for enhancing crime forecasting accuracy |
| title_full | Hybrid of deep learning and exponential smoothing for enhancing crime forecasting accuracy |
| title_fullStr | Hybrid of deep learning and exponential smoothing for enhancing crime forecasting accuracy |
| title_full_unstemmed | Hybrid of deep learning and exponential smoothing for enhancing crime forecasting accuracy |
| title_short | Hybrid of deep learning and exponential smoothing for enhancing crime forecasting accuracy |
| title_sort | hybrid of deep learning and exponential smoothing for enhancing crime forecasting accuracy |
| work_keys_str_mv | AT buttumairmuneer hybridofdeeplearningandexponentialsmoothingforenhancingcrimeforecastingaccuracy AT letchmunansukumar hybridofdeeplearningandexponentialsmoothingforenhancingcrimeforecastingaccuracy AT hassanfadratulhafinaz hybridofdeeplearningandexponentialsmoothingforenhancingcrimeforecastingaccuracy AT kohtiengwei hybridofdeeplearningandexponentialsmoothingforenhancingcrimeforecastingaccuracy |