Development of a predictive model for crime investigation and emergency response system
| dc.contributor.author | Robert, Buki Oladele | |
| dc.date.accessioned | 2025-02-04T14:07:25Z | |
| dc.date.available | 2025-02-04T14:07:25Z | |
| dc.date.issued | 2024-05 | |
| dc.description | The Master theis contains tables and figures | |
| dc.description.abstract | Ensuring public safety through efficient crime investigation and emergency response is crucial in today's complex world. This study presents a predictive model for an integrated Crime Investigation and Emergency Response System, leveraging data-driven analysis, advanced machine learning algorithms, and modern Information Technology (IT). The research aims to enhance law enforcement and emergency response protocols, recognizing the critical role of IT in managing critical incidents. The study addresses challenges in crime investigation, particularly violent offenses, by employing machine learning strategies incorporating regression and classification techniques. The primary objective is to uncover patterns and insights to predict perpetrator characteristics such as age, gender, and their relationship with the victim. Through comprehensive data analysis of a dataset containing 638,454 crime records from 1980 to 2014, the research identified 190,282 unsolved crimes, with approximately 100,000 involving handguns. The Municipal Police agency reported the highest number of unsolved crimes, highlighting the need for improved investigative tools. The predictive model's performance was evaluated using the Receiver Operating Characteristic (ROC) curve, demonstrating a remarkable accuracy with an Area Under the ROC Curve (AUC) of 95%. The model exhibited high accuracy rates in predicting the perpetrator's gender (96%) and relationship with the victim (97%), significantly outperforming an existing model. These results underscore the potential of the developed predictive model to enhance law enforcement capabilities and emergency response procedures. The study recommends further integration of data-centric approaches in public safety operations to improve efficiency and outcomes. . | |
| dc.identifier.citation | Robert, B. O. (2024). Development of a predictive model for crime investigation and emergency response system (Unpublished Master's Thesis). Federal University of Technology, Owerri, Nigeria | |
| dc.identifier.uri | https://repository.futo.edu.ng/handle/20.500.14562/1613 | |
| dc.language.iso | en | |
| dc.publisher | Federal University of Technology, Owerri | |
| dc.rights | Attribution-NonCommercial-ShareAlike 4.0 International | en |
| dc.rights.uri | http://creativecommons.org/licenses/by-nc-sa/4.0/ | |
| dc.subject | Civil intelligence | |
| dc.subject | emergency | |
| dc.subject | multi-linear regression | |
| dc.subject | K-NN | |
| dc.subject | ANN | |
| dc.subject | Department of Information Management Technology | |
| dc.title | Development of a predictive model for crime investigation and emergency response system | |
| dc.type | Master’s Thesis |