OBINALI, CHUKWUEMEKA (2026) DEVELOPMENT OF AN INTELLIGENT MOBILE-BASED EMERGENCY DETECTION AND AUTOMATED SOS SYSTEM. Other thesis, Godfrey Okoye University, Enugu Nigeria.
![[img]](https://eprints.gouni.edu.ng/style/images/fileicons/text.png) |
Text
OBINALI_CHUKWUEMEKA_400lv_PDF_project.pdf Download (1MB) |
Abstract
The increasing prevalence of insecurity, violent crimes, accidents, and sudden medical emergencies has heightened the need for effective and timely emergency response systems, particularly in environments where access to immediate help is limited. Traditional emergency response methods largely depend on manual actions such as phone calls or panic buttons, which may be ineffective when victims are incapacitated, restrained, unconscious, or unable to react promptly. This challenge underscores the need for intelligent systems capable of autonomously detecting danger and initiating emergency responses without relying solely on user intervention. The core problem this study addresses is the inadequacy of existing safety solutions for situations where users cannot manually trigger emergency alerts. Delays in communication during such incidents significantly reduce the chances of rescue and survival. The study seeks to answer how artificial intelligence and smartphone sensor data can be used to automatically detect dangerous situations and promptly notify emergency contacts. To address this problem, the study adopts a system design and implementation methodology. The proposed Development of an Intelligent Mobile-Based Emergency Detection and Automated SOS System leverages smartphone sensors, including motion, location, and sound data, combined with artificial intelligence techniques for anomaly and danger detection. A backend system is developed using Python-based frameworks to process data, manage alerts, and coordinate automated emergency messaging to predefined contacts. Simulated data and controlled test scenarios are used to evaluate system performance. The results of the study demonstrate that the system can successfully detect abnormal or potentially dangerous situations and automatically transmit SOS alerts containing real-time location information. The prototype shows improved responsiveness compared to manual-only emergency systems and effectively reduces reliance on direct user interaction during critical moments. The study contributes to the field of intelligent safety systems by presenting a practical and scalable approach to automated emergency detection and response. The findings highlight the potential of AI- driven solutions to enhance personal safety and emergency preparedness, while providing a foundation for future research, system optimization, and possible real-world deployment.
| Item Type: | Thesis (Other) |
|---|---|
| Subjects: | Q Science > Q Science (General) |
| Divisions: | Faculty of Computing And Information Technology (FACIT) |
| Depositing User: | Cynthia Ugwuoti |
| Date Deposited: | 24 Jul 2026 10:45 |
| Last Modified: | 24 Jul 2026 10:45 |
| URI: | http://eprints.gouni.edu.ng/id/eprint/5917 |
Actions (login required)
 |
View Item |
