A Deep Learning-Based Gunshot Detection IoT System with Enhanced Security Features and Testing Using Blank Guns

Although the U.S. makes up only 5% of the global population, it accounts for approximately 31% of public mass shootings. Gun violence and mass shootings not only result in loss of life and injury but also inflict lasting psychological trauma, cause property damage, and lead to significant economic losses. We recently developed and published an embedded system prototype for detecting gunshots in an indoor environment. The proposed device can be attached to the walls or ceilings of schools, offices, clubs, places of worship, etc., similar to smoke detectors or night lights, and they can notify the first responders as soon as a gunshot is fired. The proposed system will help to stop the shooter early and the injured people can be taken to the hospital quickly, thus more lives can be saved. In this project, a new custom dataset of blank gunshot sounds is recorded, and a deep learning model using both time and frequency domain features is trained to classify gunshot and non-gunshot sounds with 99% accuracy. The previously developed system suffered from several security and privacy vulnerabilities. In this research, those vulnerabilities are addressed by implementing secure Message Queuing Telemetry Transport (MQTT) communication protocols for IoT systems, better authentication methods, Wi-Fi provisioning without Bluetooth, and over-the-air (OTA) firmware update features. The prototype is implemented in a Raspberry Pi Zero 2W embedded system platform and successfully tested with blank gunshots and possible false alarms.