Mass shootings are one of the biggest domestic crises faced by America. According to CNN in the last 10 years alone, there have been 180 school shootings totaling over 350 victims; and according to a study conducted by the University of Albany the average police response time to a mass shooting event is 6 minutes longer than the average duration of mass shootings. Meaning that in most mass shootings police response is effectively useless in saving lives and neutralizing any threats. Our Inspiration for this project was to lower the response time of emergency services, thereby helping to increase the effectiveness first responders can have on active shooter situations.
Warning Shot uses machine learning algorithms trained to recognize specific soundwave properties. This machine-learning algorithm can then be applied to the case of gunshots, allowing our program to recognize when a firearm is discharged inside a specific area (usually a classroom). From here Warning Shot sends an SMS message to students who have signed up to receive alert messages.
Python was chosen as the main language used when building Warning Shot. For the machine learning algorithms the Tensorflow library was utilized. To create a signup form to send SMS messages HTML and CSS were used to create a front end website that was connected to Django and Twilio as backend code.
Developing a stronger machine learning accuracy rating and building features that allow Warning Shot to be a fully implementable product for schools and common areas such as malls, concerts, and movie theaters.
css3, django, html5, python, tensorflow, twilio