Eleven years ago, I started deep research into the disciples of preventative, predictive, and precision medicines with a personal commitment to ending childhood diseases. It always weighed heavy on my heart that no parent should ever have to bury their child. As I sit here finishing my education, research, book, and patents, something else weighs on my heart and soul. My dear friend narrowly adverted being a victim in a mass shooting type of event yesterday. It breaks my heart that we are at this point and haven't come up with actionable solutions. I am an engineer specializing in complex problems and utilizing disruptive technologies and innovation to develop solutions. Hear me out as I look at this problem while keeping all variables at the forefront.
1) Identify high-priority areas like schools, places of worship, etc.
2) Develop an Early Warning Mass Shooting & Acts of Violence System. AI, Machine Learning, and Deep Learning systems can be developed to look at video frames in real-time to determine potential violence risks. By using computer-based analytical vision, the system can detect motion patterns that could indicate a risk of violence. By applying facial recognition, the system can identify individuals in the video and compare them against known violent offenders. Furthermore, behavior analysis algorithms can analyze movement in order to assess risk levels. This type of system is especially useful for events such as concerts, sports games, and political rallies where large numbers of people are gathered in close proximity. Additionally, this approach could be used to monitor public spaces for trends in criminal activity or suspicious behavior.
A Tensor Processing Unit (TPU) is an AI-focused hardware accelerator designed for running neural network workloads. TPUs are specialized pieces of hardware that have been optimized for specific tasks like image processing, natural language processing, and machine learning. These accelerators are built to deliver high performance while consuming minimal power, making them ideal for edge computing applications.
Edge TPUs can perform up to 4 trillion operations per second (TOPS), making them well-suited for high-performance AI inference applications. These devices are powerful enough to process complex models with large batch sizes and fast response times. Additionally, these TPUs offer low power consumption (generally 0.5 Watts per trillion operations per second). With the ability to rapidly process video frames in real time, Edge TPUs are ideal for developing AI/ML/DL solutions that can detect potential violence risks in video streams.
3) Develop a National Early Warning Mass Shooting & Acts of Violence System Division that focuses on developing Supervised Learning Models within Machine Learning to build classification models. This area of study will focus on predicting if people are likely to commit acts of violence based on a Violent Crime Risk Assessment (VCRA). VCRA focuses on analyzing the behaviors and characteristics of individuals in order to identify the likelihood that they will engage in violent behavior. This field typically entails using supervised machine learning algorithms to analyze a variety of factors such as social class, psychological traits, criminal history, and demographic information. By combining these data points with real-time video frames, AI/ML/DL systems can be developed to detect potential violence risks with high accuracy.
4) Make it a federal priority to implement in high-priority areas as quickly as possible. Fund through Early Warning Mass Shooting & Acts of Violence System tax on weapons, ammunition, and mature-based video games. I understand that no one likes additional taxes, but we have to put an end to this violence. These are my five minutes of thoughts on how we could address this problem while being respectful to all parties.