Clean Water AI

Peter Ma

Peter Ma

San Francisco

11 3
  • 0 Collaborators

Using AI and high definition cameras for bacteria classification and ensure safety in water sources. Sign up for updates at http://www.cleanwaterai.com ...learn more

Project status: Under Development

Internet of Things, Artificial Intelligence

Groups
Movidius™ Neural Compute Group

Intel Technologies
AI DevCloud / Xeon, Intel Opt ML/DL Framework, Movidius NCS

Links [3]

Overview / Usage

According to World Health Organization over 2 billion people are affected by contaminated water. Contaminated water contributes to spreading of disease and health issues such as cholera, diarrhoea, dysentery, typhoid, and polio. Contaminated water contributes to over 500,000 diarrhoeal deaths each year.

The total solution is priced around $500 US dollars, using an inexpensive microscope, a laptop capable of running Unbuntu, and the Intel Movidius Neural Compute Stick. Going forward we plan to build the entire solution into a single IoT device and place them around water sources around the world

Check for updates at http://www.cleanwaterai.com

Methodology / Approach

Using the Intel Movidius Neural Compute stick, and an off the shelf microscope we have created Clean Water AI. Our AI is trained to detect water contaminants and able to detect if water is clean and drinkable vs contaminated and a potential health risk. The neural network model was trained using the Caffe Framework powered by Intel's DevCloud service, and we used NodeJS for the front end website.

Technologies Used

Intel DevCloud, Intel Movidius NCS, Intel Nervana AI, Intel Xeon Processor, Up2 board

Comments (3)