How Our Sensors Work
Our technology is innovation that makes the impossible possible.
Our technology uses two pieces of magic working together: an incredible sensor technology with cutting-edge computer vision and deep-learning algorithms.
The in-line, optical sensor technology is the core of our innovative platform. We use light scattering technology for rapid, on-site determinations of major compounds in raw milk. Our monitoring equipment fits into the milking line of existing dairy equipment, making it technologically accessible and cost-effective for dairy producers whether they have a state-of-the-art robotic milking system, a more common milking parlor system, or a tie-stall system. This technology does not require the use of any chemicals, meaning that the milk that is used to take measurements is unaltered, and can be returned to the milking line after measurement. This reduces the operational costs of the technology and eliminates the use of chemicals inside of dairy barns.
What is light scattering?
Our technology relies on the principle of light scattering: A beam of directed light passes through a medium (raw milk) and hits small particles that cause the beam to change direction and scatter. During this process, a portion of the light may be absorbed or reflected altering the intensity of the scattered beam. Particles of different sizes, in various concentrations, will have unique scattering patterns that can be observed.
Until our technology, the application of forward-angle light scattering in fluids has been limited to specific applications and has often been too costly for non-laboratory uses. With our sensor, it is now possible to detect several compounds across a wide range of particulate sizes, including small and large molecules, single-cells, using a cost-effective sensor system.
Predicting trends with deep learning and neural nets.
Artificial neural networks use algorithms, big data, and the computational power of graphic processing units (GPUs) to find patterns and connexions between data sets. This branch of machine learning enables computers to achieve complex calculations and learn at speed, accuracy, and scale that has not before been possible.
We use computer vision and deep neural networks to build robust algorithms to predict the presence and concentrations of major compounds in raw milk. We have collected thousands of milk samples to train a predictive model. This data set has yielded algorithms that act as the baseline of prediction, while additional data sets will allow us to improve and deepen the predictive algorithm and ensure accuracy and consistency across a wide range of use cases.
This approach has enabled the company to develop a series of robust models for determinations of fat content, protein content, trace antibiotics, and progesterone. Together, these compounds make it possible to ensure milk quality and to rapidly diagnose multiple major dairy diseases, including sub-clinical and clinical mastitis, ketosis, and acidosis.
See what we measure.
Our sensors help farmers improve milk quality and herd health. We deliver on the data they need.