CUDA

Bed Exits

CUDA Python Tensorflow NodeJS Angular TypeScript
Foresite Healthcare develops advanced sensor technologies for passive, privacy-protecting, around-the-clock monitoring and artificial intelligence-based predictive analytics to enable preventive care and personized interventions in hospitals and senior living facilities. Foresite hired Positronic to be a deep learning and data science provider to help drive the next generation of hospital monitoring solutions. Positronic developed a deep-learning neural network solution, leveraging convolutional and LSTM technology, that accurately predicts before patients attempt to exit their beds. Read more...

Biomarker Discovery

CUDA Python Tensorflow TypeScript Angular NodeJS Mongo
Stratus, is the leading provider of In-Home Video EEG Testing in the United States. Stratus hired Positronic to build a feature extraction and deep learning platform capable of detecting subtle differences between EEGs obtained in different clinical states for the creation of potential biomarkers of drugs and disease states. data The platform allows the user must to select or upload a batch of EEG files. The platform provides controls for general file management functions to keep the ever-growing datasets manageable. Read more...

Real-Time EEG Diagnosis

CUDA Python Tensorflow
Stratus, is the leading provider of In-Home Video EEG Testing in the United States. The stated goal of the Stratus AI initiative is to improve the quality and data of neurophysiology studies. Currently, the publicly announced projects include: artificial intelligence interpretation of EEGs, biomarker discovery services, and the EEGenix database. Stratus hired Positronic to be deep learning and data science provider. What follows is some information about the work we did to facilitate the goal of AI interpretation of EEGs. Read more...

NVIDIA Support

Python CUDA Tensorflow
Recently we were given the privilege to provide technical support to the NVIDIA deep learning research teams. NVIDIA provided supercomputers (DGX-2) for two months, during which time our technical team helped propel forward technology development used to parallelize very large LSTM neural networks.