Search Results - alan+bovik

2 Results Sort By:
Deep Neural Networks for Real-Time Non-invasive Continuous Peripheral Oxygen Saturation Monitoring (Case No. 2024-227)
Summary: UCLA researchers in the Department of Anesthesiology have developed a novel pulse oximetry methodology utilizing deep neural networks for non-invasive monitoring. Background: In the US alone, over 5 million patients are admitted to the ICU for oxygen saturation monitoring. They, as well as the more than 15 million patients undergoing surgery,...
Published: 7/26/2024   |   Inventor(s): Sungsoo (Danny) Kim, Sohee Kwon, Mia Markey, Alan Bovik, Akos Rudas, Ravi Pal, Maxime Cannesson
Keywords(s): Artifical Intelligence (Machine Learning, Data Mining), Blood Pressure, cardiovascular monitoring, central venous pressure (CVP), Continuous blood pressure monitoring, critical care, Deep learning-based sensing, deep-learning analysis algorithms, heart failure, hemodynamic monitoring, machine learning modeling, Monitoring (Medicine), neural network, non-invasive monitoring, Oxygen, Oxygen Saturation, pulmonary arterial pressure (PAP), Swan-Ganz catheter
Category(s): Medical Devices > Monitoring And Recording Systems, Software & Algorithms > Digital Health
An efficient codec for improved quality streaming video at low bitrates
Background The ultimate goal of a successful video compression system is to reduce data volume while retaining the perceptual quality of the decompressed data. Standard video compression techniques, such as H.264, HEVC, VP9 and others, have well-known limits and tradeoffs between rate and distortion, especially at low bitrates. Better video compression...
Published: 12/8/2023   |   Inventor(s): Alan Bovik, Georgios-Alex Dimakis, Sungsoo Kim, Jin Soo Park, Christos Bampis
Keywords(s): Artificial intelligence (AI), Codec, Machine learning, Streaming video, Video compression
Category(s): Physical sciences > Video