Search Results - classification

5 Results Sort By:
2022-230 Polarization Multiplexed Diffractive Computing: All-Optical Implementation of a Group of Linear Transformations Through a Polarization-Encoded Diffractive Network
Summary: UCLA researchers in the Department of Electrical and Computer Engineering have developed an all-optical diffractive network that can find applications in machine learning-related vision tasks and all-optical computing systems. Background: Optical computing is a gateway to the future, as it can revolutionize computation by making classically...
Published: 8/21/2023   |   Inventor(s): Aydogan Ozcan, Jingxi Li
Keywords(s): Advanced Computing / AI, all-optical diffractive computing, all-optical transformation, Artifical Intelligence (Machine Learning, Data Mining), Artificial Intelligence, artificial-intelligent materials, classification, Deep Learning, diffractive network, diffractive processor, Electrical, Electrical Engineering, Internet of Things (IoT), Machine Vision, machine vision task, multiplexing, Optical Coherence , Optical Communication , Optical Fiber Copper Wire And Cable, Optical Microscope, Optics, polarization multiplexed diffractive processor, polarization multiplexing, polarization-based machine vision tasks, polarization-encoded diffractive network
Category(s): Electrical, Electrical > Instrumentation, Software & Algorithms, Software & Algorithms > Artificial Intelligence & Machine Learning, Software & Algorithms > Data Analytics, Optics & Photonics, Electrical > Electronics & Semiconductors
DNA Methylation Based Non-invasive Blood Diagnostic Assay for Precision Cancer Detection and Classification
This technology includes a panel of 46 genomic loci of DNA methylation (represented by CpG dinucleotides on different chromosomes) with application in blood-based cancer screening. The markers robustly distinguish tumor from normal samples using 8 loci and classify 13 different tumor types. Using 39 loci, inventors were able to discriminate between...
Published: 10/28/2024   |   Inventor(s): Gennady Margolin, Laura Elnitski
Keywords(s): assay, Based, Blood, CANCER, CLASSIFICATION, Detection, diagnostic, DNA, Humans, Methylation, NON-INVASIVE, PRECISION, VCXXXX, WBXXXX, WIXXXX, XEXXXX
Category(s): Application > Research Materials, Application > Diagnostics, TherapeuticArea > Oncology, Application > Therapeutics
Algorithm for Detection of Real-Time Damage using Acoustic Emissions
Reference #: 01546 The University of South Carolina is offering licensing opportunities for Algorithm for Detection of Real-Time Damage using Acoustic Emissions Background: Other methods of damage detection rely on historical data (meaning that they will need to collect multiple days, weeks, or months of data before they can make a determination...
Published: 9/3/2022   |   Inventor(s): Paul Ziehl, Casey Cole
Keywords(s): acoustic emission, Acoustic emissions, classification, damage, decision tree
Category(s): Advanced Materials, Engineering and Physical Sciences
Device for Automating Sorting of Haploid Maize Kernels
Uses Spectroscopy to Rapidly Distinguish and Sort Haploid Seeds for Maize Breeding Single kernel near-infrared reflectance spectroscopy (NIRS) has been refined to sort haploid kernels created for use in maize breeding. Using the methods developed by UF’s researchers should reduce labor costs associated with manual sorting of seeds and multiply...
Published: 2/22/2024   |   Inventor(s): Andrew Settles, Jeffrey Gustin
Keywords(s): Breeding, classification, haploid, Maize, Spectroscopy
Category(s): Technology Classifications > Agricultural, Technology Classifications > Agricultural > Diagnostics
Correntropy Loss Function that Promotes Robust Training in Artificial Neural Networks
Algorithm Resists Outliers to Provide Accurate Data Classification for Random Sets of DataThe Correntropy Loss, or C-loss, function stabilizes signals in artificial neural networks to optimally classify random data points and resist the presence of outliers in a given sample. Artificial neural networks are statistical models that process information...
Published: 6/27/2021   |   Inventor(s): Jose Principe, Abhishek Singh
Keywords(s): classification, Data Mining, Neural networks, Robust Training
Category(s): Technology Classifications > Engineering > Computer Science