Virtual Impactor-Based Label-Free Bio-Aerosol Detection Using Holography and Deep Learning (Case No. 2023-037)
Innovation:
UCLA researchers have developed a virtual impactor-based bio-aerosol detector. The use of a virtual impactor is coupled with computer imaging and a neural network for classification, removing the need for any maintenance-necessitating filtration, secondary labeling, or external analysis. Multiple holographic images are captured of each particle, capturing volumetric information with a vast field-of-view; enabling higher classification accuracy and detailed visualization from multiple angles. By leveraging a deep neural network, it achieves a >92% accuracy in classifying diverse pollen types. The system is compact and cost-effective to manufacture. Capture, imaging, and analysis is all done within a single, closed system, enabling real-time, long term air quality monitoring. In addition, this technology can be utilized to monitor bacterial and viral particulates for a diverse array of applications.
Potential Applications:
• Indoor air quality monitoring
• Environmental monitoring
• Agricultural & plant biology research
• HVAC system integration
• Viral or bacterial monitoring
• Bioterrorism defense
Air Quality Monitoring Using Mobile Microscopy and Machine Learning (Case No. 2017-513)
Innovation:
Field-portable cost-effective platform for high-throughput quantification of particulate matter (PM) using computational lens-free microscopy and machine-learning
Advantages:
- Field-portable/ mobile solution
- Cost-effective platform
- High-throughput quantification of particulate matter (air)
- Uses computational lens-free microscopy and machine-learning
- High accuracy
- Easy to use
Potential Applications:
- Field particulate matter/air monitoring
Bio-Aerosol Detection Using Mobile Microscopy and Machine Learning (Case No. 2019-722)
Innovation:
UCLA researchers have developed a virtual impactor-based bio-aerosol detector. Virtual impactors are devices used to separate airborne particles into distinct airstreams based on their size. The use of a virtual impactor is coupled with lens-less computational imaging, sidestepping the need for filtration and maintenance. By leveraging a deep neural network, it achieves a >94% accuracy in classifying diverse pollen types. The system is compact and cost-effective to manufacture. Capture, imaging, and analysis is all done within a single, portable closed system, enabling real-time, long term air quality monitoring.
Potential Applications:
• Indoor air quality monitoring
• Environmental monitoring
• Agricultural & plant biology research
• Industrial applications: food processing, fermentation
• Bioterrorism detection
Advantages:
• Cost effective
• Hand-held, portable
• Wireless control
• Label-free detection
• Extended, real-time monitoring
• >94% accuracy in identifying different pollen types.