An innovative solution that integrates machine learning with hyperspectral imaging to enhance food safety detection. This approach improves accuracy, efficiency, and cost-effectiveness in identifying contaminants compared to traditional methods.
The integration of machine learning (ML) with hyperspectral imaging (HSI) represents a groundbreaking advancement in food safety detection. This technology aims to significantly improve the accuracy and efficiency of detecting contaminants in food products, surpassing traditional methods. By leveraging detailed spectral and spatial data provided by HSI, ML models can identify physical, chemical, and biological contaminants more comprehensively and rapidly. This results in a faster, more cost-effective process that reduces reliance on manual testing and chemical reagents.
Key features:
Currently at Technology Readiness Level 3, this solution has undergone initial testing and validation. The next phase involves refining the machine learning models and deploying them in pilot settings for real-time analysis. The aim is to complete these stages within a 12-month timeline, further validating the technology's effectiveness and scalability.
Binghamton University is a large, comprehensive public research university in the State University of New York system. Industry collaborates on campus through an advanced technologies complex with shared labs and prototyping facilities, and a health sciences campus adjacent to regional hospital partners. A downtown incubator and maker spaces connect faculty and startups with suppliers and manufacturing in New York’s Southern Tier, while co-op and internship pathways build talent pipelines for corporate R&D. Research is supported by competitive federal funding from agencies such as NSF, NIH, DOE, and DoD, with additional state and industry sponsorship. A dedicated technology transfer office streamlines IP protection, licensing, and startup formation.