DSFAS-AI: FOOD QUALITY EVALUATION LEVERAGING ROBUST, DOMAIN ADAPTIVE DEEP LEARNING ON MILLIMETER WAVE (MMWAVE) IMAGES

Project: Research project

Project Details

Description

The modern food industry has been rapidly developing with a goal to strive supply markets and consumers with safe, nutritious, and high-quality products. However, quality assurance is challenging with raising issue of learning bias in processing large amount of data and generalizing to the evaluation of new food type. Traditional quality assurance methods based on chemical experiments and subjective evaluations also fail to meet the requirement of high volume food production and high food quality criteria. It is critical to search for more advanced, non-invasive, fast, reliable, and affordable sensing techniques and data science tools that will enable automated and real-time decision making to ensure food product safety.In this project, we propose to combine artificial intelligence (AI) and millimeter wave imaging to ensure the analysis of massive food data efficient and effective. We will use robust learning technology to reduce bias in machine learning and use few-shot learning to develop a generalizable platform for images from new food types. The system will be implemented by inexpensive imaging system using millimeter wave chipset. Ultimately, we expect to develop this innovative nanotechnology that will make a long-range contribution to data science and U.S. Agriculture and Food Systems.
StatusActive
Effective start/end date15/02/2214/02/25

Fingerprint

Explore the research topics touched on by this project. These labels are generated based on the underlying awards/grants. Together they form a unique fingerprint.