TY - JOUR
T1 - AI-Enabled Optical Sensing for Smart and Precision Food Drying
T2 - Techniques, Applications and Future Directions
AU - da Silva Ferreira, Marcus Vinicius
AU - Ahmed, Md Wadud
AU - Oliveira, Marciano
AU - Sarang, Sanjay
AU - Ramsay, Sheyla
AU - Liu, Xue
AU - Malvandi, Amir
AU - Lee, Youngsoo
AU - Kamruzzaman, Mohammed
N1 - This study was financially supported by the Center for Advanced Research in Drying (CARD), a U.S. National Science Foundation Industry University Cooperative Research Center. CARD is located at Worcester Polytechnic Institute and the University of Illinois at Urbana-Champaign (co-site).
PY - 2024
Y1 - 2024
N2 - Recent developments in alternative drying techniques have significantly heightened interest in innovative technologies that improve the yield and quality of dried goods, enhance energy efficiency, and facilitate continuous monitoring of drying processes. Artificial intelligence (AI)-enabled optical sensing technologies have emerged as promising tools for smart and precise monitoring of food drying processes. Food industries can leverage AI-enabled optical sensing technologies to gain a comprehensive understanding of drying dynamics, optimize process parameters, identify potential issues, and ensure product consistency and quality. This review systematically discusses the application of selected optical sensing technologies, such as near-infrared (NIR) spectroscopy, hyperspectral imaging, and conventional imaging (i.e., computer vision) powered by AI. After covering the basics of optical sensing technologies for smart drying and an overview of different drying methods, it explores various optical sensing techniques for monitoring and quality control of drying processes. Additionally, the review addresses the limitations of these optical sensing technologies and their prospects in smart drying.
AB - Recent developments in alternative drying techniques have significantly heightened interest in innovative technologies that improve the yield and quality of dried goods, enhance energy efficiency, and facilitate continuous monitoring of drying processes. Artificial intelligence (AI)-enabled optical sensing technologies have emerged as promising tools for smart and precise monitoring of food drying processes. Food industries can leverage AI-enabled optical sensing technologies to gain a comprehensive understanding of drying dynamics, optimize process parameters, identify potential issues, and ensure product consistency and quality. This review systematically discusses the application of selected optical sensing technologies, such as near-infrared (NIR) spectroscopy, hyperspectral imaging, and conventional imaging (i.e., computer vision) powered by AI. After covering the basics of optical sensing technologies for smart drying and an overview of different drying methods, it explores various optical sensing techniques for monitoring and quality control of drying processes. Additionally, the review addresses the limitations of these optical sensing technologies and their prospects in smart drying.
KW - Artificial intelligence
KW - Chemometrics
KW - Hyperspectral imaging
KW - Machine learning
KW - Near-infrared
KW - Optical sensing
KW - Smart drying
UR - http://www.scopus.com/inward/record.url?scp=85209721490&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85209721490&partnerID=8YFLogxK
U2 - 10.1007/s12393-024-09388-0
DO - 10.1007/s12393-024-09388-0
M3 - Article
AN - SCOPUS:85209721490
SN - 1866-7910
JO - Food Engineering Reviews
JF - Food Engineering Reviews
ER -