Article
Agricultural Engineering
Alessandro Benelli, Chiara Cevoli, Angelo Fabbri, Luigi Ragni
Summary: In this study, hyperspectral imaging was used to evaluate the ripeness of 'Hayward' kiwifruit and develop models for predicting soluble solids content and flesh firmness. The results showed that hyperspectral imaging is suitable for predicting kiwi quality attributes and their classification.
BIOSYSTEMS ENGINEERING
(2022)
Article
Food Science & Technology
Chitra Sivakumar, Muhammad Mudassir Arif Chaudhry, Jitendra Paliwal
Summary: The research investigated the feasibility of using hyperspectral imaging to classify pulse flours based on pulse type and milling methods. Supervised classification models showed high accuracy in differentiating flour samples based on color attributes and protein overtones, providing a reliable method for characterization of pulse flours in the food industry.
LWT-FOOD SCIENCE AND TECHNOLOGY
(2022)
Article
Chemistry, Multidisciplinary
Esther Kho, Behdad Dashtbozorg, Joyce Sanders, Marie-Jeanne T. F. D. Vrancken Peeters, Frederieke van Duijnhoven, Henricus J. C. M. Sterenborg, Theo J. M. Ruers
Summary: Developing algorithms for analyzing hyperspectral images as an intraoperative tool for margin assessment during breast-conserving surgery requires a dataset with reliable histopathologic labels. By comparing tissue slices and lumpectomy datasets, using wavelengths with appropriate penetration depth to develop tissue classification algorithms was explored. Spectral differences between tissue slices and lumpectomy datasets were observed, affecting the discrimination of different tissue types.
APPLIED SCIENCES-BASEL
(2021)
Article
Plant Sciences
Yanjie Li, Mahmoud Al-Sarayreh, Kenji Irie, Deborah Hackell, Graeme Bourdot, Marlon M. Reis, Kioumars Ghamkhar
Summary: By utilizing hyperspectral imaging data and machine learning, we have achieved automated identification and mapping of weeds in ryegrass/clover pastures, with the most reliable and robust prediction result being 89.1% accuracy using Multilayer Perceptron based on superpixels method.
FRONTIERS IN PLANT SCIENCE
(2021)
Article
Agricultural Engineering
Xiaping Fu, Jinchao Chen, Jianyi Zhang, Feng Fu, Chuanyu Wu
Summary: This study explored the detection of adulterants in powdered food, finding that light penetration depth and adulterant particle size have an impact on detection results, with better results found for particle sizes of 380-270 mm and 270-250 mm.
BIOSYSTEMS ENGINEERING
(2021)
Article
Food Science & Technology
Sara Leon-Ecay, Ainara Lopez-Maestresalas, Maria Teresa Murillo-Arbizu, Maria Jose Beriain, Jose Antonio Mendizabal, Silvia Arazuri, Carmen Jaren, Phillip D. Bass, Michael J. Colle, David Garcia, Miguel Romano-Moreno, Kizkitza Insausti
Summary: This research aimed to create a model using hyperspectral imaging (HSI) to classify beef samples according to their tenderness degree. Two strategies were used to obtain different textures, and classification models were created using partial least squares discriminant analysis (PLS-DA) method. The results showed that HSI technology combined with chemometrics has the potential to differentiate and classify meat samples based on their textural characteristics.
Article
Food Science & Technology
Shekh Mukhtar Mansuri, Subir Kumar Chakraborty, Naveen Kumar Mahanti, R. Pandiselvam
Summary: This study aimed to investigate the effectiveness of models (PLS-DA, ANN, and 1D-CNN) in predicting fungal contamination in maize kernels using hyperspectral imaging (HSI), and explore their relationship with the orientation of the germ with respect to the HSI camera lens. The results showed that with proper model selection and germ orientation, HSI can accurately detect and separate infected maize kernels.
Article
Agronomy
Xuan Chu, Pu Miao, Kun Zhang, Hongyu Wei, Han Fu, Hongli Liu, Hongzhe Jiang, Zhiyu Ma
Summary: This study used hyperspectral imaging to assess the maturity and quality of dwarf bananas, demonstrating that hyperspectral imaging is an effective tool for evaluating banana maturity and quality.
Article
Food Science & Technology
Yongzhen Gou, Yaping Han, Jie Li, Xiyue Niu, Guocai Ma, Qian Xu
Summary: Gas Chromatography-Ion Mobility Spectrometry (GC-IMS) analysis was used to explore the aromatic differences between Xinjiang cow milk powder and specialty milk powder. Different volatile compounds were detected in the milk powders, and specific compounds were identified as valid markers for discrimination. A GC-IMS fingerprint spectra was established for visual discrimination of the milk powders.
Article
Biochemistry & Molecular Biology
Anastasiia Surkova, Andrey Bogomolov
Summary: By utilizing confocal Raman microscopy, this study investigates the chemical microstructure of milk samples of various compositions. The results show the spatial distribution of the main chemical components, such as fat, protein, and lactose, using intuitive graphical maps.
Article
Chemistry, Analytical
Mario Gabrielli, Vanessa Lancon-Verdier, Pierre Picouet, Chantal Maury
Summary: This study successfully established prediction models for sugar, total flavonoid, and total anthocyanin contents in table grapes using hyperspectral imaging technology, providing a new method for characterizing grape quality. Optimized wavelength selection and pre-treatment methods play important roles in the prediction models.
Review
Dermatology
Lt. Pushkar Aggarwal, Francis A. Papay
Summary: Multispectral/hyperspectral imaging plays an important role in dermatology diagnostics by providing novel information about skin lesions at the cellular level. Current research focuses on distinguishing melanoma from benign nevi for non-invasive diagnosis. Combining multispectral/hyperspectral imaging with smartphones is also being explored for creating portable and affordable devices.
EXPERIMENTAL DERMATOLOGY
(2022)
Article
Food Science & Technology
Jose Marcelino S. Netto, Fernanda A. Honorato, Patricia M. Azoubel, Louise E. Kurozawa, Douglas F. Barbin
Summary: This study presented a quick and non-destructive means to evaluate the melon drying process under different pretreatments using hyperspectral images in near infrared. The results showed that the use of vacuum and the combination of vacuum and ultrasound resulted in uniform drying, facilitating water diffusion in the samples.
LWT-FOOD SCIENCE AND TECHNOLOGY
(2021)
Article
Food Science & Technology
Marina De Gea Neves, Ronei Jesus Poppi, Marcia Cristina Breitkreitz
Summary: The study developed a non-invasive and rapid method using NIR and chemometric tools to determine the authenticity of plant-based protein powders and classify possible adulterations. By combining OC-PLS for authentication and PLS2-DA for adulterant classification, the methodology showed high sensitivity and specificity in detecting adulterants such as soy, whey, and wheat in the protein powders.
Article
Chemistry, Applied
Xiaobin Wang
Summary: The effective penetration depth of light into different wheat flours was determined using the partial least squares-discriminant analysis (PLS-DA) method and double-layer samples. The classification model established showed high accuracy, providing a reliable basis for the detection of additives in wheat flour.
JOURNAL OF BIOBASED MATERIALS AND BIOENERGY
(2021)
Article
Food Science & Technology
Zhenfang Liu, Min Huang, Qibing Zhu, Jianwei Qin, Moon S. Kim
Summary: A nondestructive method using spatially offset Raman spectroscopy (SORS) technique combined with data modeling analysis was proposed to assess the internal quality of intact prawns. The prediction model based on SORS enhanced data and combining Random Forest feature band selection with Support Vector Regression demonstrated the best performance in predicting prawn freshness. This rapid and nondestructive method may be feasible for assessing internal quality of materials that demonstrate surface interference, such as in-shell prawns.
Article
Food Science & Technology
Yong-Kyoung Kim, Insuck Baek, Kyung-Min Lee, Jianwei Qin, Geonwoo Kim, Byeung Kon Shin, Diane E. Chan, Timothy J. Herrman, Soon-kil Cho, Moon S. Kim
Summary: Aflatoxins, commonly found in corn, can cause severe illness, but current screening tools are expensive and cumbersome. Hyperspectral imaging techniques were used for detection, with SWIR and fluorescence models showing higher performance accuracies.
Article
Food Science & Technology
Feifei Tao, Haibo Yao, Zuzana Hruska, Kanniah Rajasekaran, Jianwei Qin, Moon Kim
Summary: This study examined the potential of line-scan Raman hyperspectral imaging system equipped with a 785 nm line laser for discrimination of uninfected control, AF36-inoculated and AF13-inoculated corn kernels. By preprocessing the spectral data and utilizing discriminant models, the technology achieved mean overall prediction accuracies of 89.47% and 75.55% for endosperm and embryo data, respectively, showcasing its usefulness in differentiating corn kernels infected with aflatoxigenic and non-aflatoxigenic fungi from uninfected control corn kernels.
JOURNAL OF CEREAL SCIENCE
(2021)
Article
Multidisciplinary Sciences
Hamed Taheri Gorji, Seyed Mojtaba Shahabi, Akshay Sharma, Lucas Q. Tande, Kaylee Husarik, Jianwei Qin, Diane E. Chan, Insuck Baek, Moon S. Kim, Nicholas MacKinnon, Jeffrey Morrow, Stanislav Sokolov, Alireza Akhbardeh, Fartash Vasefi, Kouhyar Tavakolian
Summary: This study used fluorescence imaging and deep learning algorithms to automatically detect and segment areas of fecal matter in carcass images, improving food safety assurance. The EfficientNet-B0 model and U-Net algorithm achieved accurate classification and segmentation of clean and contaminated areas on meat surfaces.
SCIENTIFIC REPORTS
(2022)
Article
Food Science & Technology
Kuanglin Chao, Walter Schmidt, Jianwei Qin, Moon Kim
Summary: This study developed a method for detecting Fipronil using infrared and Raman spectroscopy. The partial least squares regression model used in this method accurately detects the concentration of Fipronil on surfaces, with high accuracy and specificity.
JOURNAL OF FOOD MEASUREMENT AND CHARACTERIZATION
(2022)
Article
Spectroscopy
Zhenfang Liu, Min Huang, Qibing Zhu, Jianwei Qin, Moon S. Kim
Summary: This paper proposes a novel method for separating internal signals of packaged food using spatially offset Raman spectroscopy (SORS) and improved fast independent component analysis (FastICA). The effectiveness of the method is verified by experimental results, demonstrating its potential as a pretreatment method and auxiliary analysis means for the detection of packaged food.
SPECTROCHIMICA ACTA PART A-MOLECULAR AND BIOMOLECULAR SPECTROSCOPY
(2022)
Article
Agricultural Engineering
Anastasia Ktenioudaki, Carlos A. Esquerre, Cecilia M. Do Nascimento Nunes, Colm P. O'Donnell
Summary: This study aimed to develop a non-destructive system using hyperspectral imaging technology for accurate estimation of shelf-life of strawberries. Prediction models were developed for other quality attributes and biochemical properties, supporting the drive for zero waste in the food supply chain.
BIOSYSTEMS ENGINEERING
(2022)
Article
Plant Sciences
Insuck Baek, Changyeun Mo, Charles Eggleton, S. Andrew Gadsden, Byoung-Kwan Cho, Jianwei Qin, Diane E. Chan, Moon S. Kim
Summary: This study presents a method for selecting wavelength-specific spectral resolutions to optimize a line-scan hyperspectral imaging method for detecting apple bruises. The study identifies key wavelengths and determines the optimal number of key wavelengths for detecting different levels of bruise impact. It also determines the optimal spectral resolution for each key wavelength, allowing for shorter exposure times and high accuracy bruise detection. The findings of this study are important for the development of multispectral imaging systems for efficient identification of bruised apples on commercial processing lines.
FRONTIERS IN PLANT SCIENCE
(2022)
Article
Plant Sciences
Pappu Kumar Yadav, Thomas Burks, Quentin Frederick, Jianwei Qin, Moon Kim, Mark A. Ritenour
Summary: This research successfully detected eight different peel conditions on citrus fruit using hyperspectral imagery and an AI-based classification algorithm. The PCA-selected bands showed high accuracy, sensitivity, and specificity. Randomly selected bands also performed well.
FRONTIERS IN PLANT SCIENCE
(2022)
Article
Chemistry, Applied
Zhenfang Liu, Hao Zhou, Min Huang, Qibing Zhu, Jianwei Qin, Moon S. Kim
Summary: In this study, a method of packaged butter adulteration evaluation based on spatially offset Raman spectroscopy (SORS) combined with fast independent component analysis (FastICA) was proposed. The extracted butter Raman features were input into four quantitative analysis models to assess the content of butter adulteration. The results showed that the ensemble model Extra-tree has the best performance.
JOURNAL OF FOOD COMPOSITION AND ANALYSIS
(2023)
Article
Chemistry, Analytical
Hossein Kashani Zadeh, Mike Hardy, Mitchell Sueker, Yicong Li, Angelis Tzouchas, Nicholas MacKinnon, Gregory Bearman, Simon A. Haughey, Alireza Akhbardeh, Insuck Baek, Chansong Hwang, Jianwei Qin, Amanda M. Tabb, Rosalee S. Hellberg, Shereen Ismail, Hassan Reza, Fartash Vasefi, Moon Kim, Kouhyar Tavakolian, Christopher T. Elliott
Summary: This study aims to develop a handheld multimode spectroscopic system for fish quality assessment that is fast, non-destructive, and easy-to-use. Data fusion of visible near infra-red (VIS-NIR) and short wave infra-red (SWIR) reflectance and fluorescence (FL) spectroscopy is applied to classify fish freshness. The study shows that multi-mode spectroscopy achieves 95% accuracy, improving the accuracies of single-mode spectroscopies by 26, 10, and 9% respectively.
Article
Spectroscopy
M. M. Oliveira, A. T. Badaro, C. A. Esquerre, M. Kamruzzaman, D. F. Barbin
Summary: In this study, NIR spectroscopy combined with the EMCVS method was used to successfully predict the cocoa shell content in cocoa powders. The results showed that this combination is an accurate and reliable tool.
SPECTROCHIMICA ACTA PART A-MOLECULAR AND BIOMOLECULAR SPECTROSCOPY
(2023)
Proceedings Paper
Agriculture, Multidisciplinary
Jianwei Qin, Oscar Monje, Matthew R. Nugent, Joshua R. Finn, Aubrie E. O'Rourke, Ralph F. Fritsche, Insuck Baek, Diane E. Chan, Moon S. Kim
Summary: This paper presents the development of an automated hyperspectral system for monitoring plant health in NASA's space missions, with a focus on monitoring salad crops. The system uses reflectance and fluorescence imaging in the spectral region of 400-1000 nm. A compact line-scan hyperspectral camera, LED line lights, and a linear translation stage are the major hardware components. Control software was developed using LabVIEW. The system was tested in a growth chamber at NASA Kennedy Space Center and successfully detected drought stress on lettuce leaves.
SENSING FOR AGRICULTURE AND FOOD QUALITY AND SAFETY XIV
(2022)
Proceedings Paper
Agriculture, Multidisciplinary
Feifei Tao, Haibo Yao, Zuzana Hruska, Kanniah Rajasekaran, Jianwei Qin, Moon Kim
Summary: This study aims to explore the effectiveness of Raman hyperspectral imaging in detecting aflatoxin contamination in corn kernels in a rapid and non-destructive manner. The results show that the accuracy of the two discriminant models ranges from 77.9% to 82.0%.
SENSING FOR AGRICULTURE AND FOOD QUALITY AND SAFETY XIV
(2022)
Article
Chemistry, Physical
Walter F. Schmidt, Fu Chen, C. Leigh Broadhurst, Jianwei Qin, Michael A. Crawford, Moon S. Kim
Summary: Polyunsaturated fatty acids, such as DHA, DPA, and EPA, have similar structures but differ in their biological activities and utilization in mammalian tissues. Among them, DHA plays a unique role in certain tissues and cannot be substituted by other fatty acids. Research shows that the conformational changes in DHA may be affected by structural analogs.
JOURNAL OF MOLECULAR LIQUIDS
(2022)