Based on physical and chemical characteristics, optical sensing methods for real-time inspection of food, water and agricultural products can produce rapid, accurate, and consistent inspection solutions for product quality and safety. Advances in sensing technology have broadened the field of applications suitable for computerized optical instrumentation. No longer restricted to detailed laboratory analyses or simplified implementation in industrial or commercial settings, optical sensing technologies now can accommodate non-destructive, comprehensive, high-resolution spectral and image analyses for real-world safety and quality inspection on rapid food-processing lines.

This conference will focus on optical, spectroscopic, and spectral imaging sensing techniques, and approaches for the use of chemical imaging and biosensors, for rapid or non-destructive assessment of safety and quality for meats, fruits, vegetables, and water. Novel techniques, instruments for real-time measurement and processing, and industrial applications of optoelectronic sensing systems to detect diseases, defects, and fecal or bacterial contamination on meats, fruits, vegetables and water will be emphasized.

Contributed papers are solicited concerning, but not limited to, the following areas:
;
In progress – view active session
Conference 12120

Sensing for Agriculture and Food Quality and Safety XIV

5 - 6 April 2022
View Session ∨
  • 1: Raman Spectroscopy and Imaging
  • 2: Near-Infred Spectroscopy
  • 3: Spectral Imaging Applications
  • 4: Hyperspectral Imaging
  • Poster Session
  • 5: Remote Sensing
  • 6: Biosensors
  • 7: Contamination & Sanitation Inspection I
  • 8: Contamination & Sanitation Inspection II
Information

POST-DEADLINE ABSTRACT SUBMISSIONS

  • Submissions are accepted through 07-February
  • Notification of acceptance by 21-February

Call for Papers Flyer (346KB)
Session 1: Raman Spectroscopy and Imaging
5 April 2022 • 9:30 AM - 10:30 AM EDT
Session Chair: Jianwei Qin, Agricultural Research Service (United States)
12120-1
Author(s): Feifei Tao, Haibo Yao, Zuzana Hruska, Mississippi State Univ. (United States); Kanniah Rajasekaran, Jianwei Qin, Moon Kim, USDA Agricultural Research Service (United States)
5 April 2022 • 9:30 AM - 9:50 AM EDT
Show Abstract + Hide Abstract
The Raman detection technology offers several advantages over traditional detection methods, such as rapidness, non-destructiveness, and high-throughput. Therefore, the line-scan Raman hyperspectral imaging system equipped with a 785 nm line laser was utilized to identify aflatoxin contamination on single corn kernels in this study. A total of 900 kernels were assigned into three treatment groups of 300 kernels each. Treatments included inoculation with an aflatoxigenic A. flavus (AF13), non-aflatoxigenic A. flavus (AF36), or sterile distilled water (control). One hundred kernels were sampled from each treatment following 3, 5 and 8 days after inoculation, to obtain diverse samples. The kernels were imaged on both endosperm and germ sides over the 103-2831 cm-1 wavenumber region. The reference aflatoxin concentration in each kernel was determined by the VICAM AflaTest method. Using the mean spectrum extracted from the preprocessed Raman image of each kernel over the 400-2200 cm-1 wavenumber region, the partial least-squares discriminant analysis (PLS-DA) models were established. The results showed that, based upon the classification threshold of 20 ppb, the mean overall prediction accuracies achieved 82.6% and 86.1% using the endosperm- and germ-side spectra, respectively. The corresponding mean overall prediction accuracies were 85.3% and 89.0% when 100-ppb was applied as the classification threshold. This study demonstrates that the line-scan Raman hyperspectral imaging technology can be a useful alternative tool in differentiation of aflatoxin contamination in agricultural products.
12120-2
Author(s): Cristian Andrighetto, Veneto Agricoltura (Italy); Lorenzo Cocola, CNR-Istituto di Fotonica e Nanotecnologie (Italy); Paola De Dea, Veneto Agricoltura (Italy); Massimo Fedel, CNR-Istituto di Fotonica e Nanotecnologie (Italy); Angiolella Lombardi, Veneto Agricoltura (Italy); Fabio Melison, Luca Poletto, CNR-Istituto di Fotonica e Nanotecnologie (Italy)
5 April 2022 • 9:50 AM - 10:10 AM EDT
Show Abstract + Hide Abstract
Raman spectroscopy is employed as a contactless measurement technique for CO2 and H2 detection in the headspace of spore contaminated milk cultures. Since the non-invasive nature of this technique, it is possible to study the overall dynamics of the atmosphere in the headspace of different containers during the whole incubation time, providing a time-resolved measurement without disturbing the culture growth and evolution. Its inherent multi-gas detection feature leads to the distinction between different types of bacteria through the observation of the gases produced. When compared to the traditional methods, the results also demonstrate the ability to early determine contaminated samples.
12120-3
Author(s): Geonwoo Kim, Gyeongsang National Univ. (Korea, Republic of); Hoonsoo Lee, Chungbuk National Univ. (Korea, Republic of); Insuck Baek, USDA Agricultural Research Service (United States); Byoung-Kwan Cho, Chungnam National Univ. (Korea, Republic of); Moon Kim, USDA Agricultural Research Service (United States)
5 April 2022 • 10:10 AM - 10:30 AM EDT
Show Abstract + Hide Abstract
The occurrence of microplastics (MPs) in table salt is widely known as a serious harmful material for human health. In this study, nondestructive analysis for detection of MPs in table salt was conducted using Raman line-scan hyperspectral imaging.
Session 2: Near-Infred Spectroscopy
5 April 2022 • 11:00 AM - 12:10 PM EDT
Session Chair: Byoung-Kwan Cho, Chungnam National Univ. (Korea, Republic of)
12120-4
Author(s): Ana Garrido-Varo, José Antonio Entrenas, María del Mar Garrido-Cuevas, Dolores C. Pérez-Marín, Univ. de Córdoba (Spain)
5 April 2022 • 11:00 AM - 11:30 AM EDT
Show Abstract + Hide Abstract
The uptake by the industry of the existing knowledge about the online NIR analysis is being much slower, compared to the acceptance of the at-line analysis. The Research Group of the authors since 2001 has been in close collaboration with the largest Spanish rendering plant to evalate the ability of different for the quality control of animal protein processed by-products. Since 2017, and after several years of research, the company decided to invest in a on-line project. The work done until, for moving from at line to on line analysis in the rendering plant will be summarised in the Conference.
12120-5
Author(s): Dolores C. Pérez-Marín, Irina Torres, José Antonio Entrenas, Ana Garrido-Varo, Univ. de Córdoba (Spain)
5 April 2022 • 11:30 AM - 11:50 AM EDT
Show Abstract + Hide Abstract
Iberian pork meat has exceptional sensory and nutritional attributes, which are related to the breed and the feeding regime of the animals. Regarding the breed purity, two categories can be considered: 100% Iberian products and Iberian products coming from crossed animals (Iberian x Duroc). The aim of this work was to evaluate the viability of using portable Near-infrared sensors for the in situ authentication of Iberian pork fresh meat according to its breed. Models were developed using partial least squares discriminant analysis. The results confirm the viability of using NIRS to guarantee the authenticity of the Iberian pork meat.
12120-7
Author(s): María del Mar Garrido-Cuevas, Ana Garrido-Varo, Dolores C. Pérez-Marín, Univ. de Córdoba (Spain)
5 April 2022 • 11:50 AM - 12:10 PM EDT
Show Abstract + Hide Abstract
Software tools for chemometric analysis of NIRS data have existed since the first NIRS instruments appeared on the market in the late 1970s. Generally, these software appear attached to a certain instrumentation. Recently, some works have started to use open-source software, such as R and Python, but the development status is still in its infancy, particularly in the case of the latter. This work tries to generate information on the potential of the open-source Python software for the implementation of multivariate algorithms and signal pre-treatment methods for the quantitative and qualitative NIRS analysis of olive oils.
Session 3: Spectral Imaging Applications
5 April 2022 • 1:30 PM - 2:30 PM EDT
Session Chair: Dolores C. Pérez-Marín, Univ. de Córdoba (Spain)
12120-8
Author(s): Sangjoon Lee, Hangi Kim, Byoung-Kwan Cho, Chungnam National Univ. (Korea, Republic of)
5 April 2022 • 1:30 PM - 1:50 PM EDT
Show Abstract + Hide Abstract
Mosquitoes are the most life-threatening insect to human on Earth. Main disease vector mosquitoes inhabiting in Korea cause Zika fever, Yellow fever, Malaria, West Nile fever, Japanese encephalitis, etc. Only Malaria has cure among them. Usually, the disease vector mosquito species are counted and identified manually with optical microscopy, which needs huge labor and causes human error. Although the recent mosquito trap devices are developed, they can only count the number of mosquitoes without the species identification. This study proposes a deep learning image analysis technique to identify species along with the population of mosquitoes using SWIN-transformer model. The non-maximum suppression (NMS) technique for both RGB and fluorescence images has been applied for the improvement of prediction accuracy. Results revealed that the proposed model has achieved good performance for mosquito identification.
12120-9
Author(s): Hoonsoo Lee, Seunghyun Lim, Jinhwan Ryu, Hwanjo Chung, Chungbuk National Univ. (Korea, Republic of)
5 April 2022 • 1:50 PM - 2:10 PM EDT
Show Abstract + Hide Abstract
Due to climate change, the demand for stable production of crops continues to increase. It is necessary to develop crops that can cope with abnormal climate by qualitatively and quantifying the stress index of crops from high temperature, low temperature, drought periods and flooding and flood. Chinese cabbage is one of Korea's representative vegetable crops and is the main ingredient of kimchi. Chinese cabbage grows well below 20 degrees. However, when exposed to high temperatures, the head-formation and soft-rot disease of cabbage have a fatal effect on production. Therefore, it is important to evaluate heat stress index of the Chinese cabbage. In this study, the multispectral imaging camera was used to qualitatively and quantify the heat stress index of Chinese cabbage. Thirty-eight spectral image data were obtained from 460nm to 870nm and were analyzed by chemometrics method. The spectra were found to be significantly different between the Chinese cabbages grown at 36 degrees and at 20 degrees. Therefore, it was confirmed that the spectral imaging data can be utilized to evaluate the difference of growth information of the Chinese cabbage based on the high-temperature stress. 
12120-10
Author(s): Juntae Kim, Byoung-Kwan Cho, Chungnam National Univ. (Korea, Republic of)
5 April 2022 • 2:10 PM - 2:30 PM EDT
Show Abstract + Hide Abstract
This study was conducted to confirm the localization possibility of the automated pork carcass grading machines in Korea. This experiment has used a total of 174 carcasses. Image analysis was conducted in three main steps: 1) image preprocessing, 2) feature extraction, 3) regression model build-up. For features extraction and model building, we used the U-net and Gaussian processing regression respectively. The Analysis was done for prediction of LMP and seven different prime cuts. The prediction results were satisfactory to the European minimum standards thus making the localization of the pork carcass grading machine possible.
Session 4: Hyperspectral Imaging
5 April 2022 • 3:00 PM - 5:00 PM EDT
Session Chair: Byoung-Kwan Cho, Chungnam National Univ. (Korea, Republic of)
12120-11
Author(s): Jianwei Qin, USDA Agricultural Research Service (United States); Oscar Monje, Matthew R. Nugent, Joshua R. Finn, Aubrie E. O’Rourke, Ralph F. Fritsche, NASA Kennedy Space Ctr. (United States); Insuck Baek, Diane E. Chan, Moon S. Kim, USDA Agricultural Research Service (United States)
5 April 2022 • 3:00 PM - 3:20 PM EDT
Show Abstract + Hide Abstract
A compact and automated hyperspectral imaging system has been developed to monitor plant health and enhance food safety for controlled-environment produce production in NASA space missions. The prototype system is designed to inspect pick-and-eat salad crops using both reflectance and fluorescence imaging techniques. The system has been installed into a plant growth chamber at NASA Kennedy Space Center for imaging lettuce samples grown under normal, drought, and overwatering conditions. Spectral and image processing algorithms have been developed for background removal, leaf area estimation, band selection, and vegetation index calculation for detecting plant stresses encountered in space crop production.
12120-12
Author(s): Oscar Monje, Amentum (United States); Ralph F. Fritsche, NASA Kennedy Space Ctr. (United States); Jianwei Qin, Moon S. Kim, USDA Agricultural Research Service (United States)
5 April 2022 • 3:20 PM - 3:40 PM EDT
Show Abstract + Hide Abstract
Future space crop production systems will require that plant health and food safety is determined with minimal crew intervention. A prototype hyperspectral and chlorophyll fluorescence imaging system was designed for early symptom detection of abiotic plant stress in crop production systems. A watering system was developed for imposing water stress treatments (mild or severe drought, flooding) on candidate leafy green crops to be grown on the International Space Station. Daily images recorded changes in crop reflectance and chlorophyll fluorescence during 28-day growouts. Harvest data recorded leaf area, fresh weight, dry weight, plant height and leaf number. The imaging and harvest data were used to evaluate the ability of the prototype imaging system to differentiate between the water stress treatments.
12120-13
Author(s): Ye-Na Kim, Byoung-Kwan Cho, Chungnam National Univ. (Korea, Republic of)
5 April 2022 • 3:40 PM - 4:00 PM EDT
Show Abstract + Hide Abstract
This experiment was conducted to predict fatty acid contents in beef using short-wave infrared (SWIR) hyperspectral imaging (HSI) technique. The HSI datasets were acquired from the longissimus dorsi and further evaluated the quality parameter of these samples. A partial least square regression (PLSR) model with spectral preprocessing was applied to predict the fatty acid in beef samples. The obtained results showed high coefficients of determination (R2 > 0.8). The overall outcomes suggest that the SWIR-HSI technique might be utilized as non-destructive measurement tool for the determination of fatty acid content in beef.
12120-14
Author(s): Insuck Baek, USDA Agricultural Research Service (United States); Yong-Kyoung Kim, National Agricultural Products Quality Management Service (Korea, Republic of); Moon Kim, USDA Agricultural Research Service (United States)
5 April 2022 • 4:00 PM - 4:20 PM EDT
Show Abstract + Hide Abstract
Corn is commonly used as a good source of food and feed, as well as for producing cooking oil and starch. However, corn is among the many agricultural staples that can be easily contaminated with aflatoxin, a poisonous mycotoxin produced by molds that can have serious effects on human and animal health, and rapid and effective methods for detecting aflatoxin in the corn are lacking for on-site use in food processing operations. This study investigated the use of short-wavelength infrared (900 - 2500 nm) hyperspectral image data for detecting aflatoxin in ground maize, using measurements of aflatoxin content via chemical analysis for sample reference. Preliminary results are reported for the development of a detection model using deep learning to detect aflatoxin-contaminated corn powder.
12120-15
Author(s): Iyll-Joon Doh, Diana Vanessa Sarria Zuniga, Robert E. Pruitt, Bartek Rajwa, J. Paul Robinson, Euiwon Bae, Purdue Univ. (United States)
5 April 2022 • 4:20 PM - 4:40 PM EDT
Show Abstract + Hide Abstract
We have developed a hyperspectral elastic light scatter (ELS) phenotyping instrument to explore the relationship between the wavelength of the incident beam and the elastic light-scatter pattern of a bacterial colony, and, ultimately, to enhance the classification efficiency of non-invasive ELS-based systems employed in microbiology. The new instrument consists of a supercontinuum (SC) laser and acousto-optic tunable filter (AOTF), which enables the selection of the wavelength of interest allowing multiple spectral patterns in a single measurement. A primitive experiment with the microflora found on green leafy vegetables derived an encouraging result, showing over 90% of average classification accuracy when classifying colonies from 2 bacterial species utilizing 70 spectral bands from SC-laser. The presented hyperspectral ELS system employs feature reduction and selection procedures to enhance the robustness and ultimately lessen the complexity of data collection.
12120-6
Author(s): Irina Torres, Univ. de Córdoba (Spain); Marina Cocchi, Univ. degli Studi di Modena e Reggio Emilia (Italy); María Teresa Sánchez, Ana Garrido Varo, Dolores Pérez Marín, Univ. de Córdoba (Spain)
5 April 2022 • 4:40 PM - 5:00 PM EDT
Show Abstract + Hide Abstract
Hyperspectral images are typically acquired at high spatial and spectral resolutions, being essential the reduction of data for the implementation of this technology at industrial level. The aim of this work was the optimization and development of algorithms for the selection of the region of interest in oranges hyperspectral data. PLS and its multilinear version, NPLS, were used to model the internal quality of oranges. The results obtained in external validation enabled to carry out a screening of the product according to its flavour, confirming that the use of multilinear models could reduce the noise and data redundancy.
Poster Session
5 April 2022 • 6:00 PM - 8:00 PM EDT
12120-33
Author(s): Zahidur Rahman, LaGuardia Community College (United States); Leonid Roytman, The City Univ. of New York (United States); Md. S. Rahman, Supriya K. Kundu, Bangladesh Rural Development Board (Bangladesh)
5 April 2022 • 6:00 PM - 8:00 PM EDT
Show Abstract + Hide Abstract
This research apply National Oceanic Atmospheric Administration (NOAA) polar orbiting environmental satellite remote sensing data to predict agricultural crop yield (rice) in Bangladesh . The impetus for the proposed research is the need to address a very serious problem of climate change facing Bangladesh and the resulting threat to food production in the country. Crop growth monitoring and yield estimation can provide important information for government agencies in planning food procurement activities. The sooner this information is available, the lower the economic risk, translating into greater efficiency and increased return on investments. The main goals of the proposed research is to develop a probability-based model for agricultural crop prediction and monitoring in Bangladesh represented globally
12120-34
Author(s): Juan Manuel Cáceres-Nevado, Ana Garrido-Varo, Emiliano De Pedro, Dolores C. Pérez-Marín, Univ. de Córdoba (Spain)
5 April 2022 • 6:00 PM - 8:00 PM EDT
Show Abstract + Hide Abstract
Intramuscular fat is one the main components that influences quality of Iberian cured meat products and affects the sensory properties and the texture of dry-cured products. The objective of this study was the determination of the intramuscular fat content in dry-cured loins from Iberian x Duroc crossbreed pigs using a handheld NIR spectrometer working in the spectral range from 908.1 to 1676.2 nm. The results obtained confirming the feasibility of using NIR technology to assess the intramuscular fat content in dry-cured loins.
12120-35
Author(s): Dimitrios A. Exarchos, Anastasios Vasiliadis, Stergios Dragatzikis, Theodore Matikas, Univ. of Ioannina (Greece)
5 April 2022 • 6:00 PM - 8:00 PM EDT
Show Abstract + Hide Abstract
Agricultural products’ quality and safety is critical from production tο the final customer. Although the traditional expiration date of products provides a basic safety assurance, often products before the expiration date may suffered significant alterations for several reasons, such as power interruptions during the supply or due to accidental destruction of packaging. These issues force food companies to use more expensive and less environmentally friendly packaging to improve safety. The consumer, on the other hand, pays products of higher cost and, in general, the economic balance get worse. In the current study, novel printable sensors and assessment techniques are being developed, enabling new safety and traceability solutions and are also capable to verify the authenticity and origin of packaged agri-food products. These sensors which are directly printable to packaging materials, are battery-less wireless interdigital sensing systems capable to provide real-time information about the food quality easily in almost any mobile device equipped with NFC technology. The newly introduced technology is a useful tool for identifying food authenticity and for protecting consumers from fraud.
12120-36
Author(s): Giuseppe Bonifazi, Riccardo Gasbarrone, Silvia Serranti, Sapienza Univ. di Roma (Italy)
5 April 2022 • 6:00 PM - 8:00 PM EDT
Show Abstract + Hide Abstract
The traditional method used to measure beer density requires the utilization of a hydrometer. In this study, a simple and fast approach to assess sugar content in hopped wort of artisanal beer, based on the utilization of a portable spectroscopic device working in the Short-Wave InfraRed (SWIR) region (1000-2400 nm) by collecting spectra in transflectance mode, is adopted in order to be utilized both off- and on-line. The proposed approach, faster than the traditional hydrometric method, will allow to realize a better control of the process, reducing production cost and increasing, at the same time, product quality.
12120-37
Author(s): Hangi Kim, Byoung-Kwan Cho, Chungnam National Univ. (Korea, Republic of)
5 April 2022 • 6:00 PM - 8:00 PM EDT
Show Abstract + Hide Abstract
Since most of the plant diseases are detected after symptom onset by the human eye, then the recovery is very difficult. Therefore, early and accurate detection of plant diseases is important in preventing crop yield reduction. In recent years, image processing techniques have been applied for plant disease detection using RGB images and deep learning. Further, early detection of plant disease using hyperspectral imaging is in progress. In this study, a deep learning based model has been developed for early detection of plant disease using VIS/NIR hyperspectral imaging (HSI) technique and Convolutional Neural Network (CNN). HSI data were obtained from healthy and disease-infected tomato plants. The proposed model has been developed by applying a new CNN algorithm that utilized spatial and spectral characteristics of HSI technique. The result showed that the proposed model can be used for early detection of plant disease using hyperspectral and deep learning techniques.
12120-38
Author(s): Min-Jee Kim, Changyeun Mo, Hye-In Lee, Jae-Hyun Choi, Kyoung Jae Lim, Jae E. Yang, Kangwon National Univ. (Korea, Republic of)
5 April 2022 • 6:00 PM - 8:00 PM EDT
Show Abstract + Hide Abstract
Worldwide, carbon credits are becoming increasingly important to prepare for future environmental problems. Soil is the largest storage of carbon in terrestrial ecosystems, increasing soil organic carbons(SOCs) has the potential to offset emissions of greenhouse gas. However, since SOCs are changed according to rainfall, cultivation, and the inflow of pollutants, it is necessary to predict SOC through on-time monitoring. Recently, visible–near infrared (Vis-NIR) hyperspectral imaging technique serve as a rapid and non-destructive technique to estimate various properties of soil. The purpose of this study was to evaluate a method for the prediction of SOCs using Vis-NIR hyperspectral imaging technique. The SOCs prediction model was developed through Partial Least Squares Regression and Convolutional neural networks models. The results were showed that the Vis-NIR hyperspectral image technique can be used to predict the SOCs.
12120-39
Author(s): Qinghui Guo, Yankun Peng, Wenlong Zou, China Agricultural Univ. (China); Kuanglin Chao, USDA Agricultural Research Service (United States)
5 April 2022 • 6:00 PM - 8:00 PM EDT
Show Abstract + Hide Abstract
Clenbuterol and ractopamine can be used to improve carcass leanness in swine, but their residues in pork also pose health risks. This study used surface enhanced Raman spectroscopy (SERS) technology to establish MLR prediction models for clenbuterol, ractopamine and their mixture in pork, respectively, to achieve rapid detection and identification of ractopamine (RAC) and clenbuterol hydrochloride (CL) residues in pork. In this study, acetonitrile was used to extract clenbuterol and ractopamine from pork for SERS detection. Multiple scattering correction (MSC) and adaptive iterative reweighting penalty least squares (AIR-PLS) correction methods were used to remove noise and fluorescence background from Raman spectra. Without the use of coagulant, the detection limits of clenbuterol and ractopamine were 0.8 mg/kg and 1mg/kg, respectively. NaCl enhancers were used to detect pork extracts containing 0.01~1mg/kg ractopamine and clenbuterol, respectively. The limits of detection were 0.03 mg/kg and 0.04 mg/kg, respectively, and the coefficient of determination between the content and predicted measured value was 0.951 and 0.962, respectively. Finally, for the mixed detection of clenbuterol and ractopamine, the predictive correlation coefficient was 0.943, the root mean square error was 0.005 mg/kg, and the detection limits were 0.05 mg/kg and 0.06mg/kg, respectively. This study provides a basis for further exploration of trace clenbuterol and ractopamine detection by surface enhanced Raman spectroscopy.
12120-40
Author(s): Chansong Hwang, Moon Kim, USDA Agricultural Research Service (United States)
5 April 2022 • 6:00 PM - 8:00 PM EDT
Show Abstract + Hide Abstract
As the food market for user convenience grows, strict management is required for hygiene and food safety in food processing facilities. Hyperspectral imaging techniques can be easily used to sanitation monitoring of equipment surfaces in food processing plants compared to the traditional sanitary inspection methods. Residues, considered contaminants, were made by diluting fruits juice. To acquire hyperspectral image data, droplets of each concentration were placed on the stainless steel surface and dried for 24h. Principal Component Analysis (PCA) was performed to select the optimal wavebands to reduce dimension of fluorescence imaging data. Support Vector machine (SVM) and cross-validation methods were used to classify and validate the image data. The purpose of this study is to develop a technology that contributes to agriculture and food safety industries by rapid monitoring the residues still remaining on the equipment surface after food processing.
Session 5: Remote Sensing
6 April 2022 • 8:20 AM - 10:00 AM EDT
Session Chair: Haibo Yao, Mississippi State Univ. (United States)
12120-16
Author(s): M. M. Nabi, Mississippi State Univ. (United States); Volkan Senyurek, Geosystems Research Institute, Mississippi State Univ. (United States); Ali Cafer Gurbuz, Mississippi State Univ. (United States)
6 April 2022 • 8:20 AM - 8:40 AM EDT
Show Abstract + Hide Abstract
Global Navigation System Reflectometry (GNSS-R) plays a vital role in estimating soil moisture nowadays. Cyclone Global Navigation Satellite System (CYGNSS) consists of eight micro-satellite, can detect surface reflection that mapped into a Delay-Doppler Maps (DDM) with 17 delay bins and 11 Doppler bins. These DDM images contain important earth surface information that can be extracted using popular deep-learning techniques. In this paper, we will evaluate some of the popular pre-trained networks and calculate the performance based on SMAP soil moisture products. This is a supervised learning-based regression problem, and we modify the pre-trained network based on our problem statement.
12120-17
Author(s): Francisco Perez, The Univ. of Texas at Tyler (United States); Saif Islam, Univ. of California, Davis (United States); Shawana Tabassum, The Univ. of Texas at Tyler (United States)
6 April 2022 • 8:40 AM - 9:00 AM EDT
Show Abstract + Hide Abstract
This work focuses on correlating electrical responses of living plants with variations in environmental conditions. A bell pepper plant was subjected to heat and touch stimuli, and water stress. For every 50 degrees increment in leaf temperature, there was a 3-fold enhancement in the voltage measured from the stem. A burst of voltage spikes was observed when the leaf was touched. For a water-stressed plant, the voltage spiked at the beginning of the stress cycle but subsided after the first day. Our findings support that probing the electrical responses of plants will not only enable local climate monitoring, but also allow the growers to intervene immediately to reduce crop losses.
12120-18
Author(s): Yufeng Zheng, The Univ. of Mississippi Medical Ctr. (United States); Erol Sarigul, Girish Panicker, Alcorn State Univ. (United States); Diane Stott, Purdue Univ. (United States)
6 April 2022 • 9:00 AM - 9:20 AM EDT
Show Abstract + Hide Abstract
We developed convolutional neural network (CNN) models using drone pictures to estimate vineyard leaf area index (LAI) and canopy coverage. These parameters are traditionally measured using hand-held devices (e.g., line-intercept) and calculated manually, which is labor intensive and hard to apply to large-scale areas. We collected airborne images or videos by flying a low-altitude drone with a built-in digital camera over a large-scale vineyard. The airborne images convey all necessary information for developing CNN models. To date, we have collected data from the same vineyard over several years. The ground truth values were manually measured using line-intercept at the same time of airborne imaging. Specifically, we trained three CNN models to estimate canopy coverage, LAI, and dry leaf weight. The estimated results over a large vineyard will help guide planting cover crops to prevent soil erosion and calculating the correct amounts of fertilization and foliar sprays of pesticides.
12120-19
Author(s): Eun-sung Park, Ajay P. Kumar, Byoung-Kwan Cho, Chungnam National Univ. (Korea, Republic of)
6 April 2022 • 9:20 AM - 9:40 AM EDT
Show Abstract + Hide Abstract
It is crucial to improve the efficiency of plant breeding and crop yield in order to fulfill rising food demands. In plant phenotyping study, the capability to correlate morphological traits of plants plays an important role. However, measuring the plant phenotypes manually is prone to human errors, labor intensive and time-consuming. Hence, it is important to develop techniques for measurement of plant phenotypic data accurately and rapidly. The objective of this study was to find out the feasibility of point cloud data of 3D LiDAR including RGB image for plant phenotyping. The obtained results were then verified through the manually acquired data for sorghum and soybean plant samples. The overall results showed remarkable correlation between point cloud data and manually acquired data for plant phenotyping. This correlation indicates that the 3D Lidar imaging system have potential to measure phenotypes of crops in rapid and accurate way.
12120-20
Author(s): Brian Song, Roslyn High School (United States); Jeongkyu Lee, Northeastern Univ. (United States)
6 April 2022 • 9:40 AM - 10:00 AM EDT
Show Abstract + Hide Abstract
New York State’s second top agricultural product is maize and they are the fourth largest producer in the nation. However, maize diseases, in particular northern corn leaf blight (NLB), which has risen in severity over the years, can cause devastating yield loss if not detected and treated early. To address these, a novel deep learning algorithm is introduced based on the YOLOv3 object detection algorithm. The new algorithm had an emphasis on improving accuracy while maintaining similar speed to the original YOLOv3 algorithm. Dense blocks, composed of convolutional layers in a dense connection pattern, are used to improve accuracy and decrease parameters.
Session 6: Biosensors
6 April 2022 • 10:30 AM - 11:50 AM EDT
Session Chair: Jianwei Qin, Agricultural Research Service (United States)
12120-21
Author(s): Hyun Jung Min, Amanda J. Deering, Hansel Mina Cordoba, J. Paul Robinson, Euiwon Bae, Purdue Univ. (United States)
6 April 2022 • 10:30 AM - 10:50 AM EDT
Show Abstract + Hide Abstract
Infection with foodborne pathogens such as Salmonella spp. is of high risk for people with a weakened immune system. Microbiological culture method has been used in general for detection of pathogens from the food matrix; however, it is time consuming and requires experience and good level of laboratory skills. In the food safety field, various techniques which allows the rapid and simple detection have been developed at the level of a user-friendly tool for detecting the foodborne pathogens. Quartz crystal microbalance (QCM) are mass-based biosensor which measures the microgram level mass changes, enabling a user to observe the presence of the pathogen simply and rapidly. When the pathogens are bound on vibrating quartz surface, the resonant frequency of a quartz crystal will be changed due to the mass of the pathogens. In this study, the QCM detected killed Salmonella Typhimurium in the range of 〖10〗^5-〖10〗^9 CFU/mL, correlating to the averaged frequency shifts. The actual concentrations of Salmonella from the culture method were compared to the difference in the resonant frequency. The QCM sensor were treated with 11-Mercaptoundecanoic acid (11-MUDA), and EDC-NHS following by antibodies and bovine serum albumin (BSA) to utilize the antibody-antigen reaction. With a usage of peristaltic pump, the solutions could be introduced to the surface while frequencies could be monitored for each step in real-time. To acquire the evidence of Salmonella, the surfaces of the quartz crystal with the fluoresce labeled antibody were captured by the fluorescence microscope. The QCM biosensor showed the possibility of detection of Salmonella in less time, compared with the conventional method.
12120-22
Author(s): Shawana Tabassum, The Univ. of Texas at Tyler (United States)
6 April 2022 • 10:50 AM - 11:10 AM EDT
Show Abstract + Hide Abstract
Salicylic acid (SA) is an important regulator of induced defense mechanisms in plants. In-situ monitoring of this phytohormone will facilitate the early identification of crop stresses. Toward this endeavor, this work reports an LSPR (localized surface plasmon resonance)-based fiber-optic sensor functionalized with a copper-based metal-organic framework (CuMOF) for selectively measuring SA levels in sap. In our preliminary experiment, the fiber-optic sensor exhibited a sensitivity of 0.0117 % light reflection variations per μM concentration of SA and a limit-of-detection of 37 μM. The developed sensor could hold promises in future in-situ probe development for real-time measurements of phytohormones in plant sap.
12120-23
Author(s): Iyll-Joon Doh, Brianna Dowden, Valery Patsekin, Bartek Rajwa, J. Paul Robinson, Euiwon Bae, Purdue Univ. (United States)
6 April 2022 • 11:10 AM - 11:30 AM EDT
Show Abstract + Hide Abstract
A portable bacterial colony classification tool based on colonies’ reflective elastic light-scatter (ELS) patterns has been developed using a smartphone, a green laser, and a projector screen material. The phone camera, which is located behind the screen, captures the pattern using the camera sensor. The collected patterns are utilized to extract the distinctive scatter-related features across the organisms for the classification. This ELS technique can be applied to the organisms that are grown on opaque media. The adaptation of the smartphone camera as an imaging device dramatically reduced the dimension of the system to a palm-size. It made it wholly portable and easy to carry. For the validation of the instrument, five different bacteria species were grown on opaque agar media and tested. The results showed over 90% of overall accuracy in differentiating the organisms.
12120-24
Author(s): Xi Wu, Cole Reynolds, Euiwon Bae, Bartek Rajwa, J. Paul Robinson, Purdue Univ. (United States)
6 April 2022 • 11:30 AM - 11:50 AM EDT
Show Abstract + Hide Abstract
Recently, more attention has focused on food safety due to emerging and re-emerging outbreaks caused by foodborne pathogens, such as Norovirus, Salmonella Typhimurium, Escherichia coli et al. We have also started to address mycotoxins, which are the secondary metabolites from fungal species such as Aspergillus, Fusarium and Alternaria growing on agricultural commodities in the field or during storage. They usually pose threats to human and animal health and bring significant economic loss. Conventional methods are time-consuming, expensive and require large-scale instruments and skilled technicians. Therefore, our goal is to develop a molecular point-of-detection (POD) platform which is sensitive and specific to detect low pathogen concentrations and trace amounts of mycotoxin in foods and agricultural products. Herein, we propose to combine a custom-designed, inexpensive microchip with loop mediated isothermal amplification (LAMP) on a miniaturized portable device to detect low levels of foodborne pathogens and mycotoxins often associated with serious foodborne illnesses. Specifically, LAMP reactions are performed to amplify DNA in the microchip, along with heating and sensing by using the miniaturized device. Our molecular POD platform is designed to detect pathogens and mycotoxins within 40 minutes without DNA extraction and present similar specificity and sensitivity when compared to qPCR. Summarily, LAMP offers an efficient new assay format for rapid and specific nucleic acid-based detection. Coupled with the custom-designed microchip, our platform provides a proof-of-principle to achieve low-cost and widespread foodborne pathogens and mycotoxins testing at the POD which is highly desirable to keep analysis time and costs low, but more importantly be a field use application.
Session 7: Contamination & Sanitation Inspection I
6 April 2022 • 1:20 PM - 2:30 PM EDT
Session Chair: Moon S. Kim, Agricultural Research Service (United States)
12120-25
Author(s): Fartash Vasefi, SafetySpect Inc. (United States)
6 April 2022 • 1:20 PM - 1:50 PM EDT
Show Abstract + Hide Abstract
The contamination and sanitation inspection and disinfection (CSI-D) system has been developed to enable rapid detection, immediate intervention, and documentation of organic residue (debris), saliva, respiratory droplets on surfaces that may cause contamination disease spread. Novel aspects of the CSI-D solution include the combination of contamination identification and immediate remediation of the potential threat (bacteria, virus) using UVC light disinfection, and documenting this process to provide traceable evidence of disinfection. CSI-D reveals invisible contamination and truly defines cleanliness with measurements and documentation to provide reassurance to staff and promote cleanliness to customers.
12120-26
Author(s): Kouhyar Tavakolian, Univ. of North Dakota (United States)
6 April 2022 • 1:50 PM - 2:10 PM EDT
Show Abstract + Hide Abstract
Sanitation inspection is an ongoing concern for food distributors, restaurant owners, caterers, and others who handle and serve food. They must prevent food contamination but now must also deal with potential infection spread among workers and customers. Beyond zero tolerance legal requirements and damage to institutional or restaurant reputation, loss of trust with workers and customers can be very costly. We provide fluorescence imaging results that were measured, analyzed, and recorded on different high touch surfaces in restaurants and institutional kitchens. We have developed an algorithm to classify cleanliness levels based on the extent of organic residues detected.
12120-27
Author(s): Xi Wu, Sungho Shin, Euiwon Bae, Carmen Gondhalekar, J. Paul Robinson, Bartek Rajwa, Purdue Univ. (United States)
6 April 2022 • 2:10 PM - 2:30 PM EDT
Show Abstract + Hide Abstract
Laser-induced breakdown spectroscopy (LIBS) has become an emerging analytical technique for the characterization of agricultural products due to its efficiency, minimal sample preparation, and rapid elemental detection. The rising level of food fraud has prompted approaches for detection and prevention of fraud which often involves replacing high-quality components with inferior alternatives. Therefore, a rapid and portable detection method for authenticity verification and safety evaluation of marketed food and drink products is highly demanded. We utilized a custom-designed benchtop and commercial handheld LIBS instruments for food authentication tasks. Specifically, we focused on high-value regional agricultural commodities such as European alpine-style cheeses, coffee, spices, balsamic vinegar, and vanilla. Liquid samples were measured on paper and solid samples were ablated directly on the surface by both LIBS systems to collect spectra. The pre-processed LIBS spectra were used to train and test multiple classifiers for classification and validation of tested samples. Moreover, water activity of alpine-style cheeses sampled every two-week up to 2-month storage was determined to provide information regarding the impact of storage on LIBS-based product classification. Interestingly, among four different Comté AOP reserve cheeses, the 12-months aged ones showed no statistically significant change in water activity which indicated an extended product shelf life. In general, despite the small changes in water activity, the classification of cheese with LIBS systems remained stable and robust. The experiments showed that field-deployable, portable LIBS devices may offer a fast, simple, and inexpensive authentication platform for agricultural products with minimal or no sample preparation.
Session 8: Contamination & Sanitation Inspection II
6 April 2022 • 3:30 PM - 5:10 PM EDT
Session Chair: Fartash Vasefi, SafetySpect Inc. (United States)
12120-28
Author(s): Amit Morey, Auburn Univ. (United States); Jianwei Qin, Diane Chan, Insuck Baek, Moon Kim, USDA Agricultural Research Service (United States); Nicholas MacKinnon, Stanislav Sokolov, Alireza Akhbardeh, Fartash Vasefi, SafetySpect Inc. (United States)
6 April 2022 • 3:30 PM - 3:50 PM EDT
Show Abstract + Hide Abstract
Poultry meat is the most consumed meat in the US. To ensure a wholesome and safe product, carcasses and the viscera are inspected for disease and other conditions indicating they should be condemned as unfit for consumption. Septicemia-Toxemia (SepTox) is the most common carcass condemnation observed and reported. In this paper, we present a fast, convenient, and easy-to-use handheld system to detect SepTox for condemnation in post-eviscerated poultry carcasses. We provide fluorescence imaging measurements and analysis on poultry carcasses for developing machine learning models to classify carcasses with SepTox for future high speed process line automated imaging.
12120-29
Author(s): Thomas Burks, Siddhartha Mehta, Univ. of Florida (United States); Jianwei Qin, Moon Kim, USDA Agricultural Research Service (United States); Mark Ritenour, Univ. of Florida (United States)
6 April 2022 • 3:50 PM - 4:10 PM EDT
Show Abstract + Hide Abstract
We evaluate a handheld multispectral fluorescence imaging device to detect a bacterial colony on leafy greens. The most common diseases causing illness transmitted by leafy vegetables are norovirus, Shiga toxin-producing E. coli (STEC), and Salmonella, according to a CDC. Listeria and Cyclospora can also cause these illnesses. We will test the efficacy of a Contamination, Sanitization Inspection, and Disinfection (CSI-D) system using light at two fluorescence excitation wavelengths, ultraviolet C (UVC) at 275 nm and violet at 405 nm. Tests will evaluate the detection efficacy of device on inoculated control specimens of leafy greens during a time lapsed study.
12120-30
Author(s): Sungho Shin, Brianna Dowden, Iyll-Joon Doh, Xi Wu, Bartek Rajwa, Euiwon Bae, J. Paul Robinson, Purdue Univ. (United States)
6 April 2022 • 4:10 PM - 4:30 PM EDT
Show Abstract + Hide Abstract
Real-time detection of the foodborne pathogens, toxins, and contaminating chemicals for biodefense and food analysis is an important task for the prevention of food outbreaks and to ensure consumer safety. Numerous methods exist for detection including nucleic acid-based methods such as polymerase chain reaction (PCR), immunological-based methods, and optical methods. Optical imaging via fluorescence relies on the excitation of samples to emit longer wavelength of photons. Several approaches exist in both benchtop and portable devices. By controlling the wavelength of the excitation source, this method can be applied for disinfection of pathogens using additional excitation irradiation after detection. This study evaluated the feasibility of a commercially available fluorescence-based imaging system to detect and disinfect pathogens on surfaces. The tested device used two different excitation wavelengths, 405 nm for detection and 275 nm for disinfection of pathogens. Five different colonies including E. coli, K. pneumoniae, S. enteritidis (gram negative), S. aureus, and L. innocua (gram positive) were prepared and diluted in phosphate buffered saline (PBS) or water over a 5 log range. Samples of different concentrations were placed on glass slides for fluorescence image measurement, or placed in well plates for disinfection of 20 µl droplets. Raw images were converted to grayscale, and background noise was filtered. When using the disinfection mode, samples were exposed to UVC while increasing energy density from 3.5 to 38.5 mJ/cm2, as well as changing exposure time and working distance. After incubation at 30 ºC for 24 hours, the number of colonies on the plate were counted. A summary of pathogen detection and percentage of bacteria killing rate depending on concentrations and energy densities will be presented.
12120-31
Author(s): Hamed Taheri Gorji, Seyed Mojtaba Shahabi, Univ. of North Dakota (United States); Lucas Q. Tande, Univ. of Minnesota (United States); Akshay Sharma, SUNY Polytechnic Institute (United States); Jianwei Qin, Diane E. Chan, Insuck Baek, USDA Agricultural Research Service (United States); Fartash Vasefi, Nicholas MacKinnon, Alireza Akhbardeh, SafetySpect Inc. (United States); Moon S. Kim, USDA Agricultural Research Service (United States); Kouhyar Tavakolian, Univ. of North Dakota (United States)
6 April 2022 • 4:30 PM - 4:50 PM EDT
Show Abstract + Hide Abstract
Meat and poultry can be contaminated by pathogens like E. coli and salmonella. Animal fecal matter and ingesta host these pathogens, so developing a method to detect contamination on meat surfaces is crucial. We visited four meat processing facilities and used a handheld fluorescence imaging device to detect fecal matter or ingesta on carcasses. We investigated the efficiency and reliability of a state-of-the-art semantic segmentation algorithm to segment fecal or ingesta contaminated regions in meat surfaces images. Industry could use CSI-D to train employees in trimming carcasses as part of their Hazard Analysis Critical Control Point zero tolerance plan.
12120-32
Author(s): Kouhyar Tavakolian, Univ. of North Dakota (United States)
6 April 2022 • 4:50 PM - 5:10 PM EDT
Show Abstract + Hide Abstract
This paper introduces an autonomous robot system with an intelligent contaminant detection and disinfection device. The system can maneuver and using a robotic arm can detect, disinfect, and document invisible organic contamination on surfaces that may host pathogens. We will present repeated autonomous detection of hard-to-see potato starch biofilms on a conveyor belt surface. The system will be designed to report the time and location of the detected contamination on a digital floor plan. The system also records the amount of germicidal energy dosage to the surface by calculating the optical power, exposure time and distance to the surface.
Conference Chair
USDA Agricultural Research Service (United States)
Conference Chair
Chungnam National Univ. (Korea, Republic of)
Program Committee
USDA Agricultural Research Service (United States)
Program Committee
USDA Agricultural Research Service (United States)
Program Committee
Univ. de Córdoba (Spain)
Program Committee
Korea Research Institute of Standards and Science (Korea, Republic of)
Program Committee
Naoshi Kondo
Kyoto Univ. Graduate School of Agriculture (Japan)
Program Committee
USDA Agricultural Research Service (United States)
Program Committee
USDA Agricultural Research Service (United States)
Program Committee
USDA Agricultural Research Service (United States)
Program Committee
China Agricultural Univ. (China)
Program Committee
Univ. de Córdoba (Spain)
Program Committee
Agricultural Research Service (United States)
Program Committee
Amrita Sahu
Altria Group, Inc. (United States)
Program Committee
Stellenbosch Univ. (South Africa)
Program Committee
Mississippi State Univ. (United States)
Program Committee
Zhejiang Univ. (China)
Program Committee
USDA Agricultural Research Service (United States)
Additional Information