Skip to main content
ARS Home » Northeast Area » Beltsville, Maryland (BARC) » Beltsville Agricultural Research Center » Environmental Microbial & Food Safety Laboratory » Research » Research Project #440790

Research Project: Advancement of Sensing Technologies for Food Safety and Security Applications

Location: Environmental Microbial & Food Safety Laboratory

2022 Annual Report

Objective 1: Develop and validate an autonomous unmanned aerial vehicle with multimode imaging technologies for preharvest inspection of produce fields for animal intrusion and fecal contamination, and for irrigation water quality monitoring. Objective 2: Advance the development of customized compact spectral sensing technologies for food inspection and sanitation assessment in food processing, and for controlled-environment produce production, with embedded automated detection results for non-expert end users. Sub-objective 2.A: Develop a handheld line-scan hyperspectral imaging device with enhanced capabilities for contamination and sanitation inspection in food processing environments. Sub-objective 2.B: Develop a compact automated hyperspectral imaging platform for food safety and plant health monitoring for controlled-environment produce production in NASA space missions. Objective 3: Develop innovative spectroscopic and optical methods to characterize food composition and nondestructively detect adulterants and contaminants, for screening and inspecting agricultural commodities and commercially prepared food materials. Sub-objective 3.A: Develop a transportable multimodal optical sensing system for rapid, automated, and intelligent biological and chemical food safety inspection. Sub-objective 3.B: Develop a novel apparatus enabling dual-modality concomitant detection, along with associated methods and procedures, for assuring food integrity.

The overall goal of this project is to develop and validate automated sensing tools and techniques to reduce food safety risks in food production and processing environments. Engineering-driven research will develop the next generation of rapid, intelligent, user-friendly sensing technologies for use in food production, processing, and other supply chain operations. Feedback from industrial and regulatory end users, and from stakeholders throughout the food supply chain, indicates that effective automated sensing and instrumentation systems require real-time data processing to provide non-expert users with a clear understanding and ability to make decisions based on the system output. Towards this end, we will develop unmanned aerial vehicles with multimodal remote sensing platforms and on-board data-processing capability to provide real-time detection and classification of animal intrusion and fecal contamination in farm fields and of irrigation water microbial quality. We will upgrade our existing handheld imaging device for contamination and sanitation inspection with multispectral imaging and embedded computing and artificial intelligence. We are also partnering with the NASA Kennedy Space Center to develop a novel, compact, automated hyperspectral platform for monitoring food safety and plant health of space crop production systems. Food safety and integrity requires identifying adulterants, foreign materials, and microbial contamination as well as authenticating ingredients. We will develop innovative multimodal optical sensing systems utilizing dual-band laser Raman, and Raman plus infrared, for simultaneous detection on a single sampling site. Spectroscopic and spectral imaging-based methodologies will be developed to enhance detection efficacy for liquid or powder samples. These systems will be supported with intuitive, intelligent sample-evaluation software and procedures for both biological and chemical contaminants.

Progress Report
Significant progress has been made for all objectives of the project, which fall under National Program 108. For Objective 1, ARS scientists in Beltsville, Maryland, started development and design of the field transportable multimodal imaging system. This system will be used to validate the results of small Unmanned Autonomous Vehicle (sUAV) system and provide reference data during the processes of sensor calibration and post-collection data processing. The sensor suite that will be used in both field cart and (sUAV) units was finalized, and scientists began testing on these sensors. A full 3-D model of the field transportable system was completed to verify fit and dimensions, and the parts from this design will be purchased. Testing was done to confirm the viability of certain design parameters such as weight and linear actuator load capacity. Parts of this testing were corroborated using calculations within 3-D CAD with the specific goal of making the cart usable for a wide range of end users from both accessibility and crop variety standpoints. This design will be used as the first prototype platform to take sample images and work to optimize the data quality and simplify the collection process. For Objective 2A, ARS scientists in Beltsville, Maryland, continued to work with multiple collaborators for testing and commercialization of ARS portable multispectral imaging technology for contamination and sanitization inspection. Based on an exclusive license for the ARS-patented (US patent no. US 8,310,544) handheld fluorescence imaging, a commercial prototype Contamination Sanitization Inspection and Disinfection (CSI-D) device was developed in 2021. The handheld CSI-D device provides visualization of contamination on food contact surface via ultraviolet-A (UVA) fluorescence imaging, disinfection via ultraviolet-C (UVC) illumination, and documentation of cleanliness. Experiments were conducted to determine detection efficacy of the CSI-D devices for various vegetable and meat sample smears on food contact surfaces such commercial grade cutting boards and stainless-steel plates. Furthermore, ARS scientists completed the development of fully automated bench-top UV illumination systems to evaluate effectiveness of ultraviolet-B (UVB) and UVC for germicidal applications. The first system consists of a 305-nm UVB LED module with a cooling fan, a height-adjustable sample holder, a single-board computer with a touchscreen monitor, and a safety trigger. This system was used to measure UVB irradiance at varying distances to determine parameters suitable for germicidal applications on foodborne bacteria. Experiments were conducted to determine the efficacies of the UVC radiation for killing pathogenic bacteria grown in Petri dishes. ARS scientists in Beltsville, Maryland, developed a fully automated UV illumination and germicidal system which includes 305 nm UVB, 275 nm UVC, and mixed UVB-UVC LED modules, a programmable linear stage, a depth and RGB camera for sample imaging, a data logger, a single-board computer with a touchscreen monitor, and a safety trigger. This system will be used to establish optimal UVB and UVC parameters along with efficacy, safety, and functionality, for nonchemical control of pathogens For Objective 2B, in collaboration with NASA Kennedy Space Center (KSC), ARS scientists in Beltsville, Maryland, continued to develop next-generation hyperspectral imaging technology suitable for plant health and food safety monitoring in fresh produce production systems for future spaceflight. ARS scientists finished development and testing of a compact hyperspectral system equipped with broadband and UVA light for reflectance and fluorescence measurements. The prototype system and its control software were transferred and installed in a plant growth chamber at KSC for experiments on pick-and-eat salad crops. Hyperspectral reflectance and fluorescence images were acquired from Dragoon lettuce, pak choi, mizuna, and radish grown by KSC scientists under normal and abiotic stress conditions (e.g., drought and overwatering). ARS scientists developed hyperspectral image processing and machine learning classification programs for data analysis. Results from the lettuce experiment showed that machine learning classification models have the potential for early detection of drought stress on lettuce leaves prior to visible symptoms and leaf size differences. ARS scientists visited the KSC to improve the current system and plan to develop a new XYZ gantry imaging system for automated scanning of multiple plant growth chambers. For Objective 3A, in collaboration with National Agricultural Products Quality Management Service, South Korea, ARS scientists in Beltsville, Maryland, developed a multimodal optical sensing system for automated and intelligent biological and chemical assessment in food safety applications. The system uses two pairs of point lasers and spectrometers, at 785 and 1064 nm, to conduct dual-band Raman sensing, which can be used for samples generating low- and high-fluorescence interference signals, respectively. Automated data acquisition was realized using a fast XY-moving stage for solid, powder, and liquid samples placed in well plates or randomly scattered in standard Petri dishes (e.g., bacterial colonies). The system capability was demonstrated by an example application for rapid identification of five common foodborne bacteria. Using a machine-learning model based on a linear support vector machine, over 98% classification accuracy was achieved using spectra automatically collected from bacterial colonies for the five species grown on nonselective agar in Petri dishes. A patent application for the methodology and prototype system was approved by ARS National Mechanical & Measurement Patent Committee and will be filed to USPTO for a formal application. In collaboration with a CRADA partner, ARS scientists in Beltsville, Maryland, continued work to develop fish authentication methods based on multimode hyperspectral imaging techniques to address issues of species mislabeling and fraud as well as freshness of fish fillets. In this continuing study, two ARS in-house developed line-scan hyperspectral systems were used to collect reflectance and fluorescence images from fish fillet samples of additional species and from selected fillets for freshness study. Imaging experiments and DNA tests have been completed for over 60 major fish species. A hyperspectral image database with DNA barcoding species labels was established and shared with the CRADA partner. Machine learning AI models and spectral and image fusion algorithms were developed to classify fish species and freshness. The results will be used to design and develop portable smart sensing devices for industrial applications for on-site fish species and freshness inspection. For Objective 3B, we report a simple procedure to obtain fipronil samples at concentrations from 0.5 ppm to 11 ppm and measure the infrared (IR) spectra of fipronil samples. A partial least squares regression model has been developed to estimate the concentration of fipronil. The 3D chemical structure of fipronil was described, vibrational modes were assigned to IR wavelengths and compared with Raman wavelengths in the same spectral range. Raman spectra and IR spectra differentially detect symmetrical and asymmetrical vibrational modes in the same molecule. The fipronil vibrational mode near 2249 cm-1 was found to be much more intense in Raman than in the IR spectrum. We also examined the remaining IR and spectral fingerprint of fipronil to determine which vibrational modes are bigger in IR relative to those more intense in the Raman. Although IR and Raman spectra are often deemed to be in principle “complementary,” experimental evidence on spectral data on any given specific particular compound in practice is sparse. We had previously published experimental evidence comparing IR and Raman spectral data for turmeric powder mixed with white turmeric powder. The word “complementary” means more information is present when two data sets are both present. Whether IR and Raman spectral information provide identical identification information is clearly undetermined because experimental data comparing the two data sets has so rarely been published. The question of whether the spectral difference between the two techniques can be an even more definitively precise fingerprint was addressed with fipronil. Instead of using a single mode fingerprint in either IR or Raman, we found through using a dual modality technique that only a small number of specific wavenumbers paired in IR and Raman together are fully sufficient to precisely identify fipronil structure.

1. Handheld fluorescence imaging device for surface contamination detection and disinfection. Cleaning and sanitation are critical components of USDA and FDA Hazard Analysis Critical Control Point (HACCP) regulation and management systems for food safety. Currently contamination inspection is conducted by human inspectors via either visual examination or spot-check testing, which is a process that limits productivity and is prone to error. Based on an ARS patented technology, a commercial contamination, sanitization inspection and disinfection (CSI-D) handheld imaging device has recently been developed for preventing infection in food preparation and serving facilities. The CSI-D device provides an innovative solution encompassing visualization of contamination using UV fluorescence imaging, disinfection of contamination using UVC illumination, and documentation of cleanliness. In demonstration experiments, the device can achieve one hundred percent sterilization for three selected pathogens under ten seconds, including a fungus (Aspergillus fumigatus), a bacterium (Streptococcus pneumonia), and a virus (influenza A). The commercialized CSI-D device will help improve efficacies for USDA-FSIS and the food processing industry for HACCP contamination and sanitation inspections required in Food Safety and Modernization Act (FSMA).

2. Identification of fecal contamination on meat carcasses using handheld fluorescence imaging and deep learning techniques. Animal fecal matter and ingesta, which can host bacterial pathogens such as E. coli and Salmonella, are a potential contaminant source for various meat products. Detection of fecal contamination on meat carcasses is important to reduce food safety risks from foodborne diseases for consumers. In this study, a contamination, sanitization inspection and disinfection (CSI-D) handheld imaging device, which was developed and commercialized based on an ARS patented technology, was used to collect fluorescence images from beef and sheep carcasses in three meat processing facilities in North Dakota. State-of-the-art deep learning algorithms were developed to segment and identify areas of the fecal residues in the fluorescence images. The results demonstrated that the clean and fecal contaminated carcasses can be differentiated with an approximate accuracy of ninety seven percent. The combination of the CSI-D handheld imaging and deep learning techniques would benefit the meat industry and regulatory agencies (e.g., USDA FSIS and FDA) in ensuring and enforcing food safety standards for meat and related products.

3. Species classification of fish fillets using simulated annealing-based hyperspectral data optimization. Many fish fillets are similar in appearance, which makes them a target for economically motivated fraud. Mixing less expensive species into more expensive species is a common fraudulent practice in the seafood industry. This study developed a data analysis methodology to support design of a future spectroscopy-based system for detecting mislabeling of fish fillets. Three types of spectra—fluorescence, visible and near-infrared reflectance, and short-wave infrared reflectance—were obtained from hyperspectral images of fish fillet samples for 25 common species. Algorithms were developed for wavelength selection, data fusion, and machine learning classification. Based on a multi-layer perceptron neural network classifier, a ninety-five percent classification accuracy was achieved using the fusion of the three spectral modes with seven wavelengths selected by a simulated annealing method. The data analysis methods developed in this study can facilitate development of a rapid and cost-effective spectral sensing device for on-site inspection of the fish fillet mislabeling, which can be used for authentication of the fish fillets and other related food products by the seafood industry and regulatory agencies.

4. Rapid detection of aflatoxins in ground maize using spectral imaging techniques. Food crops such as maize, peanuts, and tree nuts can be contaminated with aflatoxin, which is produced by certain fungi and is considered a carcinogen. Many countries have established maximum allowable limits for the presence of aflatoxin in foods and thus there is a great interest worldwide in developing rapid and nondestructive methods to screen high volumes of food products for aflaxtoxin contamination. This study investigated the development of classification models to use with four hyperspectral imaging methods—fluorescence by ultraviolet excitation, visible/near-infrared reflectance, short-wave infrared reflectance, and Raman—to detection naturally-occurring levels of aflatoxin contamination in samples of ground maize. The results demonstrated that effective classification models were possible with all four hyperspectral imaging methods, indicating great promise for the development of non-destructive imaging methods that can be used by regulatory agencies and processors for high volume sample screening of ground maize and other products that are vulnerable to contamination.

5. Identification of corn kernels infected with aflatoxin using line-scan hyperspectral Raman imaging. Corn is one of the most susceptible crops to fungal infection. Effective methods for detecting aflatoxigenic fungi on corn kernels are important to reduce the risk of aflatoxin contamination entering the food and feed chains. In this study, a new detection method based on high-throughput hyperspectral Raman imaging was developed to differentiate healthy and artificially inoculated corn kernels with aflatoxigenic and non-aflatoxigenic fungi. Raman spectral differences between the healthy and the contaminated corn samples on both endosperm and germ sides of the kernels were investigated. Three-class discriminant models were developed based on mean spectra extracted from the Raman images of each kernel, and the best classification accuracy was achieved at ninety percentusing the endosperm data. The proposed method provides new possibilities to inspect for aflatoxin contamination on the corn kernels. The technique would benefit the food industry in helping to ensure the safety and quality of the corn and related food and feed products and benefit regulatory agencies with an interest in enforcing standards of food safety and quality for the corn products.

6. Nondestructive detection of adulterated sugar through plastic packaging using spatially offset Raman imaging. Safety and quality inspection of packaged foods and ingredients is important and challenging for both the food industry and regulatory agencies. Nondestructive detection of food adulterants through packaging using optical sensing techniques is difficult due to complex interactions between light and the packaging materials. This study developed a novel method using a laser-based spatially offset Raman imaging technique for detection of adulterated sugar in plastic packaging. Raman image and spectral data were collected from adulterated sugar samples that were made by mixing soft sugar and cheap glucose as an adulterant in different ratios. A mathematic prediction model was developed and was successfully used to evaluate the adulteration ratios for the mixed sugar samples through packaging. The results proved that the proposed method can be used for through-packaging inspection of the foods and ingredients for safety and quality applications. The technique would benefit the food industry in ensuring the safety and quality of packaged food products and benefit regulatory agencies with an interest in enforcing standards of food safety and quality for packaged foods and ingredients.

7. A rapid dual modality method for detecting insecticide fipronil on solid surfaces. Fipronil is a broad-spectrum insecticide banned from use in the food supply in the U.S. and European Union. An incident of poultry eggs tainted with fipronil in 2017 caused a recall of millions of eggs affecting more than 40 countries. ARS scientists in Beltsville, Maryland, have developed an in situ spectroscopic process for assaying fipronil on surfaces, verifying its identity, and validated the methodology developed. For fipronil in a [500 cm-1] in-common wavenumber range, two maximum intensity peaks in IR spectra were easily differentiated along with two different maximum intensity peaks in Raman spectra. The differences in the wavenumber intensities between IR results and Raman results in this selected spectral range demonstrates the complementary nature of IR and Raman: each contains critical spectral information absent in the other mode. The practical analytical advantage of using dual modality detection was demonstrated using fipronil. The same methodology can be applied to other compounds either for product verification or for identifying specific contaminants/adulterants. The in situ dual modality measurements enable more reliable and more accurate food product testing and monitoring that can be useful in food processing operations.

Review Publications
Delwiche, S.R., Baek, I., Kim, M.S. 2021. Does spatial region of interest (ROI) matter in multispectral and hyperspectral imaging of segmented wheat kernels. Biosystems Engineering. 212:106-114.
Stocker, M., Pachepsky, Y.A., Hill, R.L., Kim, M.S. 2022. Elucidating spatial patterns of E. coli in two irrigation ponds with empirical orthogonal functions. Journal of Hydrology. 609:127770.
Joshi, R., Baek, I., Joshi, R., Kim, M.S., Cho, B. 2022. Detection of fabricated eggs using Fourier Transform Infrared (FT- IR) spectroscopy coupled with multivariate classification techniques. Food Analytical Methods.
Chao, K., Schmidt, W.F., Qin, J., Kim, M.S. 2022. A rapid and precise spectroscopic method for detecting fipronil insecticide on solid surfaces. Journal of Food Measurement and Characterization.
Ahmed, M.R., Yasmin, J., Park, E., Kim, G., Kim, M.S., Wakholi, C., Mo, C., Cho, B. 2020. Classification of watermelon seeds using morphological patterns of X-ray imaging: A comparison of conventional machine learning and deep learning. Sensors. 23(20), 6753.
Broadhurst, C., Schmidt, W.F., Qin, J., Chao, K., Kim, M.S. 2021. Continuous gradient temperature Raman spectroscopy of 1-stearoyl-2-docosahexonyl, 1-stearoyl- 2-arachidonoyl, and 1,2-steroyl phosphocholines. Chemistry and Physics of Lipids.
Liu, Z., Huang, M., Zhu, Q., Qin, J., Kim, M.S. 2021. Detection of adulterated sugar with plastic packaging based on spatially offset Raman imaging. Journal of the Science of Food and Agriculture. 101:6281-6288.
Kim, G., Lee, H., Baek, I., Cho, B., Kim, M.S. 2021. Quantitative detection of benzoyl peroxide in wheat flour using line-scan short-wave infrared hyperspectral imaging. Sensors and Actuators B: Chemical. 352:130997.
Kim, G., Lee, H., Cho, B., Baek, I., Kim, M.S. 2021. Quantitative evaluation of food-waste components in organic fertilizer using visible–near-infrared hyperspectral imaging. Applied Sciences. 11(17):8201.
Joshi, R., Sathasivam, R., Park, S., Lee, H., Kim, M.S., Baek, I., Cho, B. 2021. Application of Fourier transform infrared spectroscopy and multivariate analysis methods for the non-destructive evaluation of phenolics compounds in moringa powder. Agriculture.
Liu, Z., Huang, M., Zhu, Q., Qin, J., Kim, M.S. 2022. A packaged food internal Raman signal separation method based on spatially offset Raman spectroscopy combined with FastICA. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy. 275:121154.
Nabwire, S., Wakholi, C., Faquurzada, M., Arief, M., Kim, M.S., Baek, I., Cho, B. 2022. Estimation of cold stress, plant age, and number of leaves in watermelon plants using image analysis. Frontiers in Plant Science. 13:847225.
Tao, F., Yao, H., Hruska, Z., Rajasekaran, K., Qin, J., Kim, M.S. 2021. Use of line-scan Raman hyperspectral imaging to identify corn kernels infected with Aspergillus flavus. Journal of Cereal Science. 102:103364.
Stocker, M., Pachepsky, Y.A., Smith, J., Morgan, B.J., Hill, R., Kim, M.S. 2021. Persistent patterns of E. coli concentrations in two irrigation ponds from three years of monitoring. Water, Air, and Soil Pollution.
Park, E., Kim, Y., Omari, M., Suh, H., Faqeezada, M., Kim, M.S., Baek, I., Cho, B. 2021. High-throughput phenotyping approach for the evaluation of heat stress in Korean ginseng (Panax ginseng Meyer) using hyperspectral reference image. Sensors. 21:5634.
Tunny, S., Amanah, H., Faqeerzada, M., Wakholi, C., Baek, I., Kim, M.S., Cho, B. 2022. Multispectral wavebands selection for the detection of potential foreign materials in fresh-cut vegetables. Sensors. 22:1775.
Schmidt, W.F., Chen, F., Broadhurst, C.L., Qin, J., Crawford, M.A., Kim, M.S. 2022. Unique and redundant spectral fingerprints of docosahexaenoic, alpha-linolenic and gamma-linolenic acids in binary mixtures. Journal of Molecular Liquids. 358:119222.
Wakholi, C., Nabwire, S., Kim, J., Bae, J.H., Baek, I., Kim, M.S., Cho, B. 2021. Economic analysis of an image-based beef carcass yield estimation system in Korea. Animals. 12:7.
Amanah, H., Tunny, S.S., Masithoh, R., Choung, M., Kim, K., Kim, M.S., Baek, I., Lee, W., Cho, B. 2022. Nondestructive prediction of isoflavones and oligosaccharides in intact soybean seed using Fourier transform near-infrared (FT-NIR) and Fourier transform infrared (FT-IR) spectroscopic techniques. Foods.
Nam, S., Baek, I., Hillyer, M.B., He, Z., Barnaby, J.Y., Condon, B.D., Kim, M.S. 2022. Thermosensitive textiles by silver nanoparticle-filled brown cotton fibers. Nanoscale Advances. 4:3725-3736.
Gorji, H.T., Shahabi, S.M., Sharma, A., Tamde, L.Q., Husarik, K., Qin, J., Chan, D.E., Baek, I., Kim, M.S., Mackinnon, N., Morro, J., Sokolov, S., Akhbardeh, A., Vasefi, F., Tavakolian, K. 2022. Combining deep learning and fluorescence imaging to automatically identify fecal contamination on meat carcasses. Nature Scientific Reports. 12:2392.
Joshi, R., Sathasivam, R., Kumar, P., Patel, A.K., Nguyen, B.V., Faqeerzaada, M.A., Park, S., Lee, S., Kim, M.S., Baek, I., Cho, B. 2022. Comparative determination of phenolic compounds in Ara-bidopsis Thaliana leaf powder under distinct stress conditions using Fourier-Transform Infrared (FT-IR) and Near-Infrared (FT-NIR) Spectroscopy. Plants. 11(7):836.
Kim, Y., Baek, I., Lee, K., Qin, J., Kim, G., Shin, B.K., Chan, D.E., Herman, T.J., Cho, S., Kim, M.S. 2021. Investigation of reflectance, fluorescence, and Raman hyperspectral imaging techniques for rapid detection of aflatoxins in ground maize. Food Control. 132:108479.
Chauvin, J., Duran, R., Tavakolian, K., Akhbardeh, A., Mackinnon, N., Qin, J., Chan, D.E., Hwang, C., Baek, I., Kim, M.S., Isaacs, R., Yilmaz, A., Roungchun, J., Hellberg, R., Vasefi, F. 2021. Simulated annealing-based hyperspectral data optimization for fish species classification: Can the number of measured wavelengths be reduced? Food Control. 11:10628.
Kumar, P., Faqeerzada, M., Park, E., Kim, Y., Joshi, R., Amanah, H., Sultana, T., Kim, H., Nabwire, S., Baek, I., Kim, M.S., Cho, B. 2022. Analysis of RGB plant images to identify root rot disease in Korean ginseng plants using deep learning. Applied Sciences. 12:2489.
Sueker, M., Stromsodt, K., Gorji, H.T., Vesafi, F., Khan, N., Schmidt, T., Varma, R., Mackinnon, N., Sokolov, S., Akhbardeh, A., Qin, J., Chan, D.E., Baek, I., Kim, M.S., Tavakolian, K. 2021. Handheld multispectral fluorescence imaging system to detect and disinfect surface contamination. Sensors.
Li, L., Peng, Y., Li, Y., Yang, C., Chao, K. 2021. Rapid and low-cost detection of moldy apple core based on an optical sensor system. Postharvest Biology and Technology.