Hyperspectral Imaging and Machine Learning as a Nondestructive Method for Proso Millet Seed Detection and Classification.

Millet is a small-seeded cereal crop with big potential. There are many different cultivars of proso millet (Panicum miliaceum L.) with different characteristics, bringing forth the issue of sorting which are important for growers, processors, and consumers. Current methods of grain cultivar detection and classification are subjective, destructive, and time-consuming. Therefore, there is a need to develop nondestructive methods for sorting the cultivars of proso millet. In this study, the feasibility of using near-infrared (NIR) hyperspectral imaging (900-1700 nm) to discriminate between different cultivars of proso millet seeds was evaluated. A total of 5000 proso millet seeds were randomly obtained and investigated from the ten most popular cultivars in the United States, namely Cerise, Cope, Earlybird, Huntsman, Minco, Plateau, Rise, Snowbird, Sunrise, and Sunup. To reduce the large dimensionality of the hyperspectral imaging, principal component analysis (PCA) was applied, and the first two principal components were used as spectral features for building the classification models because they had the largest variance. The classification performance showed prediction accuracy rates as high as 99% for classifying the different cultivars of proso millet using a Gradient tree boosting ensemble machine learning algorithm. Moreover, the classification was successfully performed using only 15 and 5 selected spectral features (wavelengths), with an accuracy of 98.14% and 97.6%, respectively. The overall results indicate that NIR hyperspectral imaging could be used as a rapid and nondestructive method for the classification of proso millet seeds.

The Magnitude and Impact of Food Allergens and the Potential of AI-Based Non-Destructive Testing Methods in Their Detection and Quantification.

Reaction to food allergens is on the increase and so is the attending cost on consumers, the food industry, and society at large. According to FDA, the "big-eight" allergens found in foods include wheat (gluten), peanuts, egg, shellfish, milk, tree nuts, fish, and soybeans. Sesame was added to the list in 2023, making the target allergen list nine instead of eight. These allergenic foods are major ingredients in many food products that can cause severe reactions in those allergic to them if found at a dose that can elicit a reaction. Defining the level of contamination that can elicit sensitivity is a work in progress. The first step in preventing an allergic reaction is reliable detection, then an effective quantification method. These are critical steps in keeping contaminated foods out of the supply chain of foods with allergen-free labels. The conventional methods of chemical assay, DNA-PCR, and enzyme protocols like enzyme-linked immunosorbent assay are effective in allergen detection but slow in providing a response. Most of these methods are incapable of quantifying the level of allergen contamination. There are emerging non-destructive methods that combine the power of sensors and machine learning to provide reliable detection and quantification. This review paper highlights some of the critical information on the types of prevalent food allergens, the mechanism of an allergic reaction in humans, the measure of allergenic sensitivity and eliciting doses, and the conventional and emerging AI-based methods of detection and quantification-the merits and downsides of each type.

Trends in millet and pseudomillet proteins - Characterization, processing and food applications.

Millets are small-seeded crops which have been well adopted globally owing to their high concentration of macro and micronutrients such as protein, dietary fibre, essential fatty acids, minerals and vitamins. Considering their climate resilience and potential role in nutritional and health security, the year 2023 has been declared as 'International Year of Millets' by the United Nations. Cereals being the major nutrient vehicle for a majority population, and proteins being the second most abundant nutrient in millets, these grains can be a suitable alternative for plant-based proteins. Therefore, this review was written with an aim to succinctly provide an overview of the available literature take on the characterization, processing and applications of millet-based proteins. This information would play an important role in realizing the research gap restricting the utilization of complete potential of millet proteins. This can be further used by researchers and food industries for understanding the scope of millet proteins as an ingredient for novel food product development.

The propensity of fomite spread of SARS-CoV-2 virus through produce supply chain.

Background: The global community has battled the spread of SAR-CoV-2 for almost 2 years, and the projection is that the virus may be recurrent like the seasonal flu. The SARS-CoV-2 pandemic disrupted activities within the food supply chain that cost billions of dollars globally. This has heightened concerns about fomite spread of the virus through surfaces. There is an urgent need to understand the risk portends by this virus along the produce supply chain with conditions (low temperature and high relative humidity) conducive to extended survival of the virus. Main body: Pre-dating SARS-CoV-2 are other types of coronaviruses that had lower infection and mortality rates. There are some similarities between the former and the new coronavirus, especially with regards to transmission modes and their survivability on surfaces. There is evidence of other coronaviruses' survival on surfaces for weeks. Currently, there are limited evidence-based studies to enlighten us on how the virus is transmitted within the produce supply chain. A few studies claim that the virus could spread through the cold supply chains. However, these are not sufficient to make a conclusive inference about the deadly SARS-CoV-2. Conclusions: This paper provides a succinct review of the literature on current understanding of the transmission, survivability, and risk SARS-CoV-2 portend to humans within the produce supply chain and calls for more evidence-based research to allay or alert us of the potential risk of fomite transmission of SARS-CoV-2. The paper also highlights examples of conventional and novel non-thermal inactivation and sanitation methods applicable to this type of virus.

Modification of plant proteins for improved functionality: A review.

The market trend towards plant-based protein has seen a significant increase in the last decade. This trend has been projected to continue in the coming years because of the strong factors of sustainability and less environmental impact associated with the production of plant-based protein compared to animal, aside from other beneficial health claims and changes in consumers' dietary lifestyles. In order to meet market demand, there is a need to have plant-based protein ingredients that rival or have improved quality and functionality compared to the traditional animal protein ingredients they may replace. In this review article, we present a detailed and concise summary of the functionality challenges of some plant protein ingredients with associated physical, chemical, and biological processing techniques (traditional and emerging technologies) that have been attempted to enhance them. We cataloged the differences between several studies that seek to address the functionality challenges of selected plant-based protein ingredients without overtly commenting on a general technique that addresses the functionality of all plant-based protein ingredients. Additionally, we elucidated the chemistry behind some of these processing techniques and how they modify the protein structure for improved functionality. Although, many food industries are shifting away from chemical modification of proteins because of the demand for clean label product and the challenge of toxicity associated with scale-up of this technique, so physical and biological techniques are widely being adopted to produce a functional ingredient such as texturized vegetable proteins, hydrolyzed vegetable protein, clean label protein concentrates, de-flavored protein isolates, protein flour, and grits.

Current applications of gluten-free grains - a review.

The population of Americans suffering from celiac, gluten intolerance, and wheat allergy is 1 in every 14 people. Also, many are choosing gluten-free (GF) diets nowadays because of the perception that it is a healthier option for them. Therefore, in the last decade, the GF market in the US and all over the world has seen significant growth. Globally, GF product sales reached 4.63 billion USD in 2017, and are expected to reach 6.47 billion USD by 2023, a projected compound annual growth rate of 7.6%. Several grains like millet, corn, sorghum, and pseudocereals like amaranth, quinoa, and teff are the main ingredients for a gluten diet. Though most of them have a comparable nutrient profile as common grains, the main challenge to their acceptability is the quality departure from gluten-containing counterparts and imbalance nutrients that ensue when food processing aids like starch, gums, and enzymes are used. In this review, we profiled some of the common grains, their characteristics, functionality and the various food types they are used for. We also reviewed the impact of some of the current food processing aids like starch, hydrocolloids used for improving functionality, and processing techniques like extrusion suitable for making remarkable GF foods.

Nondestructive Detection of Codling Moth Infestation in Apples Using Pixel-Based NIR Hyperspectral Imaging with Machine Learning and Feature Selection.

Codling moth (CM) (Cydia pomonella L.), a devastating pest, creates a serious issue for apple production and marketing in apple-producing countries. Therefore, effective nondestructive early detection of external and internal defects in CM-infested apples could remarkably prevent postharvest losses and improve the quality of the final product. In this study, near-infrared (NIR) hyperspectral reflectance imaging in the wavelength range of 900-1700 nm was applied to detect CM infestation at the pixel level for three organic apple cultivars, namely Gala, Fuji and Granny Smith. An effective region of interest (ROI) acquisition procedure along with different machine learning and data processing methods were used to build robust and high accuracy classification models. Optimal wavelength selection was implemented using sequential stepwise selection methods to build multispectral imaging models for fast and effective classification purposes. The results showed that the infested and healthy samples were classified at pixel level with up to 97.4% total accuracy for validation dataset using a gradient tree boosting (GTB) ensemble classifier, among others. The feature selection algorithm obtained a maximum accuracy of 91.6% with only 22 selected wavelengths. These findings indicate the high potential of NIR hyperspectral imaging (HSI) in detecting and classifying latent CM infestation in apples of different cultivars.

Quality Assessment of Beef Using Computer Vision Technology.

Imaging technique or computer vision (CV) technology has received huge attention as a rapid and non-destructive technique throughout the world for measuring quality attributes of agricultural products including meat and meat products. This study was conducted to test the ability of CV technology to predict the quality attributes of beef. Images were captured from longissimus dorsi muscle in beef at 24 h post-mortem. Traits evaluated were color value (L*, a*, b*), pH, drip loss, cooking loss, dry matter, moisture, crude protein, fat, ash, thiobarbituric acid reactive substance (TBARS), peroxide value (POV), free fatty acid (FFA), total coliform count (TCC), total viable count (TVC) and total yeast-mould count (TYMC). Images were analyzed using the Matlab software (R2015a). Different reference values were determined by physicochemical, proximate, biochemical and microbiological test. All determination were done in triplicate and the mean value was reported. Data analysis was carried out using the programme Statgraphics Centurion XVI. Calibration and validation model were fitted using the software Unscrambler X version 9.7. A higher correlation found in a* (r=0.65) and moisture (r=0.56) with 'a*' value obtained from image analysis and the highest calibration and prediction accuracy was found in lightness (r2 c=0.73, r2 p=0.69) in beef. Results of this work show that CV technology may be a useful tool for predicting meat quality traits in the laboratory and meat processing industries.

Non-Destructive Technologies for Detecting Insect Infestation in Fruits and Vegetables under Postharvest Conditions: A Critical Review.

In the last two decades, food scientists have attempted to develop new technologies that can improve the detection of insect infestation in fruits and vegetables under postharvest conditions using a multitude of non-destructive technologies. While consumers' expectations for higher nutritive and sensorial value of fresh produce has increased over time, they have also become more critical on using insecticides or synthetic chemicals to preserve food quality from insects' attacks or enhance the quality attributes of minimally processed fresh produce. In addition, the increasingly stringent quarantine measures by regulatory agencies for commercial import-export of fresh produce needs more reliable technologies for quickly detecting insect infestation in fruits and vegetables before their commercialization. For these reasons, the food industry investigates alternative and non-destructive means to improve food quality. Several studies have been conducted on the development of rapid, accurate, and reliable insect infestation monitoring systems to replace invasive and subjective methods that are often inefficient. There are still major limitations to the effective in-field, as well as postharvest on-line, monitoring applications. This review presents a general overview of current non-destructive techniques for the detection of insect damage in fruits and vegetables and discusses basic principles and applications. The paper also elaborates on the specific post-harvest fruit infestation detection methods, which include principles, protocols, specific application examples, merits, and limitations. The methods reviewed include those based on spectroscopy, imaging, acoustic sensing, and chemical interactions, with greater emphasis on the noninvasive methods. This review also discusses the current research gaps as well as the future research directions for non-destructive methods' application in the detection and classification of insect infestation in fruits and vegetables.

Effect of Germination and Extrusion on Physicochemical Properties and Nutritional Qualities of Extrudates and Tortilla from Wheat.

Wheat is the most common grain in the temperate region. Modifying its constituent through food processing improves its functionality and nutrient access. In this study, the combined effect of germination and extrusion on physicochemical properties and nutritional qualities of extrudates and tortilla from wheat was evaluated. Results showed that germination significantly increased (P <0.05) the γ-aminobutyric acid content in germinated whole wheat (GW) and extruded germinated whole wheat (EGW) as compared to the control of whole wheat (WW). Germination also significantly increased the protein content, reducing sugar and total soluble sugar content in GW, while extrusion had much increasing impact on reducing sugar content in extruded samples. Specific mechanical energy during extrusion was reduced as feed moisture content increased from 20 to 30%. Higher extruder screw speed (350 rpm) led to better expansion ratio at low moisture content (20%) as compared to low screw speed (200 rpm). Extrusion significantly increased the starch digestibility but decreased the protein digestibility in extrudates. Tortilla made from 100% WW had about the same physical characteristics, namely color and rollability, with tortilla made from 85% WW with 15% GW, 85% WW with 15% extruded whole wheat (EW), and 85% WW with 15% EGW. Tortilla made from 85% WW with 15% GW showed the largest diameter, thinnest thickness and least extensibility. A 15% extruded germinated wheat (350 rpm) addition in 85% WW showed significant increase of γ-aminobutyric acid content in tortilla compared to the control (100% WW).

Effect of Carboxylmethyl Cellulose Coating and Osmotic Dehydration on Freeze Drying Kinetics of Apple Slices.

The effect of different concentrations of sugar solution (hypertonic) (30%, 45% and 60% w/v) and carboxyl methyl cellulose (CMC) (0%, 1% and 2% w/v) coating on freeze drying of apple slices was studied. In total, nine treatments with respect to concentrations of hypertonic solution and coating layer were prepared to analyze their influence on the physical and chemical properties of freeze dried apple slices. It was observed that increase in the sugar solution concentration, decreased the moisture content of the apple slices significantly impacting its water activity, texture and sugar gain. Application of different concentrations of CMC coating had no significant effect on the properties of dried apple slices. A significant change was observed for color of CMC coated freeze dried apple slices pretreated with 60% sugar solution. Drying kinetics of pretreated apple slices were fitted by using two drying models, Newton's and Page's. Page's model showed higher R-square and lower root mean square error (RSME) compared to Newton's model.