Markov Transition Field Combined with Convolutional Neural Network Improved the Predictive Performance of Near-Infrared Spectroscopy Models for Determination of Aflatoxin B1 in Maize

Discrimination of New and Aged Seeds Based on On-Line Near-Infrared Spectroscopy Technology Combined with Machine Learning

The harvest year of maize seeds has a significant impact on seed vitality and maize yield. Therefore, it is vital to identify new seeds. In this study, an on-line near-infrared (NIR) spectra collection device (899-1715 nm) was designed and employed for distinguishing maize seeds harvested in different years. Compared with least squares support vector machine (LS-SVM), k-nearest neighbor (KNN), and extreme learning machine (ELM), the partial least squares discriminant analysis (PLS-DA) model has the optimal recognition performance for maize seed harvest years. Six different preprocessing methods, including Savitzky-Golay smoothing (SGS), standard normal variate transformation (SNV), multiplicative scatter correction (MSC), Savitzky-Golay 1 derivative (SG-D1), Savitzky-Golay 2 derivative (SG-D2), and normalization (Norm), were used to improve the quality of the spectra. The Monte Carlo cross-validation uninformative variable elimination (MC-UVE), competitive adaptive reweighted sampling (CARS), bootstrapping soft shrinkage (BOSS), successive projections algorithm (SPA), and their combinations were used to obtain effective wavelengths and decrease spectral dimensionality. The MC-UVE-BOSS-PLS-DA model achieved the classification with an accuracy of 88.75% using 93 features based on Norm preprocessed spectral data. This study showed that the self-designed NIR collection system could be used to identify the harvested years of maize seed.

Research on detection of potato varieties based on spectral imaging analytical algorithm

Potatoes are popular among consumers due to their high yield and delicious taste. However, due to the numerous varieties of potatoes, different varieties are suitable for different processing methods. Therefore, it is necessary to distinguish varieties after harvest to meet the needs of processing enterprises and consumers. In this study, a new visible-near-infrared spectroscopic analysis method was proposed, which can achieve detection of five potato varieties. The method measures the transmission and reflection spectra of potatoes using a spectral acquisition system, encodes one-dimensional spectra into two-dimensional images using Gramian Angular Summation Field (GASF), Gramian Angular Difference Field (GADF), Markov Transition Field (MTF) and Recurrence Plot (RP), and improves the coordinated attention mechanism module and embeds the improved module into the ConvNeXt V2 model to build the ConvNeXt V2-CAP model for potato variety classification. The results show that compared with directly using one-dimensional classification models, image encoding of spectral data for classification greatly improves the accuracy. Among them, the best accuracy of 99.54% is achieved by using GADF image encoding of transmission spectra combined with the ConvNeXt V2-CAP model for classification, which is 16.28% higher than the highest accuracy of the one-dimensional classification model. The CAP attention mechanism module improves the performance of the model, especially when the dataset is small. When the training set is reduced to 150 images, the accuracy of the model is improved by 2.33% compared to the original model. Therefore, it is feasible to classify potato varieties using visible-near infrared spectroscopy and image encoding technology.

Combining AI Tools with Non-Destructive Technologies for Crop-Based Food Safety: A Comprehensive Review

On a global scale, food safety and security aspects entail consideration throughout the farm-to-fork continuum, considering food's supply chain. Generally, the agrifood system is a multiplex network of interconnected features and processes, with a hard predictive rate, where maintaining the food's safety is an indispensable element and is part of the Sustainable Development Goals (SDGs). It has led the scientific community to develop advanced applied analytical methods, such as machine learning (ML) and deep learning (DL) techniques applied for assessing foodborne diseases. The main objective of this paper is to contribute to the development of the consensus version of ongoing research about the application of Artificial Intelligence (AI) tools in the domain of food-crop safety from an analytical point of view. Writing a comprehensive review for a more specific topic can also be challenging, especially when searching within the literature. To our knowledge, this review is the first to address this issue. This work consisted of conducting a unique and exhaustive study of the literature, using our TriScope Keywords-based Synthesis methodology. All available literature related to our topic was investigated according to our criteria of inclusion and exclusion. The final count of data papers was subject to deep reading and analysis to extract the necessary information to answer our research questions. Although many studies have been conducted, limited attention has been paid to outlining the applications of AI tools combined with analytical strategies for crop-based food safety specifically.

Classification of Food Additives Using UV Spectroscopy and One-Dimensional Convolutional Neural Network

Food additives are utilized in countless food products available for sale. They enhance or obtain a specific flavor, extend the storage time, or obtain a desired texture. This paper presents an automatic classification system for five food additives based on their absorbance in the ultraviolet domain. Solutions with different concentrations were created by dissolving a measured additive mass into distilled water. The analyzed samples were either simple (one additive solution) or mixed (two additive solutions). The substances presented absorbance peaks between 190 nm and 360 nm. Each substance presents a certain number of absorbance peaks at specific wavelengths (e.g., acesulfame potassium presents an absorbance peak at 226 nm, whereas the peak associated with potassium sorbate is at 254 nm). Therefore, each additive has a distinctive spectrum that can be used for classification. The sample classification was performed using deep learning techniques. The samples were associated with numerical labels and divided into three datasets (training, validation, and testing). The best classification results were obtained using CNN (convolutional neural network) models. The classification of the 404 spectra with a CNN model with three convolutional layers obtained a mean testing accuracy of 92.38% ± 1.48%, whereas the mean validation accuracy was 93.43% ± 2.01%.

Handheld Fluorescence Spectrometer Enabling Sensitive Aflatoxin Detection in Maize

Aflatoxins are among the main carcinogens threatening food and feed safety while imposing major detection challenges to the agrifood industry. Today, aflatoxins are typically detected using destructive and sample-based chemical analysis that are not optimally suited to sense their local presence in the food chain. Therefore, we pursued the development of a non-destructive optical sensing technique based on fluorescence spectroscopy. We present a novel compact fluorescence sensing unit, comprising both ultraviolet excitation and fluorescence detection in a single handheld device. First, the sensing unit was benchmarked against a validated research-grade fluorescence setup and demonstrated high sensitivity by spectrally separating contaminated maize powder samples with aflatoxin concentrations of 6.6 µg/kg and 11.6 µg/kg. Next, we successfully classified a batch of naturally contaminated maize kernels within three subsamples showing a total aflatoxin concentration of 0 µg/kg, 0.6 µg/kg and 1647.8 µg/kg. Consequently, our novel sensing methodology presents good sensitivity and high potential for integration along the food chain, paving the way toward improved food safety.