Search

Seaweed has attracted great attention as a healthy and nutritious food. Traditional seaweed processing plants mainly rely on manual visual inspection to identify and remove inferior seaweed. Accurate and rapid harvest period classification and impurity detection are key to improving productivity and processing speed in seaweed processing plants. Although many studies on seaweed have been conducted in laboratory environments, currently, the plants lack effective tools to obtain real-time and reliable information on seaweed quality. To address this challenge, the deep transfer learning-based computer vision was applied to identify inferior seaweeds, including those from the third harvest, fourth harvest, and impure seaweeds in this work. Specifically, YOLOv8 and YOLOv5 were utilized as base transfer learning models. By loading various pre-trained weight files, this study was able to automatically classify Porphyra haitnensis into four categories based on the harvest period and simultaneously detect four types of common impurities in it. Among the tested models, YOLOv8n-cls achieved the best trade-off in classifying the harvest period, with a Top-1 accuracy of 93.5%. This represented a significant improvement of 16% compared to the performance without transfer learning. The detection speed for a single image was 8.2 ms, and the model size was only 2.82 Mb. On the other hand, YOLOv8n exhibited outstanding performance in impurity detection, with a mean average precision of 99.14%, a single image detection speed of 4.3 ms, and a model size of 5.95 Mb. The results demonstrated the potential of YOLOv8 with transfer learning to objectively assist or even replace decision-making by assembly line workers. This study will not only enhance the quality control, production efficiency, and economic benefits of the seaweed processing industry but also drive the automation equipment and systems of seaweed-related enterprises towards greater intelligence and efficiency. [ABSTRACT FROM AUTHOR]

Mathematical models based on infrared spectroscopy and machine learning have been successfully used to trace the origin of soybeans. However, as previous research reported, it is necessary to employ spectra data that undergo multiple pre-processing operations in order to achieve optimal accuracy during model training. And these established models are only capable of predicting samples with identical spectra pre-processing. Specifically, baseline correction, which necessitates individual processing of each spectrum, requiring substantial investments of time and human resources with a large dataset. In this study, the spectra augmentation technique was proposed based on the theory of data augmentation, in order to simplify or even eliminate the pre-processing steps for the prediction dataset. The technique utilized a combination of the standard spectra pre-processed data and the "boost data" to train models, specifically, a total of 180 spectra, including 90 pre-processed standard spectra and 90 "boost" spectra. The "boost" data refers to data without the standard spectra pre-processing. On the prediction dataset without the standard spectra pre-processing, the model with the spectra augmentation technique had an accuracy of 0.91 for the recognition of Northeast China soybeans, while the accuracy of the model with the training method frequently reported in previous studies only reached 0.71, demonstrating that the model trained with the proposed technique possessed higher robustness and generalization capabilities. The spectra augmentation technique can maintain high accuracy while simplifying spectra pre-processing steps on prediction data, therefore, providing a more efficient and expedited method for practical food traceability and authentication. [ABSTRACT FROM AUTHOR]

The quality of seaweed is greatly influenced by its harvest period. Hence, the development of efficient and precise analytical techniques for identifying the harvest period is significant from a practical standpoint. In this study, mid-infrared spectroscopy was utilized to perform quantitative analysis of nutritional components, evaluate the quality grades, and determine the harvest period of Porphyra haitanensis. While the outcomes of one-factor analysis of variance and correlation analysis indicated a general decrease in P. haitanensis quality with each subsequent harvest, the nutritional contents of samples obtained from the first and fifth harvest were similar, suggesting that the harvest period alone could not fully represent the quality of seaweed. To create discriminant models of the harvest period, decision tree, K-nearest neighbor, partial least squares-discriminant analysis, and adaptive boosting algorithms were adopted based on band integral areas and a small sample size (30 per harvest period, 6 periods in total). The adaptive boosting algorithm provided the most comprehensive results with regards to forecast accuracy (96.7%), macro precision (0.971), macro recall (0.965) and RMSE (0.183). The findings demonstrated that band integral areas of the mid-infrared spectroscopy not only provided quantitative information on the nutrients but also offered effective prediction variables for classification algorithms. Thus, the proposed method can serve as an essential instrument to evaluate the seaweed quality swiftly and precisely. [ABSTRACT FROM AUTHOR]

Nuclear magnetic resonance (NMR) spectroscopy, also known as magnetic resonance spectroscopy, is a preeminent and noninvasive analytical technique that provides detailed information about the structure, dynamics, reaction state, and chemical environment of molecules. The development of NMR spectroscopy has led to the awarding of many Nobel Prizes, and today NMR spectroscopy serves as an important and irreplaceable tool in physics and chemistry. Two-dimensional (2D) NMR is effective at separating resonances which have similar chemical shifts, although the interpretation of 2D spectra can be challenging. A systematic density operator-based derivation will aid the understanding of the quantitative mechanism of 2D NMR spectroscopy and the interpreting of outcomes of 2D NMR experiments. Therefore, in this study, we systematically analyzed and compared the quantitative basis of 2D and 1D NMR. Meanwhile, as a proof of principle, simulations using the FID Appliance software toolkit were performed and interpreted using a brain phantom, a popular model for studying brain metabolites. The scheme shown in this paper will facilitate the understanding of quantitative 2D NMR spectroscopic analyses in chemistry and biology. [ABSTRACT FROM AUTHOR]

A correction to this article has been published and is linked from the HTML and PDF versions of this paper. The error has not been fixed in the paper. [ABSTRACT FROM AUTHOR]