Simultaneous determination of pigments of spinach (Spinacia oleracea L.) leaf for quality inspection using hyperspectral imaging and multi-task deep learning regression approaches.

Rapid and accurate determination of pigment content is important for quality inspection of spinach leaves during storage. This study aimed to use hyperspectral imaging at two spectral ranges (visible/near-infrared, VNIR: 400-1000 nm; NIR: 900-1700 nm) to simultaneously determine the pigment (chlorophyll a, chlorophyll b, total chlorophyll, and carotenoids) content in spinach stored at different durations and conditions (unpackaged and packaged). Partial least squares (PLS), back propagation neural network (BPNN) and convolutional neural network (CNN) were used to establish single-task and multi-task regression models. Single-task CNN (STCNN) models and multi-task CNN (MTCNN) models obtained better performances than the other models. The models using VNIR spectra were superior to those using NIR spectra. The overall results indicated that hyperspectral imaging with multi-task learning could predict the quality attributes of spinach simultaneously for spinach quality inspection under various storage conditions. This research will guide food quality inspection by simultaneously inspecting multiple quality attributes.

Detection of peach soluble solids based on near-infrared spectroscopy with High Order Spatial Interaction network.

BACKGROUND: Due to the scalability of deep learning technology, researchers have applied it to the non-destructive testing of peach internal quality. In addition, the soluble solids content (SSC) is an important internal quality indicator that determines the quality of peaches. Peaches with high SSC have a sweeter taste and better texture, making them popular in the market. Therefore, SSC is an important indicator for measuring peach internal quality and making harvesting decisions. RESULTS: This article presents the High Order Spatial Interaction Network (HOSINet), which combines the Position Attention Module (PAM) and Channel Attention Module (CAM). Additionally, a feature wavelength selection algorithm similar to the Group-based Clustering Subspace Representation (GCSR-C) is used to establish the Position and Channel Attention Module-High Order Spatial Interaction (PC-HOSI) model for peach SSC prediction. The accuracy of this model is compared with traditional machine learning and traditional deep learning models. Finally, the permutation algorithm is combined with deep learning models to visually evaluate the importance of feature wavelengths. Increasing the order of the PC-HOSI model enhances its ability to learn spatial correlations in the dataset, thus improving its predictive performance. CONCLUSION: The optimal model, PC-HOSI model, performed well with an order of 3 (PC-HOSI-3), with a root mean square error of 0.421 °Brix and a coefficient of determination of 0.864. Compared with traditional machine learning and deep learning algorithms, the coefficient of determination for the prediction set was improved by 0.07 and 0.39, respectively. The permutation algorithm also provided interpretability analysis for the predictions of the deep learning model, offering insights into the importance of spectral bands. These results contribute to the accurate prediction of SSC in peaches and support research on interpretability of neural network models for prediction. © 2024 Society of Chemical Industry.

Hyperspectral Imaging Using a Convolutional Neural Network with Transformer for the Soluble Solid Content and pH Prediction of Cherry Tomatoes.

Cherry tomatoes are cultivated worldwide and favored by consumers of different ages. The soluble solid content (SSC) and pH are two of the most important quality attributes of cherry tomatoes. The rapid and non-destructive measurement of the SSC and pH of cherry tomatoes is of great significance to their production and consumption. In this research, hyperspectral imaging combined with a convolutional neural network with Transformer (CNN-Transformer) was utilized to analyze the SSC and pH of cherry tomatoes. Conventional machine learning and deep learning models were established for the determination of the SSC and pH. The findings demonstrated that CNN-Transformer yielded outstanding results in predicting the SSC, with the coefficient of determination of calibration (R2C), validation (R2V), and prediction (R2P) for the SSC being 0.83, 0.87, and 0.83, respectively. Relatively worse results were obtained for the pH value prediction, with R2C, R2V, and R2P values of 0.74, 0.68, and 0.60, respectively. Furthermore, the visualization of the CNN-Transformer model revealed the wavelength weight distributions, indicating that the 1380-1650 nm range served as the characteristic band for the SSC, while the spectral range at 945-1280 nm was the characteristic band for pH. In conclusion, integrating spectral information features with the attention mechanism of Transformer through a convolutional neural network can enhance the accuracy of predicting the SSC and pH for cherry tomatoes.

Rice seed vigor detection based on near-infrared hyperspectral imaging and deep transfer learning.

Vigor is one of the important factors that affects rice yield and quality. Rapid and accurate detection of rice seed vigor is of great importance for rice production. In this study, near-infrared hyperspectral imaging technique and transfer learning were combined to detect rice seed vigor. Four varieties of artificial-aged rice seeds (Yongyou12, Yongyou1540, Suxiangjing100, and Longjingyou1212) were studied. Different convolutional neural network (CNN) models were built to detect the vigor of the rice seeds. Two transfer strategies, fine-tuning and MixStyle, were used to transfer knowledge among different rice varieties for vigor detection. The experimental results showed that the convolutional neural network model of Yongyou12 classified the vigor of Yongyou1540, Suxiangjing100, and Longjingyou1212 through MixStyle transfer knowledge, and the accuracy reached 90.00%, 80.33%, and 85.00% in validation sets, respectively, which was better or close to the initial modeling performances of each variety. MixStyle statistics are based on probabilistic mixed instance-level features of cross-source domain training samples. When training instances, new domains can be synthesized, which increases the domain diversity of the source domain, thereby improving the generalization ability of the trained model. This study would help rapid and accurate detection of a large varieties of crop seeds.

A study of auxiliary screening for Alzheimer's disease based on handwriting characteristics.

Background and objectives: Alzheimer's disease (AD) has an insidious onset, the early stages are easily overlooked, and there are no reliable, rapid, and inexpensive ancillary detection methods. This study analyzes the differences in handwriting kinematic characteristics between AD patients and normal elderly people to model handwriting characteristics. The aim is to investigate whether handwriting analysis has a promising future in AD auxiliary screening or even auxiliary diagnosis and to provide a basis for developing a handwriting-based diagnostic tool. Materials and methods: Thirty-four AD patients (15 males, 77.15 ± 1.796 years) and 45 healthy controls (20 males, 74.78 ± 2.193 years) were recruited. Participants performed four writing tasks with digital dot-matrix pens which simultaneously captured their handwriting as they wrote. The writing tasks consisted of two graphics tasks and two textual tasks. The two graphics tasks are connecting fixed dots (task 1) and copying intersecting pentagons (task 2), and the two textual tasks are dictating three words (task 3) and copying a sentence (task 4). The data were analyzed by using Student's t-test and Mann-Whitney U test to obtain statistically significant handwriting characteristics. Moreover, seven classification algorithms, such as eXtreme Gradient Boosting (XGB) and Logistic Regression (LR) were used to build classification models. Finally, the Receiver Operating Characteristic (ROC) curve, accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and Area Under Curve (AUC) were used to assess whether writing scores and kinematics parameters are diagnostic. Results: Kinematic analysis showed statistically significant differences between the AD and controlled groups for most parameters (p < 0.05, p < 0.01). The results found that patients with AD showed slower writing speed, tremendous writing pressure, and poorer writing stability. We built statistically significant features into a classification model, among which the model built by XGB was the most effective with a maximum accuracy of 96.55%. The handwriting characteristics also achieved good diagnostic value in the ROC analysis. Task 2 had a better classification effect than task 1. ROC curve analysis showed that the best threshold value was 0.084, accuracy = 96.30%, sensitivity = 100%, specificity = 93.41%, PPV = 92.21%, NPV = 100%, and AUC = 0.991. Task 4 had a better classification effect than task 3. ROC curve analysis showed that the best threshold value was 0.597, accuracy = 96.55%, sensitivity = 94.20%, specificity = 98.37%, PPV = 97.81%, NPV = 95.63%, and AUC = 0.994. Conclusion: This study's results prove that handwriting characteristic analysis is promising in auxiliary AD screening or AD diagnosis.

Identification of geographical origins of Radix Paeoniae Alba using hyperspectral imaging with deep learning-based fusion approaches.

The Radix Paeoniae Alba (Baishao) is a traditional Chinese medicine (TCM) with numerous clinical and nutritional benefits. Rapid and accurate identification of the geographical origins of Baishao is crucial for planters, traders and consumers. Hyperspectral imaging (HSI) was used in this study to acquire spectral images of Baishao samples from its two sides. Convolutional neural network (CNN) and attention mechanism was used to distinguish the origins of Baishao using spectra extracted from one side. The data-level and feature-level deep fusion models were proposed using information from both sides of the samples. CNN models outperformed the conventional machine learning methods in classifying Baishao origins. The generalized Gradient-weighted Class Activation Mapping (Grad-CAM++) was utilized to visualize and identify important wavelengths that significantly contribute to model performance. The overall results illustrated that HSI combined with deep learning strategies was effective in identifying the geographical origins of Baishao, having good prospects of real-world applications.

Hyperspectral Imaging with Machine Learning Approaches for Assessing Soluble Solids Content of Tribute Citru.

Tribute Citru is a natural citrus hybrid with plenty of vitamins and nutrients. Fruits' soluble solids content (SSC) is a critical quality index. This study used hyperspectral imaging at two spectral ranges (400-1000 nm and 900-1700 nm) to determine SSC in Tribute Citru. Partial least squares regression (PLSR) and support vector regression (SVR) models were established in order to determine SSC using the spectral information of the calyx and blossom ends. The average spectra of both ends as well as their fusion was studied. The successive projections algorithm (SPA) and the correlation coefficient analysis (CCA) were used to examine the differences in characteristic wavelengths between the two ends. Most models achieved performances with the correlation coefficient of the training, validation, and testing sets over 0.6. Results showed that differences in the performances among the models using the one-sided and two-sided spectral information. No particular regulation could be found for the differences in model performances and characteristic wavelengths. The results illustrated that the sampling side was an influencing factor but not the determinant factor for SSC determination. These results would help with the development of real-world applications for citrus quality inspection without concerning the sampling sides and the spectral ranges.

Application of Visible/Near-Infrared Spectroscopy and Hyperspectral Imaging with Machine Learning for High-Throughput Plant Heavy Metal Stress Phenotyping: A Review.

Heavy metal pollution is becoming a prominent stress on plants. Plants contaminated with heavy metals undergo changes in external morphology and internal structure, and heavy metals can accumulate through the food chain, threatening human health. Detecting heavy metal stress on plants quickly, accurately, and nondestructively helps to achieve precise management of plant growth status and accelerate the breeding of heavy metal-resistant plant varieties. Traditional chemical reagent-based detection methods are laborious, destructive, time-consuming, and costly. The internal and external structures of plants can be altered by heavy metal contamination, which can lead to changes in plants' absorption and reflection of light. Visible/near-infrared (V/NIR) spectroscopy can obtain plant spectral information, and hyperspectral imaging (HSI) can obtain spectral and spatial information in simple, speedy, and nondestructive ways. These 2 technologies have been the most widely used high-throughput phenotyping technologies of plants. This review summarizes the application of V/NIR spectroscopy and HSI in plant heavy metal stress phenotype analysis as well as introduces the method of combining spectroscopy with machine learning approaches for high-throughput phenotyping of plant heavy metal stress, including unstressed and stressed identification, stress types identification, stress degrees identification, and heavy metal content estimation. The vegetation indexes, full-range spectra, and feature bands identified by different plant heavy metal stress phenotyping methods are reviewed. The advantages, limitations, challenges, and prospects of V/NIR spectroscopy and HSI for plant heavy metal stress phenotyping are discussed. Further studies are needed to promote the research and application of V/NIR spectroscopy and HSI for plant heavy metal stress phenotyping.

Identification of Rice Seed Varieties Based on Near-Infrared Hyperspectral Imaging Technology Combined with Deep Learning.

Rice is one of the most important food crops in the world, and rice seed varieties are related to the yield and quality of rice. This study used near-infrared (NIR) hyperspectral technology with conventional machine learning methods (support vector machine (SVM), logistic regression (LR), and random forest (RF)) and deep learning methods (LeNet, GoogLeNet, and residual network (ResNet)) to establish variety identification models for five common types of rice seeds. Among the deep learning methods, the classification accuracies of most models were higher than 95%. This study further used the deep learning methods to establish variety identification models for 10 varieties of rice seeds without considering their types. Among them, the ResNet model had the best classification results. The classification accuracy on the test set was 86.08%. This study used the saliency map method to visualize each convolutional neural network (CNN) model to find the band region that contributed the most to the data. The results showed that the bands with the largest data contribution were mainly concentrated at approximately 1300-1400 nm and secondarily concentrated at approximately 1050-1250 nm. The overall results showed that NIR hyperspectral imaging technology combined with deep learning could effectively distinguish rice seeds of different varieties. This method provided an effective way to identify rice seed varieties in a quick and nondestructive manner.

Wood recognition using image texture features.

Inspired by theories of higher local order autocorrelation (HLAC), this paper presents a simple, novel, yet very powerful approach for wood recognition. The method is suitable for wood database applications, which are of great importance in wood related industries and administrations. At the feature extraction stage, a set of features is extracted from Mask Matching Image (MMI). The MMI features preserve the mask matching information gathered from the HLAC methods. The texture information in the image can then be accurately extracted from the statistical and geometrical features. In particular, richer information and enhanced discriminative power is achieved through the length histogram, a new histogram that embodies the width and height histograms. The performance of the proposed approach is compared to the state-of-the-art HLAC approaches using the wood stereogram dataset ZAFU WS 24. By conducting extensive experiments on ZAFU WS 24, we show that our approach significantly improves the classification accuracy.