Application and interpretation of deep learning methods for the geographical origin identification of Radix Glycyrrhizae using hyperspectral imaging

Rapid identification of medicinal plants via visual feature-based deep learning

BACKGROUND

Traditional Chinese Medicinal Plants (CMPs) hold a significant and core status for the healthcare system and cultural heritage in China. It has been practiced and refined with a history of exceeding thousands of years for health-protective affection and clinical treatment in China. It plays an indispensable role in the traditional health landscape and modern medical care. It is important to accurately identify CMPs for avoiding the affected clinical safety and medication efficacy by the different processed conditions and cultivation environment confusion.

RESULTS

In this study, we utilize a self-developed device to obtain high-resolution data. Furthermore, we constructed a visual multi-varieties CMPs image dataset. Firstly, a random local data enhancement preprocessing method is proposed to enrich the feature representation for imbalanced data by random cropping and random shadowing. Then, a novel hybrid supervised pre-training network is proposed to expand the integration of global features within Masked Autoencoders (MAE) by incorporating a parallel classification branch. It can effectively enhance the feature capture capabilities by integrating global features and local details. Besides, the newly designed losses are proposed to strengthen the training efficiency and improve the learning capacity, based on reconstruction loss and classification loss.

CONCLUSIONS

Extensive experiments are performed on our dataset as well as the public dataset. Experimental results demonstrate that our method achieves the best performance among the state-of-the-art methods, highlighting the advantages of efficient implementation of plant technology and having good prospects for real-world applications.

Hyperspectral discrimination of ginseng variety and age from Changbai Mountain area

BACKGROUND

The efficacy and market value of Panax ginseng Meyer are significantly influenced by its diversity and age. Traditional identification methods are prone to subjective biases and necessitate the use of destructive sample processing, leading to the loss and wastage of ginseng. Consequently, non-destructive in-situ identification has emerged as a crucial subject of interest for both researchers and the ginseng industry. The advancement of technology and the expansion of research have introduced spectral technology and image processing technology as novel approaches and concepts for non-destructive in-situ identification.

METHODS

Hyperspectral imaging (HSI) is a methodology that combines conventional spectroscopy and imaging to acquire comprehensive spectral and spatial data from various samples. In this study, we investigated the use of Support Vector Machine (SVM) and Spectral Angle Mapper (SAM) classifier algorithms, in conjunction with HSI classification technology, for quasi-Artificial Intelligence (quasi-AI) ginseng identification. To enhance the hyperspectral images prior to SVM classification, we compared the efficacy of Principal Component Analysis (PCA), Minimum Noise Fraction (MNF), and Independent Component Analysis (ICA).

RESULTS

The classification of ginseng based on age was accomplished through the utilization of Radial Basis Function (RBF) kernel SVM and SAM algorithm, which was trained on feature enhanced images. The classification of WMG, MCG, and GG is primarily based on age, with the endmember spectrum serving as the foundation for SAM and SVM.

CONCLUSION

The "endmember spectrum set" derived from the classification outcomes can serve as the "mutation point" for identifying ginseng of different ages.

Screening the phytotoxicity of micro/nanoplastics through non-targeted metallomics with synchrotron radiation X-ray fluorescence and deep learning: Taking micro/nano polyethylene terephthalate as an example

Microplastics (MPs) and nanoplastics (NPs) are global pollutants with emerging concerns. Methods to predict and screen their toxicity are crucial. Elemental dyshomeostasis can be used to assess toxicity of environmental pollutants. Non-targeted metallomics, combining synchrotron radiation X-ray fluorescence (SRXRF) and machine learning, has successfully differentiated cancer patients from healthy individuals. The whole idea of this work is to screen the phytotoxicity of nano polyethylene terephthalate (nPET) and micro polyethylene terephthalate (mPET) through non-targeted metallomics with SRXRF and deep learning algorithms. Firstly, Seed germination, seedling growth, photosynthetic changes, and antioxidant activity were used to evaluate the toxicity of mPET and nPET. It was showed that nPET, at 10 mg/L, was more toxic to rice seedlings, inhibiting growth and impairing chlorophyll content, MDA content, and SOD activity compared to mPET. Then, rice seedling leaves exposed to nPET or mPET was examined with SRXRF, and the SRXRF data was differentiated with deep learning algorithms. It was showed that the one-dimensional convolutional neural network (1D-CNN) model achieved 98.99% accuracy without data preprocessing in screening mPET and nPET exposure. In all, non-targeted metallomics with SRXRF and 1D-CNN can effectively screen the exposure and phytotoxicity of nPET/mPET and potentially other emerging pollutants. Further research is needed to assess the phytotoxicity of different types of MPs/NPs using non-targeted metallomics.

Prediction performance and reliability evaluation of three ginsenosides in Panax ginseng using hyperspectral imaging combined with a novel ensemble chemometric model

Panax ginseng C. A. Meyer (PG) is a health-promoting food, and its ginsenosides (Rb1, Rg1, Re) content, as the quality indicator, is affected by the planting modes (garden or forest ginsengs) and years. Effective prediction of this content remains to be investigated. In this study, hyperspectral (HSI) combined with ensemble model (CGRU-GPR) including the convolutional neural network (CNN), gate recurrent unit (GRU), and Gaussian process regression (GPR) realized a comprehensive evaluation of the prediction performance and predictive uncertainty. With effective wavelengths, the proposed CGRU-GPR model improved operation efficiency and obtained satisfactory prediction results with relative percent deviation (RPD) values all higher than 2.70 in three ginsenosides. Meanwhile, the interval prediction with a high prediction interval coverage probability (PICP) of 0.97 - 1.0 and a low mean width percentage (MWP) of 0.7 - 1.66 indicated a low prediction uncertainty. This study provides a rapid and reliable method for predicting ginsenosides contents in PG.

Identification of Turtle-Shell Growth Year Using Hyperspectral Imaging Combined with an Enhanced Spatial-Spectral Attention 3DCNN and a Transformer

Turtle shell (Chinemys reecesii) is a prized traditional Chinese dietary therapy, and the growth year of turtle shell has a significant impact on its quality attributes. In this study, a hyperspectral imaging (HSI) technique combined with a proposed deep learning (DL) network algorithm was investigated for the objective determination of the growth year of turtle shells. The acquisition of hyperspectral images was carried out in the near-infrared range (948.72-2512.97 nm) from samples spanning five different growth years. To fully exploit the spatial and spectral information while reducing redundancy in hyperspectral data simultaneously, three modules were developed. First, the spectral-spatial attention (SSA) module was developed to better protect the spectral correlation among spectral bands and capture fine-grained spatial information of hyperspectral images. Second, the 3D convolutional neural network (CNN), more suitable for the extracted 3D feature map, was employed to facilitate the joint spatial-spectral feature representation. Thirdly, to overcome the constraints of convolution kernels as well as better capture long-range correlation between spectral bands, the transformer encoder (TE) module was further designed. These modules were harmoniously orchestrated, driven by the need to effectively leverage both spatial and spectral information within hyperspectral data. They collectively enhance the model's capacity to extract joint spatial and spectral features to discern growth years accurately. Experimental studies demonstrated that the proposed model (named SSA-3DTE) achieved superior classification accuracy, with 98.94% on average for five-category classification, outperforming traditional machine learning methods using only spectral information and representative deep learning methods. Also, ablation experiments confirmed the effectiveness of each module to improve performance. The encouraging results of this study revealed the potentiality of HSI combined with the DL algorithm as an efficient and non-destructive method for the quality control of turtle shells.

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.

Rapidly detecting fennel origin of the near-infrared spectroscopy based on extreme learning machine

Fennel contains many antioxidant and antibacterial substances, and it has very important applications in food flavoring and other fields. The kinds and contents of chemical substances in fennel vary from region to region, which can affect the taste and efficacy of the fennel and its derivatives. Therefore, it is of great significance to accurately classify the origin of the fennel. Recently, origin detection methods based on deep networks have shown promising results. However, the existing methods spend a relatively large time cost, a drawback that is fatal for large amounts of data in practical application scenarios. To overcome this limitation, we explore an origin detection method that guarantees faster detection with classification accuracy. This research is the first to use the machine learning algorithm combined with the Fourier transform-near infrared (FT-NIR) spectroscopy to realize the classification and identification of the origin of the fennel. In this experiment, we used Rubberband baseline correction on the FT-NIR spectral data of fennel (Yumen, Gansu and Turpan, Xinjiang), using principal component analysis (PCA) for data dimensionality reduction, and selecting extreme learning machine (ELM), Convolutional Neural Network (CNN), recurrent neural network (RNN), Transformer, generative adversarial networks (GAN) and back propagation neural network (BPNN) classification model of the company realizes the classification of the sample origin. The experimental results show that the classification accuracy of ELM, RNN, Transformer, GAN and BPNN models are above 96%, and the ELM model using the hardlim as the activation function has the best classification effect, with an average accuracy of 100% and a fast classification speed. The average time of 30 experiments is 0.05 s. This research shows the potential of the machine learning algorithm combined with the FT-NIR spectra in the field of food production area classification, and provides an effective means for realizing rapid detection of the food production area, so as to merchants from selling shoddy products as good ones and seeking illegal profits.

End-to-End Fusion of Hyperspectral and Chlorophyll Fluorescence Imaging to Identify Rice Stresses

Herbicides and heavy metals are hazardous substances of environmental pollution, resulting in plant stress and harming humans and animals. Identification of stress types can help trace stress sources, manage plant growth, and improve stress-resistant breeding. In this research, hyperspectral imaging (HSI) and chlorophyll fluorescence imaging (Chl-FI) were adopted to identify the rice plants under two types of herbicide stresses (butachlor (DCA) and quinclorac (ELK)) and two types of heavy metal stresses (cadmium (Cd) and copper (Cu)). Visible/near-infrared spectra of leaves (L-VIS/NIR) and stems (S-VIS/NIR) extracted from HSI and chlorophyll fluorescence kinetic curves of leaves (L-Chl-FKC) and stems (S-Chl-FKC) extracted from Chl-FI were fused to establish the models to detect the stress of the hazardous substances. Novel end-to-end deep fusion models were proposed for low-level, middle-level, and high-level information fusion to improve identification accuracy. Results showed that the high-level fusion-based convolutional neural network (CNN) models reached the highest detection accuracy (97.7%), outperforming the models using a single data source (<94.7%). Furthermore, the proposed end-to-end deep fusion models required a much simpler training procedure than the conventional two-stage deep learning fusion. This research provided an efficient alternative for plant stress phenotyping, including identifying plant stresses caused by hazardous substances of environmental pollution.

Detection of Pesticide Residue Level in Grape Using Hyperspectral Imaging with Machine Learning

Rapid and accurate detection of pesticide residue levels can help to prevent the harm of pesticide residue. This study used visible/near-infrared (Vis-NIR) (376–1044 nm) and near-infrared (NIR) (915–1699 nm) hyperspectral imaging systems (HISs) to detect the level of pesticide residues. Three different varieties of grapes were sprayed with four levels of pesticides. Logistic regression (LR), support vector machine (SVM), random forest (RF), convolutional neural network (CNN), and residual neural network (ResNet) models were used to build classification models for pesticide residue levels. The saliency maps of CNN and ResNet were conducted to visualize the contribution of wavelengths. Overall, the results of NIR spectra performed better than those of Vis-NIR spectra. For Vis-NIR spectra, the best model was ResNet, with the accuracy of over 93%. For NIR spectra, LR was the best, with the accuracy of over 97%, but SVM, CNN, and ResNet also showed closed and fine results. The saliency map of CNN and ResNet presented similar and closed ranges of crucial wavelengths. Overall results indicated deep learning performed better than conventional machine learning. The study showed that the use of hyperspectral imaging technology combined with machine learning can effectively detect the level of pesticide residues in grapes.