Medicinal plants have incredibly high economic value, and a practical evaluation of their quality is the key to promoting industry development. The deep learning model based on residual convolutional neural network (ResNet) has the advantage of automatic extraction and the recognition of Fourier transform near-infrared spectroscopy (FT-NIR) features. Models are difficult to understand and interpret because of unknown working mechanisms and decision-making processes. Therefore, in this study, artificial feature extraction methods combine traditional partial least squares discriminant analysis (PLS-DA) and support vector machine (SVM) models to understand and compare deep learning models. The results show that the ResNet model has significant advantages over traditional models in feature extraction and recognition. Secondly, preprocessing has a great impact on the feature extraction and feature extraction, and is beneficial for improving model performance. Competitive adaptive reweighted sampling (CARS) and variable importance in projection (VIP) methods screen out more feature variables after preprocessing, but the number of potential variables (LVs) and successive projections algorithm (SPA) methods obtained is fewer. The SPA method only extracts two variables after preprocessing, causing vital information to be lost. The VIP feature of traditional modelling yields the best results among the four methods. After spectral preprocessing, the recognition rates of the PLS-DA and SVM models are up to 90.16% and 88.52%. For the ResNet model, preprocessing is beneficial for extracting and identifying spectral image features. The ResNet model based on synchronous two-dimensional correlation spectra has a recognition accuracy of 100%. This research is beneficial to the application development of the ResNet model in foods, spices, and medicinal plants.

Orchids are significant ornamental plants whose viral infection results in substantial economic damage. Cymbidium mosaic virus (CymMV), Odontoglossum ringspot virus (ORSV), and Cymbidium ringspot virus (CymRSV) represent three important and prevalent orchid viruses. The detection system proposed in this study uses a triplex TaqMan quantitative real-time PCR assay to identify CymMV, ORSV, and CymRSV in a simultaneous manner. We designed specific primers and probes for CymMV, ORSV, and CymRSV, with amplified sequences of 156 bp, 148 bp, and 145 bp, respectively. The minimum detection limit of the triplex qRT-PCR assay for CymMV and CymRSV was 1 copy/assay, and the minimum detection limit was 10 copies/assay for ORSV. The minimum stable detection limits for CymMV, ORSV, and CymRSV were 10, 10², and 10² copies/assay, respectively. Therefore, this system exhibited higher sensitivity (approximately 10 to 10⁴-fold) than RT–PCR. The intra-and interassay CVs of Cq values are less than 0.55 and 0.95%, respectively, indicating that the triplex assay is highly reliable and accurate. In addition, 66 samples from five different orchid genera were analyzed using the established assay and gene chip. The detection results demonstrated that the triplex probe qRT–PCR demonstrated higher sensitivity than the gene chip, indicating that the triplex real-time PCR assay could be used for the detection of field samples. Our findings suggest that the triplex real-time RT–PCR detection system represents a rapid, simple, and accurate tool for detecting CymMV, ORSV, and CymRSV on orchids.

Cymbidium mosaic virus (CymMV) and Odontoglossum ringspot virus (ORSV) are among the world’s most serious and widespread orchid viruses; they often infect orchids, causing devastating losses to the orchid industry. Therefore, it is critical to establish a method that can rapidly and accurately detect viruses in the field using simple instruments, which will largely reduce the further spread of viruses and improve the quality of the orchid industry and is suitable for mass promotion and application at grassroots agrotechnical service points. In this investigation, we established a rapid amplification method for virus detection at 39 °C for 35 min to detect the presence of CymMV and ORSV simultaneously, sensitively, and specifically in orchids. Primers for the capsid protein (CP)-encoding genes of both viruses were designed and screened, and the reaction conditions were optimized. The experimental amplification process was completed in just 35 min at 39 °C. There were no instances of nonspecific amplification observed when nine other viruses were present. The RPA approach had detection limits of 10⁴ and 10³ copies for pMD19T-CymMV and pMD19T-ORSV, respectively. Moreover, the duplex RT-RPA investigation confirmed sensitivity and accuracy via a comparison of detection results from 20 field samples with those of a gene chip. This study presents a precise and reliable detection method for CymMV and ORSV using RT-RPA. The results demonstrate the potential of this method for rapid virus detection. It is evident that this method could have practical applications in virus detection processes.