RESUMEN
Long-staple cotton from Xinjiang is renowned for its exceptional quality. However, it is susceptible to contamination with plastic film during mechanical picking. To address the issue of tricky removal of film in seed cotton, a technique based on hyperspectral images and AlexNet-PCA is proposed to identify the colorless and transparent film of the seed cotton. The method consists of black and white correction of hyperspectral images, dimensionality reduction of hyperspectral data, and training and testing of convolutional neural network (CNN) models. The key technique is to find the optimal way to reduce the dimensionality of the hyperspectral data, thus reducing the computational cost. The biggest innovation of the paper is the combination of CNNs and dimensionality reduction methods to achieve high-precision intelligent recognition of transparent plastic films. Experiments with three dimensionality reduction methods and three CNN architectures are conducted to seek the optimal model for plastic film recognition. The results demonstrate that AlexNet-PCA-12 achieves the highest recognition accuracy and cost performance in dimensionality reduction. In the practical application sorting tests, the method proposed in this paper achieved a 97.02% removal rate of plastic film, which provides a modern theoretical model and effective method for high-precision identification of heteropolymers in seed cotton.
RESUMEN
OBJECTIVE: To investigate the effect of CD86 gene modified recipient dendritic cell (DC) on mix cultured donor-derived islet with recipient-derived lymphocyte in vitro. METHODS: DCs were separated from bone marrow of BALB/c mice and identified by flow cytometry. Chemically synthesized CD86 siRNA was transferred into DC. Donor islets were separated from the pancreas of SD rats. Acridine orange (AO)/Propidium iodide (PI) staining was conducted to assess the viability of islets. Lymphocytes were collected from the spleen of SD rats and then co-cultured with CD86 gene modified recipient DCs. CD86 gene modified recipient DC, donor-derived islet (400 IEQ) and recipient-derived lymphocyte (1 x 10(6)) were mix cultured in vitro. Four groups were set: blank group (islets of SD rat only), control 1 group (islets of SD rat with splenic lymphocyte of BALB/c mice) , control 2 group (islets of SD rat, splenic lymphocyte of BALB/c mice with normal recipient DC) and experimental group (islets of rat, splenic lymphocyte of BALB/c mice with CD86 gene modified recipient DC). After 3 days culture, the cellular morphology of culture was observed with light inverted microscope. The levels of IL-2, IL-4, IL-10 and IFN-γ in the culture supernatant were tested, and islets viability was assessed by AO/PI staining. GSIS was conducted and stimulation index (SD was calculated. RESULTS: Typical DC morphology was found from the collected cells. The positive rates of CD1lc, CD80 and CD86 protein expression on DCs were 86.26% ± 9.73%, 72.64% ± 8.55% and 77.18% ± 10.23%, respectively. The positive rate of CD86 protein expression on DCs after transfection was 23.64% ± 5.25%. The viability of islets was over 95%. After 3 days culture, the level of IL-10 increased significantly and the levels of IL-2 and INF-γ decreased significantly in experimental group (vs. control 1 and control 2 groups, P < 0.05). The level of IL-4 was similar in control 1, control 2 and experimental groups, but the proliferation rate of lymphocyte in the experimental group was the lowest one, the viability of islets in the experimental group was the best and the SI was the highest. The levels of IL-2, IL-4, IL-10 and IFN-γ in the experimental group were higher than those in the blank group. CONCLUSION: CD86 gene modified recipient DC loaded with donor-derived antigen could protect the islet function in vitro to some extent.