- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
Classification of Sugar Beets Based on Hyperspectral and Extreme Learning Machine Methods
摘要： Sugar beet varieties were classified based on hyperspectral technology and the Extreme Learning Machine (ELM) algorithm. The influences of seven pretreatment methods, namely, Savitzky-Golay smoothing (SG), the first derivative (FD) method, SG smoothing combined with the FD method (SG-FD), logarithmic transformation (LT), LT combined with the FD method (LT-FD), the standard normal variate (SNV) method, and SNV combined with the FD method (SNV-FD), on the recognition performance of the ELM model were analyzed to select the best pretreatment method. To simplify the input variables, the standard deviation peak method was used to extract the feature bands for different preprocessed spectral data. The experimental results showed that for different pretreatment methods, the recognition rates of sugar beet varieties by ELM models were all over 80%. Additionally, the combination of different pretreatment methods and FD effectively improved the signal-to-noise ratio and enhanced the accuracy and stability of spectral models. Overall, the recognition accuracy of the ELM models established based on the feature bands was better than that established based on all bands, which suggests that the feature bands extracted by the standard deviation peak method are effective. Based on the SG-FD pretreatment method, the ELM models established using all bands and feature bands both achieved the highest recognition effect. Specifically, the recognition rates of the prediction sets were 93.94% and 95.45%, respectively.
关键词： Standard deviation peak method,ELM,Different pretreatment methods,Sugar beet variety,Hyperspectral
更新于2025-09-23 15:23:52
-
Variety-dependent responses of rice plants with differential cadmium accumulating capacity to cadmium telluride quantum dots (CdTe QDs): Cadmium uptake, antioxidative enzyme activity, and gene expression
摘要： The excess release of engineered nanomaterials into farmland poses a serious threat to food security. Although rice varieties exhibit substantial variation in cadmium accumulation, their responses to Cd-based nanoparticles are largely unknown. In this work, we investigated the accumulation of cadmium telluride quantum dots (CdTe QDs at 0.5, 1.0, 2.5, 5.0 mg-Cd/L) in two rice varieties with different Cd accumulation capacity. It was found that 5.0 mg-Cd/L of CdTe QDs had minor growth inhibition to the high-Cd-accumulating variety (T705) relative to the low-Cd-accumulating variety (X24) after 7-day exposure. The two rice varieties had comparable Cd content in roots; however, T705 exhibited higher Cd content in shoots than X24. Transmission electron and confocal laser scanning microscopic observations demonstrated that more CdTe QDs can be transported and accumulated from roots to shoots in T705. The activities and gene expression of antioxidative enzymes in leaves of T705 increased more significantly than those of X24. Our findings for the first time validated that Cd accumulation divergence exists in different rice varieties when they are exposed to Cd-based QDs, the genetic basis for which needs to be further examined.
关键词： Gene expression,Antioxidant enzyme activity,Cadmium accumulation,Rice variety,Cadmium telluride quantum dots
更新于2025-09-19 17:13:59
-
Robust Classification of Tea Based on Multi-Channel LED-Induced Fluorescence and a Convolutional Neural Network
摘要： A multi-channel light emitting diode (LED)-induced fluorescence system combined with a convolutional neural network (CNN) analytical method was proposed to classify the varieties of tea leaves. The fluorescence system was developed employing seven LEDs with spectra ranging from ultra-violet (UV) to blue as excitation light sources. The LEDs were lit up sequentially to induce a respective fluorescence spectrum, and their ability to excite fluorescence from components in tea leaves were investigated. All the spectral data were merged together to form a two-dimensional matrix and processed by a CNN model, which is famous for its strong ability in pattern recognition. Principal component analysis combined with k-nearest-neighbor classification was also employed as a baseline for comparison. Six grades of green tea, two types of black tea and one kind of white tea were verified. The result proved a significant improvement in accuracy and showed that the proposed system and methodology provides a fast, compact and robust approach for tea classification.
关键词： tea,variety,classification,convolutional neural network,EEM,LED,fluorescence
更新于2025-09-16 10:30:52
-
[American Society of Agricultural and Biological Engineers 2017 Spokane, Washington July 16 - July 19, 2017 - ()] 2017 Spokane, Washington July 16 - July 19, 2017 - <i>Variety classification of maize kernels using near infrared (NIR) hyperspectral imaging</i>
摘要： Variety classification of maize kernels was evaluated using near infrared (NIR) hyperspectral imaging in this work. Firstly, NIR hyperspectral images of kernels of four widely used maize varieties were acquired within effective spectral range of 1000-2500 nm. Spectral math was used to compensate for minor lighting differences, and band math combined with threshold method was used to remove the background from images. Minimum noise fraction (MNF) was adopted to reduce noise. Texture features (mean, variance, homogeneity, contrast, dissimilarity, entropy, second moment, and correlation) as appearance character of each maize kernel were calculated and extracted to establish classification model combined with spectra data. Moving average smoothing and standard normal variate were applied on the raw spectra extracted from hyperspectral images. Four optimal wavelengths (1352.20 nm, 1615.50 nm, 1733.10 nm, and 2478.20 nm) were selected by competitive adaptive reweighted sampling (CARS) method. Partial least squares discriminant analysis (PLSDA) was employed to build varieties classification models, based on full wavelength data, the four wavelengths data, and combination of spectral and textural features at four wavelengths, respectively. Results demonstrated that PLSDA model based on combination of spectral and textural features had the best performance with accuracies of 0.89, 0.83 for calibration and prediction set, which indicated the hyperspectral imaging technique with combination of spectral and textural features had a potential of application for variety classification.
关键词： Variety classification,Maize kernel,NIR hyperspectral imaging,Partial least squares discriminant analysis (PLSDA),Competitive adaptive reweighted sampling (CARS) method
更新于2025-09-04 15:30:14