- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
Predicting Apple Firmness and Soluble Solids Content Based on Hyperspectral Scattering Imaging Using Fourier Series Expansion
摘要： This article reports on using a Fourier series expansion method to extract features from hyperspectral scattering profiles for apple fruit firmness and soluble solids content (SSC) prediction. Hyperspectral scattering images of ‘Golden Delicious’ (GD), ‘Jonagold’ (JG), and ‘Delicious’ (RD) apples, harvested in 2009 and 2010, were acquired using an online hyperspectral imaging system over the wavelength region of 500 to 1000 nm. The moment method and Fourier series expansion method were used to analyze the scattering profiles of apples. The zeroth-first order moment (Z-FOM) spectra and Fourier coefficients were extracted from each apple, which were then used for developing fruit firmness and SSC prediction models using partial least squares (PLS) and least squares support vector machine (LSSVM). The PLS models based on the Fourier coefficients improved the standard errors of prediction (SEP) by 4.8% to 19.9% for firmness and by 2.4% to 13.5% for SSC, compared with the PLS models using the Z-FOM spectra. The LSSVM models for the prediction set of Fourier coefficients achieved better SEP results, with improvements of 4.4% to 11.3% for firmness and 2.8% to 16.5% for SSC over the LSSVM models for the Z-FOM spectra data and 3.7% to 12.6% for firmness and 5.4% to 8.6% for SSC over the PLS models for the Fourier coefficients. Experiments showed that Fourier series expansion provides a simple, fast, and effective means for improving hyperspectral scattering prediction of fruit internal quality when used with either PLS or LSSVM.
关键词： Partial least squares,Soluble solids content,Apples,Least squares support vector machine,Fourier series expansion,Hyperspectral scattering imaging,Firmness
更新于2025-09-23 15:22:29
-
Estimating Daily Solar Radiation from Monthly Values Over Selected Nigeria Stations for Solar Energy Utilization
摘要： The solar radiation needed for effective research into solar energy utilization can be determined using concise and reliable data which can be gotten from hourly or daily data. The parameters which govern a physical model of the sky should be taken hourly or daily. The values which fluctuate according to the fluctuating changes in the meteorological and environmental situations should be analyzed with data over a short period of time. These parameters include the sunshine hours, Solar radiation, cloud cover, temperature etc. In predicting the performance of solar energy conversion devices, a sequence of daily radiation is always required. The daily data are not readily available, hence, there is need for the derivation of the needed, which is the daily solar radiation data from the available- the monthly averages. For many stations in Nigeria, only monthly long-term averages are available and the problem of extracting reliable information always sets in. Therefore, this paper proffers solutions to this by establishing a procedure for the derivation of daily solar radiation from the monthly averages using Fourier series.
关键词： Solar radiation,Daily data,Month averages,Fourier series
更新于2025-09-09 09:28:46
-
[IEEE 2018 IEEE International Conference on Computational Electromagnetics (ICCEM) - Chengdu (2018.3.26-2018.3.28)] 2018 IEEE International Conference on Computational Electromagnetics (ICCEM) - Resonance Frequency Inversion of Cold Unmagnetized Plasma Based on CDLT-FDTD and PSO Methods
摘要： Current density Laplace finite-difference time-domain (CDLT-FDTD) method conjunction with particle swarm optimization (PSO) method is introduced to reconstruct the resonance frequency of cold unmagnetized plasma medium. During the inversion, the resonance frequency of the plasma is reconstructed by Fourier series expansion method and the traditional direct method, respectively. The simulation results show that the Fourier series expansion method has better reconstruction accuracy than the traditional direct method, and the number of unknowns is only 1/3 of that of the traditional direct method.
关键词： finite-difference time-domain method,Fourier series expansion,particle swarm optimization,Current density Laplace transform
更新于2025-09-04 15:30:14