激光与光电子学进展, 2019, 56 (11): 113001, 网络出版: 2019-06-13
基于高光谱成像技术结合堆栈自动编码器-极限学习机方法的苹果硬度检测 下载: 1002次
Firmness Detection for Apples Based on Hyperspectral Imaging Technology Combined with Stack Autoencoder-Extreme Learning Machine Method
光谱学 高光谱成像技术 硬度 堆栈自动编码器 极限学习机 无损检测 spectroscopy hyperspectral imaging techniques firmness stack autoencoder extreme learning machine nondestructive testing
摘要
将堆栈自动编码器(SAE)与极限学习机(ELM)联合,建立了深度神经网络预测模型(SAE-ELM)。利用苹果高光谱图像提取出的光谱数据,对深度神经网络的权值和阈值进行了初始化和微调。与传统ELM模型预测结果相比,SAE-ELM的预测集决定系数和残留预测偏差分别从0.7345和1.968提升至0.7703和2.116,预测集方均根误差从1.6297降至1.2837。研究结果表明:深度学习网络SAE-ELM模型的预测性能优于传统的ELM模型,将其用于预测苹果硬度是可行的。
Abstract
Based on a stack autoencoder (SAE) combined with an extreme learning machine (ELM), we built a deep neural-network prediction model, SAE-ELM. We initialized and fine-tuned the weights and thresholds of the deep neural networks using the spectral data extracted from the hyperspectral images of apples. Compared with the results of the traditional ELM model, the SAE-ELM determination coefficient of the prediction set increases from 0.7345 to 0.7703, the SAE-ELM residual prediction bias increases from 1.968 to 2.116, and the square root error of the prediction set decreases from 1.6297 to 1.2837. These research results show that the performance of the SAE-ELM model is superior to that of the traditional ELM model, and it is feasible for the proposed model to predict apple firmness.
饶利波, 庞涛, 纪然仕, 陈晓燕, 张洁. 基于高光谱成像技术结合堆栈自动编码器-极限学习机方法的苹果硬度检测[J]. 激光与光电子学进展, 2019, 56(11): 113001. Libo Rao, Tao Pang, Ranshi Ji, Xiaoyan Chen, Jie Zhang. Firmness Detection for Apples Based on Hyperspectral Imaging Technology Combined with Stack Autoencoder-Extreme Learning Machine Method[J]. Laser & Optoelectronics Progress, 2019, 56(11): 113001.