Abstract In order to effectively realize the spectral detection of heavy metal content, a deep learning method which consisted of stacked auto-encoders (SAE) and partial least squares support vector machine regression (LSSVR) is proposed to obtain depth features and establish cadmium (Cd) detection model. The Vis-NIR hyperspectral images of 1120 lettuce leaf samples were obtained and the whole region of lettuce leaf sample spectral data was collected and preprocessed with different spectral pre-treatment methods. Successive projections algorithm (SPA), partial least squares regression (PLSR) and SAE were used to acquire the optimum wavelength, respectively. Besides, the characteristic wavelengths were used to build partial least squares support vector machine regression (LSSVR) models. Furthermore, the best prediction performance for detecting Cd content in lettuce leaves was obtained by Savitzky-Golay combined with first derivative (SG-1st) pre-processing method, with Rp2 of 0.9487, RMSEP of 0.01049 ​mg/kg and RPD of 3.330 using SAE-LSSVR method. The results of this study indicated that deep learning method coupled with hyperspectral imaging technique has great potential for detecting heavy metal content in lettuce leaves.

中文翻译：

---

基于深度学习的高光谱数据回归方法快速预测生菜叶片镉残留

摘要 为了有效实现重金属含量的光谱检测，提出了一种由堆叠自编码器（SAE）和偏最小二乘支持向量机回归（LSSVR）组成的深度学习方法，获取深度特征并建立镉（Cd ) 检测模型。获得了1120个生菜叶片样品的Vis-NIR高光谱图像，收集了整个区域的生菜叶片样品光谱数据，并采用不同的光谱预处理方法进行了预处理。分别使用逐次投影算法(SPA)、偏最小二乘回归(PLSR)和SAE来获得最佳波长。此外，特征波长用于建立偏最小二乘支持向量机回归（LSSVR）模型。此外，Savitzky-Golay结合一阶导数（SG-1st）预处理方法获得了检测生菜叶片Cd含量的最佳预测性能，Rp2为0.9487，RMSEP为0.01049 mg/kg，RPD为3.330，使用SAE- LSSVR 方法。本研究结果表明，深度学习方法结合高光谱成像技术在检测生菜叶片中的重金属含量方面具有巨大潜力。