Study on One-Dimensional Convolutional Neural Network Model Based on Near-Infrared Spectroscopy Data
TANG Jie1, LUO Yan-bo2, LI Xiang-yu2, CHEN Yun-can1, WANG Peng1, LU Tian3, JI Xiao-bo4, PANG Yong-qiang2*, ZHU Li-jun1*
1. Chongqing Key Laboratory of Scientific Utilization of Tobacco Resources, Chongqing 400060, China
2. China National Tobacco Quality Supervision & Test Center, Zhengzhou 450001, China
3. Shanghai Shuzhiwei Information Technology Co., Ltd., Shanghai 200444, China
4. Department of Chemistry of Shanghai University, Shanghai 200444, China
Abstract:Near-infrared spectroscopy technology has been widely applied for detection in various industries. However, traditional methods struggle to gather key information from the spectral data, leading to significant model prediction errors. This study explores the regression modeling of one-dimensional convolutional neural networks (1DCNN) on near-infrared data, focusing on the chemical composition of 452 plants from the Solanaceae family. Through parameter optimization, the study suggests that the optimal settings for the model include 64 channels in the intermediate convolutional layer, a maximum pooling layer of 1, 6 convolutional layers, and 5 channels in the final convolutional layer. These findings can serve as a reference for future model research. The root mean square error of the model's test set ranges from 0.02 to 0.49, with an average relative error of 0.8%~1.7%, significantly lower than previous literature. Compared to traditional methods, 1DCNN can fully utilize all of the near-infrared spectral data while maintaining a simple model structure and strong predictive capabilities. This work provides new insights for data processing in near-infrared spectroscopy research and promotes the application and development of this technology.
Key words:One-dimensional convolutional neural network; Near-infrared spectroscopy; Deep learning
唐 杰,罗彦波,李翔宇,陈云璨,王 鹏,卢 天,纪晓波,庞永强,朱立军. 基于近红外光谱数据的一维卷积神经网络模型研究[J]. 光谱学与光谱分析, 2024, 44(03): 731-736.
TANG Jie, LUO Yan-bo, LI Xiang-yu, CHEN Yun-can, WANG Peng, LU Tian, JI Xiao-bo, PANG Yong-qiang, ZHU Li-jun. Study on One-Dimensional Convolutional Neural Network Model Based on Near-Infrared Spectroscopy Data. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(03): 731-736.
[1] ZHAO Juan-juan, YE Shun, XU Ke, et al(赵娟娟,叶 顺,徐 可,等). Journal of Henan Normal University(河南师范大学学报), 2021, 49(1):45.
[2] JIANG Hong-lin, LIU Hui-jie, WANG Xue-jie, et al(蒋宏霖,刘会杰,王学杰,等). Science and Innovation(科技与创新), 2019, 138(18):153.
[3] Liu Taiang, Zhang Qing, Chang Dongping, et al. Analytical Letters, 2018, 51(12): 1935.
[4] LUO Qiong, LI Qing, YU Xiao-hong, et al(罗 琼, 李 青, 于小红,等). Anhui Agricultural Science(安徽农业科学), 2016, 44(30):72.
[5] Omar Jone, Slowikowski Boleslaw, Boix Ana. Forensic Science International, 2019, 294:15.
[6] LI Ming, LIU Wei-juan, ZHU Yan-mei, et al(李 明, 刘维涓, 朱艳梅,等). Advances in Laser and Optoelectronics(激光与光电子学进展), 2022, 59(7):374.
[7] CAI Feng, LIU Tai-ang, ZHANG Zhao-ping, et al(蔡 峰, 刘太昂, 张朝平,等). Computer and Applied Chemistry(计算机与应用化学), 2014, 31(8):969.
[8] HU Yun, LIU Na, JI Hou-wei, et al(胡 芸, 刘 娜, 姬厚伟,等). Anhui Agricultural Science(安徽农业科学), 2017, 45(19):78.
[9] Jiang Daiyu, Qi Guanqiu, Hu Gang, et al. Infrared Physics & Technology, 2020, 111:103494.
[10] Wei Kesu, Bin Jun, Wang Feng, et al. Analytical Letters, 2022, 55(13):2089.
[11] Peng Yuhan, Bi Yiming, Dai Lu, et al. ACS Omega, 2022, 7(30):26407.
[12] Wu Lijun, Wang Baoxing, Zhang Lei, et al. Journal of Near Infrared Spectroscopy, 2020, 28(3):153.
[13] Liang Youyan, Zhao Le, Guo Junwei, et al. ACS Omega,2022, 7(43):38650.