|
|
|
|
|
|
Accuracy Comparison of the Machine Learning Algorithm Used to Raman Real Sample Collection in the Front Line of Public Security |
LI Zhi-hao, SHEN Jun*, BIAN Rui-hua, ZHENG Jian |
The Third Research Institute of Ministry of Public Security,Shanghai 200031,China |
|
|
Abstract Raman spectroscopy equipment comes into use in the front line of public security gradually, which is mainly used for the detection of inflammable,explosive and easily-made drug chemicals. However, workers without professional knowledge may not be able to perform detection in full accordance with the best conditions. Frequent problems such as defocusing, offsetting and short sampling time may cause a great influence on the final comparison. In this article, five mainstream machine learning algorithms were used to train and classify the original data collected during the actual inspection and handling of the case. Also, the accuracy comparisons was given in this paper. According to the result, algorithm with the best accuracy will be used to improve the Raman spectroscopy in the future. The collected data were all from the EVA3000 Raman spectrometer developed by the Third Research Institute of the Ministry of Public Security. The spectrometer had been equipped in certain provinces, cities, prefectures and counties across the country. Front-line inspection personnel would periodically transmit the raw data back to the EVA3000’s back office management system. Through the management system, the raw data generated during the actual inspection was collected. A total of 160 cases including phenylacetic acid, methylene chloride, ephedrine and nitrobenzene, which had been qualitatively determined, were randomly extracted from the uploaded database. The 40-, 60-, 100-, 150-, 200-, 300-, 500-time trainings and predictions with decision trees, random forests, AdaBoost, support vector machines and artificial neural networks were executed to calculate average accuracy respectively. From the experimental results, we can see that among the five learning algorithms, the ranking of the prediction accuracy to actual samples is roughly random forest≈AdaBoost>decision tree>SVM>ANNs. The verification results are generally consistent with the experimental ones. The accuracy of random forest is similar to AdaBoost because both algorithms constantly build new training data sets from the original ones and improve the weight of the wrong samples in the next training. On the other hand, SVM and ANNs are perceptron-based algorithms. It can be seen that in the current mainstream algorithms, bootstrap aggregating method is more suitable for the sampling training of actual samples. In the next step, the research team will continue to optimize existing algorithms and implement them in the back office management system for on-line detection. The results of this paper are of great significance for further using machine learning algorithms to the practical applications in the field of the front line of public security.
|
Received: 2018-06-10
Accepted: 2018-10-22
|
|
Corresponding Authors:
SHEN Jun
E-mail: 63368207@qq.com
|
|
[1] CHENG Cheng(成 诚). 2016 Paper Collection for Seminar on Infrared and Remote Sensing Technology and Applications(2016年红外、遥感技术与应用研讨会暨交叉学科论坛论文集),2016. 84.
[2] JIANG Lin-hua, SHEN Jun, YU Zhi-hao, et al(蒋林华, 沈 俊, 余治昊, 等). Optical Instruments(光学仪器), 2018, 40(2): 31.
[3] Rafael Pino-Mejías, María-Dolores Jiménez-Gamero, María-Dolores Cubiles-de-la-Vega, et al. Pattern Recognition Letters, 2008, 29(3): 265.
[4] Suykens J A K, Vandewalle J. Neural Processing Letters,1999,9(3):293.
[5] Rubin Daniel B. Statistical Applications in Genetics and Molecular Biology, 2011, 10(1):54.
[6] Srinivas Y, Stanley Raj A, Hudson Oliver D, et al. Geoscience Frontiers, 2012, 3(5): 729. |
[1] |
LI Jie, ZHOU Qu*, JIA Lu-fen, CUI Xiao-sen. Comparative Study on Detection Methods of Furfural in Transformer Oil Based on IR and Raman Spectroscopy[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(01): 125-133. |
[2] |
WANG Fang-yuan1, 2, HAN Sen1, 2, YE Song1, 2, YIN Shan1, 2, LI Shu1, 2, WANG Xin-qiang1, 2*. A DFT Method to Study the Structure and Raman Spectra of Lignin
Monomer and Dimer[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(01): 76-81. |
[3] |
LI Xin-ting, ZHANG Feng, FENG Jie*. Convolutional Neural Network Combined With Improved Spectral
Processing Method for Potato Disease Detection[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(01): 215-224. |
[4] |
XING Hai-bo1, ZHENG Bo-wen1, LI Xin-yue1, HUANG Bo-tao2, XIANG Xiao2, HU Xiao-jun1*. Colorimetric and SERS Dual-Channel Sensing Detection of Pyrene in
Water[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(01): 95-102. |
[5] |
WANG Xin-qiang1, 3, CHU Pei-zhu1, 3, XIONG Wei2, 4, YE Song1, 3, GAN Yong-ying1, 3, ZHANG Wen-tao1, 3, LI Shu1, 3, WANG Fang-yuan1, 3*. Study on Monomer Simulation of Cellulose Raman Spectrum[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(01): 164-168. |
[6] |
BAO Hao1, 2,ZHANG Yan1, 2*. Research on Spectral Feature Band Selection Model Based on Improved Harris Hawk Optimization Algorithm[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(01): 148-157. |
[7] |
LAN Yan1,WANG Wu1,XU Wen2,CHAI Qin-qin1*,LI Yu-rong1,ZHANG Xun2. Discrimination of Planting and Tissue-Cultured Anoectochilus Roxburghii Based on SMOTE and Inception-CNN[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(01): 158-163. |
[8] |
LI Hu1, ZHONG Yun1, 2, FENG Ya-ting1, LIN Zhen1, ZHU Shi-jiang1, 2*. Multi-Vegetation Index Soil Moisture Inversion Model Based on UAV
Remote Sensing[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(01): 207-214. |
[9] |
WANG Lan-hua1, 2, CHEN Yi-lin1*, FU Xue-hai1, JIAN Kuo3, YANG Tian-yu1, 2, ZHANG Bo1, 4, HONG Yong1, WANG Wen-feng1. Comparative Study on Maceral Composition and Raman Spectroscopy of Jet From Fushun City, Liaoning Province and Jimsar County, Xinjiang Province[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(01): 292-300. |
[10] |
CHENG Hui-zhu1, 2, YANG Wan-qi1, 2, LI Fu-sheng1, 2*, MA Qian1, 2, ZHAO Yan-chun1, 2. Genetic Algorithm Optimized BP Neural Network for Quantitative
Analysis of Soil Heavy Metals in XRF[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(12): 3742-3746. |
[11] |
LI Wei1, TAN Feng2*, ZHANG Wei1, GAO Lu-si3, LI Jin-shan4. Application of Improved Random Frog Algorithm in Fast Identification of Soybean Varieties[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(12): 3763-3769. |
[12] |
WANG Zhi-qiang1, CHENG Yan-xin1, ZHANG Rui-ting1, MA Lin1, GAO Peng1, LIN Ke1, 2*. Rapid Detection and Analysis of Chinese Liquor Quality by Raman
Spectroscopy Combined With Fluorescence Background[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(12): 3770-3774. |
[13] |
LIU Hao-dong1, 2, JIANG Xi-quan1, 2, NIU Hao1, 2, LIU Yu-bo1, LI Hui2, LIU Yuan2, Wei Zhang2, LI Lu-yan1, CHEN Ting1,ZHAO Yan-jie1*,NI Jia-sheng2*. Quantitative Analysis of Ethanol Based on Laser Raman Spectroscopy Normalization Method[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(12): 3820-3825. |
[14] |
LU Wen-jing, FANG Ya-ping, LIN Tai-feng, WANG Hui-qin, ZHENG Da-wei, ZHANG Ping*. Rapid Identification of the Raman Phenotypes of Breast Cancer Cell
Derived Exosomes and the Relationship With Maternal Cells[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(12): 3840-3846. |
[15] |
SHEN Si-cong, ZHANG Jing-xue, CHEN Ming-hui, LI Zhi-wei, SUN Sheng-nan, YAN Xue-bing*. Estimation of Above-Ground Biomass and Chlorophyll Content of
Different Alfalfa Varieties Based on UAV Multi-Spectrum[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(12): 3847-3852. |
|
|
|
|