Glass classification and identification based on mRMR-random forest algorithm

Nian Li; Zhuoyuan Chen; Yalei Jian

doi:10.54097/hset.v42i.7067

Authors

Nian Li
Zhuoyuan Chen
Yalei Jian

DOI:

https://doi.org/10.54097/hset.v42i.7067

Keywords:

Random Forest, Minimum redundancy, algorithm Feature Extraction.

Abstract

With the increasing importance of conservation and identification of antiquities, there are numerous methods for the identification of antiquities. In order to realise the analysis and identification of the components of ancient glass objects, this paper establishes a random forest identification model based on the original data, random forest feature extraction and the maximum correlation minimum redundancy algorithm (mRMR), and compares and analyses its effectiveness on various datasets. The mrmr algorithm-based random forest discrimination model achieved a combined accuracy and ROC curve coverage area (AUC value) of 1 on the unweathered dataset, which was close to a perfect model with high confidence in predicting the discrimination results; while the AUC value of the repeatedly trained model was not stable enough on the weathered dataset. Thus, this paper proposes a mrmr-based random forest-based discrimination model, which achieves an optimal AUC value of 0.9393 when the number of decision trees is 30 and the maximum number of splits is 10.

Downloads

Download data is not yet available.

References

Sichin Bilig, Li Qinghui, Gan Fuxi. Analysis of ancient Chinese potassium glass fractions by laser exfoliation-inductively coupled plasma-atomic emission spectrometry/mass spectrometry[J]. Analytical Chemistry,2013,41(09):1328-1333.

WANG Jie, LI Mo, MA Qinglin, ZHANG Zhiguo, ZHANG Meifang, WANG Julin. A weathering study of an octagonal lead-barium glass vessel from the Warring States period[J]. Glass and enamel,2014,42(02): 6-13.DOI: 10.13588/j.cnki.g.e.1000-2871.2014.02.002

Pei-Bei Zhang,Min Hu. Improved random forest based on grid search for customer satisfaction prediction[J]. Journal of Beijing University of Information Science and Technology (Natural Science Edition),2021,36(04):50-53+58.DOI: 10.16508/j.cnki.11-5866/n.2021.04.010.

Li F. Research on Web user anomalous behavior analysis by mRMR-XGBoost two-layer model[D]. Liaoning University, 2021. doi: 10.27209/d.cnki.glniu.2021.000721.

Yang ZL, Zhang D. Kmeans++-based adaptive superpixel drop point method[J]. Semiconductor optoelectronics,2022,43(03): 585-591.DOI:10.16818/j. issn1001-5868.2022011306.

Ma Liangyu, Zhao Shangyu, Sun Jiaming, Yu Shilai. Abnormal state warning of wind turbine based on grid search optimization ERF model[J]. Thermal Power Engineering,2022,37(02): 160-166.DOI: 10.16146/j.cnki.rndlgc.2022.02.022.

Fatih Özyurt. A fused CNN model for WBC detection with MRMR feature selection and extreme learning machine [J]. Soft Computing: A Fusion of Foundations, Methodologies and Applications,2020,24(9212).

Cabrera Andrew, Bouterse Alexander, Nelson Michael, Razzouk Jacob, Ramos Omar, Chung David, Cheng Wayne, Danisa Olumide. Predicting short-term outcomes after posterior decompression and instrumented fusion for cervical spondylolisthesis using a random forest machine learning algorithm[J]. Journal of clinical neuroscience: the official journal of the Australasian Society for Neurosurgery, 2022.

Gao Xuemei,Yang Xichao,Chen Berru,Lin Lin. Simulation of population spatialization in the Bohai Rim based on random forest model[J]. Journal of Geoinformation Science,2022,24(06):1150-1162.

LI Cast, ZHANG Qingyong, KONG Linghua, LIAN Guofu, LI Peng. Identification of hardness of GCr15 steel based on laser-induced breakdown spectroscopy with random forest[J]. China Laser,2022,49(09):40-49.

Cheng Xiaoyu, Zhou Aitao, Guo Yanzhen, Cheng Cheng, Li Debo. A method for predicting gas outflow from retrieval workings based on random forest and support vector machine[J]. Coal Mine Safety,2022,53(10): 205-211.DOI: 10.13347/j.cnki.mkaq.2022.10.028.

Zhou Jinglei, Zhou Zhi, Cui Lin. Application of variational modal decomposition and random forest feature selection algorithm for anomalous sound classification of loudspeakers[J]. Vibration and Shock,2022,41(20): 277-283.DOI: 10.13465/j.cnki.jvs.2022.20.034.

Hu W, Zhang XY, Li ZEN, Li Q, Wang H. Short-term load forecasting based on optimized VMD-mRMR-LSTM model[J]. Power System Protection and Control,2022,50(01): 88-97.DOI: 10.19783/j.cnki.pspc.210313.

Li Shunyong, Wang Change. A new maximum correlation minimum redundancy feature selection algorithm[J]. Journal of Intelligent Systems,2021,16(04):649-661.

Liu Jiaxing. Support vector regression based on grid search hyperparameter optimization[J]. Science and Technology Innovation,2022(13):71-74.