Comparison of SVM, RF and ELM on an Electronic Nose for the Intelligent Evaluation of Paraffin Samples.

Hong Men,Songlin Fu,Yan Shi,Jingjing Liu,Jialin Yang,Meiqi Cheng

doi:10.3390/s18010285

Hong Men, Songlin Fu + Show 4 more

Open Access

https://doi.org/10.3390/s18010285

Copy DOI

Abstract

Paraffin odor intensity is an important quality indicator when a paraffin inspection is performed. Currently, paraffin odor level assessment is mainly dependent on an artificial sensory evaluation. In this paper, we developed a paraffin odor analysis system to classify and grade four kinds of paraffin samples. The original feature set was optimized using Principal Component Analysis (PCA) and Partial Least Squares (PLS). Support Vector Machine (SVM), Random Forest (RF), and Extreme Learning Machine (ELM) were applied to three different feature data sets for classification and level assessment of paraffin. For classification, the model based on SVM, with an accuracy rate of 100%, was superior to that based on RF, with an accuracy rate of 98.33–100%, and ELM, with an accuracy rate of 98.01–100%. For level assessment, the R2 related to the training set was above 0.97 and the R2 related to the test set was above 0.87. Through comprehensive comparison, the generalization of the model based on ELM was superior to those based on SVM and RF. The scoring errors for the three models were 0.0016–0.3494, lower than the error of 0.5–1.0 measured by industry standard experts, meaning these methods have a higher prediction accuracy for scoring paraffin level.

Highlights

China is a major paraffin producer, exporter, and consumer, annually exporting about 70% of total world paraffin trade volume, and playing an important role in the development of the international paraffin market
Design of paraffin odor analysis system: in this paper, we introduced a new method for testing paraffin odor level based on the electronic nose, designed and developed the paraffin odor analysis system
Classification of paraffin samples: Support Vector Machine (SVM), Random Forest (RF), and Extreme Learning Machine (ELM) were applied to three different feature data sets to build the model and compare the model accuracy rate and regression parameters

Summary

Introduction

China is a major paraffin producer, exporter, and consumer, annually exporting about 70% of total world paraffin trade volume, and playing an important role in the development of the international paraffin market. The huge market requires the faster and more precise division of the different paraffin levels [1,2,3]. When the quality inspection calibration is performed on the post-factory paraffin products, odor intensity is one of the important quality indicators. The Chinese petrochemical industry standard “Test Method for Paraffin Odor (SHT0414-2004)” is the most common paraffin odor identification method. This method involves the expert evaluation of odor using smell at the site. Having a rapid method for evaluating the paraffin odor level has practical significance for improving the profit margin in the paraffin economy and the product’s secondary development [6,7,8]

Methods

Results

Conclusion