PPubMed27 Jan 2022Cited 172×

A comparative analysis of the principal component analysis and entropy weight methods to establish the indexing measurement A comparative analysis of the PCA and entropy weight methods

Robert M. X. Wu, Zhongwu Zhang, Wanjun Yan, Jianfeng Fan, Jinwen Gou, Bao Liu, Ergun Gide, Jeffrey Soar, Bo Shen, Syed Fazal-e-Hasan, Zengquan Liu, Peng Zhang, Peilin Wang, Xinxin Cui, Zhanfei Peng, Ya Wang, Dragan Pamucar

Abstract

The literature found that the PCA method was the predominant weighting method adopted in China’s applications, and the Entropy method was the second most widely adopted weighting method. This paper aimed to determine which method between the PCA and Entropy was better for establishing a responsive weighted indexing measurement. The selected method would be used to build robust monitoring or warning systems for improving coal mining safety. Both the PCA and Entropy methods were compared using two case studies. Based on the comparative analysis of the PCA and Entropy methods in two case studies,

A figure from A comparative analysis of the principal component analysis and entropy weight methods to establish the indexing measurement A comparative analysis of the PCA and entropy weight methods — fig. from the paper

§ The Valyu brief

The paper, in five minutes

Read from the full text via Valyu Contents

The study compares PCA and Entropy weighting methods for gas‑sensor data in Chinese coal mines, finding PCA more responsive while Entropy yields slightly higher accuracy.

What’s new

i.Performed a comparative analysis of PCA and Entropy weighting methods for coal‑mine gas monitoring.
ii.Collected and processed large sensor datasets (72,650 records from Mine 1 and 198,030 from Mine 2).
iii.Evaluated method performance using reliability, validity, and correlation analyses.
iv.Provided weighted indexing measurements and visualizations for safety warning systems.
v.Identified PCA as more responsive and highlighted the need for more robust weighting approaches.

How they did it

The researchers installed gas sensors in two underground mines, cleaned the data with box‑plot outlier removal, and then applied PCA and Entropy algorithms to compute criterion weights. They used SPSS and Excel for calculations, followed by reliability, validity, and Pearson correlation analyses to compare the resulting weighted indexes.

What they found

Case Study 1 yielded 72,650 valid data points; Case Study 2 yielded 198,030 valid data points.
Literature review showed PCA used in 41.81% (10,801/25,831) of Chinese studies, Entropy in 15.80% (4,082/25,831).
Weighted index highest values: Entropy 0.4168 vs PCA 0.4126; lowest values: Entropy 0.2364 vs PCA 0.2349.
Correlation coefficients between sensor items ranged from 0.862 to 0.985 (all >0.3, p<0.01).
PCA vs Entropy weight percentages for key items (e.g., T010104: 7.22% vs 5.13%; T010106: 7.21% vs 27.29%).

Caveats

✕Subjective weighting methods were excluded, limiting insight into decision‑maker preferences.
✕PCA is sensitive to outliers, which may affect its robustness.
✕Both methods ignore expert opinions, raising questions about their applicability in real‑world decision contexts.
✕The study is based on only two case studies, so broader generalization requires further research.

§ The Valyu brief

Reading the full paper and taking notes. This takes a few seconds…

§ Ask this paper

Ask a question about this paper

Valyu reads the full text and answers from what the paper actually says.

§ Related work in other archives

Similar papers in all four archives

The same idea searched in arXiv, PubMed, bioRxiv and chemRxiv at once, so a method can lead you to where it is being applied.

AarXiv4 found

PPubMed3 found

BbioRxiv4 found

CchemRxiv2 found

Searching the other archives…