Summary of Utilising Explainable Techniques For Quality Prediction in a Complex Textiles Manufacturing Use Case, by Briony Forsberg et al.
Utilising Explainable Techniques for Quality Prediction in a Complex Textiles Manufacturing Use Case
by Briony Forsberg, Dr Henry Williams, Prof Bruce MacDonald, Tracy Chen, Dr Reza Hamzeh, Dr Kirstine Hulse
First submitted to arxiv on: 26 Jul 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: None
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper presents an innovative approach for classifying product failures in a complex textiles manufacturing dataset, leveraging explainable techniques. The study uses a New Zealand-based woollen carpet and rug manufacturer’s dataset to investigate the trade-off between accuracy and explainability. Three tree-based classification algorithms – Decision Tree, Random Forest, and XGBoost – are evaluated, along with three feature selection methods: SelectKBest, Pearson Correlation Coefficient, and Boruta. The results show that ensemble methods generally outperform the Decision Tree model, with Random Forest and Boruta combination yielding the best overall performance. A tree ensemble explaining technique is also employed to extract rule lists for human-interpretable classification models. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps us understand how to identify failed products in a manufacturing process using special techniques that make it easy to see why certain decisions were made. The researchers used data from a New Zealand company that makes carpets and rugs to test different methods. They found that combining several methods worked best, especially when they included extra information during the preparation stage. This shows how adding more details can improve the final results. |
Keywords
» Artificial intelligence » Classification » Decision tree » Feature selection » Random forest » Xgboost
