Comparison of RF-BP and RF-SVR Results for Metal Tube Rebound Angle Prediction

A 5.5 KB Excel dataset compares the performance of Random Forest-Support Vector Regression (RF-SVR) against traditional RF-BP and SVR methods for predicting the rebound angle of metal tubes. The data was authored by Ziluo Fang and last updated on May 15, 2026. It focuses on addressing challenges with non-uniform and small-sample datasets.

Use Cases

• Benchmarking RF-SVR against RF-BP and SVR algorithms based on the described methodology.
• Developing prediction models for metal tube bending rebound angles based on polynomial-generated features.
• Feature selection analysis for engineering datasets using Random Forest, as described.
• Studying regression algorithm performance on small-sample and non-uniform data.

Strengths

• Dataset is openly licensed under CC-BY-4.0.
• The description details a specific methodological approach for handling non-uniform and small-sample data.

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• The dataset is very small at 5.5 KB, indicating limited scope.

Provenance

Source

Ziluo Fang via figshare

Collection Method

Likely generated from experiments comparing RF-SVR, RF-BP, and SVR algorithms.

Freshness

Last updated 2026-05-15 17:41:05; freshness should be verified.