UCI Dataset Benchmark Results for 35 Fuzzy Soft Decision-Making Algorithms

Ömer Karakoç published a study on 2026-05-13 evaluating 35 soft decision-making algorithms based on fuzzy parameterized fuzzy soft matrices. The research benchmarks these algorithms across ten datasets from the UCI Machine Learning Repository using metrics like accuracy, precision, recall, specificity, and F1-score. Statistical significance was confirmed using Friedman and Nemenyi tests.

Use Cases

• Benchmarking fuzzy soft decision-making algorithms based on the described fpfs-matrices framework
• Selecting classification algorithms for tasks with uncertainty based on comparative F1-scores
• Validating statistical significance of algorithm performance using Friedman and Nemenyi tests

Strengths

• Benchmarks 35 distinct algorithms, providing a broad comparison
• Uses five standard evaluation metrics: accuracy, precision, recall, specificity, and F1-score
• Applies statistical significance tests (Friedman and Nemenyi) to results

Limitations

• Dataset size is only 9.5 KB, indicating a very limited scope
• Row count and column-level documentation are unknown
• The data appears to be summary results, not the original UCI datasets

Provenance

Source

figshare

Collection Method

Benchmarking study using the FPFS-CMC classifier on ten UCI datasets.

Freshness

Last updated 2026-05-13 17:44:27