Comparison of Multivariate Time-Series Imputation Methods Under Simulated Sensor Failure

5.5 KB Excel file compares data repair methods for multivariate time-series with 20% simulated sensor failures. The dataset, authored by Dongdong Tang, evaluates methods based on reconstruction accuracy metrics like RMSE and SSIM and statistical significance. It was last updated on April 29, 2026.

Use Cases

• Benchmark imputation algorithm performance based on RMSE and SSIM metrics mentioned in the description
• Simulate sensor failure scenarios based on the described 20% failure condition
• Evaluate the statistical significance of different data repair methods as indicated in the title

Strengths

• Dataset is small (5.5 KB), facilitating quick download and inspection.
• Explicitly states a 20% simulated sensor failure condition for controlled evaluation.
• Uses standard evaluation metrics (RMSE, SSIM) for comparing imputation methods.

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• Description metadata is limited; actual data quality requires manual inspection after download.

Provenance

Source

figshare

Collection Method

Likely contains results from a computational experiment comparing imputation methods.

Freshness

Last updated 2026-04-29 17:37:17; freshness should be verified.