RQ2 Monte Carlo Analysis

Cross-seed aggregate: BASELINE vs SAFE statistical comparison

Experiment Configuration

Total runs: 2000 seed x scenario pairs

5 of 5 sensors selected

Estimated total: ~2,000 tracks

Low BER, minimal drops, low latency
BER1e-6
Drop rate1%
Latency20ms ±5ms
Bandwidth512 kbps

About this analysis

Monte Carlo analysis runs multiple independent seeds per scenario and aggregates results across all runs to produce statistically stable SAFE vs BASELINE comparisons.

Each seed produces a fresh synthetic track sequence. Results are pooled across seeds to compute per-(scenario, tier) mean and standard deviation of RMS error, NEES, fusion-mode distribution, and response lag.

With 5 seeds x 20 tracks x 3 sensor types x 2 modes, each scenario cell has ~300 observations before aggregation.

No results yet

Select scenarios and seeds per scenario, then click Run Monte Carlo to generate cross-seed aggregate statistics.