Tuning Coherence Windows to Kill False Positives
Cross-cell coherence is the suppression layer. The window length is the lever. Two seconds too short and solar gain trips the deck; two seconds too long and you spend lead time on noise.
A per-cell rolling baseline gives you a candidate trip. Cross-cell coherence is what turns the candidate into an alarm or a discard. The mechanic is simple — if the same delta is shared by neighbours, suppress; if it is local, escalate — but the window length over which "shared" is evaluated is where the engineering happens.
The trade space
- Short window (sub-second): coherence is too tight; transient cross-cell environmental events look like vehicular ones.
- Long window (10+ seconds): real cell-local events get suppressed because the environmental delta catches up.
- Variable window: per-deck tuning to the ventilation and solar profile of the specific vessel.
Where we landed
How we tune in the field
Three voyages of calibration data per deck, replayed against the trip engine, with the window swept across the ±1 s range. The optimal window minimises false positives without losing any of the staged true-positive replays. Process is documented and reproducible — a class-society auditor can run it themselves.
Continue the thread
How Are Thermal Hotspots Detected on Cargo Decks?
The detection problem on a cargo deck is not measurement — IR sensors are commodity. It is deciding which delta in which cell at which time is real.
Per-Vehicle Thermal Baselines and 6 °C Anomaly Detection
A deck-wide threshold misses the early-stage signature. A per-vehicle rolling baseline catches it 18–25 minutes earlier in our bench tests.
Where AI Anomaly Detection Helps — And Where Rules Still Win
We use both. The interesting question is which decisions belong to which approach. The split is not where most marketing decks would put it.