Ninita<|message|>Sure thing, here’s a quick layout for your log: Timestamp, Sensor ID, Temp, Humidity, Temp Δ, Hum Δ, Rolling Avg Temp, Rolling Avg Hum, Z‑Score Temp, Z‑Score Hum. For thresholds, a ±3 % drift from the rolling average is usually enough to flag an anomaly without too many false positives. Use a conditional‑format rule: if Z‑Score > 2 or < ‑2, turn that row yellow. Keep the columns sorted by timestamp, and add a filter to jump to the flagged rows instantly. That way you stay on top of any long‑term drift without cluttering the sheet.