Part 4 of 11
Tracking and AI
Raw GPS is noisy. This layer turns a stream of position reports into things staff can act on: which zone a unit is in, where it is in its rental, whether its behaviour looks wrong, and when it will be back.
Location ingestion
Each report carries the device ID, a sequence number, timestamp, position, speed, heading, satellite count and the receiver’s own accuracy estimate. Before a fix is allowed to move a unit on the map, it passes these checks in order.
Rejected fixes are kept for diagnostics, never silently dropped. A tracker that suddenly produces many rejects is flagged for inspection.
Authenticate
Device certificate checked; unknown or revoked trackers are refused.
Validate format
Schema, ranges and units. Malformed messages go to a quarantine queue.
Remove duplicates and reorder
Sequence numbers handle resends and fixes arriving late from the store-and-forward buffer.
Sanity check
Reject impossible speeds, positions on land far from the dock, and timestamps in the future.
Quality and authenticity gate
Correction state, accuracy estimate and QZNMA authentication set each fix’s weight; a spoofing flag escalates.
Smooth and snap
A Kalman filter smooths the track; units at the dock snap to their berth.
Handling drift near the dock
Piers, moored hulls and buildings bounce satellite signals, so a parked unit can appear to wander 20 to 30 metres. Left alone, that drift would fire false “left dock” alerts all day.
- QZSS MADOCA-PPP corrections cut drift from metres to decimetres before any filtering
- Units in the dock zone with no IMU motion are snapped to their assigned berth
- Leaving the dock needs both GNSS movement and IMU motion, or a check-out
- Zone edges use hysteresis: an exit is confirmed only after two consecutive fixes beyond the boundary by more than the accuracy radius
- Geofence sizes are tuned in the pilot against surveyed ground-truth markers
Geofencing
Zones are drawn on the chart in the dashboard and can be changed in minutes, for example to close an area for an event or a jellyfish warning. Each zone produces the events below.
| Event | Fires when | Example |
|---|---|---|
| Approach | Unit enters the warning buffer around a restricted zone | JS-04 is within 50 m of the coral reserve and closing |
| Enter | Confirmed inside a zone | Unit inside the swim zone |
| Exit | Confirmed outside a zone it should be in | Unit has left the riding zone toward the channel |
| Dwell | Inside a zone longer than its limit | Stopped at the recovery point for 10 minutes |
| Path violation | Breaks a rule tied to a zone | Above the speed limit in the launch corridor |
| Schedule | A zone rule depends on time of day | Riding zone closes at 7pm; any unit still out is overdue |
Trip lifecycle
Every unit is always in exactly one state. Movement moves it along, but the start and end of a rental are always confirmed by staff, so billing never depends on GPS alone.
Each state change is stored with its time and position, which gives the rental timeline, route segments, stop durations and the trip report without extra work from staff.
AI anomaly detection
Rules catch what we can define in advance. The anomaly model catches what we can’t: movement that is unusual for this fleet, at this beach, at this time of day.
| Signal | What it looks like |
|---|---|
| Teleport jump | Position leaps further than any jet ski could travel between fixes. Usually a bad fix; repeated jumps, or a failed QZNMA check, suggest interference or spoofing. |
| Speed spike | Sustained speed well above the fleet norm for first-time riders, or acceleration a rental unit can’t produce. |
| Towing signature | Steady low speed with ignition off and little hull vibration. |
| Out-of-window movement | Any movement outside operating hours, or a unit leaving with no active rental. |
| Erratic pattern | Repeated tight circles near swimmers or boats, a sign of reckless riding. |
| Unusual stillness | Long stop mid-bay with no recovery request: breakdown or rider in difficulty. |
How the model works
Features are computed over a rolling window for every unit: speed and acceleration, distance between fixes versus the distance physically possible, heading variance, ignition and vibration state, zone history and time of day. An isolation forest trained on the site’s own normal riding gives each window an anomaly score from 0 to 1.
Every score comes with its top contributing factors, so a supervisor sees “speed 78 km/h, fleet norm 42” rather than a bare number. When staff mark an alert as false, that feedback is used to retune thresholds each week.
Practical first. Phase 1 runs on rules alone. The model starts in shadow mode during the pilot, learning the site’s normal patterns before it is allowed to raise alerts in Phase 3.
Try the anomaly score
A simplified version of the scoring used in the platform. Change the readings for one 10-second window and see how the score and the resulting action change.
The production model weighs many more features and learns each site’s baseline. This explorer uses fixed weights for illustration.
Ignition
Predicted return time
Knowing a unit will be back at 3:42pm rather than “around 3:40” lets staff brief and kit up the next customer in advance, and spot a late return before it happens.
A gradient-boosted model trained on the site’s past trips predicts arrival at the dock, with a confidence range. It improves as the history grows; until there is enough data, a distance-and-speed estimate is used.
Inputs
Time left on the rental, distance and heading to the dock, current speed, how this rider has ridden so far, wind and sea state, time of day, and how similar trips ended.
Outputs
Predicted arrival time, a range such as plus or minus 2 minutes, and the probability of a late return.
Actions
If late return is likely, dock staff get a nudge 5 minutes before the rental ends, and the rider buzzer (if fitted) signals “return now”.
Rules engine and alert routing
Deterministic rules and the anomaly score feed one decision step. It sets severity, chooses who is told and how, and stops the same alert from repeating.
| Situation | Severity | Who is told | Channel |
|---|---|---|---|
| Approaching a restricted zone | Warning | Dock staff on shift | App push, rider buzzer |
| Entered swim zone or restricted area | Critical | Dock staff, supervisor, patrol boat | Push, WhatsApp, SMS |
| Left the riding zone | Warning | Dock staff | App push |
| Overdue by 5 minutes | Warning | Dock staff | App push |
| Overdue by 15 minutes | Critical | Supervisor | |
| Over the corridor speed limit | Info | Logged on the trip report | Dashboard |
| Immobile on the water 3 minutes | Warning | Dock staff, patrol boat | App push |
| Movement after hours or towing signature | Critical | Owner, supervisor, night security | WhatsApp, SMS, call |
| Tamper: case opened or power cut | Critical | Supervisor, owner | WhatsApp, SMS |
| Anomaly score 0.6 to 0.8 | Warning | Dock staff | App push |
| Anomaly score 0.8 or above | Critical | Supervisor | WhatsApp, SMS |
Critical alerts need acknowledgement in the app. If nobody acknowledges within 2 minutes, the alert escalates to the next person on the rota. Repeats of the same alert for the same unit are suppressed for 2 minutes so phones don’t flood during an incident.