AI-Driven Transit Sensor Events

This dataset provides high-frequency, AI-processed sensor event data from multimodal public transit systems, including detailed attributes for vehicles, routes, stops, passenger flow, and operational anomalies. Designed for real-time analytics, it supports optimization of transit efficiency, passenger experience, and sustainability initiatives through edge AI insights and predictive metrics.

  • last updated 16 Jan 2026
  • by GoMask
The brief that made it

Passenger flow optimization and congestion analysis

Sample rows

preview · 8 of 120 rows · all 20 columns
event_idstringevent_typestringdelay_secondsintegeranomaly_detectedbooleanai_predictionstringevent_timestampdatetimesensor_idstringsensor_typestringtransit_modestringvehicle_idstringroute_idstringstop_idstringlatitudefloatlongitudefloatpassenger_countintegerconfidence_scorefloatenergy_consumption_kwhfloatraw_sensor_valuefloatweather_conditionstringtemperature_celsiusfloat
EVT0001boarding0falsenormal2024-06-21T08:23:00ZSID1021camerabusBUS137R15STP21240.7201-73.9953340.810.3234clear24.8
EVT0002alighting0falsenormal2024-06-21T08:25:00ZSID1042infraredbusBUS203RXSTP12740.7218-73.998780.930.288clear24.6
EVT0003boarding432trueovercrowded2024-06-21T08:28:00ZSID1103camerabusBUS312R09STP14140.7195-73.9925780.770.4178cloudy23
EVT0004anomaly2064truehardware_malfunction2024-06-21T08:30:00ZSID1115lidartramTRM218TR2STP30152.37454.8891blank0.048.7-9999rain16.1
EVT0005door_open0falseblank2024-06-21T09:02:00ZSID1207pressuretramTRM142TR6STP35652.36624.8953blankblank0.090cloudy15.7
EVT0006occupancy0falsenormal2024-06-21T09:05:00ZSID1216pressuretramTRM142TR6STP35652.36624.8953450.850.1345cloudy15.7
EVT0007occupancy290trueovercrowded2024-06-21T09:09:00ZSID1309pressuretramTRM218TR2STP30152.37454.8891760.740.1876rain16.1
EVT0008anomaly5092truesuspicious_activity2024-06-21T09:15:00ZSID1404lidartrainTRN088T07STP48251.5074-0.1278blank0.9712.199999cloudy20.2

What the 120 rows show

from the 120-row sample

Anomaly (event type) stands out: mean delay_seconds is 5,745, against 106.3 for the rest.

  • 36%anomaly_detected = true
  • 0median delay_seconds
  • 5sensor types
  • 6transit modes
  • 6weather conditions
  • 49median passenger_count
Mean delay_seconds by event_type120 rows
04,0008,000358.1boar…26 ro…0.0alig…15 ro…46.9occu…36 ro…5,745anom…16 ro…0.0door…10 ro…0.0door…7 rows5.7other10 ro…
delay_seconds120 rows, in bands of 1,000
05511010231322021405,00010kdelay_seconds →

Median 0, from 0 to 9,984.

ai_prediction85 rows with a value · 35 left blank
  1. normal44
  2. overcrowded19
  3. hardware_malfunction9
  4. suspicious_activity6
  5. delayed3
  6. unknown3
  7. anomaly_detected1
20 columns by typefrom the column list below
  • string 10
  • integer 2
  • float 6
  • datetime 1
  • boolean 1

Columns

20 columns in four groups
blueprint · 20 columns
columntypedescriptionexample
Text 10 columns
event_idstringUnique identifier for each sensor event recorduniqueEVT0001
sensor_idstringUnique identifier for the sensor device that generated the eventSID1021
sensor_typestringType of sensor (e.g., camera, infrared, pressure, lidar, etc.)camera · infrared · pressure · lidar · othercamera
transit_modestringMode of public transit where the event occurred (e.g., bus, train, tram, ferry, subway)6 valuesbus
vehicle_idstringUnique identifier for the vehicle involved in the pulse eventBUS137
route_idstringIdentifier for the transit route associated with the eventoptionalR15
stop_idstringIdentifier for the transit stop or station where the event occurredoptionalSTP212
event_typestringType of event detected (e.g., boarding, alighting, occupancy, anomaly, door_open, door_close, etc.)7 valuesboarding
ai_predictionstringEdge AI's predicted label or classification for the event (e.g., normal, overcrowded, delayed, suspicious_activity, etc.)7 predictions · optionalnormal
weather_conditionstringWeather condition at the location during the event (e.g., clear, rain, snow, fog, etc.)6 values · optionalclear
Numbers 8 columns
latitudefloatLatitude coordinate where the event was recorded-90 to 9040.7201
longitudefloatLongitude coordinate where the event was recorded-180 to 180-73.9953
passenger_countintegerNumber of passengers detected by the sensor at the event time0 or more · optional34
confidence_scorefloatConfidence score (0-1) assigned by the AI model to its prediction0 to 1 · optional0.81
energy_consumption_kwhfloatEstimated energy consumption (in kilowatt-hours) associated with this event (if applicable)0 or more · optional0.32
delay_secondsintegerNumber of seconds of delay detected at the event (if any)0 or more · optional0
raw_sensor_valuefloatRaw value output from the sensor at the time of the event (e.g., pressure, count, etc.)optional34
temperature_celsiusfloatAmbient temperature in Celsius at the event locationoptional24.8
Dates and times 1 column
event_timestampdatetimeDate and time when the sensor event was recorded (in UTC)2024-06-21T08:23:00Z
True or false 1 column
anomaly_detectedbooleanIndicates if an anomaly was detected by the AI (true/false)optionalfalse

Use it for

  • anomaly detect…36%38 of 105 rowsmean delay seconds by…358.1boar…0.0alig…46.9occu…5.7kanom…

    A transportation dashboard

    The anomaly_detected rate, delay_seconds by event_type and a breakdown of ai_prediction. Excel, Power BI or Tableau.

  • Why do the 16 anomaly rows have a mean delay_seconds of 5,745?

    A root-cause class exercise

    Hand out the rows and one question. The answer is in the data, not in the brief.

  • A software demo

    Believable events with event_timestamp, sensor_id and sensor_type to fill a screen in front of a buyer.

Not quite right?

Make it yours.

Same 20 columns, your size and your rules. See 20 rows before you pay.

Preview 20 rows free

1,000 rows: $1.99 · 10,000: $12.99One-time. No subscription. All prices

This dataset120 rows20 columns
Yours1,000 rows20 columns

blueprint · ai-driven-transit-sensor-events

Behind this dataset

Same schema. As many rows as you need.

These 120 rows came out of a blueprint — 20 columns with generation rules behind each one. Open it in Data Factory to retune a column, add your own, wire in foreign keys, and run it at the size you actually need.

Rules it was built with
  • Each row represents a distinct sensor event on a public transit vehicle or platform.
  • Event types include occupancy, temperature, air quality, door operations, and dwell time.
  • Sensor data is processed by edge AI to generate anomaly flags and predicted passenger flow impact.
  • Mandatory fields: timestamp, location ID, sensor type, event value, AI anomaly flag, predicted flow impact.
  • Rows must include a mix of normal and anomalous readings across various sensor types.
Rows
Open the blueprint in Data Factory

1 credit per row. Preview 20 rows free. Buy rows for the full run.

Exports
CSV, JSON, JSONL, Parquet, SQL, Excel, TSV, XML
Licence
yours to use, including commercially
API slug
ai-driven-transit-sensor-events

More in Transportation

Browse all
Also in TransportationConnected Vehicle Sensor Health LogsFleet Energy Consumption MonitoringVehicle Fleet DataAll 1,966 datasets

What should your data show?

Preview 20 rows free
No signup. No card.