Real-world parking occupancy and capacity data from NCP-operated car parks in Birmingham, UK, collected every 30 minutes from October to December 2016 for time-series occupancy prediction.
Hourly air pollutant measurements (PM2.5, PM10, SO₂, NO₂, CO, O₃) and meteorological data from 12 nationally controlled monitoring sites in Beijing, collected from March 2013 to February 2017 (420,768 instances).[page:1][web:74]
Over 2 million minute-level measurements of electric power consumption in one household near Paris over 47 months (2006–2010), including global active/reactive power, voltage, current intensity, and sub-metering for kitchen, laundry, and water heater.[page:1][web:212]
48 half-hour excerpts of two-channel ambulatory ECG recordings from 47 subjects (1975–1979), digitized at 360 Hz with expert annotations for approximately 110,000 heartbeats, widely used for arrhythmia detection research.[page:2][web:219]
Experimental office-room dataset for binary occupancy detection using indoor temperature, relative humidity, light level, COâ‚‚ concentration, and humidity ratio at one-minute intervals.[web:199]
Smart-building dataset from the M5 building, including appliance-level energy usage (watts, voltage, kWh) plus temperature, humidity, and occupancy measurements in offices, labs, kitchen, and other spaces.[web:164][web:167][web:170]
Real-world hourly air quality measurements from an array of chemical gas sensors deployed at road level in a polluted Italian city, collected from March 2004 to February 2005.[web:46][web:53][web:77]
Real smart-home energy consumption data (10-minute resolution) with indoor room sensors and outdoor weather measurements, designed to model appliance energy use in a low-energy house.[web:55][web:61][web:66]
Curated machine-learning-ready dataset from NASA’s Solar Dynamics Observatory (SDO) mission integrating multiple solar instruments for flare prediction and solar activity modeling.
Industry-standard dataset for prognostics research with simulated run-to-failure data from 100 turbofan engines including 21 sensor readings and remaining useful life (RUL) labels for predictive maintenance algorithms.
Real-time IoT sensor data from wearable health monitoring devices tracking patient vital signs including body temperature, blood pressure (systolic/diastolic), heart rate, and device battery levels for remote healthcare monitoring and predictive analytics.