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]
Time-series accelerometer and gyroscope data from smartphones and smartwatches carried by 51 subjects performing 18 activities, suitable for human activity recognition and motion-based biometrics.[web:119][web:123][web:137]
Multimodal body motion and vital sign recordings from 10 volunteers performing 12 physical activities, collected with three body-worn sensor units (chest, wrist, ankle) including 2‑lead ECG.[web:124][web:130][web:148][web:153]
Comprehensive smart energy and environment dataset from three real homes plus a microgrid of 400+ anonymous homes, including electricity usage/generation, environmental conditions, and operational events.[web:97][web:94][web:103]
Curated machine-learning-ready dataset from NASA’s Solar Dynamics Observatory (SDO) mission integrating multiple solar instruments for flare prediction and solar activity modeling.
Specialized dataset containing features influencing vehicle collisions in Internet of Vehicles (IoV) networks. Includes V2V communication data, sensor readings, traffic conditions, and collision indicators for developing intelligent collision detection and prevention systems.
Large-scale real-time air quality monitoring dataset from Dhaka, Bangladesh with 155,406 records. Captures CO, NO2, SO2, O3, PM2.5, and PM10 using IoT sensors with Arduino integration. Ideal for environmental analytics, pollution prediction, and smart city air quality management.
Two years of continuous IoT-based smart parking lot usage data collected via ThingSpeak platform. Features IR sensors and ESP32 boards monitoring slot availability, occupancy patterns, peak hours, and parking duration for urban parking management optimization.
Multimodal smart city dataset combining environmental sensors (temperature, humidity, gas, vibration, noise, motion) and surveillance images with binary anomaly labels. Designed for edge computing, urban anomaly detection, and real-time city monitoring research.
Multivariate dataset exploring the integration of IoT sensor data with AI algorithms across multiple domains. Features diverse sensor types, environmental parameters, and AI model performance metrics for hybrid intelligent systems research.