Ubiwhere Smart Lamppost Dataset

About the Dataset This dataset was collected by Ubiwhere from a smart lamp post installed in the city of Aveiro, Portugal. The smart lamp post is equipped with video and sound sensors (camera and microphone) and captures environmental and traffic-related data. Time period: Data covers from 2025-08-22 13:10:00 to 2025-08-29 12:00:00. About the Smart Lamppost This dataset was generated from a Smart Lamppost IoT installation by Ubiwhere in the city of Aveiro, Portugal. The Smart Lamppost is a modular urban infrastructure solution that supports: intelligent LED lighting with remote management and analytics, optional electric vehicle (EV) charging capability, edge computing and telemetry, neutral hosting for 4G/5G telecom services, environmental sensing (video, sound, noise level, temperature). For more details, see the product page: https://www.ubiwhere.com/en/products/smart-cities/smart-lamppost/ Dataset Description timestamp: Date and time of the observation (ISO 8601 format) GPU Usage: Percentage of GPU utilization of the device CPU Usage: Percentage of CPU utilization of the device Memory Used: Amount of RAM used by the device (in bytes) Jetson Energy: Energy consumption of the Jetson device (in joules or watt-seconds) Switch Energy: Energy consumption of the network switch (in joules or watt-seconds) Inference Time: Time taken for AI inference processing (in seconds) Tracking Time: Time taken for object tracking processing (in seconds) Noise Level: Measured environmental noise level (in decibels, dB) Temperature: Ambient temperature recorded by the sensor (in degrees Celsius) Instantaneous Person Detections: Number of persons detected in the current instant/frame Instantaneous Car Detections: Number of cars detected in the current instant/frame Instantaneous Motorcycle Detections: Number of motorcycles detected in the current instant/frame Intended Use Environmental monitoring Traffic analysis Energy consumption profiling AI and ML model training for object detection and inference optimization Smart city infrastructure research Column Summary and Data Types Descriptor Count Mean Std Min 25% 50% (Median) 75% Max GPU Usage (i64) 597,002 96.2 15.0 0.0 100.0 100.0 100.0 100.0 CPU Usage (f64) 597,002 11.2 0.7 9.6 10.8 11.1 11.4 36.5 Memory Used (i64) 597,002 7.21e9 1.07e8 5.75e9 7.11e9 7.21e9 7.30e9 7.51e9 Jetson Energy (f64) 597,002 16.1 1.3 10.4 15.0 15.9 17.0 22.1 Switch Energy (f64) 597,002 13.0 2.0 9.5 11.3 11.4 15.4 16.3 Inference Time (f64) 597,002 0.2 0.0 0.1 0.2 0.2 0.2 0.3 Tracking Time (f64) 597,002 0.0 0.0 0.0 0.0 0.0 0.0 0.0 Noise Level (f64) 597,002 12.2 7.2 -3.5 8.7 10.4 12.9 55.4 Temperature (f64) 596,972 33.8 9.7 22.1 24.7 27.3 44.7 46.6 Inst. Person Detections (i64) 597,002 0.0 1.6 0.0 0.0 0.0 0.0 777.0 Inst. Car Detections (i64) 597,002 0.0 1.3 0.0 0.0 0.0 0.0 580.0 Inst. Motorcycle Detections (i64) 597,002 0.0 0.0 0.0 0.0 0.0 0.0 7.0 📜 Citation If you use this dataset in your research, please use the citation generated by Zenodo (located in the right sidebar of this record). 🤝 Acknowledgements & Funding This work is part of the MLSysOps project, funded by the European Union’s Horizon Europe research and innovation programme under grant agreement No. 101092912. More information about the project is available at https://mlsysops.eu/