@misc{bibcite_16187,
  author = {Ayg{\"u}n Varol and Katarzyna Ko{\l}odziej and {\L}ukasz Sobczak and Micha{\l} Romaszewski and Przemys{\l}aw G{\l}omb and Naser Motlagh and Mirka Leino and Johanna Virkki},
  title = {AIRWISE: Environmental Sensor and LLM Query Dataset for Edge AI-Based Air-Quality and Thermal-Comfort Analytics},
  abstract = {<p>AIRWISE is an open benchmark dataset for edge AI, IoT environmental monitoring, and large language model (LLM) evaluation on real sensor data. It combines indoor air-quality and thermal-comfort measurements, outdoor air-quality and meteorological time series, and a labeled binary question-answering benchmark for threshold-aware reasoning and anomaly detection. The dataset supports the study {\textquotedblleft}Enabling Cloud-Level Accuracy in Edge AI through IoT Data Preprocessing{\textquotedblright}:\&nbsp;https://doi.org/10.48550/arXiv.2606.22496<br>AIRWISE provides three core resources:<br>Indoor environmental sensor dataset (BME680, 1-minute resolution). 146,000+ minute-averaged readings from Raspberry Pi + Bosch BME680 nodes in three real micro-environments (office, kitchen, hallway) at Tampere, Finland (2025-11-14 to 2025-12-18): temperature, relative humidity, barometric pressure, gas resistance, indoor air quality (IAQ) proxy, z-score anomaly detectors, and limit-annotated long-format tables with ground-truth anomaly flags.<br>Outdoor air-quality and meteorological time series (hourly, full-year 2023). Helsinki (Finland), Katowice and Warsaw (Poland): NO$_{2}$, CO, O$_{3}$, PM$_{2}$.$_{5}$, temperature, and relative humidity assembled from national monitoring networks (FMI, GIO{\'S}, IMGW-PIB), as cleaned single-series city tables (≈8,760 hourly records per city) and limit-annotated long-format tables with anomaly flags.<br>Binary LLM query benchmark (1,440 labeled yes/no questions). 240 natural-language questions per site across six sites, balanced by task type (80 air quality, 80 thermal comfort, 80 joint environmental condition), each with ground-truth answer, violation label, offending factors, and rationale {\textemdash} ready for benchmarking local/edge and cloud LLMs on sensor-grounded reasoning.<br>Also included: reference air-quality and thermal-comfort limits (EU air-quality standards and Finnish/Polish national guidelines); the unmodified institutional source files for the outdoor component (FMI exports, GIO{\'S} archive workbooks and station metadata, IMGW-PIB synoptic tables); the complete dataset-generation scripts covering every pipeline step (raw sources {\textrightarrow} cleaned tables {\textrightarrow} limit-annotated data {\textrightarrow} LLM queries) with a requirements.txt for a verified minimal Python environment; SHA-256 checksums; and a dependency-free validation script. Schemas, exact row counts, coverage, and usage examples are documented in README.md and MANIFEST.md.</p>},
  year = {2026},
  url = {https://zenodo.org/doi/10.5281/zenodo.20783874 },
  doi = {10.5281/ZENODO.20783874 },
}