Gas Sensor Array Drift Dataset (UCI ML Repository)
Abstract
"Benchmark dataset for gas sensor arrays showing drift over 36 months. Contains 13,910 measurements from 16 chemical sensors across 6 volatile organic compounds (VOCs)."
Description
Dataset Significance
Classic benchmark dataset in sensor research. Demonstrates critical challenge of sensor drift - degradation in sensor response over time due to aging and environmental factors. Essential for developing drift-robust detection algorithms.
Experimental Setup
- Duration: 36 months continuous operation
- Sensors: 16 chemical gas sensors
- Gas Types: 6 volatile organic compounds (VOCs)
- Concentrations: 10 different concentration levels
- Measurements: 13,910 total samples
Technical Parameters
- Sensor Type: Metal oxide semiconductor (MOS)
- Measurement: Sensor resistance (ohms)
- Sampling Frequency: 3.8 Hz
- Temperature: 20°C, 25°C (controlled)
- Humidity: 50%, 60%, 70% (varied)
Drift Characteristics
- Nonlinear sensor degradation over time
- Chemical sensitivity reduction
- Baseline drift patterns
- Seasonal and environmental influences
Applications
Sensor drift compensation, gas classification with aging sensors, robust feature extraction, concept drift detection, and transfer learning approaches.
Data Preview
| Batch_ID | Sensor_ID | Chemical_ID | Concentration | Measurement_Time_s | Sensor_Resistance_Ohms | Temperature_C |
|---|---|---|---|---|---|---|
| B001 | S01 | VOC_A | 50ppm | 0.26 | 4524.5 | 20 |
| B001 | S02 | VOC_A | 50ppm | 0.26 | 3850.2 | 20 |
| B001 | S03 | VOC_B | 100ppm | 0.52 | 2145.8 | 25 |
Showing first few rows for preview
Cite This Dataset
Academic (2026). Gas Sensor Array Drift Dataset (UCI ML Repository). [Dataset]. Academic. https://archive.ics.uci.edu/ml/datasets/Gas+Sensor+Array+Drift+Dataset
Source: Academic (2026)
Indexed by IoTDataset.com on Jan 13, 2026
Ready to Start Your Research?
Download this dataset directly from the official repository and start building your next breakthrough project.