ABSTRACT
These days, mobile/handheld air quality monitoring devices primarily sense pollutants and send them to the cloud without performing intelligent processing, such as soft calibration, sensor fault detection, or any onboard predictions. This paper explores the feasibility of harnessing Tiny Machine Learning (TinyML) to develop a compact system for inferring environmental pollution levels at a device’s location. Our primary challenge lies in fitting a trained machine-learning model within the device’s limited memory without compromising its accuracy or inference speed. Building upon the correlation between the Air Quality Index (AQI) and various meteorological factors, we propose a TinyML-based framework that predicts AQI using temperature, humidity, internet-sourced meteorological data, and temporal information collected through a web crawler. Our contributions encompass sensor activation, system design on a Raspberry Pi Pico W board, and hyperparameter tuning of machine learning models, culminating in an efficient XGBoost implementation within the 2MB memory constraint, achieving 75.2% accuracy with a 1615μs latency. Moreover, an accuracy of 60% was observed when a real-time validation was carried out. As per our knowledge, this system is the first-of-its-kind device that tries to embed some intelligence into a mobile air quality sensing device.
- Pedro Andrade, Ivanovitch Silva, Marianne Silva, Thommas Flores, Jordão Cassiano, and Daniel G. Costa. 2022. A TinyML Soft-Sensor Approach for Low-Cost Detection and Monitoring of Vehicular Emissions. Sensors 22, 10 (May 2022), 3838.Google ScholarCross Ref
- Mattia Antonini, Miguel Pincheira, Massimo Vecchio, and Fabio Antonelli. 2023. An Adaptable and Unsupervised TinyML Anomaly Detection System for Extreme Industrial Environments. Sensors 23, 4 (Feb. 2023), 2344.Google ScholarCross Ref
- Prithviraj Pramanik, Prasenjit Karmakar, Praveen Kumar Sharma, Soumyajit Chatterjee, Abhijit Roy, Santanu Mandal, Subrata Nandi, Sandip Chakraborty, Mousumi Saha, and Sujoy Saha. 2023. AQuaMoHo: Localized Low-cost Outdoor Air Quality Sensing over a Thermo-hygrometer. ACM Transactions on Sensor Networks 19, 3 (March 2023), 1–30.Google ScholarDigital Library
- Partha Pratim Ray. 2022. A review on TinyML: State-of-the-art and prospects. Journal of King Saud University - Computer and Information Sciences 34, 4 (April 2022), 1595–1623.Google ScholarDigital Library
- Praveen Kumar Sharma, Prasenjit Karmakar, Soumyajit Chatterjee, Abhijit Roy, Santanu Mandal, Sandip Chakraborty, Subrata Nandi, and Sujoy Saha. 2021. Can I go for a roof walk today?. In Proceedings of the 8th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation. ACM.Google ScholarDigital Library
- Vasileios Tsoukas, Eleni Boumpa, Georgios Giannakas, and Athanasios Kakarountas. 2021. A Review of Machine Learning and TinyML in Healthcare. In 25th Pan-Hellenic Conference on Informatics. ACM.Google ScholarDigital Library
- Vasileios Tsoukas, Anargyros Gkogkidis, and Athanasios Kakarountas. 2022. A TinyML-based System For Smart Agriculture. In Proceedings of the 26th Pan-Hellenic Conference on Informatics. ACM.Google ScholarDigital Library
Index Terms
- Efficient Air Quality Index Prediction on Resource-Constrained Devices using TinyML: Design, Implementation, and Evaluation
Recommendations
Real-Time Air Quality Predictions for Smart Cities using TinyML
ICDCN '24: Proceedings of the 25th International Conference on Distributed Computing and NetworkingThis paper explores the feasibility of using Tiny Machine Learning (TinyML) to develop a compact system for inferring environmental pollution levels at a device’s location. Leveraging the correlation between the Air Quality Index (AQI), the localised ...
Air quality prediction using CT-LSTM
AbstractWith the development of industry, air pollution has become a serious problem. It is very important to create an air quality prediction model with high accuracy and good performance. Therefore, a new method of CT-LSTM is proposed in this paper, in ...
Phased Scheduling for Resource-Constrained Mobile Devices in Mobile Cloud Computing
Mobile cloud computing combines wireless access service and cloud computing to improve the performance of mobile applications. Mobile cloud computing can balance the application distribution between the mobile device and the cloud, in order to achieve ...
Comments