The development of a meta-learning calibration network for low-cost sensors across domains

• Autorzy: Feng Tianliang , Xiong Xingchuang , Jin Shangzhong

Identyfikatory

DOI

10.24425/mms.2023.147957

• Języki publikacji: EN

Abstrakty

EN

Low-cost sensor arrays are an economical and efficient solution for large-scale networked monitoring of atmospheric pollutants. These sensors need to be calibrated in situ before use, and existing data-driven calibration models have been widely used, but require large amounts of co-location data with reference stations for training, while performing poorly across domains. To address this problem, a meta-learning-based calibration network for air sensors is proposed, which has been tested on ozone datasets. The tests have proved that it outperforms five other conventional methods in important metrics such as mean absolute error, root mean square error and correlation coefficient. Taking Manlleu and Tona as the source domain and Vic as the target domain, the proposed method reduces MAE and RMSE by 17.06% and 6.71% on average, and improves R2 by an average of 4.21%, compared with the suboptimal pre-trained multi-source transfer calibration. The method can provide a new idea and direction to solve the problem of cross-domain and reliance on a large amount of co-location data in the calibration of sensors.

Słowa kluczowe

EN

low-cost sensor array; ozone pollutants; timing characteristics; meta-learning algorithm; calibration

• Wydawca: Komitet Metrologii i Aparatury Naukowej PAN
• Czasopismo: Metrology and Measurement Systems
• Rocznik: 2023
• Tom: Vol. 30, nr 4
• Strony: 617--635
• Opis fizyczny: Bibliogr. 39 poz., rys., tab., wykr., wzory

Twórcy

autor

Feng Tianliang

• College of Optical and Electronic Technology, China Jiliang University, Hangzhou, Zhejiang 310018, China

autor

Xiong Xingchuang

• National Institute of Metrology, Beijing 100029, China

autor

Jin Shangzhong

• College of Optical and Electronic Technology, China Jiliang University, Hangzhou, Zhejiang 310018, China

Bibliografia

• [1] World Health Organization. (2022). Ambient air pollution attributable deaths. https://www.who.int/data/gho/data/indicators/indicator-details/GHO/ambient-air-pollution-attributable-deaths
• [2] Alphasense Ltd. (2023). Alphasense Application Note (AAN 110), Environmental changes: Temperature, pressure, humidity. http://www.alphasense.com/WEB1213/wp-content/uploads/2013/07/AAN_110.pdf
• [3] Lee, H., Kang, J., Kim, S., Im, Y., Yoo, S., & Lee, D. (2020). Long-term evaluation and calibration of low-cost particulate matter (PM) sensor. Sensors, 20(13), 3617. https://doi.org/10.3390/s20133617
• [4] Spinelle, L., Gerboles, M., Villani, M. G., Aleixandre, M., & Bonavitacola, F. (2015). Field calibration of a cluster of low-cost available sensors for air quality monitoring. Part A: Ozone and nitrogen dioxide. Sensors and Actuators B: Chemical, 215, 249-257. https://doi.org/10.1016/j.snb.2015.03.031
• [5] Christakis, I. G. H., Stavrakas, I., & Tsakiridis, O. (2020). Low cost sensor implementation and evaluation for measuring NO2 and O3 pollutants. 2020 9th International Conference on Modern Circuits and Systems Technologies (MOCAST), Bremen, Germany, 1-4. https://doi.org/10.1109/MOCAST49295.2020.9200245
• [6] Kang, Y., Aye, L., Ngo, T. D., & Zhou, J. (2022). Performance evaluation of low-cost air quality sensors: A review. Science of the Total Environment, 818, 151769. https://doi.org/10.1016/j.scitotenv.2021.151769
• [7] Morawska, L., Thai, P. K., Liu, X., Asumadu-Sakyi, A., Ayoko, G., Bartonova, A., Bedini, A., Chai, F., Christensen, B., & Dunbabin, M. (2018). Applications of low-cost sensing technologies for air quality monitoring and exposure assessment: How far have they gone? Environment International, 116, 286-299. https://doi.org/10.1016/j.envint.2018.04.018
• [8] Rai, A. C., Kumar, P., Pilla, F., Skouloudis, A. N., Di Sabatino, S., Ratti, C., Yasar, A., & Rickerby, D. (2017). End-user perspective of low-cost sensors for outdoor air pollution monitoring. Science of the Total Environment, 607, 691-705. https://doi.org/10.1016/j.scitotenv.2017.06.266
• [9] Eichstädt, S., Vedurmudi, A. P., Gruber, M., & Hutzschenreuter, D. (2022, September 19-21). Fundamental aspects in data analysis for sensor network metrology. IMEKO TC6 International Conference on Metrology and Digital Transformation, Berlin, Germany. https://doi.org/10.21014/actaimeko.v12i1.1417
• [10] Christakis, I., Hloupis, G., Tsakiridis, O., & Stavrakas, I. (2022, 8-10 June 2022). Integrated open source air quality monitoring platform. 2022 11th International Conference on Modern Circuits and Systems Technologies (MOCAST), Bremen, Germany. https://doi.org/10.1109/MOCAST54814.2022.9837555
• [11] Castell, N., Dauge, F. R., Schneider, P., Vogt, M., Lerner, U., Fishbain, B., Broday, D., & Bartonova, A. (2017). Can commercial low-cost sensor platforms contribute to air quality monitoring and exposure estimates? Environment International, 99, 293-302. https://doi.org/10.1016/j.envint.2016.12.007
• [12] Borrego, C., Costa, A. M., Ginja, J., Amorim, M., Coutinho, M., Karatzas, K., Sioumis, T., Katsifarakis, N., Konstantinidis, K., & De Vito, S. (2016). Assessment of air quality microsensors versus reference methods: The EuNetAir joint exercise. Atmospheric Environment, 147, 246-263. https://doi.org/10.1016/j.atmosenv.2016.09.050
• [13] Maag, B., Zhou, Z., & Thiele, L. (2018). A Survey on Sensor Calibration in Air Pollution Monitoring Deployments. IEEE Internet of Things Journal, 5(6), 4857-4870. https://doi.org/10.1109/jiot.2018.2853660
• [14] Narayana, M. V., Jalihal, D., & Nagendra, S. M. (2022). Establishing A Sustainable Low-Cost Air Quality Monitoring Setup: A Survey of the State-of-the-Art. Sensors, 22(1), 394. https://doi.org/10.3390/Rs22010394
• [15] Ferrer-Cid, P., Barcelo-Ordinas, J. M., Garcia-Vidal, J., Ripoll, A., & Viana, M. (2020). Multisensor Data Fusion Calibration in IoT Air Pollution Platforms. IEEE Internet of Things Journal, 7(4), 3124-3132. https://doi.org/10.1109/jiot.2020.2965283
• [16] Cordero, J. M., Borge, R., & Narros, A. (2018). Using statistical methods to carry out in field calibrations of low cost air quality sensors. Sensors and Actuators B: Chemical, 267, 245-254. https://doi.org/10.1016/j.snb.2018.04.021
• [17] Lin, Y., Dong, W., & Chen, Y. (2018). Calibrating Low-Cost Sensors by a Two-Phase Learning Approach for Urban Air Quality Measurement. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, 2(1), 1-18. https://doi.org/10.1145/3191750
• [18] Chattopadhyay, A., Huertas, A., Rebeiro-Hargrave, A., Fung, P. L., Varjonen, S., Hieta, T., Tarkoma, S., & Petaja, T. (2022). Low-Cost Formaldehyde Sensor Evaluation and Calibration in a Controlled Environment. IEEE Sensors Journal, 22(12), 11791-11802. https://doi.org/10.1109/jsen.2022.3172864
• [19] Christakis, I., Tsakiridis, O., Kandris, D., & Stavrakas, I. (2023). Air Pollution Monitoring via Wireless Sensor Networks: The Investigation and Correction of the Aging Behavior of Electrochemical Gaseous Pollutant Sensors. Electronics, 12(8), 1842. https://www.mdpi.com/2079-9292/12/8/1842
• [20] Cheng, Y., Saukh, O., & Thiele, L. (2022). SensorFormer: Efficient Many-to-Many Sensor Calibration With Learnable Input Subsampling. IEEE Internet of Things Journal, 9(20), 20577-20589. https://doi.org/10.1109/jiot.2022.3177948
• [21] Cheng, Y., Li, X., Li, Z., Jiang, S., Li, Y., Jia, J., & Jiang, X. (2014). AirCloud: a cloud-based air-quality monitoring system for everyone. Proceedings of the 12th ACM Conference on Embedded Network Sensor Systems, Memphis, Tennessee. https://doi.org/10.1145/2668332.2668346
• [22] Yu, H., Li, Q., Wang, R., Chen, Z., Zhang, Y., Geng, Y-a., Zhang, L., Cui, H., & Zhang, K. (2020). A Deep Calibration Method for Low-Cost Air Monitoring Sensors with Multilevel Sequence Modeling. IEEE Transactions on Instrumentation and Measurement, 69(9), 7167-7179. https://doi.org/10.1109/tim.2020.2978596
• [23] Jha, S. K., Kumar, M., Arora, V., Tripathi, S. N., Motghare, V. M., Shingare, A. A., Rajput, K. A., & Kamble, S. (2021). Domain Adaptation-Based Deep Calibration of Low-Cost PM2.5 Sensors. IEEE Sensors Journal, 21(22), 25941-25949. https://doi.org/10.1109/JSEN.2021.3118454
• [24] Cheng, Y., He, X., Zhou, Z., & Thiele, L. (2019). ICT: In-field Calibration Transfer for Air Quality Sensor Deployments. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, 3(1), 1-19. https://doi.org/10.1145/3314393
• [25] Li, G., Ma, R., Liu, X., Wang, Y., & Zhang, L. (2020). RCH: robust calibration based on historical data for low-cost air quality sensor deployments. Adjunct Proceedings of the 2020 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2020 ACM International Symposium on Wearable Computers, Virtual Event, Mexico. https://doi.org/10.1145/3410530.3414322
• [26] Robin, Y., Amann, J., Goodarzi, P., Schütze, A., & Bur, C. (2022). Transfer Learning to Significantly Reduce the Calibration Time of MOS Gas Sensors. 2022 IEEE International Symposium on Olfaction and Electronic Nose (ISOEN), Aveiro, Portugal. https://doi.org/10.1109/ISOEN54820.2022.9789596
• [27] Yadav, K., Arora, V., Kumar, M., Tripathi, S. N., Motghare, V. M., & Rajput, K. A. (2022). Few-Shot Calibration of Low-Cost Air Pollution (PM2.5) Sensors Using Meta Learning. IEEE Sensors Letters, 6(5), 1-4. https://doi.org/10.1109/LSENS.2022.3168291
• [28] Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, Ł., & Polosukhin, I. (2017). Attention is all you need. Proceedings of the 31st International Conference on Neural Information Processing Systems, Long Beach, California, USA. https://proceedings.neurips.cc/paper_files/paper/2017/hash/3f5ee243547dee91fbd053c1c4a845aa-Abstract.html
• [29] He, P., Liu, X., Gao, J., & Chen, W. (2017). DeBERTa: Decoding-enhanced BERT with disentangled attention. International Conference on Learning Representations, Toulon. https://arxiv.org/abs/2006.03654
• [30] Raffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M., Zhou, Y., Li, W., & Liu, P. J. (2020). Exploring the limits of transfer learning with a unified text-to-text transformer. Journal of Machine Learning Research, 21(1), 5485-5551.
• [31] Beltagy, I., Peters, M. E., & Cohan, A. (2020). Longformer: The long-document transformer. https://arxiv.org/abs/2004.05150
• [32] Wu, S., Xiao, X., Ding, Q., Zhao, P., Wei, Y., & Huang, J. (2020). Adversarial sparse transformer for time series forecasting. Proceedings of the 34th International Conference on Neural Information Processing Systems, Vancouver, BC, Canada.
• [33] Drouin, A., Marcotte, É., & Chapados, N. (2022). Tactis: Transformer-attentional copulas for time series. International Conference on Machine Learning, Hangzhou, China. https://proceedings.mlr.press/v162/drouin22a.html
• [34] Guen, V. L., & Thome, N. (2019). Shape and time distortion loss for training deep time series forecasting models. Proceedings of the 33rd International Conference on Neural Information Processing Systems, Vancouver, Canada. https://proceedings.neurips.cc/paper_files/paper/2019/file/466accbac9a66b805ba50e42ad715740-Paper.pdf
• [35] Finn, C., Abbeel, P., & Levine, S. (2017). Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks. Proceedings of the 34th International Conference on Machine Learning, Australia. https://proceedings.mlr.press/v70/finn17a.html
• [36] Parnami, A., & Lee, M. (2022). Learning from few examples: A summary of approaches to few-shot learning. https://arxiv.org/abs/2203.04291
• [37] Barcelo-Ordinas, J. M., Ferrer-Cid, P., Garcia-Vidal, J., Viana, M., & Ripoll, A. (2021). H2020 project CAPTOR dataset: Raw data collected by low-cost MOX ozone sensors in a real air pollution monitoring network. Data in Brief, 36, 107127. https://doi.org/10.1016/j.dib.2021.107127
• [38] Catalunya, G. D. (2023). Vols saber que respires? Medi Ambient. (in Catalan) http://mediambient.gencat.cat/es/05_ambits_dactuacio/atmosfera/qualitat_de_laire/vols-saber-que-respires/
• [39] Lai, G., Chang, W.-C., Yang, Y., & Liu, H. (2018). Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networks. The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval, Ann Arbor, MI, USA. https://doi.org/10.1145/3209978.3210006

Uwagi

We gratefully acknowledge the financial support provided by the China National Key R&D Program (2021YFF0600100) for our research. This support was essential in enabling our research to be conducted successfully.