A Critical View of Low Cost Sensor System Networks for Air Quality
ISEE Conference Abstracts（2018）
Abstract
Low-cost sensor systems (LCSS) represent a disruptive change in air monitoring, and pose numerous challenges. The Citi-Sense project (http://co.citi-sense.eu) that operated between 2012 and 2016 in nine European cities, provides a vivid illustration. Three use cases were deployed, on ambient air quality, on indoor environment at schools, and on the quality of urban spaces, with at times, over 300 LCSSs in use simultaneously.We aimed at providing air quality information to stakeholders, but without a clear prior idea of the purpose and DQOs: we felt that information generated by LCSSs can support several objectives. Our knowledge as to what are capabilities of the technology was low and expectations were high.Any large-scale use of LCSS requires to deploy two enabling technologies, sensing technology and information and communication technologies for data transmission, storage and use, and has a number of steps. We have deployed LCSS's from 9 different producers, in a variety of climatic conditions, from Oslo (Norway) to Haifa (Israel), and Edinburg (United Kingdom) to Beograd (Serbia). We thus demonstrate intercomaprison issues as well as the dependency of monitoring results on local conditions. Despite extensive field calibration and co-location, we were not able to quantify uncertainty sufficiently to provide comparable data across locations. However, we successfully developed an accurate real-time map, unavailable using other current methods, addressing the interest in real time information.Using LCSSs as personal monitors has similar challenges as traditional methods, and some new ones. User feedback showed that at this stage (2015), only a special interest group can successfully use the devices.We believe there is a great potential to the LCSSs, but also serious obstacles. Quality assurance and quality control of data needs further development. Correct communication of the results and expectation management are a second main barrier to successful use of LCSS.
MoreTranslated text
求助PDF
上传PDF
View via Publisher
AI Read Science
AI Summary
AI Summary is the key point extracted automatically understanding the full text of the paper, including the background, methods, results, conclusions, icons and other key content, so that you can get the outline of the paper at a glance.
Example
Background
Key content
Introduction
Methods
Results
Related work
Fund
Key content
- Pretraining has recently greatly promoted the development of natural language processing (NLP)
- We show that M6 outperforms the baselines in multimodal downstream tasks, and the large M6 with 10 parameters can reach a better performance
- We propose a method called M6 that is able to process information of multiple modalities and perform both single-modal and cross-modal understanding and generation
- The model is scaled to large model with 10 billion parameters with sophisticated deployment, and the 10 -parameter M6-large is the largest pretrained model in Chinese
- Experimental results show that our proposed M6 outperforms the baseline in a number of downstream tasks concerning both single modality and multiple modalities We will continue the pretraining of extremely large models by increasing data to explore the limit of its performance
Upload PDF to Generate Summary
Must-Reading Tree
Example
Generate MRT to find the research sequence of this paper
Data Disclaimer
The page data are from open Internet sources, cooperative publishers and automatic analysis results through AI technology. We do not make any commitments and guarantees for the validity, accuracy, correctness, reliability, completeness and timeliness of the page data. If you have any questions, please contact us by email: report@aminer.cn
Chat Paper
Summary is being generated by the instructions you defined