English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The advances of sensor technology enable people to monitor air qualitythrough widely distributed low-cost sensors. However, measurements from thesesensors usually encounter high biases and require a calibration step to reachan acceptable performance in down-streaming analytical tasks. Most existingcalibration methods calibrate one type of sensor at a time, which we callsingle-task calibration. Despite the popularity of this single-task schema, itmay neglect interactions among calibration tasks of different sensors, whichencompass underlying information to promote calibration performance. In thispaper, we propose a multi-task calibration network (MTNet) to calibratemultiple sensors (e.g., carbon monoxide and nitrogen oxide sensors)simultaneously, modeling the interactions among tasks. MTNet consists of asingle shared module, and several task-specific modules. Specifically, in theshared module, we extend the multi-gate mixture-of-experts structure toharmonize the task conflicts and correlations among different tasks; in eachtask-specific module, we introduce a feature selection strategy to customizethe input for the specific task. These improvements allow MTNet to learninteraction information shared across different tasks, and task-specificinformation for each calibration task as well. We evaluate MTNet on threereal-world datasets and compare it with several established baselines. Theexperimental results demonstrate that MTNet achieves the state-of-the-artperformance.

MTNet: A Multi-Task Neural Network for On-Field Calibration of Low-Cost Air Monitoring Sensors