~/talk

Fine-Grained Air Pollution Inference with Mobile Sensing Systems: A Weather-Related Deep ...

on YouTube 07m
Talkat UbiComp / ISWC 2020 · 2020-09-12..09-17· [machine-learning]

speakers

name:Rui Ma
links:none on file
name:Ning Liu
links:none on file
name:Xiangxiang Xu
links:none on file
name:Yue Wang
links:none on file
name:Hae Young Noh
links:none on file
name:Pei Zhang
links:none on file
name:Lin Zhang
linkedin:linzhang-us

resources

video:https://youtu.be/sbFRjXaSXSo
slides:none on file

summary

A deep autoencoder pairs an encoder with a decoder that uses a weather-related ConvLSTM whose structure is tied to an atmospheric dispersion model, enabling physics-aware interpolation of irregular mobile samples. A half-year deployment at 500m×500m×1h resolution with 8 static, 12 buses, 3 cruisers shows the offline model cuts error ~14.9% versus prior methods and the quasi‑real‑time variant reduces error ~4.2%, remaining robust to low coverage and sensor faults.

AI-written summary · about

related talks

~/search
type to search 6,249 conferences, 138,987 speakers and 185,172 talks
~/help
cmdctrl k
search every conference, speaker and series
/
focus the filter search
h
home
c
conferences
s
speakers
e
series
t
light / dark — the status bar button does the same
?
this help
esc
close this, then clear every filter — or just the search, while you are typing in it

Ignored while you are typing. Pages without a filter rail have no search to focus.