~/talk

Engineering Techniques for Binary IoT Sensors

on YouTube 32m
Talkat Conf42 Machine Learning 2021 · on Thursday, 2021-07-29· [machine-learning, iot]

speaker

name:Nidal Albeiruti
links:none on file

resources

video:https://youtu.be/1ovwCFKuEs8
slides:none on file

summary

Binary sensors produce more than on/off: the talk shows extracting elapsed-on duration, time-window aggregation, event frequency, inter-event delay and no-sensor events as concrete features that improve models, plus spatial features from sensor ensembles for localization. It demonstrates merging binary events with analog sensors (light, temperature) and using Amazon SageMaker Data Wrangler with 300+ transforms, export to pipelines/notebooks and Snowflake connectivity to make feature extraction repeatable and operational.

AI-written summary · about

chapters (6)

  1. 0:00IoT and binary sensors intro
  2. 7:04Feature engineering for ML
  3. 12:07Feature engineering explained
  4. 17:02Feature engineering for IoT
  5. 24:52SageMaker Data Wrangler overview
  6. 31:35Summary

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.