Analytics in the age of the Internet of Things #bbuzz

on YouTube ↗33m

" summary

A pipeline collects CSV accelerometer data sampled at 50 ms from 47 users into Cassandra, windows data into 5–6 s segments, extracts features (mean, variance, average resultant, average time between peaks where jogging peaks ≈250 ms and walking ≈500 ms), and trains multiclass classifiers with Spark MLlib (decision trees / random forest / logistic). Real‑time prediction uses the Spark Cassandra connector to load recent rows and apply the saved model; accuracy is good except for confusing upstairs/downstairs.

AI-written summary · about

" chapters (5)

1. 0:00Introduction and welcome
2. 4:23What is IoT and examples
3. 12:30Collecting and storing IoT data
4. 14:45Demo: Activity prediction with accelerometer
5. 31:19Uses and conclusion of IoT analytics

" related talks

• 29mIOT, timeseries and prediction with Android, Cassandra and SparkAmira Lakhal · Scalar 2016
• 49mIOT, Timeseries and prediction with Android, Cassandra and SparkAmira Lakhal · Jfokus 2016
• 40mSpark Analytics on Cassandra DataTim Berglund · Jfokus 2016
• 42mSo, You Want to "Do Big Data?"Jan Machacek · Scala Days Berlin 2016
• 01h 36mSpark for Scala DevelopersBrian M Clapper · Scala World 2017
• 32mData Science in the Internet of Things with Python and SparkRafael Schultze-Kraft · PyData Amsterdam 2017
• 21mIoT, Wavelets and Machine Learning in the Smart HomeKeita Broadwater · Scale By the Bay 2017
• 35mReal Time Marketing with Kafka, Storm, Cassandra & Spark #bbuzzVolker Janz · Berlin Buzzwords 2016