How to capture, analyse and react on IoT generated sensor data in - - PowerPoint PPT Presentation

▶
how to capture analyse and react on iot generated sensor
SMART_READER_LITE
LIVE PREVIEW

How to capture, analyse and react on IoT generated sensor data in - - PowerPoint PPT Presentation

Apr 29, 2023 158 likes •612 views

How to capture, analyse and react on IoT generated sensor data in real time Romeo Kienzler, Chief Data Scientist, IBM Watson IoT, WW Why IoT (now) ? 15 Billion connected devices in 2015 40 Billion connected devices in 2020 World

slide-1
SLIDE 1

How to capture, analyse and react on IoT generated sensor data in real time

Romeo Kienzler, Chief Data Scientist, IBM Watson IoT, WW

slide-2
SLIDE 2

Why IoT (now) ?

  • 15 Billion connected devices in 2015
  • 40 Billion connected devices in 2020
  • World population 7.4 Billion in 2016
slide-3
SLIDE 3

Why IoT (now) ?

  • 2016 90% of all data generated WW is at the

edge of an IoT device

  • This data is never
  • captured
  • analysed
  • acted on
slide-4
SLIDE 4

Why IoT (now) ?

  • 60% of data looses it’s value within milliseconds of

being generated

  • New generation of Sensors
  • low cost
  • low energy consumption
  • low data transmission cost
  • long life batteries / self supplementary
slide-5
SLIDE 5
  • Energy consumption 0.33333333 µA
  • Cost 5 US$
  • 600 mA/h
  • 70 days
  • 1 measurement /h
  • Cost 2 US$
  • Energy consumption
  • Standby 3µA
  • Rx 30 mA
  • Tx 53 mA
  • Range 800m
  • Cost 50 US$
slide-6
SLIDE 6

Why IoT (now) ?

  • If a tree falls in the forest we will hear it
  • IBM announced to invest 3 billion US$
  • Opened IBM Watson IoT Global HQ in Munich, Germany
  • As of 2015
  • 4000 IoT clients

170 countries 1400 partners 750 IoT patents 1000 Emloyees in HQ

slide-7
SLIDE 7

IBM and Siemens

  • IBM partners with Siemens Buildings

Technologies Division to maximise the potential of connected buildings

  • by the data they create (private side note)
slide-8
SLIDE 8

IBM and KONE

  • IBM partners with KONE on Cloud-based

Embedded intelligence in elevators and escalators

slide-9
SLIDE 9

IBM and KONE

  • IBM partners with KONE on Cloud-

based Embedded intelligence in elevators and escalators

slide-10
SLIDE 10

How 2 IoT?

slide-11
SLIDE 11

How 2 IoT?

What is MQTT?

  • “light weight” telemetry protocol
  • Publish-Subscribe protocol via Message Broker
  • Invented by IBM 1999
  • OASIS Standard since 2013
slide-12
SLIDE 12

How 2 IoT?

slide-13
SLIDE 13

How 2 IoT?

slide-14
SLIDE 14
slide-15
SLIDE 15
slide-16
SLIDE 16
slide-17
SLIDE 17
slide-18
SLIDE 18
slide-19
SLIDE 19

ApacheSpark

the state-of-the-art in cloud based analytics

Storage Layer (OpenStack SWIFT / Hadoop HDFS / IBM GPFS) Execution Layer (Spark Executor, YARN, Platform Symphony) Hardware Layer (Bare Metal High Performance Cluster) Graph X Streamin g SQL MLLi b BlinkD B R MLBas e

Y O U

Intel Xeon E7-4850 v2 48 core, 3 TB RAM, 72 GB HDD, 10Gbps

S T R E A M S

slide-20
SLIDE 20

Machine Learning on historic data

Source: deeplearning4j.org

slide-21
SLIDE 21

Online Learning

Source: deeplearning4j.org

slide-22
SLIDE 22
  • nline vs. historic
  • Pros
  • low storage costs
  • real-time model update
  • Cons
  • algorithm support
  • software support
  • no algorithmic improvement
  • compute power to be inline

with data rate

  • Pros
  • all algorithms
  • abundance of software
  • model re-scoring / re-

parameterisation (algorithmic improvement)

  • batch processing
  • Cons
  • high storage costs
  • batch model update
slide-23
SLIDE 23

DeepLearning

DeepLearning Apache Spark Hadoop

slide-24
SLIDE 24

Neural Networks

slide-25
SLIDE 25

Neural Networks

slide-26
SLIDE 26

Deeper (more) Layers

slide-27
SLIDE 27

Convolutional

slide-28
SLIDE 28

Convolutional

+ =

slide-29
SLIDE 29

Convolutional

slide-30
SLIDE 30
slide-31
SLIDE 31

Learning of a function

A neural network can basically learn any mathematical function

slide-32
SLIDE 32

Recurrent

slide-33
SLIDE 33

LSTM

slide-34
SLIDE 34

http://karpathy.github.io/2015/05/21/rnn-effectiveness/

slide-35
SLIDE 35
slide-36
SLIDE 36
slide-37
SLIDE 37
slide-38
SLIDE 38
  • Outperformed traditional methods, such as
  • cumulative sum (CUSUM)
  • exponentially weighted moving average (EWMA)
  • Hidden Markov Models (HMM)
  • Learned what “Normal” is
  • Raised error if time series pattern haven't been seen

before

slide-39
SLIDE 39

Learning of a program

A LSTM network is touring complete

slide-40
SLIDE 40

Problems

  • Neural Networks are computationally very complex
  • especially during training
  • but also during scoring

CPU (2009) GPU (2016) IBM SyNAPSE (2018)

slide-41
SLIDE 41

DeepLearning

the future in cloud based analytics

Storage Layer (OpenStack SWIFT / Hadoop HDFS / IBM GPFS) Execution Layer (Spark Executor, YARN, Platform Symphony) Hardware Layer (Bare Metal High Performance Cluster) Graph X Streamin g SQL MLLi b BlinkD B

DeepLearning4J ND4J

R MLBas e H2O

Y O U

GPU AVX

Intel Xeon E7-4850 v2 48 core, 3 TB RAM, 72 GB HDD, 10Gbps, NVIDIA TESLA M60 GPU

(cu)BL AS

jcuBLA S

S T R E A M S

slide-42
SLIDE 42

Why IoT (now) ?

Formal Definition (Romeo Kienzler, 2016) Cognitive IoT maximises efficiency of the system under observation by measuring all relevant parameters in order to (re)act accordingly to push the system into a state near to the global optimum

slide-43
SLIDE 43

My Vision

What if the majority of cars where connected and sensed? What if we can detect a state of unpreventable accidents? What if in such a case we just issue a 30% brake command to all vehicles? Still a dream?…

slide-44
SLIDE 44

Do it yourself…

  • DeepLearning Architecture on-click cloud

deployment

  • to be published:

http://www.ibm.com/developerworks/analytics/

  • to be announced:

Twitter: @romeokienzler

  • Find this talk on youtube:

http://ibm.biz/romeokienzler