The Rise of Engineering-Driven Analytics · improving performance Analytics in e-commerce. 9 ......
Transcript of The Rise of Engineering-Driven Analytics · improving performance Analytics in e-commerce. 9 ......
1© 2015 The MathWorks, Inc.
The Rise of Engineering-Driven
Analytics
Loren Shure
Consulting Application Engineer
Language of Technical Computing
2
The Rise of Engineering-Driven Analytics
3
The Rise of Engineering-Driven Analytics
5
Descriptive & Diagnostic
Predictive
Prescriptive
Apply robust, statistically-motivated methods to data produced from complex systems to
understand what has happened and why,
predict what will happen, and
suggest decisions or actions.
Past FutureAnalysis AnalyticsData
6
DecisionSupport
DecisionAutomation
Limited
users, scope
& technology
Pervasive
users, scope,
& technology
Analytics are now pervasiveApply robust, statistically-motivated methods to data produced from complex systems to
understand what has happened and why,
predict what will happen, and
suggest decisions or actions. DecisionSupport
Descriptive & Diagnostic
Predictive
Prescriptive
7
Big Data Compute Power Machine Learning
We have data• Engineering
• Business
• Transactional
We have compute• Desktop
Multicore, GPU
• Clusters
• Cloud computing
• Hadoop with Spark
We know how• Neural Networks• Classification
• Clustering
• Regression
• …and much more…
Analytics are pervasive – Why Now?
8
Business Data
Social profile
Geolocation
Keystroke logs
Transactions
Engineering DataImages
Predictive Model
Offer to Customer
IMPROVED
Use Image Processing
to add image data to the model,
improving performance
Analytics in e-commerce
9
Transactions
Keystroke logs
Geolocation
Social profile
Sensor
Images
Audio
Video
Using now
Source: Gartner Big Data Industry Insights, March 2016
Engineering Data
Business Data
Level of Industry / User Adoption
Consider the Data in Data Analytics
10
Transactions
Keystroke logs
Geolocation
Social profile
Sensor
Images
Audio
Video
Using now
Planned
Source: Gartner Big Data Industry Insights, March 2016
Engineering Data
Business Data
Level of Industry / User Adoption
Consider the Data in Data Analytics
11
The Rise of Engineering-Driven Analytics
12
Architecture of an analytics system
Data from businesssystems
Data from instruments and connected systems
Analyticsand MachineLearning
13
Architecture of an analytics system
Data from businesssystems
Data from instruments and connected systems
Analyticsand MachineLearning
Predictive Model deployed in smart and embedded systems
Predictive Model deployed on cloud and business systems
MATLAB & Simulink Integrates in Embedded Systems and Enterprise
IT Workflows
14
Example – BuildingIQAdaptive building energy management
15
16
25% cost reduction
17
Real-time, closed-loop optimization algorithms
Predictive Model deployed on cloud with client system and real-time data feeds
DATA - Billions of data points:Physics, energy cost, power, internal temperatures, ambient temperatures, ambient humidity, building operation schedule, comfort bounds, etc.
Weather Feeds
Current energy costs & demand
Analytics and Machine Learningplus system identification,control theory & more
MATLAB Toolboxes Just Work –
and work together!
18
We could rapidly translate our prototypes into production algorithms that deal reliably with real-world noise and uncertainty
Borislav Savkovic, BuildingIQ
Why MATLAB?
Robust numerical algorithms
Extensive visualization and analytics tools
Industry-robust and reliable mathematical optimization routines
Good object-oriented framework
Ability to interface with Java (for backend work)
Running MATLAB in the cloud in production
Unit-testing framework
MATLAB Impeccable Numerics for Trusted Results
Why MATLAB?
Robust numerical algorithms
Industry-robust and reliable mathematical optimization routines
19
Example – ScaniaAutomatic emergency braking using sensor fusion and analytics
20
21
Using Model-Based Designto build and deploy the analyticsin an embedded control system
MATLAB Integrates Analytics and
Model-Based Design
22
Implementing Sensor Fusion at Scania
Predictive Model deployed on vehicle
Vehicle logs
of video and radar data
Machine learning
to develop fusion algorithms
for situation detection
24
The Rise of Engineering-Driven Analytics
Medical Devices
AeronauticsOff-highway vehiclesAutomotive
Oil & GasIndustrial Automation Clean Energy
Retail Finance Healthcare management Internet
25
Sensor Data (~1 minute)10-100 sensors/machine
Quality State (~40 minutes)
Classification using Statistics, Machine Learning, and Neural Networks
Predictive Maintenance for polymer-based production machines
26
Deployment – a MATLAB App used by machine operators
M153
M157
State OK
State NOT OK
(C2) Implementing machine learning algorithm using MATLAB for prognostics purpose of airplane hydraulic system
Mitsubishi Heavy Industry
27
28
The need for data scientists
Domain expertise
Coding and integration skills
Statistical and mathematical
knowledge
29
What they say• Expand university programs• Train existing analysts
30
31
32
IoT open data platform for students and makers
Built-in MATLAB analysis Simulink support via Raspberry Pi
33
IoT open data platform for students and makers(D1) Implementing machine learning algorithm using MATLAB for prognostics purpose of airplane hydraulic system
Hitachi
(D1) Development of IOT system to detect anomaly operations of production system
Hitachi
34
Student Contestuse process control data to improve semiconductor yields
21 teams competed
Wafer Big Data in Hadoop
MATLAB used by winning team and 2nd place team
35
MATLAB lets you be your own data scientist
MATLAB & Simulink are Designed and Documented to be Easy for Engineers and Scientists to Use
36
Big DataCompute
Power
Machine
Learning
Limited
users, scope,
& technology
Pervasive
users, scope,
& technology
• Engineering
• Business
• Transactional
• Neural Networks
• Classification
• Clustering
• Regression• …and much more…
In MATLAB
NEW for MATLABAudio System Toolbox R2016aVision HDL Toolbox R2015a
• Native support for engineering data
• Database interfaces
• Streaming
• Desktop -Multicore, GPU
• Clusters
• Cloud computing
• Hadoop with Spark
37
Big DataCompute
Power
Machine
Learning
Limited
users, scope,
& technology
• Native support for engineering data
• Database interfaces
• Streaming
• Datastoretext, image, video, Excel files
• Timetable, string, and tall arrays 2016b
Pervasive
users, scope,
& technology
• Engineering
• Business
• Transactional
• Desktop -Multicore, GPU
• Clusters
• Cloud computing
• Hadoop with Spark
• Neural Networks
• Classification
• Clustering
• Regression
In MATLAB
38
• Native support for engineering data
• Database interfaces
• Streaming
• Datastoretext, image, video, Excel files
• Timetable, string, and tall arrays 2016b
Big DataCompute
Power
Machine
Learning
Limited
users, scope,
& technology
Pervasive
users, scope,
& technology
• Engineering
• Business
• Transactional
• Neural Networks
• Classification
• Clustering
• Regression
In MATLAB• Multicore & GPU
• MATLAB Distributed Computing Serverand EC2 Support
• Hadoop with Spark support R2016b
• MATLAB Production Server
MATLAB is fast:
- heavily optimized libraries
- JIT compiled
- takes advantage of the
compute power you have
• Desktop -Multicore, GPU
• Clusters
• Cloud computing
• Hadoop with Spark
39
Big DataCompute
Power
Machine
Learning
Limited
users, scope,
& technology
Pervasive
users, scope,
& technology
• Engineering
• Business
• Transactional
• Neural Networks
• Classification
• Clustering
• Regression
In MATLAB • Statistics and Machine Learning Toolbox
• Classification Learner App R2015a
• Neural Network Toolbox
• CNNs for Deep learning R2016a
• Machine learning with code generation
• Multicore & GPU
• MATLAB Distributed Computing Serverand EC2 Support
• Hadoop with Spark support R2016b
• MATLAB Production Server
• Native support for engineering data
• Database interfaces
• Streaming
• Datastoretext, image, video, Excel files
• Timetable, string, and tall arrays 2016b
• Desktop -Multicore, GPU
• Clusters
• Cloud computing
• Hadoop with Spark
40
Classification Learner App in Statistics and Machine Learning Toolbox
41
MATLAB Apps for Data Analytics
Distribution Fitting
System Identification
Signal Analysis
Wavelet Design and Analysis
Neural Net Fitting
Neural Net Pattern Recognition
Training Image Labeler
and many more…
With MATLAB Apps, you can complete data
science tasks more quickly and easily than
custom programming
42
Using
MATLAB R2016a
App Designer
43
Using
MATLAB R2016a
App Designer
44
Deep Learning with Neural Network Toolbox - New in R2016a
45
Deep Learning with Neural Network Toolbox - New in R2016a
46
Example –First consumer otoscope in a mobile device using machine learning and computer vision
47
The Rise of Engineering-Driven Analytics
Be your own Data Scientist!
Big DataCompute
PowerMachine Learning
Limited users, scope, & technology
Pervasive users, scope, & technology