michelle hirsch, ph.d. manager of matlab product ......business systems datafrom instruments and...
TRANSCRIPT
1
Michelle Hirsch, Ph.D.Manager of MATLAB Product ManagementMathWorks
The Rise of Engineering‐Driven Analytics
2
The Rise of Engineering‐Driven Analytics
3
The Rise of Engineering‐Driven Analytics
4
Big Data Compute Power
Machine Learning
Limited users, scope & technology
Pervasive users, scope, & technology
• Engineering• Business• Transactional
• Desktop ‐Multicore, GPU
• Clusters• Cloud computing• Hadoop
• Neural Networks• Classification• Clustering• Regression• …and much more…
Analytics are now pervasiveApply robust, statistically‐motivated
methods to data produced from complex systems to understand what has happenedand predict what will happen.
5
Business Data
Social profile
Geolocation
Keystroke logs
Transactions
Engineering DataImages
Analytics in e-commerce
Predictive Model
Offer to Customer
IMPROVED
Use Image Processing to add image data to the model,
improving performance
6
Transactions
Keystroke logs
Geolocation
Social profile
Sensor
Images
Audio
Video
Business Data
Using now
Planned
Source: Gartner Big Data Industry Insights, March 2016
Engineering Data
7
The Rise of Engineering‐Driven Analytics
8
Architecture of an analytics system
Data from businesssystems
Data from instruments and connected systems
Analyticsand MachineLearning
Predictive Model deployed in smart systems using Model-Based Design
Predictive Model deployed on cloud and business systems
MATLAB Integrates in Embedded System and Enterprise IT Workflows
9
25% cost reduction
10
Example – BuildingIQAdaptive building energy management
11
Optimising Energy Costs and Consumption at Building IQ
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!
12
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
optimisation routines Good object-oriented framework Ability to interface with Java (for backend work) Running MATLAB in the cloud in production Unit-testing framework
Why MATLAB?
Robust numerical algorithms Extensive visualization and analytics tools Industry-robust and reliable mathematical
optimisation routines Good object-oriented framework Ability to interface with Java (for backend work) Running MATLAB in the cloud in production Unit-testing framework
Why MATLAB?
Robust numerical algorithms
Industry-robust and reliable mathematical optimisation routines
MATLAB Impeccable Numericsfor Trusted Results
13
Example – ScaniaAutomatic emergency braking using sensor fusion and analytics
14
15
Using Model-Based Designto build and deploy the analyticsin an embedded control system
MATLAB Integrates Analytics andModel-Based Design
16
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
17
The Rise of Engineering‐Driven Analytics
Medical Devices
AeronauticsOff‐highway vehiclesAutomotive
Oil & GasIndustrial Automation Clean Energy
Retail Finance Healthcare management Internet
18
Sensor Data (~1 minute)10-100 sensors/machine
Quality State (~40 minutes)
Classification usingStatistics, Machine Learning, and Neural Networks
Predictive Maintenance for polymer‐based production machines
19
Deployment – a MATLAB App used by machine operators
M153
M157
State OK
State NOT OK
20
21
The need for data scientists
Domain expertise
Coding and integration skills
Statistical and mathematical
knowledge
22
What they say• Expand university programs• Train existing analysts
23
UNSW Student-Designed Solar Electric Vehicle set a World Speed Record for electric car over 500km
“MATLAB is used throughout the engineering curriculum at UNSW, most students on the Sunswiftteam had used it before to solve engineering problems. Second, MATLAB was readily available.”
Robert Makepeace, assistant team leader of Sunswift(2015)
24
TODAY,74% of AU university students
have access to MATLAB at home and personal computers.
~944,000 students
25
MATLAB lets you be your own data scientist
MATLAB is Designed and Documented to be Easy for
Engineers and Scientists to Use
26
Big Data Compute Power
Machine Learning
Limited users, scope, & technology
• Engineering data• Database
• Datastore• Map Reduce
Pervasive users, scope, & technology
• Engineering• Business• Transactional
• Desktop ‐Multicore, GPU
• Clusters• Cloud computing• Hadoop
• Neural Networks• Classification• Clustering• Regression
In MATLAB • Parallel computing• Multicore, cluster, cloud• Production servers
• Hadoop
• Statistics• Machine Learning• Neural Networks
• Classification App• Deep learning• C code generation for machine
learning
27
Example –First consumer otoscope in a mobile devicemachine learning and computer vision
28
The Rise of Engineering‐Driven Analytics
Be your own Data Scientist!
Big Data Compute Power
Machine Learning
Limited users, scope, & technology
Pervasive users, scope, & technology
29
AgendaTime Session10:00 a.m. What’s New in MATLAB10:30 a.m. Morning Tea and Networking11:00 a.m. What’s New in Simulink11:30 a.m. Customer Presentation TBD12:00 p.m. Lunch and Networking
Technical Computing Model-Based Design1:00 p.m. Deep Learning and Data Analytics with
MATLABModel-Based Design:Design with Simulation in Simulink
1:45 p.m. Predictive Maintenance with MATLAB Model-Based Design: Generating Embedded Code for Prototyping or Production
2:30 p.m. Afternoon Tea and Networking3:00 p.m. Partner Presentations3:30 p.m. End of the day
30
31