Modelle für die Zukunft dank prädiktiver Datenanalyse

Transcription

1 Modelle für die Zukunft dank prädiktiver Datenanalyse Jérémy Huard, MathWorks 2015 The MathWorks, Inc. 1

2 2

3 Temperatures change Humans have comfort bounds u t α 2 u x u y u z 2 = 0 Thermodynamic properties Electricity demand varies 3

4 4

5 Traits of Data Analytics applications 1. Diverse and/or Big Data 2. Advanced Algorithms 3. Deployment 5

6 Why MATLAB? 3 Develop embedded systems with analytics powered functionality 1 DATA Engineering, Scientific, and Field Business and Transactional Analytics that increasingly require both business and engineering data 4 Develop analytics to run on both enterprise and embedded platforms Embedded Systems 2 Enable Domain Experts to be Data Scientists Business Systems Data Scientist 6

7 Why MATLAB? 3 Develop embedded systems with analytics powered functionality 1 DATA Engineering, Scientific, and Field Business and Transactional Analytics that increasingly require both business and engineering data 4 Develop analytics to run on both enterprise and embedded platforms Smarter Embedded Systems 2 Enable Domain Experts to be Data Scientists Business Systems Data Scientist 7

8 Business and Engineering Data Business and Transactional Data Engineering, Scientific, and Field Data Repositories Databases Hadoop File I/O Text Spreadsheet XML Web Sources HTML Mapping Financial datafeeds RESTful JSON File I/O Text Spreadsheet XML CDF/HDF Image Audio Video Geospatial Communication Protocols CAN (Controller Area Network) DDS (Data Distribution Service) OPC (OLE for Process Control) XCP (explicit Control Protocol) Real-Time Sources Sensors GPS Instrumentation Cameras Communication systems Machines (embedded systems) No matter what industry our client is in, and no matter what data they ask us to analyze text, audio, images, or video MATLAB enables us to provide clear results faster. Dr. G Subrahmanya VRK Rao, Cognizant 8

9 Data handling and visualization 9

10 High-quality Feature Engineering domain-specific Extracting libraries Information from Data Data type Common Techniques for Deriving Features Sensor data Peak analysis Pulse and transition metrics Spectral measurements Signal (power, Processing bandwidth, mean frequency, median frequency) Image and video data Bag of visual words HOG (Histogram of Oriented Gradients) Minimum Eigenvalue algorithm Local feature descriptors Edge detection Image Processing Computer Vision Transactional data Decomposing timestamps into components (day, month, day of week, etc.) Calculation of aggregate Statistics values Complexity reduction 10

11 Why MATLAB? 3 Develop embedded systems with analytics powered functionality 1 DATA Engineering, Scientific, and Field Business and Transactional Analytics that increasingly require both business and engineering data 4 Develop analytics to run on both enterprise and embedded platforms Smarter Embedded Systems 2 Enable Domain Experts to be Data Scientists Business Systems Data Scientist 11

12 Enabling Domain Experts to be Data Scientists Machine Learning Statistics Image Processing Apps Language Neural Networks Signal Processing Optimization Control Systems Financial Modeling Symbolic Computing 12

13 Built-in algorithms Clustering Classification Regression 13

14 Interactive Apps to focus on machine learning, not programing Neural network Apps Classification Learner App Features Train models Assess results Export models to the MATLAB or generate MATLAB code 14

15 Why MATLAB? 3 Develop embedded systems with analytics powered functionality 1 DATA Engineering, Scientific, and Field Business and Transactional Analytics that increasingly require both business and engineering data 4 Develop analytics to run on both enterprise and embedded platforms Smarter Embedded Systems 2 Enable Domain Experts to be Data Scientists Business Systems Data Scientist 15

16 Smarter Embedded Systems RESEARCH REQUIREMENTS DESIGN C, C++ Environment Models Physical Components Algorithms IMPLEMENTATION VHDL, Verilog Structured Text TEST AND VERIFICATION Airbus Battery management Sonova Hearing implants GM Climate control Weinmann Transport ventilator Festo Industrial robots ABB Smart Grid controller MCU DSP FPGA ASIC PLC INTEGRATION manroland Printing presses FLIR Thermal imaging Daimler Cruise controller 16

17 Why MATLAB? 3 Develop embedded systems with analytics powered functionality 1 DATA Engineering, Scientific, and Field Business and Transactional Analytics that increasingly require both business and engineering data 4 Develop analytics to run on both enterprise and embedded platforms Smarter Embedded Systems 2 Enable Domain Experts to be Data Scientists Business Systems Data Scientist 17

18 Deploying Algorithms to Enterprise Systems MATLAB MATLAB Compiler MATLAB Compiler SDK Standalone Application Excel Add-in C/C ++.NET MATLAB Production Server Hadoop Python Java MATLAB Compiler enables sharing MATLAB programs without integration programming MATLAB Compiler SDK provides implementation and platform flexibility for software developers MATLAB Production Server provides the most efficient development path for secure and scalable web and enterprise applications 18

19 Enterprise Integration Forecasting Model 19

20 MATLAB Differentiators 3 Develop embedded systems with analytics powered functionality 1 DATA Engineering, Scientific, and Field Business and Transactional Analytics that increasingly require both business and engineering data 4 Develop analytics to run on both enterprise and embedded platforms Smarter Embedded Systems 2 Enable Domain Experts to be Data Scientists Business Systems Data Scientist 20

21 Learn More Presentations Machine Learning mathworks.com/machine-learning Consulting Training 21