data science popup austin: applied machine learning for iot
TRANSCRIPT
![Page 1: Data Science Popup Austin: Applied Machine Learning for IOT](https://reader034.vdocuments.mx/reader034/viewer/2022051709/586e73131a28ab99598b5335/html5/thumbnails/1.jpg)
DATA SCIENCEPOP UP
AUSTIN
Applied Machine Learning for IoT
Hank RoarkData Scientist & Hacker, H20.ai
hankroark
![Page 2: Data Science Popup Austin: Applied Machine Learning for IOT](https://reader034.vdocuments.mx/reader034/viewer/2022051709/586e73131a28ab99598b5335/html5/thumbnails/2.jpg)
DATA SCIENCEPOP UP
AUSTIN
#datapopupaustin
April 13, 2016Galvanize, Austin Campus
![Page 4: Data Science Popup Austin: Applied Machine Learning for IOT](https://reader034.vdocuments.mx/reader034/viewer/2022051709/586e73131a28ab99598b5335/html5/thumbnails/4.jpg)
Appl iedMachineLearningfor IoT
HankRoark
13-April-2016DataSciencePop-upAustin
![Page 5: Data Science Popup Austin: Applied Machine Learning for IOT](https://reader034.vdocuments.mx/reader034/viewer/2022051709/586e73131a28ab99598b5335/html5/thumbnails/5.jpg)
WHOAMI I
Lead,[email protected]
JohnDeere:Research,SoftwareProductDevelopment,HighTechVenturesLotsoftimedealingwithdataoffofmachines,equipment,satellites,weather,radar,handsampled,andon.Geospatial,temporal/timeseriesdataalmostallfromsensors.
SystemsDesignandManagement:MITPhysics:GeorgiaTech
[email protected] @hankroarkhttps://www.linkedin.com/in/hankroark
![Page 6: Data Science Popup Austin: Applied Machine Learning for IOT](https://reader034.vdocuments.mx/reader034/viewer/2022051709/586e73131a28ab99598b5335/html5/thumbnails/6.jpg)
WHYIOT?
Because it’s trending (so it must be promising)!
Internet of Things
Deep Learning
![Page 7: Data Science Popup Austin: Applied Machine Learning for IOT](https://reader034.vdocuments.mx/reader034/viewer/2022051709/586e73131a28ab99598b5335/html5/thumbnails/7.jpg)
IF YOUAREINTODATA,THEIOTHASIT
![Page 8: Data Science Popup Austin: Applied Machine Learning for IOT](https://reader034.vdocuments.mx/reader034/viewer/2022051709/586e73131a28ab99598b5335/html5/thumbnails/8.jpg)
LOTSOFDATA
![Page 9: Data Science Popup Austin: Applied Machine Learning for IOT](https://reader034.vdocuments.mx/reader034/viewer/2022051709/586e73131a28ab99598b5335/html5/thumbnails/9.jpg)
LOTSOFDATA
GETREADYFORBRONTOBYTES!!
![Page 10: Data Science Popup Austin: Applied Machine Learning for IOT](https://reader034.vdocuments.mx/reader034/viewer/2022051709/586e73131a28ab99598b5335/html5/thumbnails/10.jpg)
WOW,HOWBIGIS ABRONTOBYTE?
![Page 11: Data Science Popup Austin: Applied Machine Learning for IOT](https://reader034.vdocuments.mx/reader034/viewer/2022051709/586e73131a28ab99598b5335/html5/thumbnails/11.jpg)
Image courtesy http://www.telecom-cloud.net/wp-content/uploads/2015/05/Screen-Shot-2015-05-27-at-3.51.47-PM.png
I OT ARCH I T EC TURE I S S E TUP FOR RE IN FORC ING , E XPONENT IA L GROWTH
![Page 12: Data Science Popup Austin: Applied Machine Learning for IOT](https://reader034.vdocuments.mx/reader034/viewer/2022051709/586e73131a28ab99598b5335/html5/thumbnails/12.jpg)
MYPARTICULARCURIOSITY
![Page 13: Data Science Popup Austin: Applied Machine Learning for IOT](https://reader034.vdocuments.mx/reader034/viewer/2022051709/586e73131a28ab99598b5335/html5/thumbnails/13.jpg)
EXAMPLEFROMTHEIOTDomain:PrognosticsandHealthManagementMachine:TurbofanJetEnginesDataSet:A.SaxenaandK.Goebel(2008)."TurbofanEngineDegradationSimulationDataSet",NASAAmesPrognosticsDataRepository
PredictRemainingUsefulLifefromPartialLifeRuns
Sixoperatingmodes,twofailuremodes,manufacturingvariability
Training:249jetenginesruntofailureTest:248jetengines
![Page 14: Data Science Popup Austin: Applied Machine Learning for IOT](https://reader034.vdocuments.mx/reader034/viewer/2022051709/586e73131a28ab99598b5335/html5/thumbnails/14.jpg)
SENSORSSHOWTRENDSOVERTIME
Time
We also know remaining useful lifedecreases by at least one (1) cycle each operation.
How can one take advantage of this knowledge?
![Page 15: Data Science Popup Austin: Applied Machine Learning for IOT](https://reader034.vdocuments.mx/reader034/viewer/2022051709/586e73131a28ab99598b5335/html5/thumbnails/15.jpg)
INCORPORATINGPRIORSTATE
Disentangling the dynamic core: a research program for a neurodynamics at the large-scale MICHEL LE VAN QUYEN Biol. Res. v.36 n.1 Santiago 2003 http://dx.doi.org/10.4067/S0716-97602003000100006
One option: Phase Space Embedding
Drawbacks: Incorporates knowledge from onlysmall number of prior states
Curse of dimensionality
Another parameter (tau)
![Page 16: Data Science Popup Austin: Applied Machine Learning for IOT](https://reader034.vdocuments.mx/reader034/viewer/2022051709/586e73131a28ab99598b5335/html5/thumbnails/16.jpg)
KALMANFILTER
![Page 17: Data Science Popup Austin: Applied Machine Learning for IOT](https://reader034.vdocuments.mx/reader034/viewer/2022051709/586e73131a28ab99598b5335/html5/thumbnails/17.jpg)
FINALPIPELINE
Featureengineering• Signalprocessing,featurecreation,featureselection
Regression Models• Supervised
MachineLearning(H2O)
PostProcessing• Kalmanfilter(pykalman,inthiscase)
Not really that much different than typical machine learning pipeline
![Page 18: Data Science Popup Austin: Applied Machine Learning for IOT](https://reader034.vdocuments.mx/reader034/viewer/2022051709/586e73131a28ab99598b5335/html5/thumbnails/18.jpg)
BEFOREANDAFTERPOST-PROCESSING
CYCLE NUMBER CYCLE NUMBER
PR
ED
ICTE
D R
UL
UNIT #2UNIT #2
This presentation, data, and associated Jupyter notebooks (look in 2016_04_13_AppliedMachineLearningForIoT):https://github.com/h2oai/h2o-meetups/
![Page 19: Data Science Popup Austin: Applied Machine Learning for IOT](https://reader034.vdocuments.mx/reader034/viewer/2022051709/586e73131a28ab99598b5335/html5/thumbnails/19.jpg)
WHYH2O
FLEETTELEMATICS:PREVENTIVEMAINTENANCE
PROBLEM
• H2Osupportforcustomer’sKerberosauthenticationmechanismforHadoop
• SupportforMapReduce,YARN,R,PythonandSparkinHadoop
• In-memory,distributedarchitecture • RapiddeploymenttoproductionwithPOJO • QuickprototypingwithH2OFlow
• Fleettelematics—analyzemaintenancerecordsandvehicleperformancetomakepredictionsonwhentodopreventivemaintenance
• Couldn’tscalebysamplingdata • Tookdaystocreatemodels
IMPACT
“AnnualSavingsare$7M” –Anonymized,MemberTechnicalStaff
• Whenyoulookatthecostoftowingastrandedvehicle,technicianlossofproductivity,andthecustomerlifetimevalue,theannualsavingsis$7M.”–Anonymized,LeadMemberTechnicalStaff
Leading Mobile Telecom Operator
Telecommunications
![Page 20: Data Science Popup Austin: Applied Machine Learning for IOT](https://reader034.vdocuments.mx/reader034/viewer/2022051709/586e73131a28ab99598b5335/html5/thumbnails/20.jpg)
TAKE-AWAYS
• Knowyour“physics”o ”Physics”iswillbelikeafishfinderinthisseaofBrontobytes
o Lineardynamicsystems,Queues,Signals,etc.• BigdataandBigmodelsandSmallmodels• Keepingandeyeonpromisingnewmethods(e.g.,ConvolutionNeuralNetsandLSTM-RNN)
![Page 21: Data Science Popup Austin: Applied Machine Learning for IOT](https://reader034.vdocuments.mx/reader034/viewer/2022051709/586e73131a28ab99598b5335/html5/thumbnails/21.jpg)
H2ORESOURCES
• Downloadandgo:http://www.h2o.ai/download• Documentation:http://docs.h2o.ai/• Booklets,Datasheet:http://www.h2o.ai/resources/• Github:http://github.com/h2oai/• Training:http://learn.h2o.ai/
![Page 22: Data Science Popup Austin: Applied Machine Learning for IOT](https://reader034.vdocuments.mx/reader034/viewer/2022051709/586e73131a28ab99598b5335/html5/thumbnails/22.jpg)
THANKYOU
![Page 23: Data Science Popup Austin: Applied Machine Learning for IOT](https://reader034.vdocuments.mx/reader034/viewer/2022051709/586e73131a28ab99598b5335/html5/thumbnails/23.jpg)
DATA SCIENCEPOP UP
AUSTIN
@datapopup #datapopupaustin