SlideShare a Scribd company logo
1 of 57
Download to read offline
DERIVING MEANING FROM
WEARABLE SENSOR DATA
SAMEERA PODURI
@sameerapoduri
1530 pocket watch
wrist watch1810
digital watch1969
1530 pocket watch
wrist watch1810
digital watch1969
mobile phone1973
smartphone2008
2016 ?
• batteries shrinking
• small + low-power sensors, compute, comms
24/7 sensor data platforms!
DATA SCIENCE FOR WEARABLES:
PERCEPTION & PERSONALIZATION
• Hardware is maturing
• Sensor data is growing exponentially
• Unlocking potential requires deriving meaning from data
BEAUTY + ENGINEERING IN SERVICE OF A BETTER LIFE
Measure steps, sleep states, workouts, heart rate
DynamoDB
Kinesis
Eventing Data
JB server
User Data
Platform
Redshift
Processing
DATA INFRASTRUCTURE
DETECTING ACTIVITY & SLEEP
PEDOMETER
PEDOMETER
theory
real data
GOT DATA?
1. Deploy a model
2. Collect data
3. Retrain model
4. A/B Test
5. Repeat
PEDOMETER
Classifier
SLEEP DETECTION
SIGNALS Raw, rich Partly compressed, rich Compressed
CONTEXT Limited Sensor fusion
History, population,
weather, etc
USERS Single Single Aggregate
WHERE TO DEPLOY?
DATA PRODUCTS FOR HARDWARE
LATENCY Seconds Minutes
Minutes
+ Network delays
COMPUTE Limited Powerful
DEPLOYMENT Months Weeks Hours
WHERE TO DEPLOY?
Version 0
Most common workout 58% Accuracy
Version 1
Last workout 15% lift
Version 2
WORKOUT CLASSIFICATION
PERSONALIZED INSIGHTS
• How can I understand this data?
• How should I feel about what it tells me?
• What action should I take in response?
Smart Coach Remembers
Remember how you took 45,365 steps on July 4?
Smart Coach remembers! On your health journey,
don't forget to stop and celebrate.
Step Update
Smart Coach noticed a surge in activity. In fact,
you surpassed 9,690 steps, your typical
5:00pm average.
Last night you had 35m of REM sleep, less than
the 1h9m that is typical for your age group. One
way to improve your chances for more REM is to
try an earlier bedtime than last night's 12:35am.
You can set a bedtime Reminder for 11:35pm to
help.
REM TimeLong Journey?
Looks like you've been traveling recently, which
can throw off your routine. Try setting a bedtime
reminder for tonight to help you adjust.
Your daily average of 17,543 steps places you
in the top 3% of UP females in their 30s.
Bravo, Angela.
Welcome to the 3%
DynamoDB Redshift
User Facts
Insights
HEART RATE
“Your heart rate is 85 beats per minute.”
CONTEXT MATTERS
This morning’s resting heart rate was higher
than 61bpm, your 30-day average.
Dehydration may be the cause. If you think
you were dehydrated last night, make up for
it today with 8 glasses of water.
Start with Hydration
BEHAVIOR CHANGE
BEHAVIOR CHANGE
Commitment and
Consistency
Source: Cialdini, R. B. (2009). Influence: Science and
practice (5th edition). Boston, MA: Pearson Education.
BEHAVIOR CHANGE
Commitment and
Consistency
Foot In The Door
Technique
Source: Freedman, J.L. & Fraser, S.C. (1966). Compliance
without pressure: The foot-in-the-door technique. Journal of
Personality and Social Psychology, 4, 195-202.
BEHAVIOR CHANGE
Commitment and
Consistency
Foot In The Door
Technique
Goldilocks Tasks
Source: Pink, Daniel (2009). Drive: The Surprising Truth
About What Motivates Us. New York, NY: Riverhead Books.
BEHAVIOR CHANGE
Commitment and
Consistency
Foot In The Door
Technique
Goldilocks Tasks
Source: Carpenter, Chris. (2013) A meta-analysis of the
effectiveness of the "but you are free" compliance-gaining
technique
Reactance
BEHAVIOR CHANGE
72%Increased likelihood to go to
bed early enough to hit their
sleep goal
23mMinutes earlier to bed,
compared to if they didn’t
receive a TIW
BEHAVIOR CHANGE
DATA STORIES
HUNDREDS OF MILLIONS
NIGHTS OF SLEEP
TRILLIONS OF
STEPS
HUNDREDS OF MILLIONS
FOOD ITEMS
“The fact that the tracker
measured my sleep and my
activity level was a big part of
my recovery. I had this way to
‘metric’ my body as I went
through this. Sleep is so
important in brain function
anyway, and when you're
recovering from a brain injury,
it's even more important.”
PARTING THOUGHTS…
• Wearables will help us live healthier
• Health data at unprecedented scale and granularity
• Data Science can play a critical role in unlocking their potential
by deriving meaning from this sensor data
• Sensor and Accelerometer data

• > 1GB/sec aggregated across users

• Compacted on band into code-words
UP Band Phone
{
steps: 12,
hr: 78,
ts: 1455741797
…..
….
}
• Phone adds context to band signals 

• Collects eventing and logging data from app

• Eventing/Logging passes through Kinesis 

• User data is stored in the appropriate DB
Kinesis
Eventing Data
JB server
User Data
Phone Server
Platform
• Run batch ETL jobs using
Elastic MapReduce to
clean and process data.

• Choose the appropriate
processing framework
depending on type of job
(Hadoop/Spark)

• Store cleaned and
anonymized data in
Redshift.
Server Warehouse
Kinesis
Platform
Redshift
Processing
Aggregations
New tables of
interest
ETL Pipeline
Analyze Fields
Redshift
Add columns
Load
Kinesis
Extract
Aggregations
New tables
of interest
Transform
Create config
ANALYSIS AND EXPLORATION
WEARABLES FOR BETTER HEALTH
Chronic disease care is 86% of US healthcare cost
• Diabetes affects 12.3% population, costs $245B
• Obesity affects 36% population, costs

More Related Content

Viewers also liked

DataEngConf SF16 - BYOMQ: Why We [re]Built IronMQ
DataEngConf SF16 - BYOMQ: Why We [re]Built IronMQDataEngConf SF16 - BYOMQ: Why We [re]Built IronMQ
DataEngConf SF16 - BYOMQ: Why We [re]Built IronMQHakka Labs
 
DataEngConf SF16 - Beginning with Ourselves
DataEngConf SF16 - Beginning with OurselvesDataEngConf SF16 - Beginning with Ourselves
DataEngConf SF16 - Beginning with OurselvesHakka Labs
 
DataEngConf SF16 - Routing Billions of Analytics Events with High Deliverability
DataEngConf SF16 - Routing Billions of Analytics Events with High DeliverabilityDataEngConf SF16 - Routing Billions of Analytics Events with High Deliverability
DataEngConf SF16 - Routing Billions of Analytics Events with High DeliverabilityHakka Labs
 
DataEngConf SF16 - Collecting and Moving Data at Scale
DataEngConf SF16 - Collecting and Moving Data at Scale DataEngConf SF16 - Collecting and Moving Data at Scale
DataEngConf SF16 - Collecting and Moving Data at Scale Hakka Labs
 
DataEngConf SF16 - Tales from the other side - What a hiring manager wish you...
DataEngConf SF16 - Tales from the other side - What a hiring manager wish you...DataEngConf SF16 - Tales from the other side - What a hiring manager wish you...
DataEngConf SF16 - Tales from the other side - What a hiring manager wish you...Hakka Labs
 
DataEngConf SF16 - Unifying Real Time and Historical Analytics with the Lambd...
DataEngConf SF16 - Unifying Real Time and Historical Analytics with the Lambd...DataEngConf SF16 - Unifying Real Time and Historical Analytics with the Lambd...
DataEngConf SF16 - Unifying Real Time and Historical Analytics with the Lambd...Hakka Labs
 
DataEngConf SF16 - Recommendations at Instacart
DataEngConf SF16 - Recommendations at InstacartDataEngConf SF16 - Recommendations at Instacart
DataEngConf SF16 - Recommendations at InstacartHakka Labs
 
Always Valid Inference (Ramesh Johari, Stanford)
Always Valid Inference (Ramesh Johari, Stanford)Always Valid Inference (Ramesh Johari, Stanford)
Always Valid Inference (Ramesh Johari, Stanford)Hakka Labs
 
DataEngConf SF16 - Multi-temporal Data Structures
DataEngConf SF16 - Multi-temporal Data StructuresDataEngConf SF16 - Multi-temporal Data Structures
DataEngConf SF16 - Multi-temporal Data StructuresHakka Labs
 
DataEngConf: Apache Spark in Financial Modeling at BlackRock
DataEngConf: Apache Spark in Financial Modeling at BlackRock DataEngConf: Apache Spark in Financial Modeling at BlackRock
DataEngConf: Apache Spark in Financial Modeling at BlackRock Hakka Labs
 
DataEngConf: Feature Extraction: Modern Questions and Challenges at Google
DataEngConf: Feature Extraction: Modern Questions and Challenges at GoogleDataEngConf: Feature Extraction: Modern Questions and Challenges at Google
DataEngConf: Feature Extraction: Modern Questions and Challenges at GoogleHakka Labs
 
DatEngConf SF16 - Apache Kudu: Fast Analytics on Fast Data
DatEngConf SF16 - Apache Kudu: Fast Analytics on Fast DataDatEngConf SF16 - Apache Kudu: Fast Analytics on Fast Data
DatEngConf SF16 - Apache Kudu: Fast Analytics on Fast DataHakka Labs
 
A Primer on Entity Resolution
A Primer on Entity ResolutionA Primer on Entity Resolution
A Primer on Entity ResolutionBenjamin Bengfort
 

Viewers also liked (13)

DataEngConf SF16 - BYOMQ: Why We [re]Built IronMQ
DataEngConf SF16 - BYOMQ: Why We [re]Built IronMQDataEngConf SF16 - BYOMQ: Why We [re]Built IronMQ
DataEngConf SF16 - BYOMQ: Why We [re]Built IronMQ
 
DataEngConf SF16 - Beginning with Ourselves
DataEngConf SF16 - Beginning with OurselvesDataEngConf SF16 - Beginning with Ourselves
DataEngConf SF16 - Beginning with Ourselves
 
DataEngConf SF16 - Routing Billions of Analytics Events with High Deliverability
DataEngConf SF16 - Routing Billions of Analytics Events with High DeliverabilityDataEngConf SF16 - Routing Billions of Analytics Events with High Deliverability
DataEngConf SF16 - Routing Billions of Analytics Events with High Deliverability
 
DataEngConf SF16 - Collecting and Moving Data at Scale
DataEngConf SF16 - Collecting and Moving Data at Scale DataEngConf SF16 - Collecting and Moving Data at Scale
DataEngConf SF16 - Collecting and Moving Data at Scale
 
DataEngConf SF16 - Tales from the other side - What a hiring manager wish you...
DataEngConf SF16 - Tales from the other side - What a hiring manager wish you...DataEngConf SF16 - Tales from the other side - What a hiring manager wish you...
DataEngConf SF16 - Tales from the other side - What a hiring manager wish you...
 
DataEngConf SF16 - Unifying Real Time and Historical Analytics with the Lambd...
DataEngConf SF16 - Unifying Real Time and Historical Analytics with the Lambd...DataEngConf SF16 - Unifying Real Time and Historical Analytics with the Lambd...
DataEngConf SF16 - Unifying Real Time and Historical Analytics with the Lambd...
 
DataEngConf SF16 - Recommendations at Instacart
DataEngConf SF16 - Recommendations at InstacartDataEngConf SF16 - Recommendations at Instacart
DataEngConf SF16 - Recommendations at Instacart
 
Always Valid Inference (Ramesh Johari, Stanford)
Always Valid Inference (Ramesh Johari, Stanford)Always Valid Inference (Ramesh Johari, Stanford)
Always Valid Inference (Ramesh Johari, Stanford)
 
DataEngConf SF16 - Multi-temporal Data Structures
DataEngConf SF16 - Multi-temporal Data StructuresDataEngConf SF16 - Multi-temporal Data Structures
DataEngConf SF16 - Multi-temporal Data Structures
 
DataEngConf: Apache Spark in Financial Modeling at BlackRock
DataEngConf: Apache Spark in Financial Modeling at BlackRock DataEngConf: Apache Spark in Financial Modeling at BlackRock
DataEngConf: Apache Spark in Financial Modeling at BlackRock
 
DataEngConf: Feature Extraction: Modern Questions and Challenges at Google
DataEngConf: Feature Extraction: Modern Questions and Challenges at GoogleDataEngConf: Feature Extraction: Modern Questions and Challenges at Google
DataEngConf: Feature Extraction: Modern Questions and Challenges at Google
 
DatEngConf SF16 - Apache Kudu: Fast Analytics on Fast Data
DatEngConf SF16 - Apache Kudu: Fast Analytics on Fast DataDatEngConf SF16 - Apache Kudu: Fast Analytics on Fast Data
DatEngConf SF16 - Apache Kudu: Fast Analytics on Fast Data
 
A Primer on Entity Resolution
A Primer on Entity ResolutionA Primer on Entity Resolution
A Primer on Entity Resolution
 

Similar to DataEngConf SF16 - Deriving Meaning from Wearable Sensor Data

sameera_poduri_dataEngConf
sameera_poduri_dataEngConfsameera_poduri_dataEngConf
sameera_poduri_dataEngConfSameera Poduri
 
Using raspberry pi to capture environmental factors that affect sleep
Using raspberry pi to capture environmental factors that affect sleepUsing raspberry pi to capture environmental factors that affect sleep
Using raspberry pi to capture environmental factors that affect sleepTao Tang-Little
 
Final project ppt.pptx
Final project ppt.pptxFinal project ppt.pptx
Final project ppt.pptxMalathyN5
 
Quantified-Self and Lifelogging Meets Internet of Things (IOT)
Quantified-Self and Lifelogging Meets Internet of Things (IOT)Quantified-Self and Lifelogging Meets Internet of Things (IOT)
Quantified-Self and Lifelogging Meets Internet of Things (IOT)Dr. Mazlan Abbas
 
Casper Dream Team Application User Research Report
Casper Dream Team Application User Research Report Casper Dream Team Application User Research Report
Casper Dream Team Application User Research Report David Delgadø
 
Machine learning and Internet of Things, the future of medical prevention
Machine learning and Internet of Things, the future of medical preventionMachine learning and Internet of Things, the future of medical prevention
Machine learning and Internet of Things, the future of medical preventionPierre Gutierrez
 
BodyTrack QS Presentation, July 19, 2011
BodyTrack QS Presentation, July 19, 2011BodyTrack QS Presentation, July 19, 2011
BodyTrack QS Presentation, July 19, 2011annerwright
 
Analysis of Biometric Data for Memory Augmentation using a SenseCam (midterm)
Analysis of Biometric Data for Memory Augmentation using a SenseCam (midterm)Analysis of Biometric Data for Memory Augmentation using a SenseCam (midterm)
Analysis of Biometric Data for Memory Augmentation using a SenseCam (midterm)odcsss
 
DRIVE 2017 | 25 October - THE HUMAN TOUCH - Meaningful Data & Smart Fashion
DRIVE 2017 | 25 October - THE HUMAN TOUCH - Meaningful Data & Smart FashionDRIVE 2017 | 25 October - THE HUMAN TOUCH - Meaningful Data & Smart Fashion
DRIVE 2017 | 25 October - THE HUMAN TOUCH - Meaningful Data & Smart FashionCLICKNL
 
Data Science, Big Data and You
Data Science, Big Data and YouData Science, Big Data and You
Data Science, Big Data and YouJoel Saltz
 
Sh brief sleep_external
Sh brief sleep_externalSh brief sleep_external
Sh brief sleep_externalstealthhealth
 
Dino DNA! Health Identity from the Wrist @Jawbone
Dino DNA! Health Identity from the Wrist @JawboneDino DNA! Health Identity from the Wrist @Jawbone
Dino DNA! Health Identity from the Wrist @JawboneC4Media
 
ReLUs: An Alternative to the ReLU Activation Function - Wilder Rodrigues - Co...
ReLUs: An Alternative to the ReLU Activation Function - Wilder Rodrigues - Co...ReLUs: An Alternative to the ReLU Activation Function - Wilder Rodrigues - Co...
ReLUs: An Alternative to the ReLU Activation Function - Wilder Rodrigues - Co...Codemotion
 
Top 10 Mobile Health Apps of 2011
Top 10 Mobile Health Apps of 2011Top 10 Mobile Health Apps of 2011
Top 10 Mobile Health Apps of 2011Tyler Soliday
 
Philips Digital Health Dinner at SxSW
Philips Digital Health Dinner at SxSWPhilips Digital Health Dinner at SxSW
Philips Digital Health Dinner at SxSWRobin Raskin
 
Best prac­tices to assess and enhance brain func­tion via mobile devices and ...
Best prac­tices to assess and enhance brain func­tion via mobile devices and ...Best prac­tices to assess and enhance brain func­tion via mobile devices and ...
Best prac­tices to assess and enhance brain func­tion via mobile devices and ...SharpBrains
 
What's Next for Health & Wellness - Breaking down Mary Meeker's report
What's Next for Health & Wellness - Breaking down Mary Meeker's reportWhat's Next for Health & Wellness - Breaking down Mary Meeker's report
What's Next for Health & Wellness - Breaking down Mary Meeker's reportOgilvy Consulting
 

Similar to DataEngConf SF16 - Deriving Meaning from Wearable Sensor Data (20)

sameera_poduri_dataEngConf
sameera_poduri_dataEngConfsameera_poduri_dataEngConf
sameera_poduri_dataEngConf
 
Using raspberry pi to capture environmental factors that affect sleep
Using raspberry pi to capture environmental factors that affect sleepUsing raspberry pi to capture environmental factors that affect sleep
Using raspberry pi to capture environmental factors that affect sleep
 
Final project ppt.pptx
Final project ppt.pptxFinal project ppt.pptx
Final project ppt.pptx
 
Quantified-Self and Lifelogging Meets Internet of Things (IOT)
Quantified-Self and Lifelogging Meets Internet of Things (IOT)Quantified-Self and Lifelogging Meets Internet of Things (IOT)
Quantified-Self and Lifelogging Meets Internet of Things (IOT)
 
Casper Dream Team Application User Research Report
Casper Dream Team Application User Research Report Casper Dream Team Application User Research Report
Casper Dream Team Application User Research Report
 
Machine learning and Internet of Things, the future of medical prevention
Machine learning and Internet of Things, the future of medical preventionMachine learning and Internet of Things, the future of medical prevention
Machine learning and Internet of Things, the future of medical prevention
 
BodyTrack QS Presentation, July 19, 2011
BodyTrack QS Presentation, July 19, 2011BodyTrack QS Presentation, July 19, 2011
BodyTrack QS Presentation, July 19, 2011
 
Analysis of Biometric Data for Memory Augmentation using a SenseCam (midterm)
Analysis of Biometric Data for Memory Augmentation using a SenseCam (midterm)Analysis of Biometric Data for Memory Augmentation using a SenseCam (midterm)
Analysis of Biometric Data for Memory Augmentation using a SenseCam (midterm)
 
The Rise of Open Data
The Rise of Open DataThe Rise of Open Data
The Rise of Open Data
 
DRIVE 2017 | 25 October - THE HUMAN TOUCH - Meaningful Data & Smart Fashion
DRIVE 2017 | 25 October - THE HUMAN TOUCH - Meaningful Data & Smart FashionDRIVE 2017 | 25 October - THE HUMAN TOUCH - Meaningful Data & Smart Fashion
DRIVE 2017 | 25 October - THE HUMAN TOUCH - Meaningful Data & Smart Fashion
 
Data Science, Big Data and You
Data Science, Big Data and YouData Science, Big Data and You
Data Science, Big Data and You
 
Sh brief sleep_external
Sh brief sleep_externalSh brief sleep_external
Sh brief sleep_external
 
Dino DNA! Health Identity from the Wrist @Jawbone
Dino DNA! Health Identity from the Wrist @JawboneDino DNA! Health Identity from the Wrist @Jawbone
Dino DNA! Health Identity from the Wrist @Jawbone
 
ReLUs: An Alternative to the ReLU Activation Function - Wilder Rodrigues - Co...
ReLUs: An Alternative to the ReLU Activation Function - Wilder Rodrigues - Co...ReLUs: An Alternative to the ReLU Activation Function - Wilder Rodrigues - Co...
ReLUs: An Alternative to the ReLU Activation Function - Wilder Rodrigues - Co...
 
Top 10 Mobile Health Apps of 2011
Top 10 Mobile Health Apps of 2011Top 10 Mobile Health Apps of 2011
Top 10 Mobile Health Apps of 2011
 
Contextual sleep monitoring innovations for a healthier life
Contextual sleep monitoring innovations for a healthier life Contextual sleep monitoring innovations for a healthier life
Contextual sleep monitoring innovations for a healthier life
 
Medical mirror
Medical mirrorMedical mirror
Medical mirror
 
Philips Digital Health Dinner at SxSW
Philips Digital Health Dinner at SxSWPhilips Digital Health Dinner at SxSW
Philips Digital Health Dinner at SxSW
 
Best prac­tices to assess and enhance brain func­tion via mobile devices and ...
Best prac­tices to assess and enhance brain func­tion via mobile devices and ...Best prac­tices to assess and enhance brain func­tion via mobile devices and ...
Best prac­tices to assess and enhance brain func­tion via mobile devices and ...
 
What's Next for Health & Wellness - Breaking down Mary Meeker's report
What's Next for Health & Wellness - Breaking down Mary Meeker's reportWhat's Next for Health & Wellness - Breaking down Mary Meeker's report
What's Next for Health & Wellness - Breaking down Mary Meeker's report
 

More from Hakka Labs

DataEngConf SF16 - Spark SQL Workshop
DataEngConf SF16 - Spark SQL WorkshopDataEngConf SF16 - Spark SQL Workshop
DataEngConf SF16 - Spark SQL WorkshopHakka Labs
 
DataEngConf: Building a Music Recommender System from Scratch with Spotify Da...
DataEngConf: Building a Music Recommender System from Scratch with Spotify Da...DataEngConf: Building a Music Recommender System from Scratch with Spotify Da...
DataEngConf: Building a Music Recommender System from Scratch with Spotify Da...Hakka Labs
 
DataEngConf: Data Science at the New York Times by Chris Wiggins
DataEngConf: Data Science at the New York Times by Chris WigginsDataEngConf: Data Science at the New York Times by Chris Wiggins
DataEngConf: Data Science at the New York Times by Chris WigginsHakka Labs
 
DataEngConf: Building the Next New York Times Recommendation Engine
DataEngConf: Building the Next New York Times Recommendation EngineDataEngConf: Building the Next New York Times Recommendation Engine
DataEngConf: Building the Next New York Times Recommendation EngineHakka Labs
 
DataEngConf: Measuring Impact with Data in a Distributed World at Conde Nast
DataEngConf: Measuring Impact with Data in a Distributed World at Conde NastDataEngConf: Measuring Impact with Data in a Distributed World at Conde Nast
DataEngConf: Measuring Impact with Data in a Distributed World at Conde NastHakka Labs
 
DataEngConf: Talkographics: Using What Viewers Say Online to Measure TV and B...
DataEngConf: Talkographics: Using What Viewers Say Online to Measure TV and B...DataEngConf: Talkographics: Using What Viewers Say Online to Measure TV and B...
DataEngConf: Talkographics: Using What Viewers Say Online to Measure TV and B...Hakka Labs
 
DataEngConf: The Science of Virality at BuzzFeed
DataEngConf: The Science of Virality at BuzzFeedDataEngConf: The Science of Virality at BuzzFeed
DataEngConf: The Science of Virality at BuzzFeedHakka Labs
 
DataEngConf: Uri Laserson (Data Scientist, Cloudera) Scaling up Genomics with...
DataEngConf: Uri Laserson (Data Scientist, Cloudera) Scaling up Genomics with...DataEngConf: Uri Laserson (Data Scientist, Cloudera) Scaling up Genomics with...
DataEngConf: Uri Laserson (Data Scientist, Cloudera) Scaling up Genomics with...Hakka Labs
 
DataEngConf: Parquet at Datadog: Fast, Efficient, Portable Storage for Big Data
DataEngConf: Parquet at Datadog: Fast, Efficient, Portable Storage for Big DataDataEngConf: Parquet at Datadog: Fast, Efficient, Portable Storage for Big Data
DataEngConf: Parquet at Datadog: Fast, Efficient, Portable Storage for Big DataHakka Labs
 
DataEngConf: Apache Kafka at Rocana: a scalable, distributed log for machine ...
DataEngConf: Apache Kafka at Rocana: a scalable, distributed log for machine ...DataEngConf: Apache Kafka at Rocana: a scalable, distributed log for machine ...
DataEngConf: Apache Kafka at Rocana: a scalable, distributed log for machine ...Hakka Labs
 
DataEngConf: Building Satori, a Hadoop toll for Data Extraction at LinkedIn
DataEngConf: Building Satori, a Hadoop toll for Data Extraction at LinkedInDataEngConf: Building Satori, a Hadoop toll for Data Extraction at LinkedIn
DataEngConf: Building Satori, a Hadoop toll for Data Extraction at LinkedInHakka Labs
 

More from Hakka Labs (11)

DataEngConf SF16 - Spark SQL Workshop
DataEngConf SF16 - Spark SQL WorkshopDataEngConf SF16 - Spark SQL Workshop
DataEngConf SF16 - Spark SQL Workshop
 
DataEngConf: Building a Music Recommender System from Scratch with Spotify Da...
DataEngConf: Building a Music Recommender System from Scratch with Spotify Da...DataEngConf: Building a Music Recommender System from Scratch with Spotify Da...
DataEngConf: Building a Music Recommender System from Scratch with Spotify Da...
 
DataEngConf: Data Science at the New York Times by Chris Wiggins
DataEngConf: Data Science at the New York Times by Chris WigginsDataEngConf: Data Science at the New York Times by Chris Wiggins
DataEngConf: Data Science at the New York Times by Chris Wiggins
 
DataEngConf: Building the Next New York Times Recommendation Engine
DataEngConf: Building the Next New York Times Recommendation EngineDataEngConf: Building the Next New York Times Recommendation Engine
DataEngConf: Building the Next New York Times Recommendation Engine
 
DataEngConf: Measuring Impact with Data in a Distributed World at Conde Nast
DataEngConf: Measuring Impact with Data in a Distributed World at Conde NastDataEngConf: Measuring Impact with Data in a Distributed World at Conde Nast
DataEngConf: Measuring Impact with Data in a Distributed World at Conde Nast
 
DataEngConf: Talkographics: Using What Viewers Say Online to Measure TV and B...
DataEngConf: Talkographics: Using What Viewers Say Online to Measure TV and B...DataEngConf: Talkographics: Using What Viewers Say Online to Measure TV and B...
DataEngConf: Talkographics: Using What Viewers Say Online to Measure TV and B...
 
DataEngConf: The Science of Virality at BuzzFeed
DataEngConf: The Science of Virality at BuzzFeedDataEngConf: The Science of Virality at BuzzFeed
DataEngConf: The Science of Virality at BuzzFeed
 
DataEngConf: Uri Laserson (Data Scientist, Cloudera) Scaling up Genomics with...
DataEngConf: Uri Laserson (Data Scientist, Cloudera) Scaling up Genomics with...DataEngConf: Uri Laserson (Data Scientist, Cloudera) Scaling up Genomics with...
DataEngConf: Uri Laserson (Data Scientist, Cloudera) Scaling up Genomics with...
 
DataEngConf: Parquet at Datadog: Fast, Efficient, Portable Storage for Big Data
DataEngConf: Parquet at Datadog: Fast, Efficient, Portable Storage for Big DataDataEngConf: Parquet at Datadog: Fast, Efficient, Portable Storage for Big Data
DataEngConf: Parquet at Datadog: Fast, Efficient, Portable Storage for Big Data
 
DataEngConf: Apache Kafka at Rocana: a scalable, distributed log for machine ...
DataEngConf: Apache Kafka at Rocana: a scalable, distributed log for machine ...DataEngConf: Apache Kafka at Rocana: a scalable, distributed log for machine ...
DataEngConf: Apache Kafka at Rocana: a scalable, distributed log for machine ...
 
DataEngConf: Building Satori, a Hadoop toll for Data Extraction at LinkedIn
DataEngConf: Building Satori, a Hadoop toll for Data Extraction at LinkedInDataEngConf: Building Satori, a Hadoop toll for Data Extraction at LinkedIn
DataEngConf: Building Satori, a Hadoop toll for Data Extraction at LinkedIn
 

Recently uploaded

Unblocking The Main Thread Solving ANRs and Frozen Frames
Unblocking The Main Thread Solving ANRs and Frozen FramesUnblocking The Main Thread Solving ANRs and Frozen Frames
Unblocking The Main Thread Solving ANRs and Frozen FramesSinan KOZAK
 
Presentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreterPresentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreternaman860154
 
Partners Life - Insurer Innovation Award 2024
Partners Life - Insurer Innovation Award 2024Partners Life - Insurer Innovation Award 2024
Partners Life - Insurer Innovation Award 2024The Digital Insurer
 
Boost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivityBoost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivityPrincipled Technologies
 
Histor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slideHistor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slidevu2urc
 
The Codex of Business Writing Software for Real-World Solutions 2.pptx
The Codex of Business Writing Software for Real-World Solutions 2.pptxThe Codex of Business Writing Software for Real-World Solutions 2.pptx
The Codex of Business Writing Software for Real-World Solutions 2.pptxMalak Abu Hammad
 
Salesforce Community Group Quito, Salesforce 101
Salesforce Community Group Quito, Salesforce 101Salesforce Community Group Quito, Salesforce 101
Salesforce Community Group Quito, Salesforce 101Paola De la Torre
 
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptxHampshireHUG
 
A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)Gabriella Davis
 
The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024Rafal Los
 
GenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day PresentationGenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day PresentationMichael W. Hawkins
 
Factors to Consider When Choosing Accounts Payable Services Providers.pptx
Factors to Consider When Choosing Accounts Payable Services Providers.pptxFactors to Consider When Choosing Accounts Payable Services Providers.pptx
Factors to Consider When Choosing Accounts Payable Services Providers.pptxKatpro Technologies
 
How to convert PDF to text with Nanonets
How to convert PDF to text with NanonetsHow to convert PDF to text with Nanonets
How to convert PDF to text with Nanonetsnaman860154
 
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...Neo4j
 
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdfThe Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdfEnterprise Knowledge
 
[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdf[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdfhans926745
 
Exploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone ProcessorsExploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone Processorsdebabhi2
 
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptxEIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptxEarley Information Science
 
A Call to Action for Generative AI in 2024
A Call to Action for Generative AI in 2024A Call to Action for Generative AI in 2024
A Call to Action for Generative AI in 2024Results
 
Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...
Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...
Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...Neo4j
 

Recently uploaded (20)

Unblocking The Main Thread Solving ANRs and Frozen Frames
Unblocking The Main Thread Solving ANRs and Frozen FramesUnblocking The Main Thread Solving ANRs and Frozen Frames
Unblocking The Main Thread Solving ANRs and Frozen Frames
 
Presentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreterPresentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreter
 
Partners Life - Insurer Innovation Award 2024
Partners Life - Insurer Innovation Award 2024Partners Life - Insurer Innovation Award 2024
Partners Life - Insurer Innovation Award 2024
 
Boost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivityBoost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivity
 
Histor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slideHistor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slide
 
The Codex of Business Writing Software for Real-World Solutions 2.pptx
The Codex of Business Writing Software for Real-World Solutions 2.pptxThe Codex of Business Writing Software for Real-World Solutions 2.pptx
The Codex of Business Writing Software for Real-World Solutions 2.pptx
 
Salesforce Community Group Quito, Salesforce 101
Salesforce Community Group Quito, Salesforce 101Salesforce Community Group Quito, Salesforce 101
Salesforce Community Group Quito, Salesforce 101
 
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
 
A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)
 
The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024
 
GenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day PresentationGenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day Presentation
 
Factors to Consider When Choosing Accounts Payable Services Providers.pptx
Factors to Consider When Choosing Accounts Payable Services Providers.pptxFactors to Consider When Choosing Accounts Payable Services Providers.pptx
Factors to Consider When Choosing Accounts Payable Services Providers.pptx
 
How to convert PDF to text with Nanonets
How to convert PDF to text with NanonetsHow to convert PDF to text with Nanonets
How to convert PDF to text with Nanonets
 
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
 
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdfThe Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
 
[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdf[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdf
 
Exploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone ProcessorsExploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone Processors
 
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptxEIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
 
A Call to Action for Generative AI in 2024
A Call to Action for Generative AI in 2024A Call to Action for Generative AI in 2024
A Call to Action for Generative AI in 2024
 
Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...
Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...
Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...
 

DataEngConf SF16 - Deriving Meaning from Wearable Sensor Data

  • 1. DERIVING MEANING FROM WEARABLE SENSOR DATA SAMEERA PODURI @sameerapoduri
  • 2. 1530 pocket watch wrist watch1810 digital watch1969
  • 3. 1530 pocket watch wrist watch1810 digital watch1969 mobile phone1973 smartphone2008 2016 ?
  • 4. • batteries shrinking • small + low-power sensors, compute, comms
  • 5. 24/7 sensor data platforms!
  • 6. DATA SCIENCE FOR WEARABLES: PERCEPTION & PERSONALIZATION • Hardware is maturing • Sensor data is growing exponentially • Unlocking potential requires deriving meaning from data
  • 7.
  • 8. BEAUTY + ENGINEERING IN SERVICE OF A BETTER LIFE Measure steps, sleep states, workouts, heart rate
  • 9. DynamoDB Kinesis Eventing Data JB server User Data Platform Redshift Processing DATA INFRASTRUCTURE
  • 13. GOT DATA? 1. Deploy a model 2. Collect data 3. Retrain model 4. A/B Test 5. Repeat
  • 16. SIGNALS Raw, rich Partly compressed, rich Compressed CONTEXT Limited Sensor fusion History, population, weather, etc USERS Single Single Aggregate WHERE TO DEPLOY?
  • 17. DATA PRODUCTS FOR HARDWARE
  • 18. LATENCY Seconds Minutes Minutes + Network delays COMPUTE Limited Powerful DEPLOYMENT Months Weeks Hours WHERE TO DEPLOY?
  • 19. Version 0 Most common workout 58% Accuracy Version 1 Last workout 15% lift Version 2 WORKOUT CLASSIFICATION
  • 21. • How can I understand this data? • How should I feel about what it tells me? • What action should I take in response?
  • 22. Smart Coach Remembers Remember how you took 45,365 steps on July 4? Smart Coach remembers! On your health journey, don't forget to stop and celebrate. Step Update Smart Coach noticed a surge in activity. In fact, you surpassed 9,690 steps, your typical 5:00pm average. Last night you had 35m of REM sleep, less than the 1h9m that is typical for your age group. One way to improve your chances for more REM is to try an earlier bedtime than last night's 12:35am. You can set a bedtime Reminder for 11:35pm to help. REM TimeLong Journey? Looks like you've been traveling recently, which can throw off your routine. Try setting a bedtime reminder for tonight to help you adjust. Your daily average of 17,543 steps places you in the top 3% of UP females in their 30s. Bravo, Angela. Welcome to the 3%
  • 24. HEART RATE “Your heart rate is 85 beats per minute.”
  • 26.
  • 27.
  • 28.
  • 29. This morning’s resting heart rate was higher than 61bpm, your 30-day average. Dehydration may be the cause. If you think you were dehydrated last night, make up for it today with 8 glasses of water. Start with Hydration
  • 32. Commitment and Consistency Source: Cialdini, R. B. (2009). Influence: Science and practice (5th edition). Boston, MA: Pearson Education. BEHAVIOR CHANGE
  • 33. Commitment and Consistency Foot In The Door Technique Source: Freedman, J.L. & Fraser, S.C. (1966). Compliance without pressure: The foot-in-the-door technique. Journal of Personality and Social Psychology, 4, 195-202. BEHAVIOR CHANGE
  • 34. Commitment and Consistency Foot In The Door Technique Goldilocks Tasks Source: Pink, Daniel (2009). Drive: The Surprising Truth About What Motivates Us. New York, NY: Riverhead Books. BEHAVIOR CHANGE
  • 35. Commitment and Consistency Foot In The Door Technique Goldilocks Tasks Source: Carpenter, Chris. (2013) A meta-analysis of the effectiveness of the "but you are free" compliance-gaining technique Reactance BEHAVIOR CHANGE
  • 36. 72%Increased likelihood to go to bed early enough to hit their sleep goal 23mMinutes earlier to bed, compared to if they didn’t receive a TIW BEHAVIOR CHANGE
  • 38. HUNDREDS OF MILLIONS NIGHTS OF SLEEP TRILLIONS OF STEPS HUNDREDS OF MILLIONS FOOD ITEMS
  • 39.
  • 40.
  • 41.
  • 42.
  • 43. “The fact that the tracker measured my sleep and my activity level was a big part of my recovery. I had this way to ‘metric’ my body as I went through this. Sleep is so important in brain function anyway, and when you're recovering from a brain injury, it's even more important.”
  • 44.
  • 45.
  • 46.
  • 47. PARTING THOUGHTS… • Wearables will help us live healthier • Health data at unprecedented scale and granularity • Data Science can play a critical role in unlocking their potential by deriving meaning from this sensor data
  • 48.
  • 49.
  • 50.
  • 51.
  • 52. • Sensor and Accelerometer data • > 1GB/sec aggregated across users • Compacted on band into code-words UP Band Phone { steps: 12, hr: 78, ts: 1455741797 ….. …. }
  • 53. • Phone adds context to band signals • Collects eventing and logging data from app • Eventing/Logging passes through Kinesis • User data is stored in the appropriate DB Kinesis Eventing Data JB server User Data Phone Server Platform
  • 54. • Run batch ETL jobs using Elastic MapReduce to clean and process data. • Choose the appropriate processing framework depending on type of job (Hadoop/Spark) • Store cleaned and anonymized data in Redshift. Server Warehouse Kinesis Platform Redshift Processing Aggregations New tables of interest
  • 55. ETL Pipeline Analyze Fields Redshift Add columns Load Kinesis Extract Aggregations New tables of interest Transform Create config
  • 57. WEARABLES FOR BETTER HEALTH Chronic disease care is 86% of US healthcare cost • Diabetes affects 12.3% population, costs $245B • Obesity affects 36% population, costs