SlideShare a Scribd company logo
1 of 16
© Copyright IBM Corporation 2016
IBM Accessibility Research
1
Scott Gerard (sgerard@us.ibm.com)
Mar 10, 2018
Discovering Human Activities from Sensors
© Copyright IBM Corporation 2016
IBM Accessibility Research
Impact & business opportunity of a global demographic shift
• US – Estimated assets for this
demographic $8.4 to $11.6 Trillion
• China – Estimated “silver hair” market
to rise to $17 Trillion by 2050,
amounting to a third of the Chinese
economy.
• Japan – Estimated 65+ financial
assets $9.1 trillion
• Rising Eldercare costs will disrupt
economies 6% of US GDP and 4 to
8% of EU GDP will account for social
service costs for the Elder. PercentageofPopulation65yearsandolder
Japan
Italy
Germany
Ireland
China
Australia
Brazil
US
India
Egypt
2017
•http://www.icis.com/blogs/chemicals-and-the-economy/2015/03/worlds-demographic-dividend-turns-deficit-populations-age/
•https://www.metlife.com/assets/cao/mmi/publications/studies/2010/mmi-inheritance-wealth-transfer-baby-boomers.pdf
•http://blogs.ft.com/ftdata/2014/02/13/guest-post-adapting-to-the-aging-baby-boomers/
•http://www.marketsandmarkets.com/Market-Reports/healthcare-data-analytics-market-905.html
•http://www.bloomberg.com/bw/articles/2014-09-25/chinas-rapidly-aging-population-drives-652-billion-silver-hair-market
•Asian Journal of Gerontology & Geriatrics for Centenarians: According to the National Institute of Population and Social Security Research, Japan had 67,000 centenarians in 2014, but that number is forecast to reach 110,000 in 2020, 253,000 in 2030 and peak at 703,000 in the year 2051.
© Copyright IBM Corporation 2016
IBM Accessibility Research
Maintaining highest
possible level of
contribution
Living in Retirement
Maintaining
independenc
e & security
Mature Adult Pre-Retirement Retirement In-Home Care Assisted Living 24hr Care
Workforce
Assisted Living Providers
P&C Insurance
Financial
Services
Governments
Retail, Consumer Electronics
&Start-Tech for non-digital natives
Healthcar
e
1x cost 4x cost 8x costFixed budget
Augment
Cognitive
Capabilit
y
Biz
Cognitive Life Advisors
E
S
E
L
Empowered Living
Empowered Social
Empowered CareE
C
© Copyright IBM Corporation 2016
IBM Accessibility Research
ADLs (Activities of Daily Living)
• Activities we normally do. Determines level of care needed.
• Bathing and showering
• Personal hygiene and grooming (including brushing/combing/styling
hair)
• Dressing
• Toileting (getting to the toilet, cleaning oneself, and getting back up)
• Eating (self-feeding not including cooking or chewing and swallowing)
• Functional mobility, often referred to as "transferring", as measured by
the ability to walk, get in and out of bed, and get into and out of a chair;
the broader definition (moving from one place to another while
performing activities) is useful for people with different physical abilities
who are still able to get around independently.
• We expect to see additional ADLs in our data
• Sleeping, Watching TV, …
4
https://en.wikipedia.org/wiki/Activities_of_daily_living
© Copyright IBM Corporation 2016
IBM Accessibility Research
Core Technology: The Knowledge Reactor
5
We have developed a contextual data fusion
engine, the Knowledge Reactor (KR), that
centralizes IoT and System of Record/Engagement
data fusion to create a reactive knowledge graph
that can integrate and drive various cognitive
applications and services.
The KR is designed to scale-up and scale–down
as requirements dictate, exploiting container-based,
horizontally scalable pub-sub (Kafka) and graph
database (Tinkerpop) technologies that sit logically
atop the Watson IoT Platform.
While initially developed for the cognitive eldercare
solution, the KR is a designed to be a general-purpose
reactive data fusion platform for Cognitive IoT.
To apply to a new problem domain, only the new data
sources must be ingested and modeled in the knowledge
graph and the application-specific services added.
Existing approaches to IoT data fusion are either
ad hoc or highly application specific and not
reusable across cognitive applications, resulting in
expensive duplicate efforts in data curation,
integration and knowledge modeling for each
cognitive service or application.
© Copyright IBM Corporation 2016
IBM Accessibility Research
Knowledge Reactor Environment
6
OLTP
OLAP
Agent
WIoT
• rule-based • ML-based
© Copyright IBM Corporation 2016
IBM Accessibility Research
Avamere – High Density Sensor Deployment
Instrumenting 20 Patient rooms in Skilled Nursing Facility
& 5 Independent Living Apartment
Over 1000 sensors deployed
© Copyright IBM Corporation 2016
IBM Accessibility Research
Why Context is Crucial
Elder is reclining, watching TV, but
what is all that other activity?
No pets allowed in this facility…
but…
So what are the ADLs of an old dog?
Does it matter?
© Copyright IBM Corporation 2016
IBM Accessibility Research
The Moving Pieces
9
Master
Worker
Worker
Jupyter Notebook
runs in browser
BluemixWatson Data Platform
IBM Cloud
© Copyright IBM Corporation 2016
IBM Accessibility Research
ADL Topic Modeling
LDA (Latent Dirichlet Allocation)
10
docs topics
bag of
words
• birdRelated
• catRelated
• dogRelated
• document
• paper
• article
• 1 min window
• 2 min window
ADLs
• cooking/eating
• toileting
• bathing
• dressing
• sleeping
• transfer/mobility
• beak, fly, tweet
• paw, meow, milk
• paw, bark, bone
Bag of Words:
dog bites man ==
man bites dog
Sensors
• -fysmclent
• -fysmclsnk
• ab-nxbed--
• ab-smclbed
• ab-smcl000
• ab-smcl100
• ab-sptv--
• ab-smar3md
• ...
Bag of Readings:
using
Documents
using
Sensors
© Copyright IBM Corporation 2016
IBM Accessibility Research
Dirichlet Distribution
11
Di-ri-chlet
All distributions equal
(default)
Prefer equal mixturePrefer single topic
(not supported)
© Copyright IBM Corporation 2016
IBM Accessibility Research
Spark ML Pipeline
12
SQLTransformer
.transform()
OneHotEncoder
.transform()
GroupByWindow
.transform()
LDA
.fit()
SQLTransformer.
transform()
OneHotEncoder
.transform()
GroupByWindow
.transform()
LDAModel
.transform()
Training Pipeline
Evaluation Pipeline
sensor1 on
sensor2 on
[ 1, 0, 0 ]
[ 0, 1, 0 ]
[ 1, 1, 0 ]training data
test data
© Copyright IBM Corporation 2016
IBM Accessibility Research
ADL/Sensor
Distribution
13
• Learn sensor => ADL
• Unsupervised ML
• Spark ml LDA
SensorId cooking transferring toileting bathing TV watching sleeping
I01BBB-b-nw---- 0.16 0.13 0.18 0.18 21165.05 0.14 0.16
I01BBB-b-smar2md 100.97 40366.36 4002.56 5.99 0.39 0.32 0.41
I01BBB-b-smcl010 0.56 38.24 3051.03 0.85 0.71 0.29 55928.33
I01BBB-b-smcl020 0.27 2.27 39292.91 0.34 0.27 0.36 0.58
I01BBB-b-smclbed 0.19 0.23 0.57 0.27 0.38 0.15 24340.21
I01BBB-c-scdoor2 0.08 0.09 15012.48 0.09 0.11 0.07 0.09
I01BBB-dkscdoor- 0.19 0.15 0.23 0.21 4634.85 0.16 0.21
I01BBB-dnsachar1 0.13 15921.06 0.16 0.15 0.23 0.13 0.14
I01BBB-fyscdoor- 14182.51 0.08 0.09 0.08 0.10 0.07 0.08
I01BBB-fysmar3md 13814.08 2.98 2.20 20673.86 0.31 0.28 0.28
I01BBB-fysmclent 21057.01 0.84 0.68 15147.70 0.27 0.25 0.24
I01BBB-ktnw----- 0.14 0.12 0.17 0.17 21199.14 0.13 0.14
I01BBB-ktsccplat 0.11 0.10 0.13 0.12 11546.33 0.10 0.11
I01BBB-ktscfrez- 0.25 0.16 0.22 15388.63 0.37 0.18 0.20
I01BBB-ktscfrig- 49370.50 0.08 0.08 0.09 0.10 0.07 0.07
I01BBB-ktscutenz 0.13 0.09 0.12 3670.31 0.15 0.09 0.10
I01BBB-ktsmcl--- 6637.83 0.20 0.23 0.35 0.15 0.11 0.13
I01BBB-ktspmicrw 0.24 0.16 0.26 0.37 2.14 0.45 0.39
I01BBB-ldsawashr 0.07 0.06 0.08 0.08 0.10 0.06 24336.54
I01BBB-ldscdoor1 0.08 0.08 15140.45 0.10 0.12 0.08 0.09
I01BBB-ldsmcl--- 11246.61 29988.13 5645.84 511.05 0.49 0.37 0.51
I01BBB-lrsachar1 0.06 0.06 0.08 0.06 0.07 37033.62 0.05
I01BBB-lrsmar4md 0.32 0.32 1.29 0.29 0.34 21564.24 0.21
I01BBB-lrsmcl000 1.54 40986.87 2191.49 1.04 0.32 0.42 0.32
I01BBB-lrsmcl100 4.25 48.19 24648.51 1.04 0.62 5647.11 0.27
I01BBB-lrsmcl200 0.41 0.62 68.51 0.37 0.50 40365.33 0.26
I01BBB-lrsptv--- 0.17 0.14 0.22 0.22 0.92 0.15 0.18
I01BBB-rrnw----- 0.14 0.12 0.17 0.16 21185.14 0.13 0.14
I01BBB-rrscdoor- 0.14 0.12 0.17 0.16 0.24 16324.03 0.14
I01BBB-rrsmar1md 0.24 0.16 0.19 25992.93 0.21 0.12 0.15
I01209-rrsmclshw 0.16 0.14 0.21 0.39 10417.79 0.13 0.18
I01209-rrsmclsnk 0.88 3.46 12.06 240.63 60.90 0.60 11303.46
I01209-rrsmcltoi 0.17 0.14 0.18 26898.94 0.29 0.13 0.16
Grand Total 116420.59 127361.95 109073.76 108537.23 90219.09 120939.84 115914.54
© Copyright IBM Corporation 2016
IBM Accessibility Research
ADL by Time Window
14
cooking transferring toileting bathing TV watching sleeping max ADL
96K windows
© Copyright IBM Corporation 2016
IBM Accessibility Research
Conclusions
• Tuning
• Time window: 1 minute is good (5 min was too long)
• Alpha (# concurrent ADLs)
• Ideal: small alpha (0.1, 0.01, …)
• But Spark LDA ML doesn’t allow alpha < 1.0
• Iterations: 100 is good (35 was too few)
• Choose #ADLs up front. 6?, 7?, 10? …
• No ADL looks like “dressing” or “grooming”
• Found non-standard “Watch TV” ADL
• Interpretation
• Must manually characterize sensor sets (ADLs)
• How to transfer learning across apartments (diff sensors) ?
• Encouraging results, but more work is needed
15
© Copyright IBM Corporation 2016
IBM Accessibility Research
Backup
16

More Related Content

Similar to Discovering Activities from Sensors Using Topic Modeling

Mongo at Sailthru (MongoNYC 2011)
Mongo at Sailthru (MongoNYC 2011)Mongo at Sailthru (MongoNYC 2011)
Mongo at Sailthru (MongoNYC 2011)ibwhite
 
Big data 2017 final
Big data 2017   finalBig data 2017   final
Big data 2017 finalAmjid Ali
 
BDI- The Beginning (Big data training in Coimbatore)
BDI- The Beginning (Big data training in Coimbatore)BDI- The Beginning (Big data training in Coimbatore)
BDI- The Beginning (Big data training in Coimbatore)Ashok Rangaswamy
 
Séminaire Big Data Alter Way - Elasticsearch - octobre 2014
Séminaire Big Data Alter Way - Elasticsearch - octobre 2014Séminaire Big Data Alter Way - Elasticsearch - octobre 2014
Séminaire Big Data Alter Way - Elasticsearch - octobre 2014ALTER WAY
 
Elasticsearch : petit déjeuner du 13 mars 2014
Elasticsearch : petit déjeuner du 13 mars 2014Elasticsearch : petit déjeuner du 13 mars 2014
Elasticsearch : petit déjeuner du 13 mars 2014ALTER WAY
 
Northeastern DB Class Introduction to Marklogic NoSQL april 2016
Northeastern DB Class Introduction to Marklogic NoSQL april 2016Northeastern DB Class Introduction to Marklogic NoSQL april 2016
Northeastern DB Class Introduction to Marklogic NoSQL april 2016Matt Turner
 
Spohrer Terraces 20230711 v17.pptx
Spohrer Terraces 20230711 v17.pptxSpohrer Terraces 20230711 v17.pptx
Spohrer Terraces 20230711 v17.pptxISSIP
 
Why SKOS should be a Focal Point of your Linked Data Strategy
Why SKOS should be a Focal Point of your Linked Data StrategyWhy SKOS should be a Focal Point of your Linked Data Strategy
Why SKOS should be a Focal Point of your Linked Data StrategySemantic Web Company
 
Internet Conference 2018: Internet Measurement, how to get the relativities r...
Internet Conference 2018: Internet Measurement, how to get the relativities r...Internet Conference 2018: Internet Measurement, how to get the relativities r...
Internet Conference 2018: Internet Measurement, how to get the relativities r...APNIC
 
Data Science in Future Tense
Data Science in Future TenseData Science in Future Tense
Data Science in Future TensePaco Nathan
 
NordicHouse 20240116 AI Quantum IFTF dfiscussionv7.pptx
NordicHouse 20240116 AI Quantum IFTF dfiscussionv7.pptxNordicHouse 20240116 AI Quantum IFTF dfiscussionv7.pptx
NordicHouse 20240116 AI Quantum IFTF dfiscussionv7.pptxISSIP
 
Alibaba 2016 Computing Conference
Alibaba 2016 Computing ConferenceAlibaba 2016 Computing Conference
Alibaba 2016 Computing Conferencemarcogervasi
 
Cloudera Breakfast: Advanced Analytics Part II: Do More With Your Data
Cloudera Breakfast: Advanced Analytics Part II: Do More With Your DataCloudera Breakfast: Advanced Analytics Part II: Do More With Your Data
Cloudera Breakfast: Advanced Analytics Part II: Do More With Your DataCloudera, Inc.
 
Science agora 20161106 v2
Science agora 20161106 v2Science agora 20161106 v2
Science agora 20161106 v2ISSIP
 
ICServ2023 20230914 v8.pptx
ICServ2023 20230914 v8.pptxICServ2023 20230914 v8.pptx
ICServ2023 20230914 v8.pptxISSIP
 
Intel 20180608 v2
Intel 20180608 v2Intel 20180608 v2
Intel 20180608 v2ISSIP
 
IIoT : Old Wine in a New Bottle?
IIoT : Old Wine in a New Bottle?IIoT : Old Wine in a New Bottle?
IIoT : Old Wine in a New Bottle?Venu Vasudevan
 

Similar to Discovering Activities from Sensors Using Topic Modeling (20)

Mongo at Sailthru (MongoNYC 2011)
Mongo at Sailthru (MongoNYC 2011)Mongo at Sailthru (MongoNYC 2011)
Mongo at Sailthru (MongoNYC 2011)
 
Big data 2017 final
Big data 2017   finalBig data 2017   final
Big data 2017 final
 
BDI- The Beginning (Big data training in Coimbatore)
BDI- The Beginning (Big data training in Coimbatore)BDI- The Beginning (Big data training in Coimbatore)
BDI- The Beginning (Big data training in Coimbatore)
 
Séminaire Big Data Alter Way - Elasticsearch - octobre 2014
Séminaire Big Data Alter Way - Elasticsearch - octobre 2014Séminaire Big Data Alter Way - Elasticsearch - octobre 2014
Séminaire Big Data Alter Way - Elasticsearch - octobre 2014
 
Elasticsearch : petit déjeuner du 13 mars 2014
Elasticsearch : petit déjeuner du 13 mars 2014Elasticsearch : petit déjeuner du 13 mars 2014
Elasticsearch : petit déjeuner du 13 mars 2014
 
Northeastern DB Class Introduction to Marklogic NoSQL april 2016
Northeastern DB Class Introduction to Marklogic NoSQL april 2016Northeastern DB Class Introduction to Marklogic NoSQL april 2016
Northeastern DB Class Introduction to Marklogic NoSQL april 2016
 
Spohrer Terraces 20230711 v17.pptx
Spohrer Terraces 20230711 v17.pptxSpohrer Terraces 20230711 v17.pptx
Spohrer Terraces 20230711 v17.pptx
 
Spohrer Terraces 20230711 v17.pptx
Spohrer Terraces 20230711 v17.pptxSpohrer Terraces 20230711 v17.pptx
Spohrer Terraces 20230711 v17.pptx
 
Why SKOS should be a Focal Point of your Linked Data Strategy
Why SKOS should be a Focal Point of your Linked Data StrategyWhy SKOS should be a Focal Point of your Linked Data Strategy
Why SKOS should be a Focal Point of your Linked Data Strategy
 
Internet Conference 2018: Internet Measurement, how to get the relativities r...
Internet Conference 2018: Internet Measurement, how to get the relativities r...Internet Conference 2018: Internet Measurement, how to get the relativities r...
Internet Conference 2018: Internet Measurement, how to get the relativities r...
 
Data Science in Future Tense
Data Science in Future TenseData Science in Future Tense
Data Science in Future Tense
 
Lean Security
Lean SecurityLean Security
Lean Security
 
NordicHouse 20240116 AI Quantum IFTF dfiscussionv7.pptx
NordicHouse 20240116 AI Quantum IFTF dfiscussionv7.pptxNordicHouse 20240116 AI Quantum IFTF dfiscussionv7.pptx
NordicHouse 20240116 AI Quantum IFTF dfiscussionv7.pptx
 
Alibaba 2016 Computing Conference
Alibaba 2016 Computing ConferenceAlibaba 2016 Computing Conference
Alibaba 2016 Computing Conference
 
Cloudera Breakfast: Advanced Analytics Part II: Do More With Your Data
Cloudera Breakfast: Advanced Analytics Part II: Do More With Your DataCloudera Breakfast: Advanced Analytics Part II: Do More With Your Data
Cloudera Breakfast: Advanced Analytics Part II: Do More With Your Data
 
Science agora 20161106 v2
Science agora 20161106 v2Science agora 20161106 v2
Science agora 20161106 v2
 
ICServ2023 20230914 v8.pptx
ICServ2023 20230914 v8.pptxICServ2023 20230914 v8.pptx
ICServ2023 20230914 v8.pptx
 
Intel 20180608 v2
Intel 20180608 v2Intel 20180608 v2
Intel 20180608 v2
 
Big Data Building Blocks with AWS Cloud
Big Data Building Blocks with AWS CloudBig Data Building Blocks with AWS Cloud
Big Data Building Blocks with AWS Cloud
 
IIoT : Old Wine in a New Bottle?
IIoT : Old Wine in a New Bottle?IIoT : Old Wine in a New Bottle?
IIoT : Old Wine in a New Bottle?
 

Recently uploaded

PAG-UNLAD NG EKONOMIYA na dapat isaalang alang sa pag-aaral.
PAG-UNLAD NG EKONOMIYA na dapat isaalang alang sa pag-aaral.PAG-UNLAD NG EKONOMIYA na dapat isaalang alang sa pag-aaral.
PAG-UNLAD NG EKONOMIYA na dapat isaalang alang sa pag-aaral.KathleenAnnCordero2
 
Genshin Impact PPT Template by EaTemp.pptx
Genshin Impact PPT Template by EaTemp.pptxGenshin Impact PPT Template by EaTemp.pptx
Genshin Impact PPT Template by EaTemp.pptxJohnree4
 
The 3rd Intl. Workshop on NL-based Software Engineering
The 3rd Intl. Workshop on NL-based Software EngineeringThe 3rd Intl. Workshop on NL-based Software Engineering
The 3rd Intl. Workshop on NL-based Software EngineeringSebastiano Panichella
 
PHYSICS PROJECT BY MSC - NANOTECHNOLOGY
PHYSICS PROJECT BY MSC  - NANOTECHNOLOGYPHYSICS PROJECT BY MSC  - NANOTECHNOLOGY
PHYSICS PROJECT BY MSC - NANOTECHNOLOGYpruthirajnayak525
 
Dutch Power - 26 maart 2024 - Henk Kras - Circular Plastics
Dutch Power - 26 maart 2024 - Henk Kras - Circular PlasticsDutch Power - 26 maart 2024 - Henk Kras - Circular Plastics
Dutch Power - 26 maart 2024 - Henk Kras - Circular PlasticsDutch Power
 
Event 4 Introduction to Open Source.pptx
Event 4 Introduction to Open Source.pptxEvent 4 Introduction to Open Source.pptx
Event 4 Introduction to Open Source.pptxaryanv1753
 
Presentation for the Strategic Dialogue on the Future of Agriculture, Brussel...
Presentation for the Strategic Dialogue on the Future of Agriculture, Brussel...Presentation for the Strategic Dialogue on the Future of Agriculture, Brussel...
Presentation for the Strategic Dialogue on the Future of Agriculture, Brussel...Krijn Poppe
 
Gaps, Issues and Challenges in the Implementation of Mother Tongue Based-Mult...
Gaps, Issues and Challenges in the Implementation of Mother Tongue Based-Mult...Gaps, Issues and Challenges in the Implementation of Mother Tongue Based-Mult...
Gaps, Issues and Challenges in the Implementation of Mother Tongue Based-Mult...marjmae69
 
THE COUNTRY WHO SOLVED THE WORLD_HOW CHINA LAUNCHED THE CIVILIZATION REVOLUTI...
THE COUNTRY WHO SOLVED THE WORLD_HOW CHINA LAUNCHED THE CIVILIZATION REVOLUTI...THE COUNTRY WHO SOLVED THE WORLD_HOW CHINA LAUNCHED THE CIVILIZATION REVOLUTI...
THE COUNTRY WHO SOLVED THE WORLD_HOW CHINA LAUNCHED THE CIVILIZATION REVOLUTI...漢銘 謝
 
Anne Frank A Beacon of Hope amidst darkness ppt.pptx
Anne Frank A Beacon of Hope amidst darkness ppt.pptxAnne Frank A Beacon of Hope amidst darkness ppt.pptx
Anne Frank A Beacon of Hope amidst darkness ppt.pptxnoorehahmad
 
James Joyce, Dubliners and Ulysses.ppt !
James Joyce, Dubliners and Ulysses.ppt !James Joyce, Dubliners and Ulysses.ppt !
James Joyce, Dubliners and Ulysses.ppt !risocarla2016
 
miladyskindiseases-200705210221 2.!!pptx
miladyskindiseases-200705210221 2.!!pptxmiladyskindiseases-200705210221 2.!!pptx
miladyskindiseases-200705210221 2.!!pptxCarrieButtitta
 
Call Girls in Rohini Delhi 💯Call Us 🔝8264348440🔝
Call Girls in Rohini Delhi 💯Call Us 🔝8264348440🔝Call Girls in Rohini Delhi 💯Call Us 🔝8264348440🔝
Call Girls in Rohini Delhi 💯Call Us 🔝8264348440🔝soniya singh
 
Mathan flower ppt.pptx slide orchids ✨🌸
Mathan flower ppt.pptx slide orchids ✨🌸Mathan flower ppt.pptx slide orchids ✨🌸
Mathan flower ppt.pptx slide orchids ✨🌸mathanramanathan2005
 
SaaStr Workshop Wednesday w/ Kyle Norton, Owner.com
SaaStr Workshop Wednesday w/ Kyle Norton, Owner.comSaaStr Workshop Wednesday w/ Kyle Norton, Owner.com
SaaStr Workshop Wednesday w/ Kyle Norton, Owner.comsaastr
 
SBFT Tool Competition 2024 -- Python Test Case Generation Track
SBFT Tool Competition 2024 -- Python Test Case Generation TrackSBFT Tool Competition 2024 -- Python Test Case Generation Track
SBFT Tool Competition 2024 -- Python Test Case Generation TrackSebastiano Panichella
 
call girls in delhi malviya nagar @9811711561@
call girls in delhi malviya nagar @9811711561@call girls in delhi malviya nagar @9811711561@
call girls in delhi malviya nagar @9811711561@vikas rana
 
The Ten Facts About People With Autism Presentation
The Ten Facts About People With Autism PresentationThe Ten Facts About People With Autism Presentation
The Ten Facts About People With Autism PresentationNathan Young
 
Call Girls In Aerocity 🤳 Call Us +919599264170
Call Girls In Aerocity 🤳 Call Us +919599264170Call Girls In Aerocity 🤳 Call Us +919599264170
Call Girls In Aerocity 🤳 Call Us +919599264170Escort Service
 
Work Remotely with Confluence ACE 2.pptx
Work Remotely with Confluence ACE 2.pptxWork Remotely with Confluence ACE 2.pptx
Work Remotely with Confluence ACE 2.pptxmavinoikein
 

Recently uploaded (20)

PAG-UNLAD NG EKONOMIYA na dapat isaalang alang sa pag-aaral.
PAG-UNLAD NG EKONOMIYA na dapat isaalang alang sa pag-aaral.PAG-UNLAD NG EKONOMIYA na dapat isaalang alang sa pag-aaral.
PAG-UNLAD NG EKONOMIYA na dapat isaalang alang sa pag-aaral.
 
Genshin Impact PPT Template by EaTemp.pptx
Genshin Impact PPT Template by EaTemp.pptxGenshin Impact PPT Template by EaTemp.pptx
Genshin Impact PPT Template by EaTemp.pptx
 
The 3rd Intl. Workshop on NL-based Software Engineering
The 3rd Intl. Workshop on NL-based Software EngineeringThe 3rd Intl. Workshop on NL-based Software Engineering
The 3rd Intl. Workshop on NL-based Software Engineering
 
PHYSICS PROJECT BY MSC - NANOTECHNOLOGY
PHYSICS PROJECT BY MSC  - NANOTECHNOLOGYPHYSICS PROJECT BY MSC  - NANOTECHNOLOGY
PHYSICS PROJECT BY MSC - NANOTECHNOLOGY
 
Dutch Power - 26 maart 2024 - Henk Kras - Circular Plastics
Dutch Power - 26 maart 2024 - Henk Kras - Circular PlasticsDutch Power - 26 maart 2024 - Henk Kras - Circular Plastics
Dutch Power - 26 maart 2024 - Henk Kras - Circular Plastics
 
Event 4 Introduction to Open Source.pptx
Event 4 Introduction to Open Source.pptxEvent 4 Introduction to Open Source.pptx
Event 4 Introduction to Open Source.pptx
 
Presentation for the Strategic Dialogue on the Future of Agriculture, Brussel...
Presentation for the Strategic Dialogue on the Future of Agriculture, Brussel...Presentation for the Strategic Dialogue on the Future of Agriculture, Brussel...
Presentation for the Strategic Dialogue on the Future of Agriculture, Brussel...
 
Gaps, Issues and Challenges in the Implementation of Mother Tongue Based-Mult...
Gaps, Issues and Challenges in the Implementation of Mother Tongue Based-Mult...Gaps, Issues and Challenges in the Implementation of Mother Tongue Based-Mult...
Gaps, Issues and Challenges in the Implementation of Mother Tongue Based-Mult...
 
THE COUNTRY WHO SOLVED THE WORLD_HOW CHINA LAUNCHED THE CIVILIZATION REVOLUTI...
THE COUNTRY WHO SOLVED THE WORLD_HOW CHINA LAUNCHED THE CIVILIZATION REVOLUTI...THE COUNTRY WHO SOLVED THE WORLD_HOW CHINA LAUNCHED THE CIVILIZATION REVOLUTI...
THE COUNTRY WHO SOLVED THE WORLD_HOW CHINA LAUNCHED THE CIVILIZATION REVOLUTI...
 
Anne Frank A Beacon of Hope amidst darkness ppt.pptx
Anne Frank A Beacon of Hope amidst darkness ppt.pptxAnne Frank A Beacon of Hope amidst darkness ppt.pptx
Anne Frank A Beacon of Hope amidst darkness ppt.pptx
 
James Joyce, Dubliners and Ulysses.ppt !
James Joyce, Dubliners and Ulysses.ppt !James Joyce, Dubliners and Ulysses.ppt !
James Joyce, Dubliners and Ulysses.ppt !
 
miladyskindiseases-200705210221 2.!!pptx
miladyskindiseases-200705210221 2.!!pptxmiladyskindiseases-200705210221 2.!!pptx
miladyskindiseases-200705210221 2.!!pptx
 
Call Girls in Rohini Delhi 💯Call Us 🔝8264348440🔝
Call Girls in Rohini Delhi 💯Call Us 🔝8264348440🔝Call Girls in Rohini Delhi 💯Call Us 🔝8264348440🔝
Call Girls in Rohini Delhi 💯Call Us 🔝8264348440🔝
 
Mathan flower ppt.pptx slide orchids ✨🌸
Mathan flower ppt.pptx slide orchids ✨🌸Mathan flower ppt.pptx slide orchids ✨🌸
Mathan flower ppt.pptx slide orchids ✨🌸
 
SaaStr Workshop Wednesday w/ Kyle Norton, Owner.com
SaaStr Workshop Wednesday w/ Kyle Norton, Owner.comSaaStr Workshop Wednesday w/ Kyle Norton, Owner.com
SaaStr Workshop Wednesday w/ Kyle Norton, Owner.com
 
SBFT Tool Competition 2024 -- Python Test Case Generation Track
SBFT Tool Competition 2024 -- Python Test Case Generation TrackSBFT Tool Competition 2024 -- Python Test Case Generation Track
SBFT Tool Competition 2024 -- Python Test Case Generation Track
 
call girls in delhi malviya nagar @9811711561@
call girls in delhi malviya nagar @9811711561@call girls in delhi malviya nagar @9811711561@
call girls in delhi malviya nagar @9811711561@
 
The Ten Facts About People With Autism Presentation
The Ten Facts About People With Autism PresentationThe Ten Facts About People With Autism Presentation
The Ten Facts About People With Autism Presentation
 
Call Girls In Aerocity 🤳 Call Us +919599264170
Call Girls In Aerocity 🤳 Call Us +919599264170Call Girls In Aerocity 🤳 Call Us +919599264170
Call Girls In Aerocity 🤳 Call Us +919599264170
 
Work Remotely with Confluence ACE 2.pptx
Work Remotely with Confluence ACE 2.pptxWork Remotely with Confluence ACE 2.pptx
Work Remotely with Confluence ACE 2.pptx
 

Discovering Activities from Sensors Using Topic Modeling

  • 1. © Copyright IBM Corporation 2016 IBM Accessibility Research 1 Scott Gerard (sgerard@us.ibm.com) Mar 10, 2018 Discovering Human Activities from Sensors
  • 2. © Copyright IBM Corporation 2016 IBM Accessibility Research Impact & business opportunity of a global demographic shift • US – Estimated assets for this demographic $8.4 to $11.6 Trillion • China – Estimated “silver hair” market to rise to $17 Trillion by 2050, amounting to a third of the Chinese economy. • Japan – Estimated 65+ financial assets $9.1 trillion • Rising Eldercare costs will disrupt economies 6% of US GDP and 4 to 8% of EU GDP will account for social service costs for the Elder. PercentageofPopulation65yearsandolder Japan Italy Germany Ireland China Australia Brazil US India Egypt 2017 •http://www.icis.com/blogs/chemicals-and-the-economy/2015/03/worlds-demographic-dividend-turns-deficit-populations-age/ •https://www.metlife.com/assets/cao/mmi/publications/studies/2010/mmi-inheritance-wealth-transfer-baby-boomers.pdf •http://blogs.ft.com/ftdata/2014/02/13/guest-post-adapting-to-the-aging-baby-boomers/ •http://www.marketsandmarkets.com/Market-Reports/healthcare-data-analytics-market-905.html •http://www.bloomberg.com/bw/articles/2014-09-25/chinas-rapidly-aging-population-drives-652-billion-silver-hair-market •Asian Journal of Gerontology & Geriatrics for Centenarians: According to the National Institute of Population and Social Security Research, Japan had 67,000 centenarians in 2014, but that number is forecast to reach 110,000 in 2020, 253,000 in 2030 and peak at 703,000 in the year 2051.
  • 3. © Copyright IBM Corporation 2016 IBM Accessibility Research Maintaining highest possible level of contribution Living in Retirement Maintaining independenc e & security Mature Adult Pre-Retirement Retirement In-Home Care Assisted Living 24hr Care Workforce Assisted Living Providers P&C Insurance Financial Services Governments Retail, Consumer Electronics &Start-Tech for non-digital natives Healthcar e 1x cost 4x cost 8x costFixed budget Augment Cognitive Capabilit y Biz Cognitive Life Advisors E S E L Empowered Living Empowered Social Empowered CareE C
  • 4. © Copyright IBM Corporation 2016 IBM Accessibility Research ADLs (Activities of Daily Living) • Activities we normally do. Determines level of care needed. • Bathing and showering • Personal hygiene and grooming (including brushing/combing/styling hair) • Dressing • Toileting (getting to the toilet, cleaning oneself, and getting back up) • Eating (self-feeding not including cooking or chewing and swallowing) • Functional mobility, often referred to as "transferring", as measured by the ability to walk, get in and out of bed, and get into and out of a chair; the broader definition (moving from one place to another while performing activities) is useful for people with different physical abilities who are still able to get around independently. • We expect to see additional ADLs in our data • Sleeping, Watching TV, … 4 https://en.wikipedia.org/wiki/Activities_of_daily_living
  • 5. © Copyright IBM Corporation 2016 IBM Accessibility Research Core Technology: The Knowledge Reactor 5 We have developed a contextual data fusion engine, the Knowledge Reactor (KR), that centralizes IoT and System of Record/Engagement data fusion to create a reactive knowledge graph that can integrate and drive various cognitive applications and services. The KR is designed to scale-up and scale–down as requirements dictate, exploiting container-based, horizontally scalable pub-sub (Kafka) and graph database (Tinkerpop) technologies that sit logically atop the Watson IoT Platform. While initially developed for the cognitive eldercare solution, the KR is a designed to be a general-purpose reactive data fusion platform for Cognitive IoT. To apply to a new problem domain, only the new data sources must be ingested and modeled in the knowledge graph and the application-specific services added. Existing approaches to IoT data fusion are either ad hoc or highly application specific and not reusable across cognitive applications, resulting in expensive duplicate efforts in data curation, integration and knowledge modeling for each cognitive service or application.
  • 6. © Copyright IBM Corporation 2016 IBM Accessibility Research Knowledge Reactor Environment 6 OLTP OLAP Agent WIoT • rule-based • ML-based
  • 7. © Copyright IBM Corporation 2016 IBM Accessibility Research Avamere – High Density Sensor Deployment Instrumenting 20 Patient rooms in Skilled Nursing Facility & 5 Independent Living Apartment Over 1000 sensors deployed
  • 8. © Copyright IBM Corporation 2016 IBM Accessibility Research Why Context is Crucial Elder is reclining, watching TV, but what is all that other activity? No pets allowed in this facility… but… So what are the ADLs of an old dog? Does it matter?
  • 9. © Copyright IBM Corporation 2016 IBM Accessibility Research The Moving Pieces 9 Master Worker Worker Jupyter Notebook runs in browser BluemixWatson Data Platform IBM Cloud
  • 10. © Copyright IBM Corporation 2016 IBM Accessibility Research ADL Topic Modeling LDA (Latent Dirichlet Allocation) 10 docs topics bag of words • birdRelated • catRelated • dogRelated • document • paper • article • 1 min window • 2 min window ADLs • cooking/eating • toileting • bathing • dressing • sleeping • transfer/mobility • beak, fly, tweet • paw, meow, milk • paw, bark, bone Bag of Words: dog bites man == man bites dog Sensors • -fysmclent • -fysmclsnk • ab-nxbed-- • ab-smclbed • ab-smcl000 • ab-smcl100 • ab-sptv-- • ab-smar3md • ... Bag of Readings: using Documents using Sensors
  • 11. © Copyright IBM Corporation 2016 IBM Accessibility Research Dirichlet Distribution 11 Di-ri-chlet All distributions equal (default) Prefer equal mixturePrefer single topic (not supported)
  • 12. © Copyright IBM Corporation 2016 IBM Accessibility Research Spark ML Pipeline 12 SQLTransformer .transform() OneHotEncoder .transform() GroupByWindow .transform() LDA .fit() SQLTransformer. transform() OneHotEncoder .transform() GroupByWindow .transform() LDAModel .transform() Training Pipeline Evaluation Pipeline sensor1 on sensor2 on [ 1, 0, 0 ] [ 0, 1, 0 ] [ 1, 1, 0 ]training data test data
  • 13. © Copyright IBM Corporation 2016 IBM Accessibility Research ADL/Sensor Distribution 13 • Learn sensor => ADL • Unsupervised ML • Spark ml LDA SensorId cooking transferring toileting bathing TV watching sleeping I01BBB-b-nw---- 0.16 0.13 0.18 0.18 21165.05 0.14 0.16 I01BBB-b-smar2md 100.97 40366.36 4002.56 5.99 0.39 0.32 0.41 I01BBB-b-smcl010 0.56 38.24 3051.03 0.85 0.71 0.29 55928.33 I01BBB-b-smcl020 0.27 2.27 39292.91 0.34 0.27 0.36 0.58 I01BBB-b-smclbed 0.19 0.23 0.57 0.27 0.38 0.15 24340.21 I01BBB-c-scdoor2 0.08 0.09 15012.48 0.09 0.11 0.07 0.09 I01BBB-dkscdoor- 0.19 0.15 0.23 0.21 4634.85 0.16 0.21 I01BBB-dnsachar1 0.13 15921.06 0.16 0.15 0.23 0.13 0.14 I01BBB-fyscdoor- 14182.51 0.08 0.09 0.08 0.10 0.07 0.08 I01BBB-fysmar3md 13814.08 2.98 2.20 20673.86 0.31 0.28 0.28 I01BBB-fysmclent 21057.01 0.84 0.68 15147.70 0.27 0.25 0.24 I01BBB-ktnw----- 0.14 0.12 0.17 0.17 21199.14 0.13 0.14 I01BBB-ktsccplat 0.11 0.10 0.13 0.12 11546.33 0.10 0.11 I01BBB-ktscfrez- 0.25 0.16 0.22 15388.63 0.37 0.18 0.20 I01BBB-ktscfrig- 49370.50 0.08 0.08 0.09 0.10 0.07 0.07 I01BBB-ktscutenz 0.13 0.09 0.12 3670.31 0.15 0.09 0.10 I01BBB-ktsmcl--- 6637.83 0.20 0.23 0.35 0.15 0.11 0.13 I01BBB-ktspmicrw 0.24 0.16 0.26 0.37 2.14 0.45 0.39 I01BBB-ldsawashr 0.07 0.06 0.08 0.08 0.10 0.06 24336.54 I01BBB-ldscdoor1 0.08 0.08 15140.45 0.10 0.12 0.08 0.09 I01BBB-ldsmcl--- 11246.61 29988.13 5645.84 511.05 0.49 0.37 0.51 I01BBB-lrsachar1 0.06 0.06 0.08 0.06 0.07 37033.62 0.05 I01BBB-lrsmar4md 0.32 0.32 1.29 0.29 0.34 21564.24 0.21 I01BBB-lrsmcl000 1.54 40986.87 2191.49 1.04 0.32 0.42 0.32 I01BBB-lrsmcl100 4.25 48.19 24648.51 1.04 0.62 5647.11 0.27 I01BBB-lrsmcl200 0.41 0.62 68.51 0.37 0.50 40365.33 0.26 I01BBB-lrsptv--- 0.17 0.14 0.22 0.22 0.92 0.15 0.18 I01BBB-rrnw----- 0.14 0.12 0.17 0.16 21185.14 0.13 0.14 I01BBB-rrscdoor- 0.14 0.12 0.17 0.16 0.24 16324.03 0.14 I01BBB-rrsmar1md 0.24 0.16 0.19 25992.93 0.21 0.12 0.15 I01209-rrsmclshw 0.16 0.14 0.21 0.39 10417.79 0.13 0.18 I01209-rrsmclsnk 0.88 3.46 12.06 240.63 60.90 0.60 11303.46 I01209-rrsmcltoi 0.17 0.14 0.18 26898.94 0.29 0.13 0.16 Grand Total 116420.59 127361.95 109073.76 108537.23 90219.09 120939.84 115914.54
  • 14. © Copyright IBM Corporation 2016 IBM Accessibility Research ADL by Time Window 14 cooking transferring toileting bathing TV watching sleeping max ADL 96K windows
  • 15. © Copyright IBM Corporation 2016 IBM Accessibility Research Conclusions • Tuning • Time window: 1 minute is good (5 min was too long) • Alpha (# concurrent ADLs) • Ideal: small alpha (0.1, 0.01, …) • But Spark LDA ML doesn’t allow alpha < 1.0 • Iterations: 100 is good (35 was too few) • Choose #ADLs up front. 6?, 7?, 10? … • No ADL looks like “dressing” or “grooming” • Found non-standard “Watch TV” ADL • Interpretation • Must manually characterize sensor sets (ADLs) • How to transfer learning across apartments (diff sensors) ? • Encouraging results, but more work is needed 15
  • 16. © Copyright IBM Corporation 2016 IBM Accessibility Research Backup 16

Editor's Notes

  1. Active ageing is the process of optimizing opportunities for health, participation and security in order to enhance quality of life as people age. It applies to both individuals and population groups.