SlideShare a Scribd company logo
Put Knoesis Banner 
Smart Data - How you and I will exploit Big Data for 
personalized digital health and many other activities 
Keynote at IEEE BigData 2014, Oct 28, 2014 
Amit Sheth 
LexisNexis Ohio Eminent Scholar & Exec. Director, 
The Ohio Center of Excellence in Knowledge-enabled Computing (Kno.e.sis) 
Wright State, USA
2 
Thanks: My team (missing Pramod, Hemant, ...) 
Collaborators: Clinicians: Dr. William Abrahams (OSU-Wexner), Dr. Shalini Forbis (Dayton Childrens), Dr. 
Sangeeta Agrawal (VA), Valerie Shalin (WSU Cognitive Scientists ), Payam Barnaghi (U-Surrey), Ramesh 
Jain(UCI), … 
Funding: NSF (esp. IIS-1111183 “SoCS: Social Media Enhanced Organizational Sensemaking in Emergency 
Response,”), AFRL, NIH, Industry….
3 
Big Data 2014 
http://hrboss.com/hiringboss/articles/big-data-infographic
Only 0.5% to 1% of 
the data is used for 
analysis. 
http://www.csc.com/insights/flxwd/78931-big_data_growth_just_beginning_to_explode 4 
http://www.guardian.co.uk/news/datablog/2012/dec/19/big-data-study-digital-universe-global-volume
Variety – not just structure but modality: multimodal, multisensory 
Semi structured 
5
Velocity 
Fast Data 
Rapid Changes 
Real-Time/Stream Analysis 
Current application examples: financial services, stock brokerage, weather tracking, movies/entertainment and online retail 6
7 
Ever Increasing Connected Devices and People 
About 2 billion of the 5+ billion have data connections – so they perform “citizen sensing”. 
And there are more devices connected to the Internet than the entire human population. 
These ~2 billion citizen sensors and 10 billion devices & objects connected to the Internet 
makes this an era of IoT (Internet of Things) and Internet of Everything (IoE). 
http://www.cisco.com/web/about/ac79/docs/innov/IoT_IBSG_0411FINAL.pdf
8 
Internet of Things / Everything : Future Trends 
“The next wave of dramatic Internet growth will come through the confluence of people, 
process, data, and things — the Internet of Everything (IoE).” 
- CISCO IBSG, 2013 
Beyond the IoE based infrastructure, it is the possibility of developing applications that spans 
Physical, Cyber and the Social Worlds that is very exciting. 
http://www.cisco.com/web/about/ac79/docs/innov/IoE_Economy.pdf
10 
What has not changed? 
We are still working on the simpler representations of the real-world! 
http://artint.info/html/ArtInt_8.html 
http://en.wikipedia.org/wiki/Traffic_congestion 
solve 
represent interpret real-world 
simplified representation 
compute
11 
What should change? 
solve 
represent interpret real-world 
richer representation 
compute 
We need computational paradigms to tap into the 
rich pulse of the human populace, and utilize 
diverse data 
Represent, capture, and compute with richer and fine-grained 
representations of real-world problems 
+ 
Richer representation of 
traffic observations 
Effective solutions 
People interpreting a 
real-world event
Physical-Cyber-Social Computing for Actionable Insights from Multimodal Data 
High CO influences 
Wheezing Level (Low/High) 
High CO 
Reduced 
CO level => 
better 
Asthma 
control 
High Wheeze 
Vertical Operators 
(Semantic abstraction) operates on 
Artifacts at each level and 
transcends them to the 
next level. 
Horizontal Operators 
(Semantic Integration) operates 
on data from heterogeneous 
sources to create 
Integrated/correlated 
data streams. 
High Luminosity 
Carbon Monoxide 
“a holistic treatment of data, 
information, and knowledge 
integrate, correlate, interpret, 
Low Luminosity 
Wheeze 
Luminosity 
Low Wheeze 
from the PCS worlds to 
and provide contextually 
1Amit Sheth, Pramod Anantharam, Cory Henson, 'Physical-Cyber-Social Computing: An Early 21st Century Approach,' IEEE Intelligent Systems, vol. 28, no. 1, 
pp. 78-82, Jan.-Feb., 2013. http://doi.ieeecomputersociety.org/10.1109/MIS.2013.20 
relevant abstractions 
to humans. ”1 
12
• Healthcare: 
ADFH, Asthma, 
GI, Demintia 
– Using kHealth system 
• Traffic Analytics: 
– Understanding traffic flow 
• Social Media Analysis : 
– Crisis coordination using Twitris 
13 
I will use applications in 3 domains to demonstrate
14 
MIT Technology Review, 2012 
The Patient of the Future 
http://www.technologyreview.com/featuredstory/426968/the-patient-of-the-future/
Asthma: A Multi-faceted and Symptomatically Variable Health Challenge 
15 
Personal level 
Signals 
Public level 
Signals 
Population level 
Signals 
“ … survey indicates that adult patients and caregivers of pediatric patients 
report variability in asthma symptoms over time, even when asthma medications are taken.”1 
1Marcus, Philip, Kevin R. Murphy, Abid Rahman, and Christopher D. O’Brien. "Intrapatient symptom 
variability in adults and children with asthma: Results of a survey." Advances in therapy 22, no. 5 (2005): 488-497.
Far better an approximate answer to the right question, which is often vague, than the exact answer to the 
wrong question, which can always be made precise. 
-- John Tukey, Ann. Math. Stat. 33 (1962) 
16 
Asthma: Actionable Information 
How is my Asthma control? 
Should I take additional medication today? 
How can I reduce my asthma attacks at home?
17 
Asthma: Challenges in Heterogeneity, Variability, and Personalization 
Contextual Personalized Actionable 
Personal level 
Signals 
Public level 
Signals 
Population level 
Signals 
Domain 
Knowledge 
http://www.tuberktoraks.org/managete/fu_folder/2011-03/html/2011-3-291-311.html 
OR
18 
My 2004-2005 formulation of SMART DATA - Semagix 
Formulation of Smart Data 
strategy providing services 
for Search, Explore, Notify. 
“Use of Ontologies and 
Data repositories to gain 
relevant insights”
Smart Data (2014 retake) 
Smart data makes sense out of Big data 
It provides value from harnessing the 
challenges posed by volume, velocity, variety 
and veracity of big data, in-turn providing 
actionable information and improve decision 
making. 
19
Another perspective on Smart Data 
OF human, BY human FOR human 
Smart data is about extracting value by 
improving human involvement in data creation, 
processing and consumption. 
It is about (improving) 
computing for human experience. 
20
‘OF human’ : Relevant Real-time Data Streams for Human Experience 
Petabytes of Physical(sensory)-Cyber-Social Data everyday! 
More on PCS Computing: http://wiki.knoesis.org/index.php/PCS 
21
Use of Prior Human-created Knowledge Models 
22 
‘BY human’: Involving Crowd Intelligence in data processing 
Crowdsourcing and Domain-expert guided 
Machine Learning Modeling
Weather Application 
Asthma Healthcare 
Application 
Personal 
Public Health 
Detection of events, such as wheezing 
sound, indoor temperature, humidity, 
dust, and CO level 
High CO content at 
home during day 
23 
‘FOR human’ : Improving Human Experience (Smart Health) 
Population Level 
Action in the Physical World 
Luminosity 
CO level 
CO in gush 
during day time
‘FOR human’ : Improving Human Experience (Smart Energy) 
Weather Application 
Power Monitoring Application 
Personal Level Observations 
Electricity usage over a day, device at 
work, power consumption, cost/kWh, 
heat index, relative humidity, and public 
events from social stream 
24 
Population Level Observations 
Action in the Physical World 
Washing and drying has 
resulted in significant cost 
since it was done during peak 
load period. Consider 
changing this time to night.
25 
Big Data is pervasive - 
It is Smart Data that matter!
DATA 
Observations from 
machine and social 
sensors 
KNOWLEDGE 
for interpretation of 
observations 
ACTIONS 
situation awareness useful 
for decision making 
26 
Primary challenge is to bridge the gap between data and 
actions 
Contextualization 
Personalization
“the top part of the brain is involved in setting up plans, controlling movements, registering 
changes in where objects are located in space, and revising plans when anticipated events 
do not occur.” 
27 
In the process, engaging both top and bottom brain 
“bottom is involved in classifying and interpreting what we perceive, and allows us to 
confer meaning on the world.” 
“The Theory of Cognitive Modes* emphasizes the constant and 
close interaction of the top and bottom systems. They don’t work in 
isolation — or in competition — but seamlessly together.” 
*http://brainblogger.com/2013/12/19/top-brain-bottom-brain-part-3-the-theory-of-cognitive-modes/ 
by G. Wayne Miller and Stephen M. Kosslyn, PhD | December 19, 2013
28 
Can we take inspiration from the ‘Theory of Cognitive Modes’ to develop a 
computational model? 
T & B B T 
Mover Perceiver Simulator Adaptor 
http://online.stanford.edu/pgm-fa12 
T- Top brain, B- Bottom brain 
our baby step toward 
a computational model for perception 
(Machine Perception)
29 
Toward a symbiotic partnership between machines and people 
J. 
McCarthy 
M. 
Weiser 
D. 
Engelbart 
J. C. R. Licklider 
htttp://j.mp/k-che 
http://knoesis.org/index.php/Computing_For_Human_Experience
30 
How are machines supposed to integrate and interpret sensor data? 
RDF OWL 
Semantic Sensor Networks (SSN)
31 
W3C Semantic Sensor Network Ontology 
Lefort, L., Henson, C., Taylor, K., Barnaghi, P., Compton, M., Corcho, O., Garcia-Castro, R., Graybeal, J., Herzog, A., Janowicz, K., 
Neuhaus, H., Nikolov, A., and Page, K.: Semantic Sensor Network XG Final Report, W3C Incubator Group Report (2011).
32 
W3C Semantic Sensor Network Ontology 
Lefort, L., Henson, C., Taylor, K., Barnaghi, P., Compton, M., Corcho, O., Garcia-Castro, R., Graybeal, J., Herzog, A., Janowicz, K., 
Neuhaus, H., Nikolov, A., and Page, K.: Semantic Sensor Network XG Final Report, W3C Incubator Group Report (2011).
SSN 
Ontology 
3 Interpreted data 
(abductive) 
[in OWL] 
e.g., diagnosis 
2 Interpreted data 
(deductive) 
[in OWL] 
e.g., threshold 
1 Annotated Data 
[in RDF] 
e.g., label 
0 Raw Data 
[in TEXT] 
e.g., number 
Intellego 
Hyperthyroidism 
… … 
Elevated 
Blood 
Pressure 
Systolic blood pressure of 150 mmHg 
“150” 
33 
Levels of Abstraction
34 
What if we could automate this interpretation of Data? 
… and do it efficiently and at scale
35 
Making sense of sensor data with 
Henson et al An Ontological Approach to Focusing Attention and Enhancing Machine Perception on the Web, Applied Ont, 2011
36 
People are good at making sense of sensory input 
What can we learn from cognitive models of perception? 
The key ingredient is prior knowledge
Observe 
Property 
* based on Neisser’s cognitive model of perception 
Perceive 
Feature 
Explanation 
Discrimination 
1 
2 
Translating low-level signals 
into high-level knowledge 
Focusing attention on those 
aspects of the environment that 
provide useful information 
Prior Knowledge 
37 
Convert large number of observations to semantic 
abstractions that provide insights and translate into 
decisions 
Perception Cycle*
38 
To enable machine perception, 
Semantic Web technology is used to integrate 
sensor data with prior knowledge on the Web 
W3C SSN XG 2010-2011, SSN Ontology
W3C Semantic Sensor 
Network (SSN) Ontology Bi-partite Graph 
39 
Prior knowledge on the Web
W3C Semantic Sensor 
Network (SSN) Ontology Bi-partite Graph 
40 
Prior knowledge on the Web
Observe 
Property 
Perceive 
Feature 
Explanation 
1 
Explanation 
Translating low-level 
signals into high-level 
knowledge 
41 
Explanation is the act of choosing the objects or events that best account 
for a set of observations; often referred to as hypothesis building
Inference to the best explanation 
• In general, explanation is an abductive problem; 
and hard to compute 
Finding the sweet spot between abduction and OWL 
• Single-feature assumption* enables use of 
OWL-DL deductive reasoner 
* An explanation must be a single feature which accounts for 
all observed properties 
42 
Explanation is the act of choosing the objects or events that best account 
for a set of observations; often referred to as hypothesis building 
Representation of Parsimonious Covering Theory in OWL-DL 
Explanation
Explanation 
ExplanatoryFeature ≡ ∃ssn:isPropertyOf—.{p1} ⊓ … ⊓ ∃ssn:isPropertyOf—.{pn} 
Observed Property Explanatory Feature 
elevated blood pressure 
clammy skin 
palpitations 
Hypertension 
Hyperthyroidism 
Pulmonary Edema 
43 
Explanatory Feature: a feature that explains the set of observed 
properties
Discrimination 
Observe 
Property 
Perceive 
Feature 
Explanation 
Discrimination 
2 
Focusing attention on those 
aspects of the environment 
that provide useful 
information 
44 
Discrimination is the act of finding those properties that, if observed, 
would help distinguish between multiple explanatory features
Discrimination 
ExpectedProperty ≡ ∃ssn:isPropertyOf.{f1} ⊓ … ⊓ ∃ssn:isPropertyOf.{fn} 
Expected Property Explanatory Feature 
elevated blood pressure 
clammy skin 
palpitations 
Hypertension 
Hyperthyroidism 
Pulmonary Edema 
45 
Expected Property: would be explained by every explanatory feature
Discrimination 
NotApplicableProperty ≡ ¬∃ssn:isPropertyOf.{f1} ⊓ … ⊓ ¬∃ssn:isPropertyOf.{fn} 
Not Applicable Property Explanatory Feature 
elevated blood pressure 
clammy skin 
palpitations 
Hypertension 
Hyperthyroidism 
Pulmonary Edema 
46 
Not Applicable Property: would not be explained by any explanatory 
feature
Discrimination 
DiscriminatingProperty ≡ ¬ExpectedProperty ⊓ ¬NotApplicableProperty 
Discriminating Property Explanatory Feature 
elevated blood pressure 
clammy skin 
palpitations 
Hypertension 
Hyperthyroidism 
Pulmonary Edema 
47 
Discriminating Property: is neither expected nor not-applicable
Semantic scalability: Resource savings of abstracting sensor data 
48 
Orders of magnitude resource savings for generating and storing relevant 
abstractions vs. raw observations. 
Relevant abstractions 
Raw observations
Qualities 
-High BP 
-Increased Weight 
Entities 
-Hypertension 
-Hypothyroidism 
kHealth 
Machine Sensors 
Personal Input 
EMR/PHR 
Comorbidity risk 
score e.g., 
Charlson Index 
Longitudinal studies 
of cardiovascular 
risks 
- Find risk factors 
- Validation 
- domain knowledge 
- domain expert 
Find contribution of 
each risk factor 
Risk Assessment Model 
Current 
Observations 
-Physical 
-Physiological 
-History 
Risk Score 
(e.g., 1 => continue 
3 => contact clinic) 
Validate correlations Model Creation 
Historical 
observations e.g., 
EMR, sensor 
observations 
49 
Risk Score: from Data to Abstraction and Actionable Information
Use of OWL reasoner is resource intensive 
(especially on resource-constrained devices), 
in terms of both memory and time 
• Runs out of resources with prior knowledge >> 15 nodes 
• Asymptotic complexity: O(n3) 
50 
How do we implement machine perception efficiently on a 
resource-constrained device?
Approach 1: Send all sensor 
observations to the cloud for 
processing 
intelligence at the edge 
51 
Approach 2: downscale semantic 
processing so that each device is 
capable of machine perception
Efficient execution of machine perception 
010110001101 
0011110010101 
1000110110110 
101100011010 
0111100101011 
000110101100 
0110100111 
52 
Use bit vector encodings and their operations to encode prior 
knowledge and execute semantic reasoning 
Henson et al. 'An Efficient Bit Vector Approach to Semantics-based Machine Perception in Resource-Constrained Devices, 
ISWC 2012.
Efficiency Improvement 
• Problem size increased from 10’s to 1000’s of 
nodes 
• Time reduced from minutes to milliseconds 
• Complexity growth reduced from polynomial to 
linear 
O(n3) < x < O(n4) O(n) 
53 
Evaluation on a mobile device
1 Translate low-level data to high-level knowledge 
Machine perception can be used to convert low-level 
sensory signals into high-level knowledge useful for 
decision making 
2 Prior knowledge is the key to perception 
Using SW technologies, machine perception can be 
formalized and integrated with prior knowledge on the 
Web 
3 Intelligence at the edge 
By downscaling semantic inference, machine 
perception can execute efficiently on resource-constrained 
devices 
54 
Semantic Perception for smarter analytics: 3 ideas to takeaway
kHealth 
Knowledge-enabled Healthcare 
Applied to ADHF, Asthma, GI, and Dementia 
55
Brief Introduction Video
Empowering Individuals (who are not Larry Smarr!) for their own health 
Through physical monitoring and 
analysis, our cellphones could act as 
an early warning system to detect 
serious health conditions, and 
provide actionable information 
canary in a coal mine 
kHealth: knowledge-enabled healthcare 
57
1http://www.nhlbi.nih.gov/health/health-topics/topics/asthma/ 
2http://www.lung.org/lung-disease/asthma/resources/facts-and-figures/asthma-in-adults.html 
3Akinbami et al. (2009). Status of childhood asthma in the United States, 1980–2007. Pediatrics,123(Supplement 3), S131-S145. 
60 
25 
million 
300 
million 
$50 
billion 
155,000 
593,000 
People in the U.S. are 
diagnosed with asthma 
(7 million are children)1. 
People suffering from 
asthma worldwide2. 
Spent on asthma alone 
in a year2 
Hospital admissions in 
20063 
Emergency department 
visits in 20063 
Asthma: Severity of the problem
WHY Big Data to Smart Data: Asthma example 
what can we do to avoid asthma episode? 
Understanding relationships between 
health signals and asthma attacks 
for providing actionable information 
61 
Value 
What risk factors influence asthma control? 
What is the contribution of each risk factor? 
semantics 
Velocity Veracity 
Variety Volume 
Real-time health signals from personal level (e.g., Wheezometer, NO in breath, 
accelerometer, microphone), public health (e.g., CDC, Hospital EMR), and 
population level (e.g., pollen level, CO2) arriving continuously in fine grained 
samples potentially with missing information and uneven sampling frequencies.
kHealth: Health Signal Processing Architecture 
Personal level 
Signals 
Public level 
Signals 
Population level 
Signals 
Domain 
Knowledge 
Risk Model 
Events from 
Social Streams 
Take Medication before 
going to work 
Contact doctor 
Avoid going out in the 
evening due to high pollen 
levels 
Analysis 
Personalized 
Actionable 
Information 
Data Acquisition & 
aggregation 
62
63 
Asthma Domain Knowledge 
Asthma Control 
and Actionable Information 
Domain 
Knowledge 
Asthma Control 
à 
Daily Medication 
Choices for starting 
therapy 
Not Well Controlled Poor Controlled 
Severity Level 
of Asthma 
(Recommended Action) (Recommended Action) (Recommended Action) 
Intermittent Asthma SABA prn - - 
Mild Persistent Asthma Low dose ICS Medium ICS Medium ICS 
Moderate Persistent 
Asthma 
Medium dose ICS alone 
Or with 
LABA/montelukast 
Medium ICS + 
LABA/Montelukast 
Or High dose ICS 
Medium ICS + 
LABA/Montelukast 
Or High dose ICS* 
Severe Persistent Asthma High dose ICS with 
LABA/montelukast 
Needs specialist care Needs specialist care 
	 
ICS= inhaled corticosteroid, LABA = inhaled long-acting beta2-agonist, SABA= inhaled short-acting beta2-agonist ; 
*consider referral to specialist
64 
Patient Health Score (diagnostic) 
How controlled is my asthma? 
Risk assessment 
model 
Semantic 
Perception 
Personal level 
Signals 
Public level 
Signals 
Domain 
Knowledge 
Population level 
Signals 
GREEN -- Well Controlled 
YELLOW – Not well controlled 
Red -- poor controlled
Background 
Knowledge 
65 
Patient Health Score (diagnostic): Details 
Physical-Cyber-Social System Observations Health Signal Extraction Health Signal Understanding 
Personal 
Population Level 
Acceleration readings from 
on-phone sensors 
Wheeze – Yes 
Do you have tightness of chest? –Yes 
Risk Category assigned by 
doctors 
<Wheezing=Yes, time, location> 
<ChectTightness=Yes, time, location> 
<PollenLevel=Medium, time, location> 
<Pollution=Yes, time, location> 
<Activity=High, time, location> 
PollenLevel 
Wheezing 
ChectTightness 
Pollution 
Activity 
PollenLevel 
Wheezing 
ChectTightness 
Pollution 
Activity 
RiskCategory 
<PollenLevel, ChectTightness, Pollution, 
Activity, Wheezing, RiskCategory> 
<2, 1, 1,3, 1, RiskCategory> 
<2, 1, 1,3, 1, RiskCategory> 
<2, 1, 1,3, 1, RiskCategory> 
<2, 1, 1,3, 1, RiskCategory> 
. 
. 
. 
Expert 
Knowledge 
Sensor and personal 
observations 
tweet reporting pollution level 
and asthma attacks 
Signals from personal, personal 
spaces, and community spaces 
Qualify 
Quantify 
Enrich 
Outdoor pollen and pollution 
Public Health 
Well Controlled - continue 
Not Well Controlled – contact nurse 
Poor Controlled – contact doctor
66 
Patient Vulnerability Score (prognostic) 
How vulnerable* is my control level today? 
Risk assessment 
model 
Semantic 
Perception 
Personal level 
Signals 
Public level 
Signals 
Domain 
Knowledge 
Population level 
Signals 
Patient health 
Score 
*considering changing environmental conditions and current control level
67 
Patient Vulnerability Score (prognostic): Details 
Sensordrone – for monitoring 
environmental air quality 
Wheezometer – for monitoring 
wheezing sounds 
Can I reduce my asthma attacks at night? 
What are the triggers? What is the wheezing level? 
What is the exposure level over a day? 
What is the propensity toward asthma? 
Commute to Work 
Luminosity 
CO level 
CO in gush 
during day time 
Actionable 
Information 
Personal level 
Signals 
Public level 
Signals 
Population level 
Signals 
What is the air quality indoors?
Sensordrone 
(Carbon monoxide, 
temperature, humidity) 
Node Sensor 
(exhaled Nitric Oxide) 
68 
Sensors 
Android Device 
(w/ kHealth App) 
Total cost: ~ $500 
kHealth Kit for the application for Asthma management 
Along with two sensors in the kit, the application uses a variety of population 
level signals from the web: 
Pollen level Air Quality Temperature & Humidity
69 
Usability and decision support trial 
Dr. Shalini G. Forbis, MD, MPH
Preliminary insights from patient data 
S1 S2 
Sensor data QA data 
Number of 
Observations 
36 
108 
40 
121
Medication (Albuterol) related to decreasing Exhaled Nitric Oxide 
1 
0.9 
0.8 
0.7 
0.6 
0.5 
0.4 
0.3 
0.2 
0.1 
0 
Did patient take albuterol last 
night due to cough or wheeze? 
0.25 
0.2 
0.15 
0.1 
0.05 
0 
Exhaled Nitric Oxide
Activity limitation related to high exhaled Nitric Oxide 
1 
0.9 
0.8 
0.7 
0.6 
0.5 
0.4 
0.3 
0.2 
0.1 
0 
How much did asthma or asthma 
symptoms limit patient's activity today? 
0.25 
0.2 
0.15 
0.1 
0.05 
0 
Exhaled Nitric Oxide
Low exhaled Nitric Oxide observed with absence of coughing 
1 
0.9 
0.8 
0.7 
0.6 
0.5 
0.4 
0.3 
0.2 
0.1 
0 
Has patient had wheeze, chest 
tightness, or asthma related 
6/2/2014 
6/3/2014 
6/4/2014 
6/5/2014 
6/6/2014 
6/7/2014 
6/8/2014 
6/9/2014 
6/10/2014 
6/11/2014 
6/12/2014 
cough today? 
0.25 
0.2 
0.15 
0.1 
0.05 
0 
Nitric Oxide
Activity limitation observed with high pollen activity 
2.5 
2 
1.5 
1 
0.5 
0 
Pollen 
1 
0.9 
0.8 
0.7 
0.6 
0.5 
0.4 
0.3 
0.2 
0.1 
0 
How much did asthma or asthma 
symptoms limit patient's activity 
today?
75 
Two research directions for kHealth asthma with more data… 
Root cause analysis Action Recommendation 
Find Triggers of Asthma 
Derive the cause of asthma 
attacks for a given patient 
using statistical techniques 
+ knowledge of asthma and 
its triggers 
Minimize Asthma Attacks 
Model actions based on the 
utility theory (cost of 
actions & its rewards) + 
knowledge of action 
consequences
• Healthcare: 
ADFH, Asthma, GI 
– Using kHealth system 
• Traffic Analytics: 
– Understanding traffic flow 
• Social Media Analysis : 
– Crisis coordination using Twitris 
76 
I will use applications in 3 domains to demonstrate
78 
Understanding traffic flow variations
Big Data to Smart Data: Traffic Management example 
Vehicular traffic data from San Francisco Bay Area aggregated from on-road 
sensors (numerical) and incident reports (textual) 
Value 
Can we detect the onset of traffic congestion? 
Can we characterize traffic congestion based on events? 
Can we provide actionable information to decision makers? 
semantics 
Velocity Veracity 
Variety Volume 
Representing prior knowledge of 
traffic lead to a focused exploration 
of this massive dataset 
Every minute update of speed, volume, travel time, and occupancy resulting in 
178 million link status observations, 738 active events, and 146 scheduled 
events with many unevenly sampled observations collected over 3 months. 
79 http://511.org/
Semantic Annotation using Background Knowledge 
slow-moving-traffic 
Domain knowledge in the 
form of traffic vocabulary 
Image Credit: http://traffic.511.org/index 
Domain knowledge of 
traffic flow synthesized 
from sensor data 
80 
Explained-by 
Horizontal operator: relating/mapping data 
from different modality to a concept 
(theme) within a spatio-temporal context; 
Spatial context even include what it means 
to have a slow traffic for the type of road
• Healthcare: 
ADFH, Asthma, GI 
– Using kHealth system 
• Traffic Analytics: 
– Understanding traffic flow 
• Social Media Analysis : 
– Crisis coordination using Twitris 
81 
I will use applications in 2 domains to demonstrate
[BIG] Ad-hoc Community with Varying but [FEW] Important Intents 
Image: http://www.gizmodo.com.au/2012/04/how-we-identify-single-voices- 
82 
in-a-crowd/ 
Me and @CeceVancePR are 
coordinating a clothing/food drive 
for families affected by Hurricane 
Sandy. If you would like to donate, 
DM us 
Does anyone know how to donate 
clothes to hurricane #Sandy 
victims? 
BIG QUESTION: Can these needles be identified in the 
haystack of massive datasets? 
[REQUEST/DEMAND] 
[OFFER/SUPPLY] 
Coordination teams 
want to hear!
Uncoordinated Engagement 
• May lead to second disaster to be managed: 
– Under-supply of required demands 
– Over-supply of not required resources 
• Hurricane Sandy example, 
“Thanks, but no thanks”, NPR, 
Jan 12 2013 
Story 
link:http://www.npr.org/2013/01/09/168946170/tha 
nks-but-no-thanks-when-post-disaster-donations-overwhelm
84 
How to volunteer, donate to Hurricane 
Sandy: <URL> 
If you have clothes to donate to those who 
are victims of Hurricane Sandy … 
Red Cross is urging blood donations to 
support those affected <URL> 
I have TONS of cute shoes & purses I want 
to donate to hurricane victims … 
Does anyone know how to donate clothes 
to hurricane #Sandy victims? 
Does anyone know of community service 
organizations to volunteer to help out? 
Needs to get something, suggests scarcity: 
REQUEST (demand) 
Offers or wants to give, suggests abundance: 
OFFER (supply) 
Matching requests with offers
Want to help animals in 
#Oklahoma? @ASPCA 
tells how you can help: 
http://t.co/mt8l9PwzmO 
x 
RESPONSE TEAMS 
(including humanitarian 
org. and ‘pseudo’ 
responders) 
VICTIM SITE 
Where do I go 
to help out for 
volunteer work 
DEMAND SUPPLY 
around 
Moore? 
Anyone know? 
CITIZEN SENSORS 
Anyone know 
where to donate to 
help the animals 
from the Oklahoma 
disaster? #oklaho 
ma #dogs 
Matchable 
Matchable 
If you would like 
to volunteer 
today, help is 
desperately 
needed in 
Shawnee. Call 
273-5331 for 
more info 
85 
Match-making: Assisting Coordination 
Image: http://offthewallsocial.com/tag/social-media/
Two excellent videos 
• Vinod Khosla: the Power of Storytelling and 
the Future of Healthcare 
• Larry Smarr: The Human Microbiome and the 
Revolution in Digital Health 
86 
Wrapping up: For more on importance of what we talked about
• Big Data is every where 
– at individual and community levels - not just 
limited to corporation 
– with growing complexity: Physical-Cyber-Social 
• Analysis is not sufficient 
• Need interaction between bottom up 
techniques and top down processing 
87 
Wrapping up: Take Away
Wrapping up: Take Away 
• Focus on Humans and Improve human life and 
experience with SMART Data. 
– Data to Information to Personally and Contextually 
Relevant Abstractions (Semantic Perception) 
– Actionable Information (Value from data) to assist 
and support human in decision making. 
• Focus on Value -- SMART Data 
– Big Data Challenges without the intention of deriving 
Value is a “Journey without GOAL”. 
88
Special thanks: Pramod. This presentation covers some of the work of my PhD students. 
Key contributors: Pramod Anantharam, Cory Henson and TK Prasad. 
Amit Sheth’s 
PHD students 
Ashutos 
h 
Jadhav* 
Hemant 
Purohit 
Vinh 
Nguyen 
Lu Chen 
Pavan 
Kapanipathi* 
Pramod 
Sujan 
Perera 
Anantharam* 
Maryam Panahiazar 
Sarasi Lalithsena 
Shreyansh 
Batt 
Kalpa 
Gunaratna 
Delroy 
Cameron 
Sanjaya 
Wijeratne 
Wenbo 
Wang 
89 
Special thanks
• Among top universities in the world in World Wide Web (cf: 10-yr impact, 
Microsoft Academic Search: among top 10 in June2014) 
• Among the largest academic groups in the US in Semantic Web + Social/Sensor 
Webs, Mobile/Cloud/Cognitive Computing, Big Data, IoT, Health/Clinical & 
Biomedicine Applications 
• Exceptional student success: internships and jobs at top salary (IBM 
Watson/Research, MSR, Amazon, CISCO, Oracle, Yahoo!, Samsung, research 
universities, NLM, startups ) 
• 100 researchers including 15 World Class faculty (>3K citations/faculty avg) and 
~45 PhD students- practically all funded 
• Extensive research for largely multidisciplinary projects; world class resources; 
industry sponsorships/collaborations (Google, IBM, …) 
90
91 
Top organization in WWW: 10-yr Field Rating (MAS)
92
93 
Smart Data - How you and I will exploit Big Data 
thank you, and please visit us at 
http://knoesis.org

More Related Content

What's hot

Smart Data for you and me: Personalized and Actionable Physical Cyber Social ...
Smart Data for you and me: Personalized and Actionable Physical Cyber Social ...Smart Data for you and me: Personalized and Actionable Physical Cyber Social ...
Smart Data for you and me: Personalized and Actionable Physical Cyber Social ...
Amit Sheth
 
TRANSFORMING BIG DATA INTO SMART DATA: Deriving Value via Harnessing Volume, ...
TRANSFORMING BIG DATA INTO SMART DATA: Deriving Value via Harnessing Volume, ...TRANSFORMING BIG DATA INTO SMART DATA: Deriving Value via Harnessing Volume, ...
TRANSFORMING BIG DATA INTO SMART DATA: Deriving Value via Harnessing Volume, ...
Amit Sheth
 
Knowledge Will Propel Machine Understanding of Big Data
Knowledge Will Propel Machine Understanding of Big DataKnowledge Will Propel Machine Understanding of Big Data
Knowledge Will Propel Machine Understanding of Big Data
Amit Sheth
 
Computing for Human Experience [v4]: Keynote @ OnTheMove Federated Conferences
Computing for Human Experience [v4]: Keynote @ OnTheMove Federated ConferencesComputing for Human Experience [v4]: Keynote @ OnTheMove Federated Conferences
Computing for Human Experience [v4]: Keynote @ OnTheMove Federated Conferences
Artificial Intelligence Institute at UofSC
 
Physical Cyber Social Computing
Physical Cyber Social ComputingPhysical Cyber Social Computing
Physical Cyber Social Computing
Amit Sheth
 
Social and Physical Sensing Enabled Decision Support for Disaster Management ...
Social and Physical Sensing Enabled Decision Support for Disaster Management ...Social and Physical Sensing Enabled Decision Support for Disaster Management ...
Social and Physical Sensing Enabled Decision Support for Disaster Management ...
Artificial Intelligence Institute at UofSC
 
Knowledge-empowered Probabilistic Graphical Models for Physical-Cyber-Social ...
Knowledge-empowered Probabilistic Graphical Models for Physical-Cyber-Social ...Knowledge-empowered Probabilistic Graphical Models for Physical-Cyber-Social ...
Knowledge-empowered Probabilistic Graphical Models for Physical-Cyber-Social ...
Artificial Intelligence Institute at UofSC
 
Semantics-empowered Approaches to Big Data Processing for Physical-Cyber-Soci...
Semantics-empowered Approaches to Big Data Processing for Physical-Cyber-Soci...Semantics-empowered Approaches to Big Data Processing for Physical-Cyber-Soci...
Semantics-empowered Approaches to Big Data Processing for Physical-Cyber-Soci...
Artificial Intelligence Institute at UofSC
 
Knoesis Student Achievement
Knoesis Student AchievementKnoesis Student Achievement
Knoesis Student Achievement
Artificial Intelligence Institute at UofSC
 
A Semantics-based Approach to Machine Perception
A Semantics-based Approach to Machine PerceptionA Semantics-based Approach to Machine Perception
A Semantics-based Approach to Machine Perception
Cory Andrew Henson
 
Transforming Big Data into Smart Data for Smart Energy: Deriving Value via ha...
Transforming Big Data into Smart Data for Smart Energy: Deriving Value via ha...Transforming Big Data into Smart Data for Smart Energy: Deriving Value via ha...
Transforming Big Data into Smart Data for Smart Energy: Deriving Value via ha...
Amit Sheth
 
Physical Cyber Social Computing: An early 21st century approach to Computing ...
Physical Cyber Social Computing: An early 21st century approach to Computing ...Physical Cyber Social Computing: An early 21st century approach to Computing ...
Physical Cyber Social Computing: An early 21st century approach to Computing ...
Amit Sheth
 
Data Science and Urban Science @ UW
Data Science and Urban Science @ UWData Science and Urban Science @ UW
Data Science and Urban Science @ UW
University of Washington
 
Understanding City Traffic Dynamics Utilizing Sensor and Textual Observations
Understanding City Traffic Dynamics Utilizing Sensor and Textual ObservationsUnderstanding City Traffic Dynamics Utilizing Sensor and Textual Observations
Understanding City Traffic Dynamics Utilizing Sensor and Textual Observations
Artificial Intelligence Institute at UofSC
 
Urban Data Science at UW
Urban Data Science at UWUrban Data Science at UW
Urban Data Science at UW
University of Washington
 
Big Data Talent in Academic and Industry R&D
Big Data Talent in Academic and Industry R&DBig Data Talent in Academic and Industry R&D
Big Data Talent in Academic and Industry R&D
University of Washington
 
The UVA School of Data Science
The UVA School of Data ScienceThe UVA School of Data Science
The UVA School of Data Science
Philip Bourne
 
Adventures in Crowdsourcing : Toward Safer Content Moderation & Better Suppor...
Adventures in Crowdsourcing : Toward Safer Content Moderation & Better Suppor...Adventures in Crowdsourcing : Toward Safer Content Moderation & Better Suppor...
Adventures in Crowdsourcing : Toward Safer Content Moderation & Better Suppor...
Matthew Lease
 
The NEEDS vs. the WANTS in IoT
The NEEDS vs. the WANTS in IoTThe NEEDS vs. the WANTS in IoT
The NEEDS vs. the WANTS in IoT
Prasant Misra
 
Sensors, Signals and Sense-making in Human-Energy Relationships
Sensors, Signals and Sense-making in Human-Energy RelationshipsSensors, Signals and Sense-making in Human-Energy Relationships
Sensors, Signals and Sense-making in Human-Energy Relationships
Martha Russell
 

What's hot (20)

Smart Data for you and me: Personalized and Actionable Physical Cyber Social ...
Smart Data for you and me: Personalized and Actionable Physical Cyber Social ...Smart Data for you and me: Personalized and Actionable Physical Cyber Social ...
Smart Data for you and me: Personalized and Actionable Physical Cyber Social ...
 
TRANSFORMING BIG DATA INTO SMART DATA: Deriving Value via Harnessing Volume, ...
TRANSFORMING BIG DATA INTO SMART DATA: Deriving Value via Harnessing Volume, ...TRANSFORMING BIG DATA INTO SMART DATA: Deriving Value via Harnessing Volume, ...
TRANSFORMING BIG DATA INTO SMART DATA: Deriving Value via Harnessing Volume, ...
 
Knowledge Will Propel Machine Understanding of Big Data
Knowledge Will Propel Machine Understanding of Big DataKnowledge Will Propel Machine Understanding of Big Data
Knowledge Will Propel Machine Understanding of Big Data
 
Computing for Human Experience [v4]: Keynote @ OnTheMove Federated Conferences
Computing for Human Experience [v4]: Keynote @ OnTheMove Federated ConferencesComputing for Human Experience [v4]: Keynote @ OnTheMove Federated Conferences
Computing for Human Experience [v4]: Keynote @ OnTheMove Federated Conferences
 
Physical Cyber Social Computing
Physical Cyber Social ComputingPhysical Cyber Social Computing
Physical Cyber Social Computing
 
Social and Physical Sensing Enabled Decision Support for Disaster Management ...
Social and Physical Sensing Enabled Decision Support for Disaster Management ...Social and Physical Sensing Enabled Decision Support for Disaster Management ...
Social and Physical Sensing Enabled Decision Support for Disaster Management ...
 
Knowledge-empowered Probabilistic Graphical Models for Physical-Cyber-Social ...
Knowledge-empowered Probabilistic Graphical Models for Physical-Cyber-Social ...Knowledge-empowered Probabilistic Graphical Models for Physical-Cyber-Social ...
Knowledge-empowered Probabilistic Graphical Models for Physical-Cyber-Social ...
 
Semantics-empowered Approaches to Big Data Processing for Physical-Cyber-Soci...
Semantics-empowered Approaches to Big Data Processing for Physical-Cyber-Soci...Semantics-empowered Approaches to Big Data Processing for Physical-Cyber-Soci...
Semantics-empowered Approaches to Big Data Processing for Physical-Cyber-Soci...
 
Knoesis Student Achievement
Knoesis Student AchievementKnoesis Student Achievement
Knoesis Student Achievement
 
A Semantics-based Approach to Machine Perception
A Semantics-based Approach to Machine PerceptionA Semantics-based Approach to Machine Perception
A Semantics-based Approach to Machine Perception
 
Transforming Big Data into Smart Data for Smart Energy: Deriving Value via ha...
Transforming Big Data into Smart Data for Smart Energy: Deriving Value via ha...Transforming Big Data into Smart Data for Smart Energy: Deriving Value via ha...
Transforming Big Data into Smart Data for Smart Energy: Deriving Value via ha...
 
Physical Cyber Social Computing: An early 21st century approach to Computing ...
Physical Cyber Social Computing: An early 21st century approach to Computing ...Physical Cyber Social Computing: An early 21st century approach to Computing ...
Physical Cyber Social Computing: An early 21st century approach to Computing ...
 
Data Science and Urban Science @ UW
Data Science and Urban Science @ UWData Science and Urban Science @ UW
Data Science and Urban Science @ UW
 
Understanding City Traffic Dynamics Utilizing Sensor and Textual Observations
Understanding City Traffic Dynamics Utilizing Sensor and Textual ObservationsUnderstanding City Traffic Dynamics Utilizing Sensor and Textual Observations
Understanding City Traffic Dynamics Utilizing Sensor and Textual Observations
 
Urban Data Science at UW
Urban Data Science at UWUrban Data Science at UW
Urban Data Science at UW
 
Big Data Talent in Academic and Industry R&D
Big Data Talent in Academic and Industry R&DBig Data Talent in Academic and Industry R&D
Big Data Talent in Academic and Industry R&D
 
The UVA School of Data Science
The UVA School of Data ScienceThe UVA School of Data Science
The UVA School of Data Science
 
Adventures in Crowdsourcing : Toward Safer Content Moderation & Better Suppor...
Adventures in Crowdsourcing : Toward Safer Content Moderation & Better Suppor...Adventures in Crowdsourcing : Toward Safer Content Moderation & Better Suppor...
Adventures in Crowdsourcing : Toward Safer Content Moderation & Better Suppor...
 
The NEEDS vs. the WANTS in IoT
The NEEDS vs. the WANTS in IoTThe NEEDS vs. the WANTS in IoT
The NEEDS vs. the WANTS in IoT
 
Sensors, Signals and Sense-making in Human-Energy Relationships
Sensors, Signals and Sense-making in Human-Energy RelationshipsSensors, Signals and Sense-making in Human-Energy Relationships
Sensors, Signals and Sense-making in Human-Energy Relationships
 

Similar to Smart Data - How you and I will exploit Big Data for personalized digital health and many other activities

AI WORLD: I-World: EIS Global Innovation Platform: BIG Knowledge World vs. BI...
AI WORLD: I-World: EIS Global Innovation Platform: BIG Knowledge World vs. BI...AI WORLD: I-World: EIS Global Innovation Platform: BIG Knowledge World vs. BI...
AI WORLD: I-World: EIS Global Innovation Platform: BIG Knowledge World vs. BI...
Azamat Abdoullaev
 
Computing for Human Experience: Sensors, Perception, Semantics, Social Comput...
Computing for Human Experience: Sensors, Perception, Semantics, Social Comput...Computing for Human Experience: Sensors, Perception, Semantics, Social Comput...
Computing for Human Experience: Sensors, Perception, Semantics, Social Comput...
Amit Sheth
 
Crowdsourcing Approaches for Smart City Open Data Management
Crowdsourcing Approaches for Smart City Open Data ManagementCrowdsourcing Approaches for Smart City Open Data Management
Crowdsourcing Approaches for Smart City Open Data Management
Edward Curry
 
Computing for Human Experience: Semantics empowered Cyber-Physical, Social an...
Computing for Human Experience: Semantics empowered Cyber-Physical, Social an...Computing for Human Experience: Semantics empowered Cyber-Physical, Social an...
Computing for Human Experience: Semantics empowered Cyber-Physical, Social an...
Amit Sheth
 
What Data Can Do: A Typology of Mechanisms . Angèle Christin
What Data Can Do: A Typology of Mechanisms . Angèle Christin What Data Can Do: A Typology of Mechanisms . Angèle Christin
What Data Can Do: A Typology of Mechanisms . Angèle Christin
eraser Juan José Calderón
 
Inauguration Function - Ohio Center of Excellence in Knowledge-Enabled Comput...
Inauguration Function - Ohio Center of Excellence in Knowledge-Enabled Comput...Inauguration Function - Ohio Center of Excellence in Knowledge-Enabled Comput...
Inauguration Function - Ohio Center of Excellence in Knowledge-Enabled Comput...
Artificial Intelligence Institute at UofSC
 
Data Science Innovations : Democratisation of Data and Data Science
Data Science Innovations : Democratisation of Data and Data Science  Data Science Innovations : Democratisation of Data and Data Science
Data Science Innovations : Democratisation of Data and Data Science
suresh sood
 
Computing for Human Experience [v3, Aug-Oct 2010]
Computing for Human Experience [v3, Aug-Oct 2010]Computing for Human Experience [v3, Aug-Oct 2010]
Computing for Human Experience [v3, Aug-Oct 2010]
Artificial Intelligence Institute at UofSC
 
Building Effective Visualization Shiny WVF
Building Effective Visualization Shiny WVFBuilding Effective Visualization Shiny WVF
Building Effective Visualization Shiny WVF
Olga Scrivner
 
New and Emerging Forms of Data
New and Emerging Forms of DataNew and Emerging Forms of Data
New and Emerging Forms of Data
David De Roure
 
New Data `New Computation
New Data `New ComputationNew Data `New Computation
New Data `New Computation
David De Roure
 
Sensory transformation
Sensory transformationSensory transformation
Sensory transformation
Karlos Svoboda
 
Advanced Cyberinfrastructure Enabled Services and Applications in 2021
Advanced Cyberinfrastructure Enabled Services and Applications in 2021Advanced Cyberinfrastructure Enabled Services and Applications in 2021
Advanced Cyberinfrastructure Enabled Services and Applications in 2021
Larry Smarr
 
Cognitive Computing in Cyber Physical Systems Transformative Integration for ...
Cognitive Computing in Cyber Physical Systems Transformative Integration for ...Cognitive Computing in Cyber Physical Systems Transformative Integration for ...
Cognitive Computing in Cyber Physical Systems Transformative Integration for ...
ijtsrd
 
PatternLanguageOfData
PatternLanguageOfDataPatternLanguageOfData
PatternLanguageOfData
kimErwin
 
Energing Technology and the Creative Economy
Energing Technology and the Creative EconomyEnerging Technology and the Creative Economy
Energing Technology and the Creative Economy
Jerome Glenn
 
Big Data for the Social Sciences
Big Data for the Social SciencesBig Data for the Social Sciences
Big Data for the Social Sciences
David De Roure
 
Gordana Dodig-Crnkovic: Participating and Anticipating. Actors and Agents Net...
Gordana Dodig-Crnkovic: Participating and Anticipating. Actors and Agents Net...Gordana Dodig-Crnkovic: Participating and Anticipating. Actors and Agents Net...
Gordana Dodig-Crnkovic: Participating and Anticipating. Actors and Agents Net...
José Nafría
 
Big Data for the Social Sciences - David De Roure - Jisc Digital Festival 2014
Big Data for the Social Sciences - David De Roure - Jisc Digital Festival 2014Big Data for the Social Sciences - David De Roure - Jisc Digital Festival 2014
Big Data for the Social Sciences - David De Roure - Jisc Digital Festival 2014
Jisc
 
Elastic cognitive systems 18 6-2015-dustdar
Elastic cognitive systems 18 6-2015-dustdarElastic cognitive systems 18 6-2015-dustdar
Elastic cognitive systems 18 6-2015-dustdar
diannepatricia
 

Similar to Smart Data - How you and I will exploit Big Data for personalized digital health and many other activities (20)

AI WORLD: I-World: EIS Global Innovation Platform: BIG Knowledge World vs. BI...
AI WORLD: I-World: EIS Global Innovation Platform: BIG Knowledge World vs. BI...AI WORLD: I-World: EIS Global Innovation Platform: BIG Knowledge World vs. BI...
AI WORLD: I-World: EIS Global Innovation Platform: BIG Knowledge World vs. BI...
 
Computing for Human Experience: Sensors, Perception, Semantics, Social Comput...
Computing for Human Experience: Sensors, Perception, Semantics, Social Comput...Computing for Human Experience: Sensors, Perception, Semantics, Social Comput...
Computing for Human Experience: Sensors, Perception, Semantics, Social Comput...
 
Crowdsourcing Approaches for Smart City Open Data Management
Crowdsourcing Approaches for Smart City Open Data ManagementCrowdsourcing Approaches for Smart City Open Data Management
Crowdsourcing Approaches for Smart City Open Data Management
 
Computing for Human Experience: Semantics empowered Cyber-Physical, Social an...
Computing for Human Experience: Semantics empowered Cyber-Physical, Social an...Computing for Human Experience: Semantics empowered Cyber-Physical, Social an...
Computing for Human Experience: Semantics empowered Cyber-Physical, Social an...
 
What Data Can Do: A Typology of Mechanisms . Angèle Christin
What Data Can Do: A Typology of Mechanisms . Angèle Christin What Data Can Do: A Typology of Mechanisms . Angèle Christin
What Data Can Do: A Typology of Mechanisms . Angèle Christin
 
Inauguration Function - Ohio Center of Excellence in Knowledge-Enabled Comput...
Inauguration Function - Ohio Center of Excellence in Knowledge-Enabled Comput...Inauguration Function - Ohio Center of Excellence in Knowledge-Enabled Comput...
Inauguration Function - Ohio Center of Excellence in Knowledge-Enabled Comput...
 
Data Science Innovations : Democratisation of Data and Data Science
Data Science Innovations : Democratisation of Data and Data Science  Data Science Innovations : Democratisation of Data and Data Science
Data Science Innovations : Democratisation of Data and Data Science
 
Computing for Human Experience [v3, Aug-Oct 2010]
Computing for Human Experience [v3, Aug-Oct 2010]Computing for Human Experience [v3, Aug-Oct 2010]
Computing for Human Experience [v3, Aug-Oct 2010]
 
Building Effective Visualization Shiny WVF
Building Effective Visualization Shiny WVFBuilding Effective Visualization Shiny WVF
Building Effective Visualization Shiny WVF
 
New and Emerging Forms of Data
New and Emerging Forms of DataNew and Emerging Forms of Data
New and Emerging Forms of Data
 
New Data `New Computation
New Data `New ComputationNew Data `New Computation
New Data `New Computation
 
Sensory transformation
Sensory transformationSensory transformation
Sensory transformation
 
Advanced Cyberinfrastructure Enabled Services and Applications in 2021
Advanced Cyberinfrastructure Enabled Services and Applications in 2021Advanced Cyberinfrastructure Enabled Services and Applications in 2021
Advanced Cyberinfrastructure Enabled Services and Applications in 2021
 
Cognitive Computing in Cyber Physical Systems Transformative Integration for ...
Cognitive Computing in Cyber Physical Systems Transformative Integration for ...Cognitive Computing in Cyber Physical Systems Transformative Integration for ...
Cognitive Computing in Cyber Physical Systems Transformative Integration for ...
 
PatternLanguageOfData
PatternLanguageOfDataPatternLanguageOfData
PatternLanguageOfData
 
Energing Technology and the Creative Economy
Energing Technology and the Creative EconomyEnerging Technology and the Creative Economy
Energing Technology and the Creative Economy
 
Big Data for the Social Sciences
Big Data for the Social SciencesBig Data for the Social Sciences
Big Data for the Social Sciences
 
Gordana Dodig-Crnkovic: Participating and Anticipating. Actors and Agents Net...
Gordana Dodig-Crnkovic: Participating and Anticipating. Actors and Agents Net...Gordana Dodig-Crnkovic: Participating and Anticipating. Actors and Agents Net...
Gordana Dodig-Crnkovic: Participating and Anticipating. Actors and Agents Net...
 
Big Data for the Social Sciences - David De Roure - Jisc Digital Festival 2014
Big Data for the Social Sciences - David De Roure - Jisc Digital Festival 2014Big Data for the Social Sciences - David De Roure - Jisc Digital Festival 2014
Big Data for the Social Sciences - David De Roure - Jisc Digital Festival 2014
 
Elastic cognitive systems 18 6-2015-dustdar
Elastic cognitive systems 18 6-2015-dustdarElastic cognitive systems 18 6-2015-dustdar
Elastic cognitive systems 18 6-2015-dustdar
 

Recently uploaded

社内勉強会資料_TransNeXt: Robust Foveal Visual Perception for Vision Transformers
社内勉強会資料_TransNeXt: Robust Foveal Visual Perception for Vision Transformers社内勉強会資料_TransNeXt: Robust Foveal Visual Perception for Vision Transformers
社内勉強会資料_TransNeXt: Robust Foveal Visual Perception for Vision Transformers
NABLAS株式会社
 
Welcome back to Instagram. Sign in to check out what your
Welcome back to Instagram. Sign in to check out what yourWelcome back to Instagram. Sign in to check out what your
Welcome back to Instagram. Sign in to check out what your
Virni Arrora
 
Verified Girls Call Andheri 9930245274 Unlimited Short Providing Girls Servic...
Verified Girls Call Andheri 9930245274 Unlimited Short Providing Girls Servic...Verified Girls Call Andheri 9930245274 Unlimited Short Providing Girls Servic...
Verified Girls Call Andheri 9930245274 Unlimited Short Providing Girls Servic...
revolutionary575
 
Beautiful Girls Call Pune 000XX00000 Provide Best And Top Girl Service And No...
Beautiful Girls Call Pune 000XX00000 Provide Best And Top Girl Service And No...Beautiful Girls Call Pune 000XX00000 Provide Best And Top Girl Service And No...
Beautiful Girls Call Pune 000XX00000 Provide Best And Top Girl Service And No...
birajmohan012
 
Celebrity Girls Call Noida 9873940964 Unlimited Short Providing Girls Service...
Celebrity Girls Call Noida 9873940964 Unlimited Short Providing Girls Service...Celebrity Girls Call Noida 9873940964 Unlimited Short Providing Girls Service...
Celebrity Girls Call Noida 9873940964 Unlimited Short Providing Girls Service...
ginni singh$A17
 
Premium Girls Call Navi Mumbai 🎈🔥9920725232 🔥💋🎈 Provide Best And Top Girl Ser...
Premium Girls Call Navi Mumbai 🎈🔥9920725232 🔥💋🎈 Provide Best And Top Girl Ser...Premium Girls Call Navi Mumbai 🎈🔥9920725232 🔥💋🎈 Provide Best And Top Girl Ser...
Premium Girls Call Navi Mumbai 🎈🔥9920725232 🔥💋🎈 Provide Best And Top Girl Ser...
6459astrid
 
DU degree offer diploma Transcript
DU degree offer diploma TranscriptDU degree offer diploma Transcript
DU degree offer diploma Transcript
uapta
 
ch8_multiplexing cs553 st07 slide share ss
ch8_multiplexing cs553 st07 slide share ssch8_multiplexing cs553 st07 slide share ss
ch8_multiplexing cs553 st07 slide share ss
MinThetLwin1
 
History and Application of LLM Leveraging Big Data
History and Application of LLM Leveraging Big DataHistory and Application of LLM Leveraging Big Data
History and Application of LLM Leveraging Big Data
Jongwook Woo
 
Mumbai Girls Call Mumbai 🛵🚡9910780858 💃 Choose Best And Top Girl Service And ...
Mumbai Girls Call Mumbai 🛵🚡9910780858 💃 Choose Best And Top Girl Service And ...Mumbai Girls Call Mumbai 🛵🚡9910780858 💃 Choose Best And Top Girl Service And ...
Mumbai Girls Call Mumbai 🛵🚡9910780858 💃 Choose Best And Top Girl Service And ...
norina2645
 
OpenMetadata Spotlight - OpenMetadata @ Aspire by Vinol Joy Dsouza
OpenMetadata Spotlight - OpenMetadata @ Aspire by Vinol Joy DsouzaOpenMetadata Spotlight - OpenMetadata @ Aspire by Vinol Joy Dsouza
OpenMetadata Spotlight - OpenMetadata @ Aspire by Vinol Joy Dsouza
OpenMetadata
 
Coimbatore Girls call Service 000XX00000 Provide Best And Top Girl Service An...
Coimbatore Girls call Service 000XX00000 Provide Best And Top Girl Service An...Coimbatore Girls call Service 000XX00000 Provide Best And Top Girl Service An...
Coimbatore Girls call Service 000XX00000 Provide Best And Top Girl Service An...
vrvipin164
 
Female Girls Call Mumbai 9920725232 Unlimited Short Providing Girls Service A...
Female Girls Call Mumbai 9920725232 Unlimited Short Providing Girls Service A...Female Girls Call Mumbai 9920725232 Unlimited Short Providing Girls Service A...
Female Girls Call Mumbai 9920725232 Unlimited Short Providing Girls Service A...
45unexpected
 
CHAPTER-1-Introduction-to-Marketing.pptx
CHAPTER-1-Introduction-to-Marketing.pptxCHAPTER-1-Introduction-to-Marketing.pptx
CHAPTER-1-Introduction-to-Marketing.pptx
girewiy968
 
the unexpected potential of Dijkstra's Algorithm
the unexpected potential of Dijkstra's Algorithmthe unexpected potential of Dijkstra's Algorithm
the unexpected potential of Dijkstra's Algorithm
huseindihon
 
Celebrity Girls Call Delhi 🎈🔥9711199171 🔥💋🎈 Provide Best And Top Girl Service...
Celebrity Girls Call Delhi 🎈🔥9711199171 🔥💋🎈 Provide Best And Top Girl Service...Celebrity Girls Call Delhi 🎈🔥9711199171 🔥💋🎈 Provide Best And Top Girl Service...
Celebrity Girls Call Delhi 🎈🔥9711199171 🔥💋🎈 Provide Best And Top Girl Service...
tanupasswan6
 
Female Service Girls Call Navi Mumbai 9930245274 Provide Best And Top Girl Se...
Female Service Girls Call Navi Mumbai 9930245274 Provide Best And Top Girl Se...Female Service Girls Call Navi Mumbai 9930245274 Provide Best And Top Girl Se...
Female Service Girls Call Navi Mumbai 9930245274 Provide Best And Top Girl Se...
dizzycaye
 
Supervised Learning (Data Science).pptx
Supervised Learning  (Data Science).pptxSupervised Learning  (Data Science).pptx
Supervised Learning (Data Science).pptx
TARIKU ENDALE
 
Nipissing University degree offer Nipissing diploma Transcript
Nipissing University degree offer Nipissing diploma TranscriptNipissing University degree offer Nipissing diploma Transcript
Nipissing University degree offer Nipissing diploma Transcript
zyqedad
 
BDSM Girls Call Delhi 🎈🔥9711199171 🔥💋🎈 Provide Best And Top Girl Service And ...
BDSM Girls Call Delhi 🎈🔥9711199171 🔥💋🎈 Provide Best And Top Girl Service And ...BDSM Girls Call Delhi 🎈🔥9711199171 🔥💋🎈 Provide Best And Top Girl Service And ...
BDSM Girls Call Delhi 🎈🔥9711199171 🔥💋🎈 Provide Best And Top Girl Service And ...
fatima shekh$A17
 

Recently uploaded (20)

社内勉強会資料_TransNeXt: Robust Foveal Visual Perception for Vision Transformers
社内勉強会資料_TransNeXt: Robust Foveal Visual Perception for Vision Transformers社内勉強会資料_TransNeXt: Robust Foveal Visual Perception for Vision Transformers
社内勉強会資料_TransNeXt: Robust Foveal Visual Perception for Vision Transformers
 
Welcome back to Instagram. Sign in to check out what your
Welcome back to Instagram. Sign in to check out what yourWelcome back to Instagram. Sign in to check out what your
Welcome back to Instagram. Sign in to check out what your
 
Verified Girls Call Andheri 9930245274 Unlimited Short Providing Girls Servic...
Verified Girls Call Andheri 9930245274 Unlimited Short Providing Girls Servic...Verified Girls Call Andheri 9930245274 Unlimited Short Providing Girls Servic...
Verified Girls Call Andheri 9930245274 Unlimited Short Providing Girls Servic...
 
Beautiful Girls Call Pune 000XX00000 Provide Best And Top Girl Service And No...
Beautiful Girls Call Pune 000XX00000 Provide Best And Top Girl Service And No...Beautiful Girls Call Pune 000XX00000 Provide Best And Top Girl Service And No...
Beautiful Girls Call Pune 000XX00000 Provide Best And Top Girl Service And No...
 
Celebrity Girls Call Noida 9873940964 Unlimited Short Providing Girls Service...
Celebrity Girls Call Noida 9873940964 Unlimited Short Providing Girls Service...Celebrity Girls Call Noida 9873940964 Unlimited Short Providing Girls Service...
Celebrity Girls Call Noida 9873940964 Unlimited Short Providing Girls Service...
 
Premium Girls Call Navi Mumbai 🎈🔥9920725232 🔥💋🎈 Provide Best And Top Girl Ser...
Premium Girls Call Navi Mumbai 🎈🔥9920725232 🔥💋🎈 Provide Best And Top Girl Ser...Premium Girls Call Navi Mumbai 🎈🔥9920725232 🔥💋🎈 Provide Best And Top Girl Ser...
Premium Girls Call Navi Mumbai 🎈🔥9920725232 🔥💋🎈 Provide Best And Top Girl Ser...
 
DU degree offer diploma Transcript
DU degree offer diploma TranscriptDU degree offer diploma Transcript
DU degree offer diploma Transcript
 
ch8_multiplexing cs553 st07 slide share ss
ch8_multiplexing cs553 st07 slide share ssch8_multiplexing cs553 st07 slide share ss
ch8_multiplexing cs553 st07 slide share ss
 
History and Application of LLM Leveraging Big Data
History and Application of LLM Leveraging Big DataHistory and Application of LLM Leveraging Big Data
History and Application of LLM Leveraging Big Data
 
Mumbai Girls Call Mumbai 🛵🚡9910780858 💃 Choose Best And Top Girl Service And ...
Mumbai Girls Call Mumbai 🛵🚡9910780858 💃 Choose Best And Top Girl Service And ...Mumbai Girls Call Mumbai 🛵🚡9910780858 💃 Choose Best And Top Girl Service And ...
Mumbai Girls Call Mumbai 🛵🚡9910780858 💃 Choose Best And Top Girl Service And ...
 
OpenMetadata Spotlight - OpenMetadata @ Aspire by Vinol Joy Dsouza
OpenMetadata Spotlight - OpenMetadata @ Aspire by Vinol Joy DsouzaOpenMetadata Spotlight - OpenMetadata @ Aspire by Vinol Joy Dsouza
OpenMetadata Spotlight - OpenMetadata @ Aspire by Vinol Joy Dsouza
 
Coimbatore Girls call Service 000XX00000 Provide Best And Top Girl Service An...
Coimbatore Girls call Service 000XX00000 Provide Best And Top Girl Service An...Coimbatore Girls call Service 000XX00000 Provide Best And Top Girl Service An...
Coimbatore Girls call Service 000XX00000 Provide Best And Top Girl Service An...
 
Female Girls Call Mumbai 9920725232 Unlimited Short Providing Girls Service A...
Female Girls Call Mumbai 9920725232 Unlimited Short Providing Girls Service A...Female Girls Call Mumbai 9920725232 Unlimited Short Providing Girls Service A...
Female Girls Call Mumbai 9920725232 Unlimited Short Providing Girls Service A...
 
CHAPTER-1-Introduction-to-Marketing.pptx
CHAPTER-1-Introduction-to-Marketing.pptxCHAPTER-1-Introduction-to-Marketing.pptx
CHAPTER-1-Introduction-to-Marketing.pptx
 
the unexpected potential of Dijkstra's Algorithm
the unexpected potential of Dijkstra's Algorithmthe unexpected potential of Dijkstra's Algorithm
the unexpected potential of Dijkstra's Algorithm
 
Celebrity Girls Call Delhi 🎈🔥9711199171 🔥💋🎈 Provide Best And Top Girl Service...
Celebrity Girls Call Delhi 🎈🔥9711199171 🔥💋🎈 Provide Best And Top Girl Service...Celebrity Girls Call Delhi 🎈🔥9711199171 🔥💋🎈 Provide Best And Top Girl Service...
Celebrity Girls Call Delhi 🎈🔥9711199171 🔥💋🎈 Provide Best And Top Girl Service...
 
Female Service Girls Call Navi Mumbai 9930245274 Provide Best And Top Girl Se...
Female Service Girls Call Navi Mumbai 9930245274 Provide Best And Top Girl Se...Female Service Girls Call Navi Mumbai 9930245274 Provide Best And Top Girl Se...
Female Service Girls Call Navi Mumbai 9930245274 Provide Best And Top Girl Se...
 
Supervised Learning (Data Science).pptx
Supervised Learning  (Data Science).pptxSupervised Learning  (Data Science).pptx
Supervised Learning (Data Science).pptx
 
Nipissing University degree offer Nipissing diploma Transcript
Nipissing University degree offer Nipissing diploma TranscriptNipissing University degree offer Nipissing diploma Transcript
Nipissing University degree offer Nipissing diploma Transcript
 
BDSM Girls Call Delhi 🎈🔥9711199171 🔥💋🎈 Provide Best And Top Girl Service And ...
BDSM Girls Call Delhi 🎈🔥9711199171 🔥💋🎈 Provide Best And Top Girl Service And ...BDSM Girls Call Delhi 🎈🔥9711199171 🔥💋🎈 Provide Best And Top Girl Service And ...
BDSM Girls Call Delhi 🎈🔥9711199171 🔥💋🎈 Provide Best And Top Girl Service And ...
 

Smart Data - How you and I will exploit Big Data for personalized digital health and many other activities

  • 1. Put Knoesis Banner Smart Data - How you and I will exploit Big Data for personalized digital health and many other activities Keynote at IEEE BigData 2014, Oct 28, 2014 Amit Sheth LexisNexis Ohio Eminent Scholar & Exec. Director, The Ohio Center of Excellence in Knowledge-enabled Computing (Kno.e.sis) Wright State, USA
  • 2. 2 Thanks: My team (missing Pramod, Hemant, ...) Collaborators: Clinicians: Dr. William Abrahams (OSU-Wexner), Dr. Shalini Forbis (Dayton Childrens), Dr. Sangeeta Agrawal (VA), Valerie Shalin (WSU Cognitive Scientists ), Payam Barnaghi (U-Surrey), Ramesh Jain(UCI), … Funding: NSF (esp. IIS-1111183 “SoCS: Social Media Enhanced Organizational Sensemaking in Emergency Response,”), AFRL, NIH, Industry….
  • 3. 3 Big Data 2014 http://hrboss.com/hiringboss/articles/big-data-infographic
  • 4. Only 0.5% to 1% of the data is used for analysis. http://www.csc.com/insights/flxwd/78931-big_data_growth_just_beginning_to_explode 4 http://www.guardian.co.uk/news/datablog/2012/dec/19/big-data-study-digital-universe-global-volume
  • 5. Variety – not just structure but modality: multimodal, multisensory Semi structured 5
  • 6. Velocity Fast Data Rapid Changes Real-Time/Stream Analysis Current application examples: financial services, stock brokerage, weather tracking, movies/entertainment and online retail 6
  • 7. 7 Ever Increasing Connected Devices and People About 2 billion of the 5+ billion have data connections – so they perform “citizen sensing”. And there are more devices connected to the Internet than the entire human population. These ~2 billion citizen sensors and 10 billion devices & objects connected to the Internet makes this an era of IoT (Internet of Things) and Internet of Everything (IoE). http://www.cisco.com/web/about/ac79/docs/innov/IoT_IBSG_0411FINAL.pdf
  • 8. 8 Internet of Things / Everything : Future Trends “The next wave of dramatic Internet growth will come through the confluence of people, process, data, and things — the Internet of Everything (IoE).” - CISCO IBSG, 2013 Beyond the IoE based infrastructure, it is the possibility of developing applications that spans Physical, Cyber and the Social Worlds that is very exciting. http://www.cisco.com/web/about/ac79/docs/innov/IoE_Economy.pdf
  • 9. 10 What has not changed? We are still working on the simpler representations of the real-world! http://artint.info/html/ArtInt_8.html http://en.wikipedia.org/wiki/Traffic_congestion solve represent interpret real-world simplified representation compute
  • 10. 11 What should change? solve represent interpret real-world richer representation compute We need computational paradigms to tap into the rich pulse of the human populace, and utilize diverse data Represent, capture, and compute with richer and fine-grained representations of real-world problems + Richer representation of traffic observations Effective solutions People interpreting a real-world event
  • 11. Physical-Cyber-Social Computing for Actionable Insights from Multimodal Data High CO influences Wheezing Level (Low/High) High CO Reduced CO level => better Asthma control High Wheeze Vertical Operators (Semantic abstraction) operates on Artifacts at each level and transcends them to the next level. Horizontal Operators (Semantic Integration) operates on data from heterogeneous sources to create Integrated/correlated data streams. High Luminosity Carbon Monoxide “a holistic treatment of data, information, and knowledge integrate, correlate, interpret, Low Luminosity Wheeze Luminosity Low Wheeze from the PCS worlds to and provide contextually 1Amit Sheth, Pramod Anantharam, Cory Henson, 'Physical-Cyber-Social Computing: An Early 21st Century Approach,' IEEE Intelligent Systems, vol. 28, no. 1, pp. 78-82, Jan.-Feb., 2013. http://doi.ieeecomputersociety.org/10.1109/MIS.2013.20 relevant abstractions to humans. ”1 12
  • 12. • Healthcare: ADFH, Asthma, GI, Demintia – Using kHealth system • Traffic Analytics: – Understanding traffic flow • Social Media Analysis : – Crisis coordination using Twitris 13 I will use applications in 3 domains to demonstrate
  • 13. 14 MIT Technology Review, 2012 The Patient of the Future http://www.technologyreview.com/featuredstory/426968/the-patient-of-the-future/
  • 14. Asthma: A Multi-faceted and Symptomatically Variable Health Challenge 15 Personal level Signals Public level Signals Population level Signals “ … survey indicates that adult patients and caregivers of pediatric patients report variability in asthma symptoms over time, even when asthma medications are taken.”1 1Marcus, Philip, Kevin R. Murphy, Abid Rahman, and Christopher D. O’Brien. "Intrapatient symptom variability in adults and children with asthma: Results of a survey." Advances in therapy 22, no. 5 (2005): 488-497.
  • 15. Far better an approximate answer to the right question, which is often vague, than the exact answer to the wrong question, which can always be made precise. -- John Tukey, Ann. Math. Stat. 33 (1962) 16 Asthma: Actionable Information How is my Asthma control? Should I take additional medication today? How can I reduce my asthma attacks at home?
  • 16. 17 Asthma: Challenges in Heterogeneity, Variability, and Personalization Contextual Personalized Actionable Personal level Signals Public level Signals Population level Signals Domain Knowledge http://www.tuberktoraks.org/managete/fu_folder/2011-03/html/2011-3-291-311.html OR
  • 17. 18 My 2004-2005 formulation of SMART DATA - Semagix Formulation of Smart Data strategy providing services for Search, Explore, Notify. “Use of Ontologies and Data repositories to gain relevant insights”
  • 18. Smart Data (2014 retake) Smart data makes sense out of Big data It provides value from harnessing the challenges posed by volume, velocity, variety and veracity of big data, in-turn providing actionable information and improve decision making. 19
  • 19. Another perspective on Smart Data OF human, BY human FOR human Smart data is about extracting value by improving human involvement in data creation, processing and consumption. It is about (improving) computing for human experience. 20
  • 20. ‘OF human’ : Relevant Real-time Data Streams for Human Experience Petabytes of Physical(sensory)-Cyber-Social Data everyday! More on PCS Computing: http://wiki.knoesis.org/index.php/PCS 21
  • 21. Use of Prior Human-created Knowledge Models 22 ‘BY human’: Involving Crowd Intelligence in data processing Crowdsourcing and Domain-expert guided Machine Learning Modeling
  • 22. Weather Application Asthma Healthcare Application Personal Public Health Detection of events, such as wheezing sound, indoor temperature, humidity, dust, and CO level High CO content at home during day 23 ‘FOR human’ : Improving Human Experience (Smart Health) Population Level Action in the Physical World Luminosity CO level CO in gush during day time
  • 23. ‘FOR human’ : Improving Human Experience (Smart Energy) Weather Application Power Monitoring Application Personal Level Observations Electricity usage over a day, device at work, power consumption, cost/kWh, heat index, relative humidity, and public events from social stream 24 Population Level Observations Action in the Physical World Washing and drying has resulted in significant cost since it was done during peak load period. Consider changing this time to night.
  • 24. 25 Big Data is pervasive - It is Smart Data that matter!
  • 25. DATA Observations from machine and social sensors KNOWLEDGE for interpretation of observations ACTIONS situation awareness useful for decision making 26 Primary challenge is to bridge the gap between data and actions Contextualization Personalization
  • 26. “the top part of the brain is involved in setting up plans, controlling movements, registering changes in where objects are located in space, and revising plans when anticipated events do not occur.” 27 In the process, engaging both top and bottom brain “bottom is involved in classifying and interpreting what we perceive, and allows us to confer meaning on the world.” “The Theory of Cognitive Modes* emphasizes the constant and close interaction of the top and bottom systems. They don’t work in isolation — or in competition — but seamlessly together.” *http://brainblogger.com/2013/12/19/top-brain-bottom-brain-part-3-the-theory-of-cognitive-modes/ by G. Wayne Miller and Stephen M. Kosslyn, PhD | December 19, 2013
  • 27. 28 Can we take inspiration from the ‘Theory of Cognitive Modes’ to develop a computational model? T & B B T Mover Perceiver Simulator Adaptor http://online.stanford.edu/pgm-fa12 T- Top brain, B- Bottom brain our baby step toward a computational model for perception (Machine Perception)
  • 28. 29 Toward a symbiotic partnership between machines and people J. McCarthy M. Weiser D. Engelbart J. C. R. Licklider htttp://j.mp/k-che http://knoesis.org/index.php/Computing_For_Human_Experience
  • 29. 30 How are machines supposed to integrate and interpret sensor data? RDF OWL Semantic Sensor Networks (SSN)
  • 30. 31 W3C Semantic Sensor Network Ontology Lefort, L., Henson, C., Taylor, K., Barnaghi, P., Compton, M., Corcho, O., Garcia-Castro, R., Graybeal, J., Herzog, A., Janowicz, K., Neuhaus, H., Nikolov, A., and Page, K.: Semantic Sensor Network XG Final Report, W3C Incubator Group Report (2011).
  • 31. 32 W3C Semantic Sensor Network Ontology Lefort, L., Henson, C., Taylor, K., Barnaghi, P., Compton, M., Corcho, O., Garcia-Castro, R., Graybeal, J., Herzog, A., Janowicz, K., Neuhaus, H., Nikolov, A., and Page, K.: Semantic Sensor Network XG Final Report, W3C Incubator Group Report (2011).
  • 32. SSN Ontology 3 Interpreted data (abductive) [in OWL] e.g., diagnosis 2 Interpreted data (deductive) [in OWL] e.g., threshold 1 Annotated Data [in RDF] e.g., label 0 Raw Data [in TEXT] e.g., number Intellego Hyperthyroidism … … Elevated Blood Pressure Systolic blood pressure of 150 mmHg “150” 33 Levels of Abstraction
  • 33. 34 What if we could automate this interpretation of Data? … and do it efficiently and at scale
  • 34. 35 Making sense of sensor data with Henson et al An Ontological Approach to Focusing Attention and Enhancing Machine Perception on the Web, Applied Ont, 2011
  • 35. 36 People are good at making sense of sensory input What can we learn from cognitive models of perception? The key ingredient is prior knowledge
  • 36. Observe Property * based on Neisser’s cognitive model of perception Perceive Feature Explanation Discrimination 1 2 Translating low-level signals into high-level knowledge Focusing attention on those aspects of the environment that provide useful information Prior Knowledge 37 Convert large number of observations to semantic abstractions that provide insights and translate into decisions Perception Cycle*
  • 37. 38 To enable machine perception, Semantic Web technology is used to integrate sensor data with prior knowledge on the Web W3C SSN XG 2010-2011, SSN Ontology
  • 38. W3C Semantic Sensor Network (SSN) Ontology Bi-partite Graph 39 Prior knowledge on the Web
  • 39. W3C Semantic Sensor Network (SSN) Ontology Bi-partite Graph 40 Prior knowledge on the Web
  • 40. Observe Property Perceive Feature Explanation 1 Explanation Translating low-level signals into high-level knowledge 41 Explanation is the act of choosing the objects or events that best account for a set of observations; often referred to as hypothesis building
  • 41. Inference to the best explanation • In general, explanation is an abductive problem; and hard to compute Finding the sweet spot between abduction and OWL • Single-feature assumption* enables use of OWL-DL deductive reasoner * An explanation must be a single feature which accounts for all observed properties 42 Explanation is the act of choosing the objects or events that best account for a set of observations; often referred to as hypothesis building Representation of Parsimonious Covering Theory in OWL-DL Explanation
  • 42. Explanation ExplanatoryFeature ≡ ∃ssn:isPropertyOf—.{p1} ⊓ … ⊓ ∃ssn:isPropertyOf—.{pn} Observed Property Explanatory Feature elevated blood pressure clammy skin palpitations Hypertension Hyperthyroidism Pulmonary Edema 43 Explanatory Feature: a feature that explains the set of observed properties
  • 43. Discrimination Observe Property Perceive Feature Explanation Discrimination 2 Focusing attention on those aspects of the environment that provide useful information 44 Discrimination is the act of finding those properties that, if observed, would help distinguish between multiple explanatory features
  • 44. Discrimination ExpectedProperty ≡ ∃ssn:isPropertyOf.{f1} ⊓ … ⊓ ∃ssn:isPropertyOf.{fn} Expected Property Explanatory Feature elevated blood pressure clammy skin palpitations Hypertension Hyperthyroidism Pulmonary Edema 45 Expected Property: would be explained by every explanatory feature
  • 45. Discrimination NotApplicableProperty ≡ ¬∃ssn:isPropertyOf.{f1} ⊓ … ⊓ ¬∃ssn:isPropertyOf.{fn} Not Applicable Property Explanatory Feature elevated blood pressure clammy skin palpitations Hypertension Hyperthyroidism Pulmonary Edema 46 Not Applicable Property: would not be explained by any explanatory feature
  • 46. Discrimination DiscriminatingProperty ≡ ¬ExpectedProperty ⊓ ¬NotApplicableProperty Discriminating Property Explanatory Feature elevated blood pressure clammy skin palpitations Hypertension Hyperthyroidism Pulmonary Edema 47 Discriminating Property: is neither expected nor not-applicable
  • 47. Semantic scalability: Resource savings of abstracting sensor data 48 Orders of magnitude resource savings for generating and storing relevant abstractions vs. raw observations. Relevant abstractions Raw observations
  • 48. Qualities -High BP -Increased Weight Entities -Hypertension -Hypothyroidism kHealth Machine Sensors Personal Input EMR/PHR Comorbidity risk score e.g., Charlson Index Longitudinal studies of cardiovascular risks - Find risk factors - Validation - domain knowledge - domain expert Find contribution of each risk factor Risk Assessment Model Current Observations -Physical -Physiological -History Risk Score (e.g., 1 => continue 3 => contact clinic) Validate correlations Model Creation Historical observations e.g., EMR, sensor observations 49 Risk Score: from Data to Abstraction and Actionable Information
  • 49. Use of OWL reasoner is resource intensive (especially on resource-constrained devices), in terms of both memory and time • Runs out of resources with prior knowledge >> 15 nodes • Asymptotic complexity: O(n3) 50 How do we implement machine perception efficiently on a resource-constrained device?
  • 50. Approach 1: Send all sensor observations to the cloud for processing intelligence at the edge 51 Approach 2: downscale semantic processing so that each device is capable of machine perception
  • 51. Efficient execution of machine perception 010110001101 0011110010101 1000110110110 101100011010 0111100101011 000110101100 0110100111 52 Use bit vector encodings and their operations to encode prior knowledge and execute semantic reasoning Henson et al. 'An Efficient Bit Vector Approach to Semantics-based Machine Perception in Resource-Constrained Devices, ISWC 2012.
  • 52. Efficiency Improvement • Problem size increased from 10’s to 1000’s of nodes • Time reduced from minutes to milliseconds • Complexity growth reduced from polynomial to linear O(n3) < x < O(n4) O(n) 53 Evaluation on a mobile device
  • 53. 1 Translate low-level data to high-level knowledge Machine perception can be used to convert low-level sensory signals into high-level knowledge useful for decision making 2 Prior knowledge is the key to perception Using SW technologies, machine perception can be formalized and integrated with prior knowledge on the Web 3 Intelligence at the edge By downscaling semantic inference, machine perception can execute efficiently on resource-constrained devices 54 Semantic Perception for smarter analytics: 3 ideas to takeaway
  • 54. kHealth Knowledge-enabled Healthcare Applied to ADHF, Asthma, GI, and Dementia 55
  • 56. Empowering Individuals (who are not Larry Smarr!) for their own health Through physical monitoring and analysis, our cellphones could act as an early warning system to detect serious health conditions, and provide actionable information canary in a coal mine kHealth: knowledge-enabled healthcare 57
  • 57. 1http://www.nhlbi.nih.gov/health/health-topics/topics/asthma/ 2http://www.lung.org/lung-disease/asthma/resources/facts-and-figures/asthma-in-adults.html 3Akinbami et al. (2009). Status of childhood asthma in the United States, 1980–2007. Pediatrics,123(Supplement 3), S131-S145. 60 25 million 300 million $50 billion 155,000 593,000 People in the U.S. are diagnosed with asthma (7 million are children)1. People suffering from asthma worldwide2. Spent on asthma alone in a year2 Hospital admissions in 20063 Emergency department visits in 20063 Asthma: Severity of the problem
  • 58. WHY Big Data to Smart Data: Asthma example what can we do to avoid asthma episode? Understanding relationships between health signals and asthma attacks for providing actionable information 61 Value What risk factors influence asthma control? What is the contribution of each risk factor? semantics Velocity Veracity Variety Volume Real-time health signals from personal level (e.g., Wheezometer, NO in breath, accelerometer, microphone), public health (e.g., CDC, Hospital EMR), and population level (e.g., pollen level, CO2) arriving continuously in fine grained samples potentially with missing information and uneven sampling frequencies.
  • 59. kHealth: Health Signal Processing Architecture Personal level Signals Public level Signals Population level Signals Domain Knowledge Risk Model Events from Social Streams Take Medication before going to work Contact doctor Avoid going out in the evening due to high pollen levels Analysis Personalized Actionable Information Data Acquisition & aggregation 62
  • 60. 63 Asthma Domain Knowledge Asthma Control and Actionable Information Domain Knowledge Asthma Control à Daily Medication Choices for starting therapy Not Well Controlled Poor Controlled Severity Level of Asthma (Recommended Action) (Recommended Action) (Recommended Action) Intermittent Asthma SABA prn - - Mild Persistent Asthma Low dose ICS Medium ICS Medium ICS Moderate Persistent Asthma Medium dose ICS alone Or with LABA/montelukast Medium ICS + LABA/Montelukast Or High dose ICS Medium ICS + LABA/Montelukast Or High dose ICS* Severe Persistent Asthma High dose ICS with LABA/montelukast Needs specialist care Needs specialist care ICS= inhaled corticosteroid, LABA = inhaled long-acting beta2-agonist, SABA= inhaled short-acting beta2-agonist ; *consider referral to specialist
  • 61. 64 Patient Health Score (diagnostic) How controlled is my asthma? Risk assessment model Semantic Perception Personal level Signals Public level Signals Domain Knowledge Population level Signals GREEN -- Well Controlled YELLOW – Not well controlled Red -- poor controlled
  • 62. Background Knowledge 65 Patient Health Score (diagnostic): Details Physical-Cyber-Social System Observations Health Signal Extraction Health Signal Understanding Personal Population Level Acceleration readings from on-phone sensors Wheeze – Yes Do you have tightness of chest? –Yes Risk Category assigned by doctors <Wheezing=Yes, time, location> <ChectTightness=Yes, time, location> <PollenLevel=Medium, time, location> <Pollution=Yes, time, location> <Activity=High, time, location> PollenLevel Wheezing ChectTightness Pollution Activity PollenLevel Wheezing ChectTightness Pollution Activity RiskCategory <PollenLevel, ChectTightness, Pollution, Activity, Wheezing, RiskCategory> <2, 1, 1,3, 1, RiskCategory> <2, 1, 1,3, 1, RiskCategory> <2, 1, 1,3, 1, RiskCategory> <2, 1, 1,3, 1, RiskCategory> . . . Expert Knowledge Sensor and personal observations tweet reporting pollution level and asthma attacks Signals from personal, personal spaces, and community spaces Qualify Quantify Enrich Outdoor pollen and pollution Public Health Well Controlled - continue Not Well Controlled – contact nurse Poor Controlled – contact doctor
  • 63. 66 Patient Vulnerability Score (prognostic) How vulnerable* is my control level today? Risk assessment model Semantic Perception Personal level Signals Public level Signals Domain Knowledge Population level Signals Patient health Score *considering changing environmental conditions and current control level
  • 64. 67 Patient Vulnerability Score (prognostic): Details Sensordrone – for monitoring environmental air quality Wheezometer – for monitoring wheezing sounds Can I reduce my asthma attacks at night? What are the triggers? What is the wheezing level? What is the exposure level over a day? What is the propensity toward asthma? Commute to Work Luminosity CO level CO in gush during day time Actionable Information Personal level Signals Public level Signals Population level Signals What is the air quality indoors?
  • 65. Sensordrone (Carbon monoxide, temperature, humidity) Node Sensor (exhaled Nitric Oxide) 68 Sensors Android Device (w/ kHealth App) Total cost: ~ $500 kHealth Kit for the application for Asthma management Along with two sensors in the kit, the application uses a variety of population level signals from the web: Pollen level Air Quality Temperature & Humidity
  • 66. 69 Usability and decision support trial Dr. Shalini G. Forbis, MD, MPH
  • 67. Preliminary insights from patient data S1 S2 Sensor data QA data Number of Observations 36 108 40 121
  • 68. Medication (Albuterol) related to decreasing Exhaled Nitric Oxide 1 0.9 0.8 0.7 0.6 0.5 0.4 0.3 0.2 0.1 0 Did patient take albuterol last night due to cough or wheeze? 0.25 0.2 0.15 0.1 0.05 0 Exhaled Nitric Oxide
  • 69. Activity limitation related to high exhaled Nitric Oxide 1 0.9 0.8 0.7 0.6 0.5 0.4 0.3 0.2 0.1 0 How much did asthma or asthma symptoms limit patient's activity today? 0.25 0.2 0.15 0.1 0.05 0 Exhaled Nitric Oxide
  • 70. Low exhaled Nitric Oxide observed with absence of coughing 1 0.9 0.8 0.7 0.6 0.5 0.4 0.3 0.2 0.1 0 Has patient had wheeze, chest tightness, or asthma related 6/2/2014 6/3/2014 6/4/2014 6/5/2014 6/6/2014 6/7/2014 6/8/2014 6/9/2014 6/10/2014 6/11/2014 6/12/2014 cough today? 0.25 0.2 0.15 0.1 0.05 0 Nitric Oxide
  • 71. Activity limitation observed with high pollen activity 2.5 2 1.5 1 0.5 0 Pollen 1 0.9 0.8 0.7 0.6 0.5 0.4 0.3 0.2 0.1 0 How much did asthma or asthma symptoms limit patient's activity today?
  • 72. 75 Two research directions for kHealth asthma with more data… Root cause analysis Action Recommendation Find Triggers of Asthma Derive the cause of asthma attacks for a given patient using statistical techniques + knowledge of asthma and its triggers Minimize Asthma Attacks Model actions based on the utility theory (cost of actions & its rewards) + knowledge of action consequences
  • 73. • Healthcare: ADFH, Asthma, GI – Using kHealth system • Traffic Analytics: – Understanding traffic flow • Social Media Analysis : – Crisis coordination using Twitris 76 I will use applications in 3 domains to demonstrate
  • 74. 78 Understanding traffic flow variations
  • 75. Big Data to Smart Data: Traffic Management example Vehicular traffic data from San Francisco Bay Area aggregated from on-road sensors (numerical) and incident reports (textual) Value Can we detect the onset of traffic congestion? Can we characterize traffic congestion based on events? Can we provide actionable information to decision makers? semantics Velocity Veracity Variety Volume Representing prior knowledge of traffic lead to a focused exploration of this massive dataset Every minute update of speed, volume, travel time, and occupancy resulting in 178 million link status observations, 738 active events, and 146 scheduled events with many unevenly sampled observations collected over 3 months. 79 http://511.org/
  • 76. Semantic Annotation using Background Knowledge slow-moving-traffic Domain knowledge in the form of traffic vocabulary Image Credit: http://traffic.511.org/index Domain knowledge of traffic flow synthesized from sensor data 80 Explained-by Horizontal operator: relating/mapping data from different modality to a concept (theme) within a spatio-temporal context; Spatial context even include what it means to have a slow traffic for the type of road
  • 77. • Healthcare: ADFH, Asthma, GI – Using kHealth system • Traffic Analytics: – Understanding traffic flow • Social Media Analysis : – Crisis coordination using Twitris 81 I will use applications in 2 domains to demonstrate
  • 78. [BIG] Ad-hoc Community with Varying but [FEW] Important Intents Image: http://www.gizmodo.com.au/2012/04/how-we-identify-single-voices- 82 in-a-crowd/ Me and @CeceVancePR are coordinating a clothing/food drive for families affected by Hurricane Sandy. If you would like to donate, DM us Does anyone know how to donate clothes to hurricane #Sandy victims? BIG QUESTION: Can these needles be identified in the haystack of massive datasets? [REQUEST/DEMAND] [OFFER/SUPPLY] Coordination teams want to hear!
  • 79. Uncoordinated Engagement • May lead to second disaster to be managed: – Under-supply of required demands – Over-supply of not required resources • Hurricane Sandy example, “Thanks, but no thanks”, NPR, Jan 12 2013 Story link:http://www.npr.org/2013/01/09/168946170/tha nks-but-no-thanks-when-post-disaster-donations-overwhelm
  • 80. 84 How to volunteer, donate to Hurricane Sandy: <URL> If you have clothes to donate to those who are victims of Hurricane Sandy … Red Cross is urging blood donations to support those affected <URL> I have TONS of cute shoes & purses I want to donate to hurricane victims … Does anyone know how to donate clothes to hurricane #Sandy victims? Does anyone know of community service organizations to volunteer to help out? Needs to get something, suggests scarcity: REQUEST (demand) Offers or wants to give, suggests abundance: OFFER (supply) Matching requests with offers
  • 81. Want to help animals in #Oklahoma? @ASPCA tells how you can help: http://t.co/mt8l9PwzmO x RESPONSE TEAMS (including humanitarian org. and ‘pseudo’ responders) VICTIM SITE Where do I go to help out for volunteer work DEMAND SUPPLY around Moore? Anyone know? CITIZEN SENSORS Anyone know where to donate to help the animals from the Oklahoma disaster? #oklaho ma #dogs Matchable Matchable If you would like to volunteer today, help is desperately needed in Shawnee. Call 273-5331 for more info 85 Match-making: Assisting Coordination Image: http://offthewallsocial.com/tag/social-media/
  • 82. Two excellent videos • Vinod Khosla: the Power of Storytelling and the Future of Healthcare • Larry Smarr: The Human Microbiome and the Revolution in Digital Health 86 Wrapping up: For more on importance of what we talked about
  • 83. • Big Data is every where – at individual and community levels - not just limited to corporation – with growing complexity: Physical-Cyber-Social • Analysis is not sufficient • Need interaction between bottom up techniques and top down processing 87 Wrapping up: Take Away
  • 84. Wrapping up: Take Away • Focus on Humans and Improve human life and experience with SMART Data. – Data to Information to Personally and Contextually Relevant Abstractions (Semantic Perception) – Actionable Information (Value from data) to assist and support human in decision making. • Focus on Value -- SMART Data – Big Data Challenges without the intention of deriving Value is a “Journey without GOAL”. 88
  • 85. Special thanks: Pramod. This presentation covers some of the work of my PhD students. Key contributors: Pramod Anantharam, Cory Henson and TK Prasad. Amit Sheth’s PHD students Ashutos h Jadhav* Hemant Purohit Vinh Nguyen Lu Chen Pavan Kapanipathi* Pramod Sujan Perera Anantharam* Maryam Panahiazar Sarasi Lalithsena Shreyansh Batt Kalpa Gunaratna Delroy Cameron Sanjaya Wijeratne Wenbo Wang 89 Special thanks
  • 86. • Among top universities in the world in World Wide Web (cf: 10-yr impact, Microsoft Academic Search: among top 10 in June2014) • Among the largest academic groups in the US in Semantic Web + Social/Sensor Webs, Mobile/Cloud/Cognitive Computing, Big Data, IoT, Health/Clinical & Biomedicine Applications • Exceptional student success: internships and jobs at top salary (IBM Watson/Research, MSR, Amazon, CISCO, Oracle, Yahoo!, Samsung, research universities, NLM, startups ) • 100 researchers including 15 World Class faculty (>3K citations/faculty avg) and ~45 PhD students- practically all funded • Extensive research for largely multidisciplinary projects; world class resources; industry sponsorships/collaborations (Google, IBM, …) 90
  • 87. 91 Top organization in WWW: 10-yr Field Rating (MAS)
  • 88. 92
  • 89. 93 Smart Data - How you and I will exploit Big Data thank you, and please visit us at http://knoesis.org

Editor's Notes

  1. Starting slide Various Big data problems – Traditional examples vs what we are doing examples. Variety and Velocity than Volume. kHealth problem. People will be interested in Smart Data. Traditional ML techniques, High Performance Computing, Statistics. Human level of Abstraction is Smart data.
  2. http://www.csc.com/insights/flxwd/78931-big_data_growth_just_beginning_to_explode http://www.guardian.co.uk/news/datablog/2012/dec/19/big-data-study-digital-universe-global-volume
  3. Types of Data Formats of Data Also talk about the increase in the platforms that helps generating these data
  4. Example high velocity Big Data applications at work: financial services, stock brokerage, weather tracking, movies/entertainment and online retail. Fast data (rate at which data is coming: esp from mobile, social and sensor sources), Rapid changes – in the data content, Stream analysis – to cope with the incoming data for real-time online analytics
  5. There are over 99.4% of physical devices that may one day be connected to The Internet still unconnected. - CISCO IBSG, 2013
  6. Human interpretation of the world along with personalization context …
  7. Raw data  annotated data  statistical analysis  background knowledge based interpretation for actionable information
  8. - Larry Smarr is a professor at the University of California, San Diego And he was diagnosed with Chrones Disease What’s interesting about this case is that Larry diagnosed himself He is a pioneer in the area of Quantified-Self, which uses sensors to monitor physiological symptoms Through this process he discovered inflammation, which led him to discovery of Chrones Disease This type of self-tracking is becoming more and more common sdd link to video
  9. Characteristics of asthma – why is it a complex condition?
  10. Asthma requires that we provide contextual, personalized, and actionable information to the patient by analyzing observations from Personal, Public, and Population level modalities
  11. - HUMAN CENTRIC!!
  12. All the data related to human activity, existence and experiences More on PCS Computing: http://wiki.knoesis.org/index.php/PCS
  13. Information is CREATED by human with the Machinery available – Wikipedia tool, sensors and social networks Information is STORED in Man+Machine readable format, LOD Information is PROCESSED using the LOD and Human assisted Knowledge-based Higher level abstraction on info is now consumed in many mechanistic ways (including GIS) to provide EXPERIENCE for humans Example of a human guided modeling and improved performance http://research.microsoft.com/en-us/um/people/akapoor/papers/IJCAI%202011a.pdf
  14. Actionable information example: In Asthma use case we have a sensor – sensordrone which records luminosity and CO levels A high correlation between CO level and luminosity is found This is an actionable information to the user interpreting it as CO in gush during day time => Mitigating action can be “closing the window” during day
  15. Also, we have weather application which performs abstraction on weather sensory observations to identify blizzard conditions (food for actions!!) : -- 20,000 weather stations (with ~5 sensors per station) -- Real-Time Feature Streams - live demo: http://knoesis1.wright.edu/EventStreams/ - video demo: https://skydrive.live.com/?cid=77950e284187e848&sc=photos&id=77950E284187E848%21276
  16. Lets find it..
  17. Add personalization and contextual
  18. - what if we could automate this sense making ability? - and what if we could do this at scale?
  19. sense making based on human cognitive models
  20. perception cycle contains two primary phases explanation translating low-level signals into high-level abstractions inference to the best explanation discrimination focusing attention on those properties that will help distinguish between multiple possible explanations used to intelligently task sensors and collect additional observations (rather than brute force approach of blindly collecting all observations)
  21. perception cycle contains two primary phases explanation translating low-level signals into high-level abstractions inference to the best explanation discrimination focusing attention on those properties that will help distinguish between multiple possible explanations used to intelligently task sensors and collect additional observations (rather than brute force approach of blindly collecting all observations)
  22. A single-feature (disease) assumption means that all the observed properties (symptoms) must be explained by a single feature. i.e., this framework is not expressive enough to model comorbidity where there may be more than one feature (disease) co-existing For example, if there are two diseases causing disjoint symptoms, and all the symptoms of both the diseases are observed, then this framework will not be able to find the coverage and returns no diseases.
  23. perception cycle contains two primary phases explanation translating low-level signals into high-level abstractions inference to the best explanation discrimination focusing attention on those properties that will help distinguish between multiple possible explanations used to intelligently task sensors and collect additional observations (rather than brute force approach of blindly collecting all observations)
  24. Intelligence distributed at the edge of the network Requires resource-constrained devices (mobile phones, gateway notes, etc.) to be able to utilize SW technologies
  25. Intelligence distributed at the edge of the network Requires resource-constrained devices (mobile phones, gateway notes, etc.) to be able to utilize SW technologies Henson et al. 'An Efficient Bit Vector Approach to Semantics-based Machine Perception in Resource-Constrained Devices, ISWC 2012.
  26. compute machine perception inferences -- i.e., explanation and discrimination -- of high-complexity on a resource-constrained devices in miliseconds Difference between the other systems and what this system provides
  27. Intelligence at the age. Shipping computation and domain models to the edge (Distributed)
  28. ADHF – Acute Decompensated Heart Failure
  29. - With this ability, many problems could be solved - For example: we could help solve health problems (before they become serious health problems) through monitoring symptoms and real-time sense making, acting as an early warning system to detect problematic health conditions
  30. ADHF – Acute Decompensated Heart Failure
  31. Research on Asthma has three phases Data collection: what signals to collect? Analysis: what analysis to be done? Actionable information: what action to recommend? In the next slide, we take a peek into the analysis that we do for Asthma
  32. What is the current state of a person/patient? => Summarizing all the observations (sensor and personal) into a single score indicating health of a person Instead of presenting all the raw data (often to much e.g., Asthma application we have developed collects CO, temperature, and humidity every 10 seconds resulting in 8,640 observations/day) which may not be comprehensible to the patient, we empower them by providing actionable summaries.
  33. There are two components in making sense of Health Signals: Health signal extraction – processing, aggregating, and abstracting from raw sensor/textual data to create human intelligible abstractions Health signal understanding – derive (1) connections between abstractions and (2) Action recommendation: Continue Contact nurse Contact doctor
  34. What is the likely state of the person in future? => Given the current state and the changing environmental conditions, estimate the state of the person by summarizing it into a number which is actionable. For example, vulnerability score for a person with Asthma is computed with environmental factors (pollen, air quality, external temperature and humidity) and current state of the patient. Intuitively, a person with well controlled asthma should have a lower vulnerability score than a person with poorly controlled asthma both being in a poor environmental state.
  35. In the absence of declarative knowledge in a domain, we resort to statistical approaches to glean insights from data Even if there is declarative knowledge of a domain, it may have to be personalized The CO level may be related to the luminosity as observed by the sensordrone – as it gets brighter the CO level also increases => high CO level in daytime If such an insight is provided to a person, the interpretation can be: Some activity inside the house leads to high CO levels Outside activity leads to high CO levels inside the house Since the person knows that he/she is absent in the house during mornings, it has to be something from outside. - Person narrows down to a possible opened window at home (forgot to close more often)
  36. 1)www.pollen.com(For pollen levels) 2)http://www.airnow.gov/(For air quality levels) 3)http://www.weatherforyou.com/(For temperature and humidity)
  37. Subject 1 121 Data points from sensor observations 40 Data points from QA including one comment  Subject 2 108 Data points from sensor observations 36 Data points from QA including one comment
  38. Pucher, J., Korattyswaroopam, N., & Ittyerah, N. (2004). The crisis of public transport in India: Overwhelming needs but limited resources. Journal of Public Transportation, 7(4), 1-30.
  39. Horizontal operation
  40. People join these SM communities for variety of intentions. Varying intent may include a very small sample of important intentions to assist the coordination of actions --- request to help --- offer to help
  41. (1) Example overview
  42. Alright, so let’s motivate by this situation during emergency - Various actors: resource seekers, responder teams, resource providers at remote site And - each of these actor groups have questions --- - needs - providers - responders: wondering! Here we have social network to connect these actors and bridge the gap for communication platform But it’s potential use is yet to be realized for effective help Because.. (next slide)
  43. More at: http://wiki.knoesis.org/index.php/PCS And http://knoesis.org/projects/ssw/