EventShop Demo
-
Upload
siripen-pongpaichet -
Category
Data & Analytics
-
view
72 -
download
0
Transcript of EventShop Demo
![Page 1: EventShop Demo](https://reader035.fdocuments.in/reader035/viewer/2022062823/586f74be1a28ab10258b5cd7/html5/thumbnails/1.jpg)
UCIRVINEDonald Bren School of Information and Computer Sciences
Siripen Pongpaichet
PhD Candidate, Academic Advisor Prof. Ramesh Jain
Contact: [email protected]
Interest: complex event stream processing, multimedia information system, large scale data management, having fun doing research
![Page 2: EventShop Demo](https://reader035.fdocuments.in/reader035/viewer/2022062823/586f74be1a28ab10258b5cd7/html5/thumbnails/2.jpg)
Fundamental ProblemWeb 1.0 Connecting People to Documents
Web 2.0 Connecting People to People
“Social Life Network”
Connecting Needs to ResourcesEffectively, Efficiently, and Promptly
In given situations.
![Page 3: EventShop Demo](https://reader035.fdocuments.in/reader035/viewer/2022062823/586f74be1a28ab10258b5cd7/html5/thumbnails/3.jpg)
3
Related Services
7/03/2013
http://google.org/crisismap/sandy-2012
Mash Up: Google Crisis Maps
one-touch SOS
Mobile Applications
![Page 4: EventShop Demo](https://reader035.fdocuments.in/reader035/viewer/2022062823/586f74be1a28ab10258b5cd7/html5/thumbnails/4.jpg)
EventShop : Global Situation Detection
Situation Recognition
Evolving Global Situation
Personal Situation
Recognition
Personal EventShop
Evolving Personal Situation
Need- Resource Matcher
Recommendation Engine
PersonaDatabase
Resources
Needs
Data Ingestion
Wearable Sensors
Calendar
Location….
Dat
a So
urce
s
….
Data Ingestion
and aggregation
Database Systems
Satellite
Environmental Sensor Devices
Social Network
Internet of Things
Actionable Information
![Page 5: EventShop Demo](https://reader035.fdocuments.in/reader035/viewer/2022062823/586f74be1a28ab10258b5cd7/html5/thumbnails/5.jpg)
Big Challenges• Data Ingestion to efficiently extract data from
the Web and make them available for later computation is not-trivial.
• Stream Processing Engine to bridge the semantic gap between high level concept of situations and low level data streams.
• Situation Recognition as the next step in concept recognition.
![Page 6: EventShop Demo](https://reader035.fdocuments.in/reader035/viewer/2022062823/586f74be1a28ab10258b5cd7/html5/thumbnails/6.jpg)
05/02/2023 7
History of EventShop
• Building as part of SLN framework• Environment and visualization tool for analyzing
heterogeneous data streams in macro scale• Help non (CS) technical experts in various domains to easily
conduct experiments for detecting real-world situations• Representing geo-spatial data in grid structure called E-mage• Generic set of operators for detecting situations• Pioneers: Vivek Singh (Rutgers University), Mingyan Gao
(Google), Ish Rishabh (Live Nation Entertainment)
![Page 7: EventShop Demo](https://reader035.fdocuments.in/reader035/viewer/2022062823/586f74be1a28ab10258b5cd7/html5/thumbnails/7.jpg)
8
EventShop UI
11/13/2013
Example Notification / Alerts:
You are currently in the area where there is a high chance of flooding,
these are available shelters within 10 miles around you.Space
Time Situation
Resources
People
![Page 8: EventShop Demo](https://reader035.fdocuments.in/reader035/viewer/2022062823/586f74be1a28ab10258b5cd7/html5/thumbnails/8.jpg)
05/02/2023
OutputIngestor
Data Source Parser
Data Adapter
Emage Generator
(+resolution mapper)
Processing
EvShop Storage
Query Parser
Query Rewriter
Event Stream Processing Executor
Action Parser
Register Data Source Register Continuous Query
Situation
Emage
Visualization (e.g., Sticker from NICT)
Actuator Communication
Action Control
Event Property & Other Information
(e.g., spatio-temporal pattern)
ᴨ
ᴨµ
Data Access Manager
Live StreamArchived Stream
Situation Stream
EventShop Architecture
Physical Data Source (e.g., sensor
streams, geo-image streams)
Logical Data Source
(e.g., preprocessing data streams, social
media streams)
Raw Event
EventWarehouseNICT - Japan
![Page 9: EventShop Demo](https://reader035.fdocuments.in/reader035/viewer/2022062823/586f74be1a28ab10258b5cd7/html5/thumbnails/9.jpg)
• STT Observation is represented as:STT = <latitude,longitude,timeStamp,theme,value>
Point(40,-76), TimeStamp(12-12-12 12:00:00PT), Shelter-Availability, 1600
• A flow of STTs becomes a STT Stream:STT Stream = {STT0, ..., STTi, ...}
• E-mage is represented as:E-mage = <SW,NE,latUnit,longUnit,TimeStamp,Theme,2D Grid>
SW(40,-125), NE(50,-115), 0.1latUnit, 0.1longUnit, TimeStamp(12-12-12 12:00:00PT), Shelter-Availability, [0,0,0, 1000, 2000, …]
• A flow of E-mages forms an E-mage Stream:E-mage Stream = {E-mage0, ..., E-magei, ...}
• The cell together with STT information is called stel (spatio-temporal element),stel = <SW,NE,latUnit,longUnit,timeStamp,theme,value>
EventShop Data Representation
![Page 10: EventShop Demo](https://reader035.fdocuments.in/reader035/viewer/2022062823/586f74be1a28ab10258b5cd7/html5/thumbnails/10.jpg)
Situation Detection Operators
Pattern Matching
Aggregation
Characterization
∏ Filter
Segmentation
72%
+
+
Growth Rate = 125%
DataSupporting
parameter(s) OutputOperator Type
+
Segmentation methods
Property required
Pattern
Mask
Conversion
@
↔
Interpolation~
+ConversionMethods
(e.g., Coarse2Fine)
+Interpolation
Methods(e.g., linear Inter.)
![Page 11: EventShop Demo](https://reader035.fdocuments.in/reader035/viewer/2022062823/586f74be1a28ab10258b5cd7/html5/thumbnails/11.jpg)
14
Input: EvWHHigh change PM2.5 Event
Input: TwitterAllergy Event
Input: AirNowPM2.5 Level
Input: AirNowAir Quality Index
Raw Allergy Tweets
Count #of
Tweets
PM2.5 Emage
AQI Emage
Processing
CA
S
Output“Sticker” Allergy Risk Level
Interactive MAP
Alert Message via CPCC Apps
Email Notification Situation
PM2.5 Change Event
Properties
Segmentation: Threshold
Average
N Normalization N N
Correlation
Requirement of an unified Event Model
by UCI/NICT
![Page 12: EventShop Demo](https://reader035.fdocuments.in/reader035/viewer/2022062823/586f74be1a28ab10258b5cd7/html5/thumbnails/12.jpg)
App1: Allergy Management
![Page 13: EventShop Demo](https://reader035.fdocuments.in/reader035/viewer/2022062823/586f74be1a28ab10258b5cd7/html5/thumbnails/13.jpg)
App2: Thai Flood Emergency Response
![Page 14: EventShop Demo](https://reader035.fdocuments.in/reader035/viewer/2022062823/586f74be1a28ab10258b5cd7/html5/thumbnails/14.jpg)
Multi-Spatio-Temporal Bounding Boxes and Granularities
• “Pyramid of E-mage” resolution is introduced to represent the real world in E-mage at different (zoom) levels.
• Each Stel (a pixel in the E-mage) represents a single fixed ground location.
• Precision vs Computational Cost
![Page 15: EventShop Demo](https://reader035.fdocuments.in/reader035/viewer/2022062823/586f74be1a28ab10258b5cd7/html5/thumbnails/15.jpg)
Rasterization and Error Propagation
• Data Error Factors:– Uncertainty of data stream– Data loss during data aggregation– Uncertainty during data conversion– Data error during data conversion
• To design the situation recognition model, we need to find the new cost evaluation method that will consider both data accuracy and computational cost.
![Page 16: EventShop Demo](https://reader035.fdocuments.in/reader035/viewer/2022062823/586f74be1a28ab10258b5cd7/html5/thumbnails/16.jpg)
Enrich Personalized Asthma Risk
• Predict air quality at air quality measuring sites.
• Interpolate air quality at the locations not covered by measuring sites.
• Predict personalized asthma risk by using EventShop and Personal EventShop.
![Page 17: EventShop Demo](https://reader035.fdocuments.in/reader035/viewer/2022062823/586f74be1a28ab10258b5cd7/html5/thumbnails/17.jpg)
Daily Ozone Data
Ref- http://www.arb.ca.gov/aqmis2/aqmis2.php
![Page 18: EventShop Demo](https://reader035.fdocuments.in/reader035/viewer/2022062823/586f74be1a28ab10258b5cd7/html5/thumbnails/18.jpg)
EventShop : Global Situation Detection
Situation Recognition
Evolving Global Situation
Personal Situation
Recognition
Personal EventShop
Evolving Personal Situation
Need- Resource Matcher
Recommendation Engine
PersonaDatabase
Resources
Needs
Data Ingestion
Wearable Sensors
Calendar
Location….
Dat
a So
urce
s
….
Data Ingestion
and aggregation
Database Systems
Satellite
Environmental Sensor Devices
Social Network
Internet of Things
Actionable Information
![Page 19: EventShop Demo](https://reader035.fdocuments.in/reader035/viewer/2022062823/586f74be1a28ab10258b5cd7/html5/thumbnails/19.jpg)
05/02/2023 22
Calendar PESi
FMB (Individual’s Feeling)Accelerometer
Location
Fitness Data(Nike, Fitbit) Data
Ingestion & Aggregation
Heart RateLocation (Move)
Food Log
FMB (People’s Feeling, Location)
ESOzoneCO2SO2PM 2.5
Pollen (Tree, Grass)
Air Quality Index
Data Ingestion & Aggregation
Social Media (News, Tweets)
Weather
Macro Situation Recognition
Predictive Analytics
PersonalSituation Recognition
Persona
Asthma Allergy App Server
Data Collection
Mac
ro S
ituati
onPe
rson
al S
ituati
on
Need and Resources Recommendation
SLN Use Case
![Page 20: EventShop Demo](https://reader035.fdocuments.in/reader035/viewer/2022062823/586f74be1a28ab10258b5cd7/html5/thumbnails/20.jpg)
More +++
• Website– http://eventshop:8004/sln
• Demo– http://auge.ics.uci.edu/eventshop
• Open Source– https://github.com/eventshop
• Collaborations