Lumify is an open source big data integration, analytics, and visualization platform designed to help users discover connections and explore relationships in their data. It can ingest anything from spreadsheets and text documents, to images and video, representing this diverse data as a collection of entities, properties, and relationships between entities. Everything is stored in a scalable and secure graph database to enable advanced social network analysis and complex graph traversals. Built on proven open source technologies for big data like Hadoop, Storm, and Accumulo, Lumify supports a variety of mission-critical use cases centered around the emerging concepts of activity-based intelligence (ABI), object-based production (OBP), and human geography (HG). Its intuitive web-based user interface provides a suite of analytic options with multiple views on the data, including 2D and 3D graphs, full-text faceted search, histograms with aggregate statistics, and an interactive geographic map exploration feature. This talk will demonstrate how Lumify can be used to fuse structured and unstructured data from multiple sources into a unified knowledge base, and then analyze that knowledge to uncover hidden connections and actionable insights buried within the data's geospatial context.
Invezz.com - Grow your wealth with trading signals
Fusing Structured and Unstructured Data for Geospatial Insights in Lumify
1. Fusing Structured and Unstructured Data
for Geospatial Insights in
Charlie Greenbacker
Susan Feng
Altamira Technologies Corporation
2. is an open source
big data analysis and
visualization platform
built by Altamira engineers
3. Key Lumify Concepts
structure for organizing information (i.e., your data model)
Ontology
any “thing” you want to represent (e.g., person, place, event)
Entities
a link between two entities (e.g., leader-of, works-for, sibling-of)
Relationships
data about an entity (e.g., first name, last name, date of birth)
Properties
collection of entities and the relationships between them
Graph
5. trafficking
RESULTS
Document
94
FILTER BY ENTITY PROPERTIES
GEO LOCATION
REMOVE
Latitude
23.22
Longitude
-106.42
Radius
1000
DATE
REMOVE
is between
2014-01-01
2014-03-01
ADD FILTER
Video
27
Image
39
Event
21
Raid
21
Drug Lord
25
Person
60
Politician
35
Lumify provides full-
text search over
everything in your
graph. Use custom
filters built from
properties defined
in your ontology to
refine your search.
Search
6. Joaquin Guzman Loera
Display related
entities, find paths
to another entity,
and establish new
relationships to
other entities all
from a right-click
menu or drag and
drop action.
Link
Analysis
Connect…
Find Path…
Search Related
Remove
Remove from workspace
^
^
Add Related…
Items
Raw
^R
Documents
Images
Videos
People
Contact Information
Organizations
Events
Locations
7. Lumify provides
many different ways
to resolve new
entities, establish
relationships, and
assign properties
from the details
view, map, or
graph.
Knowledge
Building
Zarka de Mexico
Joaquin Guzman Loera
617-589-9821
Joaquin Guzman…
works at
owns
founded
advises
8. The graph leverages
drag-and-drop and
context menus to
put common
actions at your
fingertips. Use auto
layout options to
tame large graphs.
Graph
Visualization
2014-02-10
+52 1 825 5536872
+52 1 877 1211498
303-301-5881
303-904-7511
Mazatlan
Mexico City
2014-02-22
2014-02-22
Joaquin Guzman…
Zarka de Mexico
Emma Coronel
Patraca
Ismael Garcia
Javier Felix
9. Lumify ingests
unstructured text
documents, images,
video, and audio files,
then uses a variety of tools
to extract & enrich the
data for discoverability,
analysis, and visualization.
Multimedia
Analysis
Drug Lord “El Chapo” Captured in Mexico
PUBLISHED DATE
SOURCE
Audit
2014/02/22
Wikipedia
Add Property
Although Guzman had long hidden successfully in remote areas of the
Sierra Madre mountains, the arrested members of his security team told
the military he had begun venturing out to Culiacan and the beach town of
Mazatlan. A week prior to his capture, Guzman and Zambada were
reported to have attended a family reunion in Sinaloa. The Mexican military
followed the bodyguards tips to Guzman’s ex-wife’s house, but they had
trouble ramming the steel-reinforced front door, which allowed Guzman to
escape through a system of secret tunnels that connected six houses,
eventually moving south to Mazatlan. He planned to stay a few days in
Mazatlan to see his twin baby daughters before retreating to the
mountains.
On 22 February 2014, at around 6:40 a.m., Mexican authorities arrested
Guzman at a hotel in a beach front area in Mazatlan, Sinaloa, following an
operation by the Mexican Navy, with joint intelligence from the DEA and
10. Geo-tagged data
can be aggregated
and viewed using
any mapping
system with support
for OpenLayers,
including ESRI and
Google Maps.
Geospatial
Analysis
12. Sources of Geospatial Data in Lumify
geotags & coords in database records, metadata, etc.
Structured Data
location fields & addresses in spreadsheets, etc.
Semi-structured Data
place names mentioned in text documents
Unstructured Data
13. CLAVIN: an open source geoparser
geotagging & parsing of unstructured text
Turns Text into Maps
resolves place names to gazetteer records
Geospatial Entity Resolution
solves the “Springfield problem”
Disambiguation
now handles multipart location fields (e.g., [Reston|VA|US])
Versatile
created by Berico Technologies
www.clavin.io
14. How does CLAVIN work?
(i.e., machine learning + natural language processing)
17. Lumify helps analysts
fuse structured and
unstructured data
from myriad sources
into actionable
intelligence.
Intelligence
Analyst
18. Law enforcement
personnel can use
Lumify to explore
criminal networks,
uncover hidden
connections, and
develop leads.
Police
Investigator
19. Lumify analyzes
financial data and
transaction records
to help detect fraud
and identify possible
insider threats.
Financial
Analyst
photo
credit:
“Numbers
And
Finance”
by
Ken
Teegardin
(h<ps://flic.kr/p/9rn9Yh)
CC-‐BY-‐SA
2.0
20. Scientists, law firms,
news organizations,
and others can
track their research
in Lumify to unearth
latent knowledge
and discover critical
new insights.
Research
Staff
photo
credit:
“A
researcher
at
The
NaJonal
Archives
in
Kew”
by
the
UK
NaJonal
Archives
(h<p://bit.ly/1n9dhR8)
CC-‐BY
3.0
21. Built on Scalable Open Source Tech
Hadoop
CDH
4
Accumulo
ElasJcSearch
tesseract
CLAVIN
CMU
Sphinx
OpenNLP
OpenCV
ffmpeg
Apache
Storm
Secure
Graph
custom
code