Click to edit Master title style Click to edit Master title style - - PowerPoint PPT Presentation

▶
click to edit master title style click to edit master
SMART_READER_LITE
LIVE PREVIEW

Click to edit Master title style Click to edit Master title style - - PowerPoint PPT Presentation

May 04, 2023 228 likes •307 views

UNCLASSIFIED//FOR OFFICIAL USE ONLY UNCLASS/FOUO UNCLASS/FOUO AMERICAS ARMY: AMERICAS ARMY: Click to edit Master title style Click to edit Master title style THE STRENGTH OF THE NATION THE STRENGTH OF THE NATION Dr. Russell D.

slide-1
SLIDE 1

Click to edit Master title style

UNCLASS/FOUO

AMERICA’S ARMY: THE STRENGTH OF THE NATION

Click to edit Master title style

UNCLASS/FOUO

AMERICA’S ARMY: THE STRENGTH OF THE NATION

UNCLASSIFIED//FOR OFFICIAL USE ONLY

  • Dr. Russell D. Richardson, G2/INSCOM Science Advisor
  • Dr. Russell D. Richardson, G2/INSCOM Science Advisor

1

UNCLASSIFIED//FOR OFFICIAL USE ONLY

slide-2
SLIDE 2

UNCLASS/FOUO

AMERICA’S ARMY: THE STRENGTH OF THE NATION

UNCLASSIFIED

Semantic Enrichment of the Data Semantic Enrichment of the Data

Solving the Precision / Recall Conundrum with Semantic Enrichment of the Data Solving the Precision / Recall Conundrum with Semantic Enrichment of the Data

Precision

Concepts/Summarization (e.g. Terrorist Cell Leaders) Concepts/Summarization (e.g. Terrorist Cell Leaders) Resolved Entity (J h

ith ID )

Resolved Entity (J h

ith ID )

Increasing Semantic Richness

Semantically Labeled Data

Precision

y Centric Resolved Entity (John with ID xxxxx) Resolved Entity (John with ID xxxxx) Entity (Person, Object, Organization, Location) Entity (Person, Object, Organization, Location) Entity Multi‐token/Lemma/Contexual Element/ Part of Speech (Noun, Pronoun, Punctuation) Multi‐token/Lemma/Contexual Element/ Part of Speech (Noun, Pronoun, Punctuation) Token (Aggressively Indexed Words) Token (Aggressively Indexed Words)

Aggressively Index

Increasing

Recall

De‐Anonymization of Large Data Sets Detect / Match Behaviors and Patterns

Enabled by fine grain security and compliance enforcement

gg y

Determine that Two Patterns of Life are the Same but Not Necessarily Whose Pattern of Life Determine that Two Patterns of Life are the Same but Not Necessarily Whose Pattern of Life

Increasing Anonymity

ntric

Massive Data Sets for Anomaly / Change Detection Massive Data Aggregation for Machine Analytics, Baselining, and Trend Analysis Indications and Warnings Indications and Warnings Non‐Attributable Aggregate Behavior ‐ Determine Avg Traffic Speed by Tracking Cell Movement Determine the Sentiment of a Town City Region Country Non‐Attributable Aggregate Behavior ‐ Determine Avg Traffic Speed by Tracking Cell Movement Determine the Sentiment of a Town City Region Country

Non- Attributable

  • pulation Cen

‐ Determine the Sentiment of a Town, City, Region, Country ‐ Determine the Sentiment of a Town, City, Region, Country

Po

2

UNCLASSIFIED

slide-3
SLIDE 3

UNCLASS/FOUO

AMERICA’S ARMY: THE STRENGTH OF THE NATION

Extending Cloud-Enabled Advanced Analytics Extending Cloud-Enabled Advanced Analytics

All All-

  • Source

Source Analytics for ‘Big Data’ Analytics for ‘Big Data’ All All-

  • Source

Source Analytics for ‘Big Data’ Analytics for ‘Big Data’ with Advances in with Advances in Geospatial Indexing, Geospatial Indexing, Voice Index and Search, Voice Index and Search, Bi t i E tit M t Bi t i E tit M t with Advances in with Advances in Geospatial Indexing, Geospatial Indexing, Voice Index and Search, Voice Index and Search, Bi t i E tit M t Bi t i E tit M t

Voice Voice Mobile Mobile

Biometric Entity Management, Biometric Entity Management, Motion Imagery Tracks, Motion Imagery Tracks, Multi Multi-

  • INT Visualization,

INT Visualization, C ll ti M t C ll ti M t Biometric Entity Management, Biometric Entity Management, Motion Imagery Tracks, Motion Imagery Tracks, Multi Multi-

  • INT Visualization,

INT Visualization, C ll ti M t C ll ti M t

Voice Voice Mobile Mobile

Collection Management, Collection Management, Support for Mobile Devices, Support for Mobile Devices, Powerful Compute Platforms, Powerful Compute Platforms, Multi Multi Level Security Level Security Collection Management, Collection Management, Support for Mobile Devices, Support for Mobile Devices, Powerful Compute Platforms, Powerful Compute Platforms, Multi Multi Level Security Level Security Multi Multi-Level Security, Level Security, IC Shared Software, IC Shared Software, …. …. Multi Multi-Level Security, Level Security, IC Shared Software, IC Shared Software, …. ….

UNCLASSIFIED

Motion Imagery Tracks Motion Imagery Tracks

slide-4
SLIDE 4

Click to edit Master title style

UNCLASS/FOUO

AMERICA’S ARMY: THE STRENGTH OF THE NATION

Fusion Challenges Fusion Challenges

INTs

Social Media Pattern of Life

Tipping and Cueing

  • Alerts & Notifications
  • Information and Situation

Media All Source Pattern of Life Analysis

Person Location

  • Sensors
  • Information requests

Tactical Reports HUMINT

Challenges

  • 1. Cross INT Correlation

2 Entity Resolution and

  • 1. Cross INT Correlation

2 Entity Resolution and Threat Characterization Persistent and Total Entity and Asset Tracking in Entity Database

Org Unit

…

Biometrics

  • 2. Entity Resolution and

Disambiguation

  • 3. Scale of the Entity Database
  • 4. Velocity of Data Collection and

Processing 5 D t i i P tt f Lif

  • 2. Entity Resolution and

Disambiguation

  • 3. Scale of the Entity Database
  • 4. Velocity of Data Collection and

Processing 5 D t i i P tt f Lif COA Biometrics DOMEX

  • 5. Determining Patterns of Life

and Major Combat Operations with Tolerance to Errors

  • 6. Ranking Threat Severity and

Timing

  • 5. Determining Patterns of Life

and Major Combat Operations with Tolerance to Errors

  • 6. Ranking Threat Severity and

Timing ISR Optimization COA Analysis SIGINT GEOINT Cyber

  • 7. Optimizing / Synchronizing ISR
  • 8. Real‐time Tipping and Cueing
  • 7. Optimizing / Synchronizing ISR
  • 8. Real‐time Tipping and Cueing

Continuously & Always Correlating All Data into the Entity Database

4

y

Data into the Entity Database

slide-5
SLIDE 5

Click to edit Master title style

UNCLASS/FOUO

AMERICA’S ARMY: THE STRENGTH OF THE NATION

Need to Work Entity Tracking

Social Media

Threat Characterization

P1 P2 P3 (T1,L1) (T2,L1) (T3,L3) (T2,L3) (T3,L3) (T4,L3) (T1 O1) (T3 L3) (T3 L2) Same Time, Same Place

Entity Database Persist Tracks

3 COAs

Person Location

…

P3 P4 P5 L1 L2 (T1,O1) (T3,L3) (T3,L2) (T1,L2) (T2,L2) (T3,L3) (T1,L1) (T2,L2) (T3,L3) (T1,P1) (T2,P1) (T1,P4) (T3,P3) (T1,P4) (T2,P5)

Database

ted base

Form Links

L2 may be an important location as many P’s have been reported Org Unit

…

Reports/ HUMINT …

L3 L4 O1 O2 O3 ( ) ( ) ( ) (T1,L1) (T2,L1) (T3,L3) (T1,L1) (T2,L1) (T3,L3) (*,L1) (T1,P1) (T3,L3) (T1,L1) (T2,L1) (T3,L3) (T1 L1) (T2 L1) (T3 L3)

Precorrelat Linked Data

as many P s have been reported being there

…

Biometrics DOMEX …

O3 O4 O5 U1 U2 (T1,L1) (T2,L1) (T3,L3) (T1,L1) (T2,L1) (T3,L3) (T1,L1) (T2,L1) (T3,L3) (T1,L1) (T2,L1) (T3,L3) (T1 L1) (T2 L1) (T3 L3)

1 2

Patterns of Life Determined

DOMEX …

U2 U3 U4 U5 (T1,L1) (T2,L1) (T3,L3) (T1,L1) (T2,L1) (T3,L3) (T1,L1) (T2,L1) (T3,L3) (T1,L1) (T2,L1) (T3,L3) T1 (P1 L1) (P3 L1) (T3 L3) Location of P1 over time Infer P3 at L1 as O1 is at L1 P1 and P3 share location pattern

SIGINT GEOINT Cyber …

T1 T2 T3 T4 T5 (P1,L1) (P2,L3) (T3,L3) (P1,L3) (P3,L3) (T3,L3) (P2,L3) (T2,L1) (T3,L3) (T1,L1) (T2,L1) (T3,L3) (P1,L1) (P3,L1) (T3,L3)

Optimize ISR

4

5

ISR

slide-6
SLIDE 6

Click to edit Master title style

UNCLASS/FOUO

AMERICA’S ARMY: THE STRENGTH OF THE NATION

The DCGS The DCGS-

  • A ICITE Cloud (aka Red Disk)

A ICITE Cloud (aka Red Disk) at at-

  • Scale Entity Database

Scale Entity Database

  • EDH
  • Provenance
  • TDF
  • Metadata tagging

G l i

Data Interoperability Enterprise Context Decreases Information Burden

Sensors

Data Access Process ‐ User’s authorizations

  • Geo temporal extraction
  • Entity extraction and nomination
  • Artifact enrichment
  • Security Labeling
  • Metrics
  • more

Sources

DIAS

User’s

Full Spectrum Analytic Awareness

authorizations and roles are matched to data security labels

UCD

NIFI / Storm

RTAAP

Sources

  • SIGINT
  • MTI
  • WAMI
  • FMV
  • TED

Velocity & Content

Authorizations

Artifacts, Real‐Time Community

UCD

  • TED
  • Fires
  • Harmony
  • USMFT
  • Collection

Mgmt

Artifacts, Terms Statements Analytics and indexes updated h if Advanced Analytics Pipeline … updating analytics earliest as possible. Analyst’s conclusions enrich the UCD y Partners

  • Open

Source

  • Mission

Command

  • Audio
  • etc

M R M R

wrt to each artifact

  • Maximally correlated data
  • Contextual‐based navigation
  • All data under a common representation to enable
  • Classes of relationships determined at

various points

  • No all relationships need to be explicitly

expressed – correlations enable this

  • All analytic disciplines together with

M/R M/R

  • Enrichment
  • Analytics and indexes wrt

to the entire corpus,

  • Bulk and incremental

All data under a common representation to enable assess to all layers

  • Cross corpus analytics without custom code
  • Signatures are analyzed in real time
  • Logical representation needs to be consistent in
  • rder for the physical model and view to be
  • All analytic disciplines together with

correlated data among all disciplines Analytic models are represented in the UCD

6

Bulk and incremental updates

  • Data sharing

p y dynamic