“Helping non‐experts make expert decisions to achieve faster and more effective outcomes”

2019 S&ME Conference: Systems and Mission Analysis in a DOTMLPF-P Knowledge Graph

Matthew Maher and Rob Orlando

data knowledge understanding Processus Group

• Why use Knowledge Modeling (KM) with Knowledge Graphs (KGs)?

• Integrate KGs into Existing Systems Engineering or Business Processes

• DOTMLPF‐P in a Knowledge Graph for CEMA Optimization

• Summary• Next Steps• Questions

Agenda

High level Knowledge Graph Example

Personal

Pos‐EW SGT

RANK‐E5MOS‐17E20

Organization

Material

Doctrine

Training

17E Transition Course

Type‐TEWS

Role‐EA/EP/SAPOS‐ EW PL

FM 3‐38 Cyber Electromagnetic 

Activities

FM 3‐36 Electronic Warfare 

Operations

Leadership

data knowledge understanding Processus Group

Knowledge Modeling is the process of capturing knowledge and intelligence in the form of Knowledge Graphs or Ontologies.Knowledge Graphs answer the following questions:• How do I fit into the big

picture?• Are we doing the right things?• How do we work together?

Why Use Knowledge Modeling with Knowledge Graphs?

Conduct Effects Targeting

Conduct Information Collection

Conduct Information Processing

Conduct Information Analysis

Deliver ES

Report CEMA Monitoring

data knowledge understanding Processus Group

How do I fit into the big picture?• Create dynamic Situational Understanding (SU) by combining data with knowledge. Understanding that allows non-experts to

make expert decisions.• Data + Knowledge = Understanding. Understanding leads to faster, more accurate, and better coordinated decision-making.Are we doing the right things?• Define an explicit representation of a domain so everyone has the same starting point. Provide references that create a

machine and human readable knowledge base that can be used to support cognitive capabilities.• KGs map the cause and effect relationships of data and knowledge to information throughout the DOTMLPF-P domain

enabling rapid understanding of second and third order effects of decisions and actions. How do we work together?• Break down silos by translating between functional teams through the mapping of the cause and effect relationships.

• Depending on the scope, functional teams could refer to acquisitions (i.e. logistics, technical, test, business analysts, etc.), functional teams could refer to operations (i.e. intel, sustainment, maneuver, fires, signal, etc.), or functional teams could refer to both groups.

• KGs improve Knowledge Management and knowledge retention. Not everyone speaks DoDAF/MoDAF, SysML/UML. We all, however, speak subject-predicate-object.

Use Knowledge Graphs to Answers Three Core Questions

data knowledge understanding Processus Group

• Develop a multi-domain model in a KG that addresses multiple levels of depth and breadth

• Decision makers focused on the What/Why use the same data as the decision makers focused on the How.

• KGs becomes the central point for Data Strategy • KGs provide the ability to siphon structured and unstructured data

organization-wide, helping to make well-informed decisions by gaining further insight through analytics and bringing value to your data.

• KGs integrate with the Risk Management process by dynamically tracking cause and effect relationships

• Enhances Change Management process through the use of SPARQL queries to quickly extract relevant knowledge of the proposed change.

• Queries use the subject-predicate-object format that is easily understood.

• KG development aligns with an agile approach.• KG development fits easily within your sprints- The turnaround

time is quick, and the focus areas of the model can easily be identified in retrospectives and sprint planning sessions.

• DOTMLPF-P Knowledge Graphs provide the end-to-end infrastructure an organization needs to accelerate outcomes for future AI/ML/ANN capabilities.

Integrate KGs into Existing Systems Engineering or Business Processes

data knowledge understanding Processus Group

DOTMLPF‐P for CEMA Optimization

 CS(CO)_F4_

Synchronize_CEMA_Support_Ops /* 

FuncNarative "The tasks and activities required to integrate all CEMA enablers into a fused set of information that fully enables the implementation of optimized CEMA Operations (fully integreated offensive cyberspace and EW operations)." (en) */

AssetLocationPLIRPT some CS_F6_Report_CEMA_OperationsProvidesyncCEMA_Opsinfo some CS_F1_Integrate_Offensive_Cyberspace_OpsProvidesyncCEMA_Opsinfo some CS_F2_Integrate_Defensive_Cyberspace_OpsProvidesyncCEMA_Opsinfo some CS_F3_Integrate_EW_OpsReceiveIC_OpsInfo some CS_F4.1_Sync_with_ICReceiveIO_OpsInfo some CS_F4.2_Sync_with_Info_Ops_SupportsReceiveSpec_Opsinfo some CS_F4.4_Sync_Spectrum_Support_OpsReceiveTarget_Opsinfo some CS_F4.5_Sync_With_Targeting_ProcessRecieveSpace_OpsInfo some CS_F4.3_Sync_with_Space_OpsSendSPOTRpt some CS_F6_Report_CEMA_Operations'BDA(UA)Report' some CS_F6_Report_CEMA_Operations

 CS(CO)_F4.1_Sync_with_IC /*  FuncNarative "Coordinate with Intelligence Section to 

support ISR integration" (en) */

ProvideIC_OPsinfo some CS_F4_Synchronize_CEMA_Support_Ops

CS(CO)_F4.2_

 Sync_with_Info_Ops_Supports /* 

FuncNarative "The tasks and activities required to collect, compile, assess, and provide relevant information operations information as part of CEMA Support Operations." (en) */

ProvideIO_Opsinfo some CS_F4_Synchronize_CEMA_Support_Ops

CS(CO)_F4.3_ Sync_with_Space_Ops /* 

FuncNarative "The tasks and activities required to synchronize space operations with the CEMA Section." (en) */

ProvideSpace_Opsinfo some CS_F4_Synchronize_CEMA_Support_Ops

 CS(CO)_F4.4_

Sync_Spectrum_Support_Ops /* 

FuncNarative "The tasks and activities required to collect, compile, assess, and provide relevant spectrum management operations information as part of CEMA Support Operations." (en) */

ProvideSpec_OpsInfo some CS_F4_Synchronize_CEMA_Support_Ops

CS(CO)_F4.5_

 Sync_With_Targeting_Process /* 

FuncNarative "The tasks and activities required to ensure all approved and emerging targeting requirements are satisfied in accordance with the Unit of Action's execution of the mission." (en) */

ProvdeTarget_OpsInfo some CS_F4_Synchronize_CEMA_Support_Ops

FUOPS

CUOPS

Logical Task to Function Alignment

Domain Conceptual Process model = Planning

Interface and Data exchange

Logical model = Preparation Data model = Execution

TOC

USN

USAF

Joint Service Component

PED

Intel Agencies

UNCLASSIFIED / FOUO

USMC

Army,Joint, National ISR

All SIGINT vehicles have SATCOM to NSA

Engineers Artillery

Infantry

Armor

Logistics

C2

ADA

Infantry

Infantry

• Detect/Recognize/Locate

• Non-kinetic Fires

• Tip/Cue SIGINT

Electronic Warfare

Tactical SIGINT

•Detect/Recognize/Locate/Characterize

• SA (Disposition, Activity & Intent)

• Target Dev• Enable EW

MFEW Air

Mission Command•

DCGS-A

•EWPMT

• CPOF•

AFATDS

• etc…

Close Access Delivery PlatformCyber

PEDCEMACST

Aerial  Electronic Warfare for Tactical and Operational Commanders

Tailorable Terrestrial EW / Cyber / Intelligence Team Capabilities

• SIGINT/ES• EW (ES/EA/EP)• Cyber (Close Access Platform Delivery)

LEGEND

Key Comms

Threat

Boundary

Advantageous Comms

UNCLASSIFIED / FOUO

MIEW/UA Operations

CEMA Knowledge Graph

data knowledge understanding Processus Group

Draft Use Case 2 – Mission Analysis 

External Ena

blers

EWO

PLC2

PLTX

Targeting WG

IPB WG

 Sen

sors

Data 

COA Development

  PLC2 COP

 Modify Work Space

PL TX

Prepare Mission 

Analysis Brief

Publish Updated EW Running Estimate

Terrain Geometr

y

PL Emission Controls

PL Capabilit

y

RFIs

PL MA support plan

CDR

EWO

PL  Resources Available

PL Location

PL Config /status

PL Asset Allocation 

Table

S‐2

S‐3

FSO

Jamming Data

Collection Data

Start  MSYes

PL Configuration

NO=data

S‐4

Location of assets 

in support of fires

Recommend PIRs

Request Collection DataExternal support

Optimize COA

Higher HQ Plan

Warno 1

Type of Ops

AOR Move and Recon timeTimeline

CDRs Initial Guidance

Knowledge Products from 

External 

Higher HQ Intel and Knowledge 

Products

Warno 2

Risk Guidance

 UN IT AOWfF 

Priorities

Collection Plan

Deception Plan

Timeline

Movement

Specific Priorities

Mission Statement

Commanders  IntentTO CCIRs/EEFIs

EP Planning

EA Planning

ES Planning

EW MA

EW Collection Requirements

EW Target list

EW Intel Requirements

Initial Analysis of Enemy C2

List EW task for ES EW RE

EW Assumptions

EW Constraints

EW planning Guidance

EW Support Requirements

EW MA report

IPB Battlefield Framework

IPB Movement analysis

METT‐C

OCOKA

HPTL

HVTsEW 

Targets

AGM

TAIsAmmunit

ions

Analyze BF Environment

Enemy Terrain

HVT

Gaps in PIRs

External  Assets for use (External SA)

Terrain Analysis

ENEMY COAs

Start Targeting WG

Target Value Analysis

ATO Request

Intel Limits to AOI

Start IC planOAKOC*

*observations and fields of fire, avenues of approach, key terrain, obstacles, and cover and concealment 

MNVR Plan

Scheme of MNVRMNVR TimelineUnit Lanes

EW effects

Tar Selection Standard

Attack Guidance Matrix Planning

D3A‐Decide

Initial IPB

Task acquisition 

assets

Attack Means

Target MOEs

Target Set List

EW MOEs

EW Activities

EW Detect Activities

PGM Data

Target List

Weapon sys List

GEO regi ons for  EW Threat

Sensor coverage

Prim/sec Target Lines

Recommend PIRS

Process EEI

Process RFIs

GPS Protect plan

GPS Hardenin

g

PL Asset List

EMS Environm

ent survey

NO =RFI

PL Hardenin

g

PL Overlay

Fires Tasks Cyber/EW.PNT Tasks

Specific HPT

Desired Effect

Restrictions

How to Engage

Timing Engagement Fires  Ops 

Sync

Recommends Targets to 

detect, Acquire and attack

ID Combat Assessment 

Requirements

Fires RE

Weapon system 

accuracy req

Size of Enemy activity

Status of activity

Timeliness of info

S‐3 RE

MS Results

Calculate Risks

Identify Tasks

Identify Constraints

Analyze Fires Trajectories

Intel RE

Legend‐

Process

Documnet

Data Produced

Start/end effort

Decision

Relationship

PLC2 External realtionship

Negative relationship

EWO

Actor

External input

In‐direct relationships

Draft Use Case 2 – Mission Analysis 

External Ena

blers

EWO

PLC2

PLTX

Targeting WG

IPB WG

 Sen

sors

Data 

COA Development

  PLC2 COP

 Modify Work Space

PL TX

Prepare Mission 

Analysis Brief

Publish Updated EW Running Estimate

Terrain Geometr

y

PL Emission Controls

PL Capabilit

y

RFIs

PL MA support plan

CDR

EWO

PL  Resources Available

PL Location

PL Config /status

PL Asset Allocation 

Table

S‐2

S‐3

FSO

Jamming Data

Collection Data

Start  MSYes

PL Configuration

NO=data

S‐4

Location of assets 

in support of fires

Recommend PIRs

Request Collection DataExternal support

Optimize COA

Higher HQ Plan

Warno 1

Type of Ops

AOR Move and Recon timeTimeline

CDRs Initial Guidance

Knowledge Products from 

External 

Higher HQ Intel and Knowledge 

Products

Warno 2

Risk Guidance

 UN IT AOWfF 

Priorities

Collection Plan

Deception Plan

Timeline

Movement

Specific Priorities

Mission Statement

Commanders  IntentTO CCIRs/EEFIs

EP Planning

EA Planning

ES Planning

EW MA

EW Collection Requirements

EW Target list

EW Intel Requirements

Initial Analysis of Enemy C2

List EW task for ES EW RE

EW Assumptions

EW Constraints

EW planning Guidance

EW Support Requirements

EW MA report

IPB Battlefield Framework

IPB Movement analysis

METT‐C

OCOKA

HPTL

HVTsEW 

Targets

AGM

TAIsAmmunit

ions

Analyze BF Environment

Enemy Terrain

HVT

Gaps in PIRs

External  Assets for use (External SA)

Terrain Analysis

ENEMY COAs

Start Targeting WG

Target Value Analysis

ATO Request

Intel Limits to AOI

Start IC planOAKOC*

*observations and fields of fire, avenues of approach, key terrain, obstacles, and cover and concealment 

MNVR Plan

Scheme of MNVRMNVR TimelineUnit Lanes

EW effects

Tar Selection Standard

Attack Guidance Matrix Planning

D3A‐Decide

Initial IPB

Task acquisition 

assets

Attack Means

Target MOEs

Target Set List

EW MOEs

EW Activities

EW Detect Activities

PGM Data

Target List

Weapon sys List

GEO regi ons for  EW Threat

Sensor coverage

Prim/sec Target Lines

Recommend PIRS

Process EEI

Process RFIs

GPS Protect plan

GPS Hardenin

g

PL Asset List

EMS Environm

ent survey

NO =RFI

PL Hardenin

g

PL Overlay

Fires Tasks Cyber/EW.PNT Tasks

Specific HPT

Desired Effect

Restrictions

How to Engage

Timing Engagement Fires  Ops 

Sync

Recommends Targets to 

detect, Acquire and attack

ID Combat Assessment 

Requirements

Fires RE

Weapon system 

accuracy req

Size of Enemy activity

Status of activity

Timeliness of info

S‐3 RE

MS Results

Calculate Risks

Identify Tasks

Identify Constraints

Analyze Fires Trajectories

Intel RE

Legend‐

Process

Documnet

Data Produced

Start/end effort

Decision

Relationship

PLC2 External realtionship

Negative relationship

EWO

Actor

External input

In‐direct relationships

Collection Data

/Weapons/Sensor Data

Doctrine/Orders

Multi‐domains Data

Joint Warfare Tasking

Intel Data Sources Conduct 

Test

Build Prototype

Develop Software

Develop Rqmts.

Design Interfaces

CEMA Ontology(knowledge graph, cause and effect, 

domain knowledge)

Use Cases

Edge Data Analytics

Edge Data Analytics

Edge Data Analytics

Edge Data Analytics

Edge Data Analytics

Edge Data Analytics

DOTMLPF‐P in a KG: CEMA Use Case Development Example

data knowledge understanding Processus Group

• The Results- create a scientific modeling techniques, that includes advance data query through SPARQL, Deterministic data analytics, Graph based mathematical validation all in World Wide Web Consortium International Standard.

• Defining an explicate representation of a Domain that is now the creation of a machine and human readable knowledge base that can be used to support supervised learning

• Decreases expenses through operational cost efficiencies

Summary of DOTMPLF‐P in Knowledge Graphs

• The Why- To combine data with knowledge resulting in understanding. Understanding that allows Non-Experts to Make Expert Decisions.

• Data + Knowledge = Understanding, Understanding leads to faster and more accurate decision making

• The How- Through the linking of Data Science to Operational and Doctrinal knowledge.

• Using Semantic driven modeling, graph data structures and deterministic Mathematics that defines the inter-relationships of how DOTMLPF-P connect.

• The What- We created Ontologies/Knowledge Graphs that mapped the relationship of data and knowledge to information up and down DOTMLPF-P capabilities development for CEMA Optimization.

• Creating a dynamic knowledge base of how each layer of DOTMLPF-P connects to every other layer.

Data Source‐Structured, Unstructured and Semi‐Structured 

Knowledge Model (Ontology/Knowledge Graph)‐Relationship of “things”. Ops Process in a model

Algorithms‐ ML/AI,Inference, Recommendations,Entity Recognition

Shortest PathCentrality Measure Clustering PathK‐NN

Applications Machine Learning

Semantic Search

Dashboard

Knowledge Share

M&S Analytics

Knowledge Management

XML

SQL

CSV

JSON

Relational DB

Data Analytics‐calculate exact covariance matrix, precise numerical balancing of eachdata point in any data cloud 

100% numerical certainty while making assumed data‐distribution models, standard deviations and confidence intervals obsolete

Draft Use Case 2 – Mission Analysis 

External Enablers

EWO

PLC2

PLTX

Targeting WG

IPB WG

 Sensors

Data 

COA Development

   PLC 2 COP

 Modify Work Space

PL  TX

Prepare Mis sion 

Anal ysi s Brief

Publis h Updated EW R unning Estimate

Terrain Geomet r

y

PL E miss ion Controls

PL Cap abi lit

y

RFIs

PL MA support plan

CDR

EWO

P L  Resources Ava il ab le

PL Locat ion

PL C onf ig/statu s

PL  As set A llocation 

Table

S‐ 2

S‐3

FSO

Jamming Data

Collection Data

Start  MSYes

PL C onfi guration

NO=dat a

S‐4

Location of assets 

in support of fires

Recommend P IRs

R equest Coll ection DataExter nal  support

Optim ize COA

Higher HQ Plan

Warno  1

Type of Ops AOR Move  an d 

Re con t imeTimeline

CDRs  Ini tial Guidan ce

Knowle dge Product s f rom 

Externa l 

Higher  HQ I ntel an d Knowledg e 

Produ cts

Warno 2

R isk Gu idance

 UNIT  AOWf F 

Pr ior ities

Co lle ct ion  Plan

De ce ptio n Plan

Timeline

Mo vement

Sp ecif ic Pr ior ities

Missio n Sta tement

Commanders IntentTO CC IR s/EEF Is

EP Planning

EA Plan ning

ES Plannin g

EW MA

EW Co llection Requir ements

EW Target li st

EW Intel RequirementsIniti al Anal ys is 

of E nemy C2

L ist E W task for  ES EW R E

EW Assumpt ions

EW Co nstrai nts

EW planning Guidan ce

EW Suppo rt  Requirements

EW M A  repo rt

IPB B attlefi eld Framework

IPB Movement analysis

METT‐C

OCOKA

HPTL

HVTsEW 

Targets

AGM

TAIs Ammunitions

Analyze BF Environment

Enemy Ter ra in

HVT

Gap s in  PIR s

E xternal Asset s f or  use (Ex tern al SA)

Ter rain Analysis

ENEMY COAs

Start Targe ting WG

Target Value Analysis

ATO R equest

I ntel  Limits to  AOI

Star t  IC planOAKOC*

*observations and fields of fire, avenues of approach, key terrain, obstacles, and cover and concealment 

MNVR P lan

Scheme of MNVRMNVR Timel ineUnit Lanes

EW effects

Tar  Selection Standar d

Att ack Guida nce Matrix  

P lan ning

D3A‐Decide

Initi al  IPB

Task acqu isition  

asset s

Atta ck Means

T arge t MOEs

Target  Set L is t

EW MOEs

EW Act ivities

EW Detec t Activit ies

PGM Data

Target  L ist

Weapon sys  L ist

GE O regio ns for  EW Threat

Sensor co verag e

Pr im/sec Target Line s

Recommend PI RS

Process EEI

Process RFIs

GPS Protect  plan

GPS Hardenin

g

PL Ass et L ist

EMS Environm

en t survey

NO =RFI

PL Hardenin

g

PL Overl ay

Fires Tasks Cy ber/EW.PNT Tasks

Specific HPT

Desired Ef fect

Rest rictio ns

How to  Enga ge

T iming En gageme nt Fires   Ops 

Sync

Recomme nds Targ ets to 

de tect , Acqui re a nd at tack

I D Comb at Asse ssmen t Re quirements

Fi res R E

Weapon  system 

accuracy req

Size  o f En emy  activit y

S tatu s  of activit y

Timeliness of inf o

S‐3 RE

MS Resul ts

Calcu la te Risks

I denti fy 

Ta sks

I denti fy Co nstraints

Analy ze Fires Traj ector ies

Intel  RE

Legend‐

P rocess

Do cumnet

Data  P ro duced

Sta rt /en d eff ort

De ci sio n

Relat ionship

P LC 2 Externa l rea ltion ship

Neg ative rel ation ship

EWO

Acto r

Externa l  inpu t

I n‐di rect  relat ionships

Draft Use Case 2 – Mission Analysis 

External Enablers

EWO

PLC2

PLTX

Targeting WG

IPB WG

 Sensors

Data 

COA Development

   PLC 2 COP

 Modify Work Space

PL  TX

Prepare Mis sion 

Anal ysi s Brief

Publis h Updated EW R unning Estimate

Terrain Geomet r

y

PL E miss ion Controls

PL Cap abi lit

y

RFIs

PL MA support plan

CDR

EWO

P L  Resources Ava il ab le

PL Locat ion

PL C onf ig/statu s

PL  As set A llocation 

Table

S‐ 2

S‐3

FSO

Jamming Data

Collection Data

Start  MSYes

PL C onfi guration

NO=dat a

S‐4

Location of assets 

in support of fires

Recommend P IRs

R equest Coll ection DataExter nal  support

Optim ize COA

Higher HQ Plan

Warno  1

Type of Ops AOR Move  an d 

Re con t imeTimeline

CDRs  Ini tial Guidan ce

Knowle dge Product s f rom 

Externa l 

Higher  HQ I ntel an d Knowledg e 

Produ cts

Warno 2

R isk Gu idance

 UNIT  AOWf F 

Pr ior ities

Co lle ct ion  Plan

De ce ptio n Plan

Timeline

Mo vement

Sp ecif ic Pr ior ities

Missio n Sta tement

Commanders IntentTO CC IR s/EEF Is

EP Planning

EA Plan ning

ES Plannin g

EW MA

EW Co llection Requir ements

EW Target li st

EW Intel RequirementsIniti al Anal ys is 

of E nemy C2

L ist E W task for  ES EW R E

EW Assumpt ions

EW Co nstrai nts

EW planning Guidan ce

EW Suppo rt  Requirements

EW M A  repo rt

IPB B attlefi eld Framework

IPB Movement analysis

METT‐C

OCOKA

HPTL

HVTsEW 

Targets

AGM

TAIs Ammunitions

Analyze BF Environment

Enemy Ter ra in

HVT

Gap s in  PIR s

E xternal Asset s f or  use (Ex tern al SA)

Ter rain Analysis

ENEMY COAs

Start Targe ting WG

Target Value Analysis

ATO R equest

I ntel  Limits to  AOI

Star t  IC planOAKOC*

*observations and fields of fire, avenues of approach, key terrain, obstacles, and cover and concealment 

MNVR P lan

Scheme of MNVRMNVR Timel ineUnit Lanes

EW effects

Tar  Selection Standar d

Att ack Guida nce Matrix  

P lan ning

D3A‐Decide

Initi al  IPB

Task acqu isition  

asset s

Atta ck Means

T arge t MOEs

Target  Set L is t

EW MOEs

EW Act ivities

EW Detec t Activit ies

PGM Data

Target  L ist

Weapon sys  L ist

GE O regio ns for  EW Threat

Sensor co verag e

Pr im/sec Target Line s

Recommend PI RS

Process EEI

Process RFIs

GPS Protect  plan

GPS Hardenin

g

PL Ass et L ist

EMS Environm

en t survey

NO =RFI

PL Hardenin

g

PL Overl ay

Fires Tasks Cy ber/EW.PNT Tasks

Specific HPT

Desired Ef fect

Rest rictio ns

How to  Enga ge

T iming En gageme nt Fires   Ops 

Sync

Recomme nds Targ ets to 

de tect , Acqui re a nd at tack

I D Comb at Asse ssmen t Re quirements

Fi res R E

Weapon  system 

accuracy req

Size  o f En emy  activit y

S tatu s  of activit y

Timeliness of inf o

S‐3 RE

MS Resul ts

Calcu la te Risks

I denti fy 

Ta sks

I denti fy Co nstraints

Analy ze Fires Traj ector ies

Intel  RE

Legend‐

P rocess

Do cumnet

Data  P ro duced

Sta rt /en d eff ort

De ci sio n

Relat ionship

P LC 2 Externa l rea ltion ship

Neg ative rel ation ship

EWO

Acto r

Externa l  inpu t

I n‐di rect  relat ionships

Collection Data

/Weapons/Sensor Data

Doctrine/Orders

Multi‐domains Data

Joint Warfare Tasking

Intel Data Sources Conduct 

Test

Build Prototype

Develop Software

Develop Rqmts.

Design Interfaces

C O l

knowledge)

CEMA Ontology(knowledge graph, cause and effect, 

domain knowledge)

Use Cases

Data Model

Edge Data Analytics

Edge Data Analytics

Edge Data Analytics

Edge Data Analytics

Edge Data Analytics

Edge Data Analytics

Edge Data AnalyticsEdge Data 

Analytics

Edge Data Analytics

Edge Data Analytics

Edge Data Analytics

Edge Data Analytics

Edge Data Analytics

Edge Data Analytics

Results: an Explicit Representation of a CEMA Domain

data knowledge understanding Processus Group

Questions?Points of Contact: Matthew Maher (Maherm@processusgroup.org) Rob Orlando (Orlandor@processusgroup.org)