This document discusses information fusion in distributed systems. It defines information fusion as combining data or information from multiple sources to improve detection, identification, or characterization. It describes two types of fusion - data fusion, which combines raw sensor data, and information fusion, which combines already processed data. It also discusses different classifications of fusion techniques, including the level of abstraction (low, medium, high), relationships between data sources (complementary, redundant, cooperative), and Dasarathy's classification. Finally, it outlines common information fusion architectures like centralized, decentralized, and hierarchical, and applications of information fusion.

1. INFORMATION FUSION AND MAP
BUILDING IN DISTRIBUTED SYSTEMS
Submitted By :
PARESH SAO(11118049)
SHIVANI SINGH(11118068)
TARUN BEHRA(11118079)
VINIT PAYAL(11118085)
VII SEM
INFORMATION TECHNOLOGY
NIT RAIPUR
11/19/2014 INFORMATION FUSION 1

2. What Is Fusion ?
Fusion Is the process of the joining two or more things together to form a single entity .
Two Types of fusions in the field of computer science:-
1. Data Fusion
2. Information Fusion
Data Fusion:-
Data fusion is used for raw data (obtained directly from the sensors)
 Information Fusion:-
Information fusion is employed to define already processed data.

3. Information fusion implies a higher semantic level than data fusion.
Data or information to be fused can be from two sources:-
1. Sensors
2. Databases
The goal of using data/Information fusion in multi sensor environments is to obtain a lower
detection error probability and a higher reliability by using data from multiple sources.

4. Information Fusion:-
Information Fusion is the act or process of combining or associating
data or information from one or more sources to obtain improved information for detection, identification,
or characterization of that entity.
User
node
Communication
Source
node
Data from
Source
Source
node
Fused
data
Source
node

5. Classification of Data Fusion Techniques
1. Classification Based on the Relations between the Data Sources:-
a) Complementary:-
when the information provided by the input sources
represents different parts of the scene and could thus be used to obtain more
complete global information. For example, in the case of visual sensor networks,
the information on the same target provided by two cameras with different fields
of view is considered complementary.
b) Redundant:-
when two or more input sources provide information about the
same target and could thus be fused to increment the confidence. For example,
the data coming from overlapped areas in visual sensor networks are considered
redundant.

6. c) cooperative:-
when the provided information is combined into new
information that is typically more complex than the original information. For example,
multi-modal (audio and video) data fusion is considered cooperative.
2. Classification Based on the Abstraction Levels:-
A. low level fusion
B. medium level fusion
C. high level fusion
D. multiple level fusion

7. A. low level fusion:-
The raw data are directly provided as an input to the data fusion process, which provide more
accurate data (a lower signal-to-noise ratio) than the individual sources;
B. Medium level:-
Characteristics or features (shape, texture, and position) are fused to obtain features that could
be employed for other tasks. This level is also known as the feature or characteristic level
C. High Level:-
This level, which is also known as decision fusion, takes symbolic representations as sources and
combines them to obtain a more accurate decision. Bayesian’s methods are typically employed at this level
D. Multiple level fusion:
This level addresses data provided from different levels of abstraction (i.e., when a
measurement is combined with a feature to obtain a decision) :-

8. 3. Dasarathy’s Classification:-
A. data in-data out (DAI-DAO)
B. data in-feature out (DAI-FEO)
C. feature in-feature out (FEI-FEO)
D. feature in-decision out (FEI-DEO)
E. Decision In-Decision Out (DEI-DEO)

9. A. Data in-data out (DAI-DAO):-
This type of data fusion process inputs and outputs
raw data; the results are typically more reliable or accurate. Data fusion at
this level is conducted immediately after the data are gathered from the
sensors. The algorithms employed at this level are based on signal and image
processing algorithms .
B. data in-feature out (DAI-FEO):-
At this level, the data fusion process employs
raw data from the sources to extract features or characteristics that describe
an entity in the environment .
C. feature in-feature out (FEI-FEO):-
At this level, both the input and output of the
data fusion process are features. Thus, the data fusion process addresses a
set of features with to improve, refine or obtain new features. This process is
also known as feature fusion, symbolic fusion, information fusion or
intermediate-level fusion

10. D. feature in-decision out (FEI-DEO):-
This level obtains a set of features as input
and provides a set of decisions as output. Most of the classification systems
that perform a decision based on a sensor’s inputs fall into this category of
classification.
E. Decision In-Decision Out (DEI-DEO):-
This type of classification is also known as
decision fusion. It fuses input decisions to obtain better or new decisions.

11. INFORMATION FUSION ARCHITECTURE
There are three types of Information fusion Architecture
•Centralized
•Decentralize
•Hierarchal
11/19/2014 INFORMATION FUSION 11

12. CENTRALIZED
• It is the Simplest of all the architecture.
• In this a central processor fuses the reports collected by all other sensing
nodes i.e. the data is collected from different nodes and a centralized node
produces the final output.
Advantage:
Erroneous report(s) can be easily detected.
Disadvantage:
Inflexible to sensor changes and the workload is concentrated at a single
point.
11/19/2014 INFORMATION FUSION 12

13. CENTRALIZED FUSION
Arch. Type : Centralized
Processing : Moderate
Bandwidth : Moderate
Central Timeliness : Poor
node
11/19/2014 INFORMATION FUSION 13

14. DECENTRALIZED
• Data fusion occurs locally at each node on the basis of local
observations and the information obtained from neighboring nodes.
• No central processor node.
Advantages:
Scalable and tolerant to the addition or loss of sensing nodes or
dynamic changes in the network.
11/19/2014 INFORMATION FUSION 14

15. HIERARCHICAL
•Nodes are partitioned into hierarchical levels.
•The sensing nodes are at level 0 and the BS at the highest level.
•Reports move from the lower levels to higher ones.
Advantage:
Workload is balanced among nodes
11/19/2014 INFORMATION FUSION 15

16. HIERARCHICAL INFORMATION FUSION ARCHITECTURE
Arch. Type : Hierarchical
Processing : High at mid levels
Bandwidth : Moderate
Timeliness : Good
Fusion
Node
Sensor data 1
Sensor data 2
Sensor data 3
11/19/2014 INFORMATION FUSION 16

17. BENEFITS FROM INFORMATION FUSION SYSTEM
•Fusion process is necessary most of all to reduce (to filter) input
information through its integration (merging) and generalization.
•Fusion process is necessary to improve accuracy.
Fusion process is necessary to reduce uncertainty.
11/19/2014 INFORMATION FUSION 17

18. INFORMATION FUSION APPLICATION
MILITARY APPLICATION :
•Location and characterization of enemy units and weapons
•High level inferences about enemy situation
•Air to air or surface to air defense
•Ocean monitoring
•Battlefield intelligence
•Strategic warning
NON MILITARY APPLICATIONS:
•Condition based maintenance
•Detection of system faults
•Robotics
•Medical
•Environmental monitoring
•Location and identification
of natural phenomena
11/19/2014 INFORMATION FUSION 18

19. Coding Part
Node 1
Turtle_bot
Node 2
Navigation Ser.
Use data
for
robot navigation
Robot
navigation
Send /scan data
Send /cmd_vel_nev
Map
Generation
Processed /cmd_vel_nev
With
SLAM
11/19/2014 INFORMATION FUSION 19

20. Andersson, L. A. (2008). Multi-robot Information Fusion. Sweden: UniTryck, Link¨oping.
Arwin Datumaya, W. S. (2008). Design and Implementation of Multi Agent-based
information Fusion System for Decision Making Support.
Kiril Alexiev, I. N. (2006). Methods for Data and Information Fusion .
Xiang Li, M. S. (2009). Autonomous Information Fusion for Robust Obstacle Localization
on a Humanoid Robot. The Latin American Robotics Symposium .
11/19/2014 INFORMATION FUSION 20