Research Status of Artificial Neural Network and Its Application

Assumption in Aviation System

SEMINAR REPORT

Submitted for the Partial Fulfilment of the Requirement of the

DEGREE
of
BACHELOR OF TECHNOLOGY
ELECTRICAL ENGINEERING

Guided by: Submitted By:

Mr. Tarun Kumar Chheepa Ms. Mamta Mishra
Assistant Professor (IV B. Tech., VIII Sem.)

Department of Electrical Engineering

Swami Keshvanand Institute of technology Management & Gramothan

Jaipur 2019-2020

1
 CERTIFICATE

This is to certify that this seminar report entitled

“Research Status of Artificial Neural Network and Its Application Assumption
in Aviation System” being submitted by Ms. Mamta Mishra(IV B. Tech., VIII
Sem.) for the partial fulfillment of the requirement of the Degree of Bachelor of
Technology in Electrical Engineering of Swami Keshvanand Institute of technology
Management & Gramothan Jaipur is a record of the seminar work carried out by
him.

Sh. Dr. Dhanraj Chitara

Head of Department

Date: 23.04.2020
Place: JAIPUR

2
 ACKNOWLEDGMENT

It is my proud privilege and duty to acknowledge the kind of help and guidance
received from several people in preparation of this report. It would not have been
possible to prepare this report in this form without their valuable help, cooperation
and guidance.

First and foremost, I offer my sincere phrases of thanks with innate humility to the
guide of my seminar Mr. Tarun Kumar Chheepa, Assistant Professor,
Department of Electrical Engineering, SKIT, Jaipur for his impressive
suggestions, encouragement and guidance throughout the period of this report.

I would also like to mention my deep regards to Dr. Dhanraj Chitara, Head
Department of Electrical Engineering, SKIT, Jaipur for his kind cooperation and
support and allowing me to carry seminar work freely and effectively.

Lastly, I would like to dedicate my special thanks to all the faculties of Department
of Electrical Engineering for providing me all the necessary help whenever needed.

Ms. Mamta Mishra

(IV B. Tech., VIII Sem.)

3
 ABSTRACT
The application of Artificial Neural Networks in Aircraft Maintenance, Repair and Overhaul (MRO).
MRO solutions are designed to facilitate the authoring and delivery of maintenance and repair
information to the line maintenance technicians who need to improve aircraft repair turnaround time,
optimize the efficiency and consistency of fleet maintenance and ensure regulatory compliance. The
technical complexity of aircraft systems, especially in avionics, has increased to the point at which it
poses a significant troubleshooting and repair challenge for MRO personnel. As per the existing
scenario, the MRO systems in place are inefficient

the centralization and integration of the MRO database to increase its efficiency. Moreover, the
implementation of Artificial Neural Networks in this system can rid the system of many of its
deficiencies. In order to make the system more efficient we propose to integrate all the modules so as
to reduce the efficacy of repair.

. How artificial intelligence (AI) makes current airship framework incorporates an assortment of
programmed control framework that guides the flight team in route, flight administration and enlarging
the security quali- ties of the plane, and how building aircraft engine diagnostics ontology, air traffic
management, and constraint programming (CP) is useful in ATM setting. How flight security can be
enhanced through the advancement and usage of mining, utilizing its outcomes and knowledge-based
engineering (KBE) approach in an all-encompassing methodology for use in airship reasonable
outline, is discussed.

4
 INDEX

S.NO CONTENT PAGE NO

1 Chapter1
Introduction 6

2 Chapter 2
Current aviation system 9

3 Chapter 3
Artificial Neural Network(ANN) 11

3.1 Neural network 11

3.2 ANN characteristics 12

3.3 Advantage of ANN 13

3.4 Limitation of ANN 13

3.5 Application of ANN 14

4 Chapter 4
4.1 Self organizing maps 15

4.2 Multidimensional scaling 15

4.3 Fuzzy logic 15

5 Chapter 5
Application of ANN in aviation 16

6 Chapter 6
Proposed aviation system 18

7 Chapter 7
Conclusion 20

8 Chapter 8
Reference 21

5
CHAPTER 1
INTRODUCTION
This chapter will addresses challenges with Artificial Intelligence (AI) systems in aviation; It gets
very challenging for the industry now to keep its costs as low as possible and generate maximum
revenue. For this to happen the industry needs to ensure that its asset utilization is optimum. Therefore
the maintenance management system of the existing aircrafts needs to be spot on to ensure that
they spend maximum time in air so as to make the best use of its machinery. Hence the
Maintenance, Repair and Overhaul (MRO) services need to be very efficient so that the aircraft’s
‘hangar- time’ for MRO purposes is as low as possible.

MRO implementation in the aviation industry implies the improvement of processes from
the hanger to the flying hours of the aircraft by creating a framework for its total asset management.
MRO is responsible for providing on site technical support and engineering disposition in order to
reduce aircraft problems. It could likewise mean capacity anticipating and cautioning of approaching
disappointment in computerized motor screen information. Climate estimating is somewhere else
where AI will bear some significance with aeronautics. Pilots require significantly more than simply
climate picture and diversionary land- ing strip information. Existing exploration in AI is a bit of
research by each examination association, classes, and blended exchanges. Regardless of cynics,
aircrew can watch inspirations to be amped up for AI which will engage planes to outline proactive
and choose, because of machine learning and neu- ral systems. Till now, all aircraft structures were to
empower a pilot to rehearse power over carrier and systems. The accompanying stage is veritable
essential authority endeavors. This will require significant machine learning and neural frameworks to
make exceptional estimations that undertaking to ‘think’ like a human. Thus, the point of this part is
to give an outline of how the Interactive Fault Diagnosis and Isolation System (IFDIS) uses a control
based ace structure made using gathering information from reports and ace appeal from specialists. The
execution structure will in like manner supplant particular experts. The structure empowers the general
workers to talk with the system and avoid slip-ups, wrong ends or addressing one of the specific
experts. The Air Traffic Controllers (ATC) prepare by offering headings to the manufactured pilots
and correspondingly for pilots to react to the ATC. The projects fuse the discourse programming
made by utilizing neural systems. AI is about ‘man-and-machine’; not ‘man-versus machine’. The field
of mechanical technology is firmly identified with AI; knowledge is required for robots to have the
6
capacity to deal with so many errands as protest control and route. Issues to unravel incorporate possess
localization, mapping what is near and movement or way arranging. Two or three trusts that human
features, for instance, fake insight or a fabricated personality may be required. Starting late, the growing
air development asks for, and the present airplane terminal direction help capacities are limited,
contradicting interest and supplies have ended up being continuously prominent. ATC structure is a
staggering structure; the usage of framework proliferation of an aeronautics expert system is a basic
research gadget. Existing proliferation instruments have two issues, one, in perspective of single
focused hard to do broad scale reenactment of minute amusement; Second, the nonappearance of a
straightforward controller reenactment association limits (Hwang, Kim and Tomlin, 2007) for these two
request, the appropriated man-made consciousness multi-specialist advancement in air terminal
direction diversion; and used Java lingo to develop a national avionics expert system in perspective of
the field of the main model multi-operator common control propagation. Close by the relentless change
of basic flight, the significant scale advancement of various plane terminal workplaces, the central air
terminals are changing from the primary single-air terminal area to the multi-air terminal district with
a particular ultimate objective to achieve the examination of the honest as far as possible assessment
of the jumbled multi-air terminals terminal zone, all the more great and complete the process of
mirroring game plan of the multi-plane terminals terminal region ought to be made. A Multi-agent
system (MAS) is an automated structure made out of different participating shrewd Agents inside an
area. Multi-operator systems can be used to deal with issues that are troublesome or unfathomable for
an individual special- ist or a strong structure to get it. Information may fuse some methodic, down
to earth, procedural or algorithmic chase.

Air development working model of multi-air terminal zone, which relies upon the recurring pattern
question of terminal zone confine and the status of research on air movement progression, was inspected
by applying appropriated artificial intellectual prowess multi-operator theories and methodologies, and
the working strategy for the multi-gather oral joint efforts between the aircraft, controllers, and the air
terminal and so forth was pondered. The multi-specialist framework Simulation mode is created, and the
specific arrangement models of some canny operators, for instance, flight operator, controller special-
ist and air terminal control districts specialist were presented (Ma, Tao, Zhu and Lü, 2014). In general
framework and operational plan of the multi-air a terminal area air action sharp generation system was
made, which relies upon the structures of the Multi-operator and finally, a foundation which is for inves-

7
tigating the real action conditions of the multi-air terminal locale and the affirmation of the air develop-
ment keen multiplication game plan of the multi-air terminal district has be laid. The inspiration driving
instrument flight procedure is to guarantee the security and improve the profitability of air movement
errands in the terminal district, and flight approach design is a coherent organizing and sensible layout
work for the passage and departure air courses and the framework involved them.

It also acts as a technical liaison with aircraft engine and component manufacturers
about overhaul, repair and its modifications as required by aircraft policies, maintaining the system
performance and recommending action to correct abnormal trends to improve the engine reliability.
It also develops engineering modifications which retrofits to the fleet in accordance with OEM
service bulletins. The complex business of aircraft maintenance, repair and overhaul makes extremely
high demands on quality, security and accountability. IT solutions for this area are focussing
increasingly on supporting these highly sensitive processes efficiently and cost- effectively. This
system though has its flaws, it is inefficient and there is a vast scope of improvement in this field.
The Original Equipment Manufacturer (OEM) manual is an encyclopedia on the product. It contains
all the information about the product starting from its components, features, troubleshooting,
repair and its lifespan. Presently different products have different OEM manuals and if this
entire data is centralized then each products database will support the other thereby filtering the
data and increasing the probability of decision making and support systems.

Application of Artificial Neural Networks (ANN) in the MRO will help us get rid of many of its
superfluous data and help us estimate probability at the point and the extent of damage caused in
an aircraft. Neural Networks can help better detect and estimate aircraft unit fault diagnosis, corrosion
detection in ageing materials, real time assessment of engine conditions and source of damage to
unconventional structures. The application of this ANN in the MRO will help the system to work
more efficiently and if all the different modules are integrated into a single computed database then
that will further increase the accuracy of the system.

8
CHAPTER 2
CURRENT AVIATION SYSTEM

Fig. 1 shows the block diagram of the current aviation system. As per the existing system, there is a
time to time scheduled checking of the aircraft. Depending upon the inspection carried out faults are
detected. As of now, each product of an aircraft comes with an OEM manual which is provided by
the product manufacturer. The OEM manual contains detailed information about product, its
component and types and its related issues and its proper diagnosis.

This OEM manual needs to be updated time to time as per the instructions issued by the regulatory
body. Based on this data the MRO assesses the information and gives the input to the technicians
regarding fault assessment.The technicians then act accordingly as per the inputs given by the
MROs to them. This system though has its own flaws. It is highly inefficient. There is no real time
assessment of the data.

As clearly shown in Fig.2, a radical amount of data is either incorrect, hard to find or incomplete.In
order to increase its efficiency we propose the centralization of the data given by the OEM
manual and the integration of each of the parts. This method will have better probability of finding the

9
problem node in the aircraft and it’s most suited and immediate repair. Moreover, we require a
system which can give the near to accurate probability of any fault at any point in an aircraft and its
most suitable, cost effective and viable diagnosis.

One of the methods by which this can be made possible is by introducing the concept of Artificial
Neural Networks (ANN) to the system.

Figure 2: Perceived Problems in Aircraft Maintenance Information

10
CHAPTER 3
Artificial Neural Network (ANN)
3.1 NEURAL NETWORKS
An Artificial Neural Network (ANN) is a mathematical model or computational model based on
biological neural networks. It consists of an interconnected group of artificial neurons and processes
information using a connectionist approach to computation. In more practical terms neural
networks are non- linear statistical data modeling tools. They can be used to model complex
relationships between inputs and outputs or to find patterns in data. Since neural networks are best
at identifying patterns or trends in data, they are well suited for prediction or forecasting.

Artificial Neural Networks are relatively crude electronic models based on the neural structure of the
brain. The brain basically learns from experience. It is natural proof that some problems that are
beyond the scope of current computers are indeed solvable by small energy efficient packages. This
brain modelling also promises a less technical way to develop machine solutions. This new approach
to computing also provides a more graceful degradation during system overload than its more
traditional counterparts.

These biologically inspired methods of computing are thought to be the next major advancement in
the computing industry. Even simple animal brains are capable of functions that are currently
impossible for computers. Computers do rote things well, like keeping ledgers or performing complex
math. But computers have trouble recognizing even simple patterns much less generalizing those
patterns of the past into actions of the future. Intelligence is the ability to think, to imagine, creating,
memorizing, and understanding, recognizing patterns, making choices, adapting to change and learn
from experience. This is the branch of computer science concerned with making computers behave
like humans. Hence it is called as 'Artificial Intelligence.

11
3.2 ANN CHARACTERISTICS

Basically Computers are good in calculations that basically takes inputs process then and after that
gives the result on the basis of calculations which are done at particular Algorithm which are
programmed in the software’s but ANN improve their own rules, the more decisions they make, the
better decisions may become. The Characteristics are basically those which should be present in
intelligent System like robots and other Artificial Intelligence Based Applications. There are six
characteristics of Artificial Neural Network which are basic and important for this technology which
are showed with the help of diagram

Parallel
Processing
Network Collective

Structures Solution

CHARACTERISTICS OF
ANN

Fault Learning Ability

Tolerance Distributed
Memory

12
3.3 ADVANTAGE OF ANN
1. Adaptive learning: An ability to learn how to do tasks based on the data given for training or
initial experience.
2. Self-Organisation: An ANN can create its own organisation or representation of the
information it receives during learning time.
3. Real Time Operation: ANN computations may be carried out in parallel, and special
hardware devices are being designed and manufactured which take advantage of this capability.
4. Pattern recognition: is a powerful technique for harnessing the information in the data and
generalizing about it. Neural nets learn to recognize the patterns which exist in the data set.

5. neural networks are flexible in a changing environment. Although neural networks may take
some time to learn a sudden drastic change they are excellent at adapting to constantly changing
information.

6. Neural networks can build informative models whenever conventional approaches fail.
Because neural networks can handle very complex interactions they can easily model data which
is too difficult to model with traditional approaches such as inferential statistics or programming
logic.
7. Performance of neural networks is at least as good as classical statistical modelling, and better
on most problems. The neural networks build models that are more reflective of the structure of
the data in significantly less time.

3.4 LIMITATIONS OF ANN

In this technological era everything has Merits and some Demerits in others words there is
a Limitation with every system which makes this ANN technology weak in some points.
The various Limitations of ANN are:-
1) ANN is not a daily life general purpose problem solver.
2) There is no structured methodology available in ANN.
3) There is no single standardized paradigm for ANN development.
4) The Output Quality of an ANN may be unpredictable.
5) Many ANN Systems does not describe how they solve problems.

13
6) Black box Nature
7) Greater computational burden.
8) Proneness to over fitting.
9) Empirical nature of model development.

3.5 APPLICATIONS OF ANN

 Data Mining: Discovery of meaningful patterns (knowledge) from large volumes of data.
 Expert Systems: A computer program for decision making that simulates thought process
of a human expert.
 Fuzzy Logic: Theory of approximate reasoning.
 Artificial Life: Evolutionary Computation, Swarm Intelligence.
 Artificial Immune System: A computer program based on the biological immune system.
 Aviation: Airlines use expert systems in planes to monitor atmospheric conditions and
system status. The plane can be put on autopilot once a course is set for the destination.
 Weather Forecast: Neural networks are used for predicting weather conditions. Previous
data is fed to a neural network, which learns the pattern and uses that knowledge to predict
weather patterns.

 Computer Science: Researchers in quest of artificial intelligence have created spin offs
like dynamic programming, object oriented programming, symbolic programming,
intelligent storage management systems and many more such tools. The primary goal of
creating an artificial intelligence still remains a distant dream but people are getting an
idea of the ultimate path, which could lead to it.

14
CHAPTER 4
4.1 SELF ORGANISING MAPS (SOM)
The self-organizing map (SOM) is an excellent tool in exploratory phase of data mining. It projects
input space on prototypes of a low-dimensional regular grid that can be effectively utilized to visualize
and explore properties of the data. When the number of SOM units is large, to facilitate quantitative
analysis of the map and the data, similar units need to be grouped, i.e., clustered . Self- organizing
map (SOM) is a type of artificial neural network that is trained using unsupervised learning toproduce
a low-dimensional (typically two dimensional), discrete representation of the input space of the
training samples, called a map. The map seeks to preserve the topological properties of the input space
This makes SOM useful for visualizing low-dimensional views of high- dimensional data, akin to
multidimensional scaling.

4.2 MULTI-DIMENSIONAL SCALING

It is a set of related statistical techniques often used in information visualization for exploring
similarities or dissimilarities in data. MDS is a special case of ordination. An MDS algorithm starts
with a matrix of similar items, then assigns a location of each item in a low- dimensional
space, suitable for graphing or 3D visualization .

4.3 FUZZY LOGIC

Fuzzy logic is a form of multi-valued logic derived from fuzzy set theory to deal with reasoning
that is approximate rather than precise. Just as in fuzzy set theory the set membership values
can range (inclusively) between 0 to 1, in fuzzy logic the degree of truth of a statement can
range between 0 to 1 and is not constrained to the two truth values i.e. true or false as in classic
predicate logic. And when linguistic variables are used, these degrees may be managed by specific
functions.

Fuzzy logic is a new way of expressing probability. While both fuzzy logic and probability theory
can be used to represent subjective belief, fuzzy set theory uses the concept of fuzzy set membership.
The fuzzy probability can also be generalized as a possible model.

15
CHAPTER 5
APPLICATION OF NEURAL NETWORKS WORK IN AVIATION
Neural network has a great role in aircraft fault diagnosis. It uses historical data stored to analyze
the condition and trace the fault. However, neural networks cannot be the deciding factor as it is
based on probability. Hence it helps man to decide the problem and work upon it by giving the
probability of damage.

The system works according to the following procedure:

1. The information regarding the aircraft is fed into the neural system.
2. The system analyzes the data and checks for historical models corresponding
to the data.
3. Then based on the records, the system throws out probabilities.
4. An experimental model is compared to the result of the ANN model.

This neural system gives man a better idea of the current problem or condition and hence increases
efficiency of the whole MRO system.

This prediction of fault diagnosis is based on the Self-Organizing Map (SOM). SOM is a type of
artificial neural network that is trained to produce a discrete representation of the input space of
the training samples, called a map. Any input may affect many parts of an aircraft. SOM separates
the input for the different parts hence giving an output for each part .

SOM uses Multi Dimensional Scaling (MDS) in order to create its map. MDS is a set of related
statistical technique often used in information visualization for exploring similarities or dissimilarities
in data. MDS is a special case of ordination i.e. data clustering. It clusters similar data near each
other and dissimilar data far from each other.

For high performance aircraft systems, there is a need to achieve real-time and continual assessment
of aircraft condition. It is almost impossible to predict a damage of component correctly since
operating conditions might be different. Hence these conditions must be accounted for.

16
An aircraft is affected mainly by the following factors:

1. Flying Hours
2. Aircraft Repair History
3. Airport Location
4. Climate
5. Weather

Depending on these factors (called variables in the ANN program) and compared with the OEMs,
predictions are made as to the wear and tear of the parts, the next date for servicing, and replacement
of any part if needed.

• Any increase in temperature or altitude means a decrease in the aircraft's optimum performance.
At high elevation airports, an airplane requires more runway to take off. Its rate of climb will
be less, its approach will be faster, because the true air speed will be faster than the indicated air
speed and the landing roll will be longer.
• Air density also decreases with temperature. Warm air is less dense than cold. As a result, on a hot
day, an airplane will require more runway to take off, will have a poor rate of climb and a faster
approach and will experience a longer landing roll.
• The combination of high temperature and high elevation produces a situation that aerodynamically
reduces drastically the performance of the airplane. The horsepower output of the engines decrease
because its fuel-air mixture is reduced. The propeller develops less thrust because the blades, as
airfoils, are less efficient in the thin air. The wings develop less lift because the thin air exerts
less force on the airfoils. As a result, the take-off distance is substantially increased climb
performance is substantially reduced and may, in extreme situations, be non-existent.
• Depending on the number of hours an aircraft has flown in the past, and the number of repairs the
aircraft has had in the past, the efficiency of the airplane changes. This calls for different
treatment to planes in different conditions.

The neural network system analyzes these data of an aircraft and can hence suggest possible treatments
suited to that aircraft [10]. Hence diversity can be maintained and performance can be enhanced.

17
CHAPTER 6
PROPOSED AVIATION SYSTEM
The proposed system as shown in Fig.3 applies the concept of Artificial Neural Networks (ANN). In
this system when there is any problem at any part in an aircraft then that component is reviewed. After
that the OEM manuals are referred and its possible problem area and its repair are estimated and its
output is fed into the ANN as an input.

Figure3: Block diagram of proposed system

In the other half we apply the concept of Artificial Neural Network (ANN) to the system. The various
factors on which the performance of an aircraft depends such as repair history, weather, climate,
airports location, flying hours etc. are taken as inputs. We also need a collection of the historical data
of all these variables and which will also be updated in real time as per its assessment of the result
after each evaluation. These variables supported by the historical data and the input from the OEM
manual are then given to the ANN. The ANN works on the basis that the high dimensional data input
is converted to low dimensional with the help of Self Organizing Map (SOM) technique. The

18
data is then clustered with the help of Multi Dimensional Scaling (MDS), in different categories
in relevance to the other data inputs. After that relevant logic is applied in the system to create
probability prediction model of the possible percentage probability of damage in all the possible nodes
of an aircraft. Many irrelevant data is eradicated by this system based on the historical data and thus
the working of the system is also faster.

Now this Neural Network assesses both the input from the OEM manual and the data given by
the variables and then formulates the output. The output gives the possible problem nodes in an aircraft
and its repair options which is more accurate than the output given by the OEM manual. The output
of the Artificial Neural Network is then fed back into the historical data as repair history which
prepares the system for further reference thus building a database. This output will then be given to
the technicians who will act accordingly and rectify the problem.

Advantages over the existing system:-

• Less involvement of human interface.

• Real time updation of records.
• More accurate predictions of damage.
• Helps in cost minimization of maintenance.
• Better decision making and support systems.

19
CHAPTER 7
CONCLUSION
The investigations carried out confirm that the usage of ANN offers rich opportunities for
the diagnostics of air engines on board in real time mode. It will help detect the problem in an aircraft
in a more accurate and efficient manner. Application of ANN to the system can greatly modify the
creditability of the system. The survey shows that MRO spend are almost universally expected
to increase, at just over 6% annually over the next five years. And if its efficiency is increased then
that will help in cost minimization and better asset management for the airlines thereby increasing
the performance for the aviation industry.

How AI influences current air to dispatch system joins a variety of modified control structure that aides
the flight group in course, flight organization and extending the security characteristics of the plane
and how constructing airship motor diagnostics cosmology, air activity administration and imperative
programming is valuable in ATM setting. How flight security can be upgraded through the progression
and use of mining, using its results and Knowledge-Based Engineering (KBE) approach blend of a couple
of educates in a widely inclusive strategy for use in carrier sensible blueprint is examined

20
CHAPTER 8
REFERENCES
[1] Kohonen - books.google.com (2001).
[2] Frank Jackman - MRO Forecast
[3] John A. Bullimaria - Introduction to Neural Networks.
[4] Joseph B. Kruskal – Multi Dimensional Scaling.
[5] D.F. Garret – Aircraft System and Components.
[6] Dale Hurst – Aircraft System Maintenance.
[7] Basappa, Jategaonkar R.V. (1995) - Aspects of feed forward neural network modeling
and its application to lateral-directional flight data.
[8] Ghosh A.K., Raisinghani S.C., Khubchandani S. (1998) - Estimation of aircraft
lateral- directional parameters using neural networks.
[9] Hornik K., Stinchcombe M., White H. (1989) - Multi layer feed forward neural
networks are universal approximators.
[10] Maine R.E., Iliff K.W. (1986) - Identification of dynamic system- application to aircraft.
[11] Jack M. Zurada – Neural Networks in Computer Intelligence.

[12] Bradshaw, J.A., Carden, K.J., Riordan, D., 1991. Ecological ―Applications Using a Novel
Expert System Shell.
[13] Rich ,Knight and B Nair, “Artificial Intelligence”, TMH Publication
[14] Jacek M . Zurada, Introduction to Artificial Neural System”, Jaico publishing house.
[15] Ajith Abraham, “Artificial Neural Networks”, Stillwater,OK, USA, 2005.
[16] Carlos Gershenson, “Artificial Neural Networks for Beginners”, United kingdom.
[17] Almubayed, A., Hadi, A., & Atoum, J. (2015). A Model for Detecting Tor Encrypted
Traffic using Supervised Machine Learning. International Journal Of Computer
Network And Information Security, 7(7), 10–23. doi:10.5815/ijcnis.2015.07.02

[18] Amine Chatti, M. (2012). Knowledge management: A personal knowledge network

perspective. Journal of Knowledge Management, 16(5), 829–844.
doi:10.1108/13673271211262835

21
[19] Aviation Human Factors Related Industry News 1Parts of this section are compiled from
“Aviation Human Factors Industry News” and reproduced with permission of Roger
Hughes. (2015). Aviation Psychology and Applied Human Factors, 5(1), 67-69.
doi:10.1027/2192-0923/a000077

[20] Bobek, S. (1992). A framework for integrating decision support systems into office
information systems.
[21] Decision Support Systems, 8(3), 211–216. doi:10.1016/0167-9236(92)90015-H

[22] Gan, X., Tang, X., & Gao, J. (2013). Missile Autopilot Design Based on Fuzzy Self-
Tuning Immune PID Control. Advanced Materials Research, 739, 550–554. .
doi:10.4028/www.scientific.net/AMR.739.550

[23] Grabbe, S., Sridhar, B., & Mukherjee, A. (2010). Evaluation of an Integrated Traffic
Flow Management Decision Making Approach. Air Traffic Control Quarterly, 18(4),
331–358. doi:10.2514/atcq.18.4.331

[24] Hui, W., Hu, J., & Shyue, K. (2008). Role of coordinates in computational fluid
dynamics. International Journal of Computational Fluid Dynamics, 22(1-2), 3–9.
doi:10.1080/10618560701737112

[25] Hwang, I., Kim, J., & Tomlin, C. (2007). Protocol-Based Conflict Resolution for Air Traffic
Control.
[26] Air Traffic Control Quarterly, 15(1), 1–34. doi:10.2514/atcq.15.1.1

[27] Jain, A., & Kumar, A. (2017). Traffic Congestion Management System: An
Approach with Machine Learning. IMS Manthan, 12(01).
doi:10.18701/imsmanthan.v12i01.10338

[28] Jeffery, L., & Rhodes, G. (2011). Insights into the development of face recognition
mechanisms revealed by face aftereffects. British Journal of Psychology, 102(4), 799–
815. doi:10.1111/j.2044-8295.2011.02066.x PMID:21988385

[29] Juneja, P., & Kashyap, R. (2016). Optimal approach for CT image segmentation using
improved energy based method. International Journal of Control Theory and
Applications, 9(41), 599–608.

22
[30] Kashyap, R. (2018). Object boundary detection through robust active contour based
method with global information. International Journal Of Image Mining, 3(1), 22.
doi:10.1504/IJIM.2018.093008

[31] Kashyap, R., & Gautam, P. (2013). Microarray image segmentation using improved GOGAC
method.
[32] International Journal on Computer Science and Engineering, 2(4), 67–74.

[33] Kashyap, R., & Gautam, P. (2015). Modified region based segmentation of medical
images. International Conference on Communication Networks (ICCN), 209–216.
10.1109/ICCN.2015.41

[34] Kashyap, R., & Gautam, P. (2016). Fast level set method for segmentation of medical
images. In Proceedings of the International Conference on Informatics and Analytics
(ICIA-16). ACM. 10.1145/2980258.2980302

[35] Kashyap, R., & Gautam, P. (2017a). Fast Medical Image Segmentation Using Energy-
Based Method. Biometrics. Concepts, Methodologies, Tools, and Applications, 3(1),
1017–1042. doi:10.4018/978-1- 5225-0983-7.ch040

23