Air traffic controlling is a very complex task for
the air port personnel. Hence the emphasis on some new
advance computing techniques had always been a great and
important area of research. Hopfield neural networks or
simply Hopfield nets, a widely used popular category of
feedback neural network or recurrent neural networks may
play a very important role in handling issues related to air
traffic control. As Hopfield nets provide a model for the
memory of human brain and therefore they can memorize
the input patterns of any real life problem. Hence these nets
can be efficiently and effectively used for the air space
sectoring problem. In this paper, a way to divide the existing
space scenario in different sectors using Hopfield nets is
presented. It is found that this method is appropriate for
making the sectors of a congested busy air space. The result
shows that algorithm gives the near optimal solution for 48
nodes or aircrafts.
Dr Krishan Kumar : is Assistant Professor in the Department of
Computer Science, Faculty of Technology, Gurukula Kangri
University, Haridwar, Uttarakhand, India. His area of interest is
artificial neural networks (ANN) and its applications. He obtained his
M.C.A degree from IMS Ghaziabad, India and Ph. D.(CS & IT) from
Institute of Engineering & Technology, M.J.P.Rohilkhand University,
Bareilly. He has also qualified National Eligibility Test (UGC-NET) in
Computer Science and Application. Dr. Kumar has authored more
than 30 research papers in international/national Journals/
Conferences. Presently he is vice chairman of Computer Society of
India, Haridwar Chapter and elected Chairman for the session 2016-
17. He has also been working as reviewer for many reputed journals
like Elsevier, Springer etc. for last 10 years.
Artificial Neural Network
Hopfield Network
Air
Space
Collision Avoidance
Sectoring
Consequently I have simulated the results for the 48
aircrafts flying in the air at same height and same
horizontal plane. In “Table 1” only 24 binary patterns are
shown. Next 24 patterns i.e from 25 to 48 shall be
converted on the same pattern. Earlier they were in
congestion due to crossing the limit of maximum possible
aircrafts in a sector. Hopfield neural net has been
successfully applied and implemented using MATLAB;
and It seems suitable for solving the aircrafts’ space
congestion problem. The problem of enroute congestion is
similar to the most popular operation research travelling
salesman problem (TSP). Hence the division of aircrafts
into different sectors on the basis of their positions can
also be done.
[1] Bowers, Peter M., Boeing Aircraft since 1916, ISBN
0-85177-804-6, London: Putnam Aeronautical Books,
1989.
[2] E.P Gilbo, “Optimizing airport capacity utilization in
air traffic flow management subject to constraints at
arrival and departure fixes”, IEEE Transactions on
Control Systems Technology, Vol. 5, no. 5, sep. 1997.
[3] K. Kumar, R. Singh, Z. Khan, and A. Indian, “Air
Traffic Runway Allocation Problem Using ARTMAP
(ART1)”, Ubiquitous Computing and Communication
International Journal, Korea, Vol. 3, No 3, July, 2008,
pp. 130-136.
[4] Min Xue, “Airspace Sector Redesign Based on
Voronoi Diagrams”, University of California at Santa
Cruz, Moffett Field, CA 94035, 2008.
[5] Daniel Delahaye, Jean-Marc Alliot, Marc Schenauer,
and Jean-Loup Farges, “Genetic algorithms for
partitioning air space”, Proceedings of the 10th
Conference on Artificial Intelligence and Application,
IEEE, 1-4 Mar 1994, pp. 291 – 297.
[6] D. Delahaye, M. Schoenauer and J. M. Alliot,
“Airspace sectoring by evolutionary computation”,
Evolutionary Computation Proceeding by IEEE World
Congress on Computational Intelligence, IEEE
International Conference on Vol., Issue, 4-9 May
1998.
[7] B. Pesic and D. Delahaye, Daily Operational airspace
sector grouping. April 27, 1999.
[8] O babic and T Kristic, “Airspace daily operational
Sectorization by fuzzy logic”, Elsevier, 2000.
[9] Riley, V. Chatterji, G. Johnson, W. Mogford, R.
Kopardekar, P. Sieira, E. Landing, and M. Lawton, G.
“Pilot Perceptions of Airspace Complexity”, Part-2,
Digital Avionics Systems Conference. DASC 04,
IEEE, 2004.
[10] Laurene Fausett, Fundamentals of Neural networks:
Architecture, Algorithm and Applications, Pearson
Education, ISBN 978-81-317-0053, 1994.
[11] Krishan Kumar, “ART1 Neural Networks for Air
Space Sectoring”, International Journal of Computer
Applications, USA, 2012, pp. 20 – 24.
[12] Krishan Kumar, “Self Organizing Map (SOM) Neural
Networks For Air Space Sectoring”, in IEEE
International Conference Computational Intelligence
& Communication Networks, Udaipur, India, 17-18,
Nov’2014.
[13] K. Kumar, R. Singh, Z. Khan, “Air Traffic Enroute
Conflict Detection Using Adaptive Resonance Theory
Map Neural Networks (ART1)”, Ubiquitous
Computing and Communication International Journal,
Korea, Vol. 3, No 3, July, 2008, pp. 28-35.
[14] D. Klingman and J. M. Mulvey editors, Network
models and associated applications, North Holland,
ISBN: 0-444-86203-X, 1981.
[15] Gilbert Saporta, Probabilistic analysis of statistic
techniques, 1990.
[16] P.L. Tuan, H.S. Procter, and G.J. Couluris, “Advanced
productivity analysis methods for air traffic control
operations”, FAA report RD-76-164, Standford
Research Institute, Mento Park CA 94025. December
1976.
[17] Chung-Kuan Cheng, “The optimal partitioning of
networks”, Networks, 22:297-315, 1992.
[18] Lester Ingber and Bruce Rosen, “Genetic Algorithm
and fast simulated re-annealing: a comparison”,
Mathematical and Computer Modeling, 16(1):87-100,
1992.
[19] Kevin, An Introduction to Neural Networks:
Routledge. ISBN 1857285034, 2002.
[20] “Neural networks and physical systems with emergent
collective computational abilities”, Proceedings of the
National Academy of Sciences, 1982, pp. 2554-2558.
[21] “Neurons with graded response have collective
computational properties like those of two-state
neurons”, Proceedings of the National Academy of
Sciences, 1984, pp. 81:3088-3092.