Effective Sonar Target Classification via Parallel Structure of Minimal Resource Allocation Network

Authors: W.S. Lim, M.V.C. Rao

Abstract:

In this paper, the processing of sonar signals has been carried out using Minimal Resource Allocation Network (MRAN) and a Probabilistic Neural Network (PNN) in differentiation of commonly encountered features in indoor environments. The stability-plasticity behaviors of both networks have been investigated. The experimental result shows that MRAN possesses lower network complexity but experiences higher plasticity than PNN. An enhanced version called parallel MRAN (pMRAN) is proposed to solve this problem and is proven to be stable in prediction and also outperformed the original MRAN.

Keywords: Ultrasonic sensing, target classification, minimalresource allocation network (MRAN), probabilistic neural network(PNN), stability-plasticity dilemma.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1058823

References:

[1] R. P. Lippman, "An introduction to computing with neural nets", IEEE ASSP Mag., pp. 4 - 22, Apr. 1987.
[2] W. W. L. Au, "Comparison of sonar discrimination - dolphin and artificial neural network", J. Acoust. Soc. Amer., pt. 1, vol. 95, no. 5, pp. 2728 - 2735, 1994.
[3] H. L. Roitblat, W. W. L. Au, P. E. Nachtogall, R. Shizumura, and G. Moons, "Sonar recognition of targets embedded in sediment", Neural Netw., vol. 8, no. 7/8, pp. 1263 - 1273, 1995.
[4] J. A. Simmons, P. A. Saillant, J. M. Wotton, T. Haresign, M. J. Feragamo, and C. F. Moss, "Composition of biosonar images for target recognition by echolocating bats", Neural Netw., vol. 18, no. 7/8 , pp. 1239 - 1261, 1995.
[5] G. B. Willson, "Radar classification using a neural network", Proc. SPIE, Optical Engineering and Photonics in Aerospace Sensing: Application of Neural Networks, vol. 1294, pp. 200 - 210, 1990.
[6] S. Watanabe and M. Yoneyama, "An ultrasonic visual sensor for threedimensional object recognition using neural networks", IEEE Trans. Robot. Automat., vol. 8, pp. 240 - 249, Apr. 1992.
[7] I. E. Dror, M. Zagaeski, and C. F. Moss, "3-dimensional target recognition via sonar - a neural network model", Neural Networks, vol. 8, no. 1, pp. 149 - 160, 1995.
[8] R. P. Gorman and T. J. Sejnowski, "Learned classification of sonar targets using a massively parallel network", IEEE Trans. Acoust., Speech, Signal Processing, vol. 36, no. 7, pp. 1135 - 1140, 1998.
[9] B. Ayrulu and B. Barshan, "Identification of target primitives with multiple decision-making sonars using evidential reasoning," Int. J. Robot. Res., vol. 17, no. 6, pp. 598 - 623, 1998.
[10] L. Yingwei, N. Sundararajan, and P. Saratchandran, "Performance evaluation of a sequential minimal Radial Basis Function (RBF) neural network learning algorithm," IEEE Trans. Neural Networks, vol. 9, pp. 308-318, Mar. 1998.
[11] L. Yingwei, N. Sundararajan, and P. Saratchandran, "A sequential learning scheme for function approximation using minimal radial basis function neural networks," Neural Computing., vol. 9, pp. 461-478, Feb. 1997.
[12] M. Chan, C. Fung, "Incremental Adaption of Resource-Allocating Network for Non-Stationary Time Series," Neural Networks, 1999. IJCNN '99. IEEE International Joint Conference, Volume: 3 , 10-16, July 1999, pp. 1554 -1559 vol.3
[13] B. L. Pulito, T. R. Damarla, S. Nariani, "A Two-Dimensional Shift Invariant Image Classification Neural Network which overcomes the Stability / Plasticity Dilemma," Neural Networks, 1990., 1990 IJCNN International Joint Conference on 17-21 June 1990, pp. 825 -833, vol.2
[14] J. P. Albright, "An implementation and Evaluation of the ART1 Neural Network For Pattern Recognition," Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference, Volume: 1 , 27 June-2 July 1994, pp. 498 -502, vol.1
[15] Youngtae Park, "An ART2 trained Two-Stage Learning on Circularly Ordered Data Sequence," Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference, Volume: 5 , 27 June-2 July 1994, pp. 2928 -2933, vol.5
[16] Rok Rape, Dusan Fefer, Janko Drnovsek. Time Series Prediction with Neural Networks: A Case Study of Two Examples, IMTC-94, IEEE, May 1994.
[17] Ben Jacobsen. Time Series Properties of Stock Returns, Kluwer BedrijfsInformatie, 1997.
[18] Donald F. Specht, "Enhancements To Probabilistic Neural Networks," Neural Networks, 1992. IJCNN., IEEE International Joint Conference, Volume: 1 , 7-11, June 1992, pp. 761 - 768, vol.1
[19] B. Barshan, B. Ayrulu, and S. W. Utete, "Neural Network-Based Target Differentiation Using Sonar for Robotics Applications," IEEE Trans. Robotics and Automation, vol. 16, pp. 435 - 442, August 2000.
[20] N. Sundararajan, P. Saratchandran and, Lu Ying Wei, book of "Radial Basis Function Neural Network," by School of Electrical & Electronic Engineering, Nanyang Tech. Univ, S-pore.
[21] W. S. Lim, M.V.C. Rao, C.K. Loo,"Sequential Learning Neural Network For Sonar Target Differentiation," Neural Network World 2/04, 187-197.
[22] D. F. Specht, "Probablistic Neural Networks," Neural Networks 3 (1990) 109-118.
[23] D. F. Specht, "Probabilistic neural networks for classification, mapping, or associative memory," ICNN, vol.1 (San Diego, CA), July 1988, pp. 525-532.
[24] D. J. Marchette and C. E. Priebe, "The adaptive kernel neural network," Reports: AD-A217 230, 1989.
[25] P. S. Naloney, "The use of probabilistic neural networks to improve solution times for hull-to-emitter correlation problems," IJCNN, Sheraton Washington, Vol.1, 1989, pp. 289-294.
[26] D. F. Specht, "Application of probabilistic neural networks," SPIE, Appl. Artif. Neural Networks 1294 (1990) 344-353.
[27] J. J. Guo, P. B. Luh, "Selecting input factors for clusters of Gaussian radial basis function networks to improve market clearing price prediction," Power Systems, IEEE Transactions, Volume 18, Issue 2, May 2003 Page(s):665 - 672.
[28] G. B. Huang, P. Saratchandran, N. Sundararajan, "A generalized growing and pruning RBF neural network for function approximation," Neural Networks, IEEE Transactions, Volume 16, Issue 1, Jan. 2005 Page(s):57 - 67.
[29] G. B. Huang, P. Saratchandran, N. Sundararajan, "An efficient sequential learning algorithm for growing and pruning RBF networks," Systems, Man and Cybernetics, Part B, IEEE Transactions, Volume 34, Issue 6, Dec. 2004 Page(s):2284 - 2292.