Electrical Engineering

Chin-Hsing Chen1, Jiann-Der Lee2 and Ming-Chi Lin1

1Department of Electrical Engineering National Cheng Kung University Taiwan 700, R. O. C.
2Department of Electrical Engineering Chang Gung University Tao-Yuan, Taiwan 333, R. O. C.

 

Received: November 10, 1999
Accepted: June 12, 2000
Publication Date: June 12, 2000

Download Citation: ||https://doi.org/10.6180/jase.2000.3.1.04  


ABSTRACT

In this paper, four kinds of neural network classifiers have been used for the classification of underwater passive sonar signals radiated by ships. Classification process can be divided into two stages. In the preprocessing and feature extraction stage, Two-Pass Split-Windows (TPSW) algorithm is used to extract tonal features from the average power spectral density (APSD) of the input data. In the classification stage, four kinds of static neural network classifiers are used to evaluate the classification results, inclusive of the probabilistic based classifier-Probabilistic Neural Network (PNN), the hyperplane based classifier-Multilayer Perceptron (MLP), the kernel based classifierAdaptive Kernel Classifier (AKC), and the exemplar based classifierLearning Vector Quantization (LVQ). For comparison, the same classifiers but using Dyadic Wavelet Transform (DWT) in the feature extraction are used to evaluate the performance of the proposed method. Experimental results show that feature extraction using TPSW gives better classification performance than using DWT, but require more computation time. In neural network classifiers, exemplar classifiers give better performance than the others both in learning speed and classification rate. Moreover, the classifier using LVQ families with data extracted by DWT can reach the same correction rate (100%) as the classifier using various networks with data extracted by TPSW. Detail discussion for experimental results are also included.


Keywords: Underwater Signal Classification, Neural Networks, TPSW, PNN, MLP, AKC, LVQ


REFERENCES

  1. [1] Beck, S., Deuser, L., Still, R. and Whitely, J., "A hybrid neural network classifier of short duration acoustic signals," Proc. IEEE Conf. on Neural Networks for Ocean Engineering, pp.210-215 (1991).
  2. [2] Burr, D. J., "Experiments on neural net recognition of spoken and written text," IEEE Trans. on ASSP, vol. 36, no.7, pp. 1162-1168 (1988).
  3. [3] Burrascano, P., "Learning vector quantization for the Probabilistic neural networks," IEEE Trans. on Neural Networks, vol. 2, no. 4, pp. 458-461 (1991).
  4. [4] Burton, D., "Acoustic transient classification of passive sonar signals by using vector quantization," Proc. IEEE Signal Processing, pp. 126-132 (1991).
  5. [5] Cacoullos, T., "Estimation of multivariate density," Annals of the Institute of Statistical Mathematics, vol. 18, no. 2, pp. 179-189 (1966).
  6. [6] Carpenter, G. A. and Grossberg, S., "A massively parallel architecture for a selforganizing neural pattern recognition machine," Computer Vision and Image Processing, vol. 37, pp. 54-115 (1987).
  7. [7] Cohen, L., "Time-frequency distribution-a review," Proc. IEEE, vol. 77, no. 7, pp. (1989).
  8. [8] Cottle, D. W. and Hamilton, D. J.,"All neural sonar discrimination system," IEEE Conf. Neural Networks for Ocean Engineering, pp.100-105 (1991).
  9. [9] Fakhr W. and Elmasry, M. I., "A fast learning technique for the multilayer perceptron," Proc. IEEE Conf. on Neural Networks, vol. 3, pp. 257-262 (1990).
  10. [10] Geva, S. and Sitte, J., "Adaptive nearest neighbor pattern classification," IEEE Trans. on Neural Networks, vol. 2, no. 2, pp. 318- 322 (1991).
  11. [11] Ghosh, J., Chakravarthy, S., Shin, Y. and Chu, C. C., "Adaptive kernel classifiers for short-duration oceanic signals," Proc. IEEE Conf. Neural Networks for Ocean Engineering, (1991).
  12. [12] Ghosh, J., Deuser, L. M. and Beck, S. D., "A neural network based hybrid system for detection, characterization and classification of short-duration oceanic signals," IEEE Journal of Oceanic Engineering, vol. 17, no. 4, pp. 351-363 (1992).
  13. [13] Gorman, R. P. and Sejnowski, T. J., "Learned classification of sonar targets using a massively parallel network," IEEE Trans. on ASSP, vol. 36, no. 7, pp. 1135-1140 (1988).
  14. [14] Greene, R. L. and Field, R. L.,"Classification of underwater acoustic transients by artificial neural networks," IEEE Conf. Neural Networks for Ocean Engineering, pp. 110- 115 (1991).
  15. [15] Kohonen, T., "Statistical pattern recognition revisited," Advanced Neural Computer, North-Holland (1990).
  16. [16] Kosko, B., " Neural networks for signal processing," Prentice-Hall (1992).
  17. [17] Leen, T., Rudnick, M and Hammerstorm, "Hebbian feature discovery improves classifier efficiency," IEEE Conf. on Neural Networks, vol. 2, pp. 555-558 (1991).
  18. [18] Lippmann, R. P., "Pattern classification using neural networks," IEEE Communication Magazine, pp. 47-64 (1989).
  19. [19] Lippmann, R. P., "An introduction to computing with neural nets," IEEE ASSP Magazine, vol. 4, pp. 4-22 (1987).
  20. [20] Lourens, J. G., "Passive sonar detection of ships with spectrograms," Proc. IEEE Conf. on Neural Networks, vol. 1, pp. 65-70 (1989).
  21. [21] Mallat, S. G., "A theory for multiresolutions signal decomposition: The wavelet representation, IEEE Trans. on PAMI, vol. 11, pp. 674-693 (1989)
  22. [22] Morgan, D. P. and Scofield, C. L., Neural. networks and speech processing, Kluwer Academic Publishers (1991).
  23. [23] Nielsen, R. O." Sonar signal processing," Artech House, (1991).
  24. [24] Oja, E., "Principal components, minor components, and linear neural networks," Neural Networks, vol. 5, pp. 927-935 (1992).
  25. [25] Ooyen, A. V. and Nienhuis, B., "Improving the convergence of the Back-Propagation algorithm," Neural Networks, vol. 5, pp. 465- 471 (1992).
  26. [26] Renals, S. and Rohwer, R., "Phoneme classification experiments using radial basis functions," Proc. IEEE Conf. on Neural Networks, vol. 1, pp. 461-467 (1989).
  27. [27] Roth, M. W., "Survey of neural network technology for automatic target recognition," IEEE Trans. on Neural Networks, vol. 1, no. 1, pp.28-43 (1990).
  28. [28] Rummelhart, D. E. and Mcclelland, J. L., "Parallel Distributed Processing," vol. 1, MIT Press, Cambridge (1986).
  29. [29] Sanger, T. D., "Optimal unsupervised learning in a single-layer linear feedforward neural network," Neural Networks, vol. 2, pp. 459-473 (1989).
  30. [30] Scalero, R. S. and Tepedelenlioglu, N., "A fast new algorithm for training feedforward neural networks," IEEE Trans. on Signal Processing, vol. 40, no. 1, pp. 202-210 (1992).
  31. [31] Specht, D. F., "Probabilistic neural networks," Neural Networks, vol. 3, pp. 109- 118 (1990).
  32. [32] Specht, D. F., "Probabilistic neural networks and the polynomial adaline as complementary techniques for classification," IEEE Trans. on Neural Networks, vol. 1, no. 1, pp. 111-121 (1990).
  33. [33] Urick, R. J., " Principles of underwater sound," McGraw-Hill (1983).
  34. [34] Yang, J. and Dumont, G. A., "Classification of acoustic emission signals via Hebbian feature extraction," IEEE Conf. on Neural Networks, vol. 1, pp. 113-118 (1991).
  35. [35] Yassa, F. F., "Optimality in the choice of the convergence factor for gradient-based adaptive algorithms," IEEE Trans. on ASSP, vol. 35, no. 1, pp. 48-59 (1987).
  36. [36] Zurada, J. M., "Introduction to artificial neural systems," West Info Access (1992).

Latest Articles

Dynamic Analysis of the UHPFRC High-rise Building under High Explosion using Coupled Eulerian-Lagrangian Approach
Dynamic Analysis of the UHPFRC High-rise Building under High Explosion using Coupled Eulerian-Lagrangian ApproachVolume 28, Issue 2 (In Press)

Read more: ...

NSGA-II Algorithm-Based Wide Area Measurement (WAMS) Allocation with Considering Reliability
NSGA-II Algorithm-Based Wide Area Measurement (WAMS) Allocation with Considering ReliabilityVolume 28, Issue 2 (In Press)

Read more: ...

Predicting Demand for Emergency Ambulance Services: A Comparative Approach
Predicting Demand for Emergency Ambulance Services: A Comparative ApproachVolume 27, Issue 10

Read more: ...

Multi-level Semantic Fusion Network for Few-shot Multimedia Image Recognition in Education Management
Multi-level Semantic Fusion Network for Few-shot Multimedia Image Recognition in Education ManagementVolume 28, Issue 2 (In Press)

Read more: ...

River bank erosion prediction using multivariable linear regression
River bank erosion prediction using multivariable linear regressionVolume 27, Issue 12 (In Press)

Read more: ...

Optimization of Ultrasound-Assisted Pectin Extraction from Durian Rind
Optimization of Ultrasound-Assisted Pectin Extraction from Durian RindVolume 28, Issue 2 (In Press)

Read more: ...

Short-time prediction model for cross-section passenger flow in urban transit trains using GCN-AM-BiLSTM
Short-time prediction model for cross-section passenger flow in urban transit trains using GCN-AM-BiLSTMVolume 28, Issue 2 (In Press)

Read more: ...

Response Prediction Analysis of RC Frame Structures Using Support Vector Machine Algorithm
Response Prediction Analysis of RC Frame Structures Using Support Vector Machine AlgorithmVolume 28, Issue 2 (In Press)

Read more: ...

Using the non-dominated sorting genetic algorithm II for multi-objective optimization of acoustic performance in sandwich panels with cellular honeycomb core
Using the non-dominated sorting genetic algorithm II for multi-objective optimization of acoustic performance in sandwich panels with cellular honeycomb coreVolume 28, Issue 2 (In Press)

Read more: ...