Multi-Layer Perceptron Neural Network Utilizing Adaptive Best-Mass Gravitational Search Algorithm to Classify Sonar Dataset

• Autorzy: Mosavi Mohammad Reza , Khishe Mohammad , Naseri Mohammad Jafar , Parvizi Gholam Reza , Ayat Mehdi

Identyfikatory

DOI

10.24425/aoa.2019.126360

• Języki publikacji: EN

Abstrakty

EN

In this paper, a new Multi-Layer Perceptron Neural Network (MLP NN) classifier is proposed for classifying sonar targets and non-targets from the acoustic backscattered signals. Besides the capabilities of MLP NNs, it uses Back Propagation (BP) and Gradient Descent (GD) for training; therefore, MLP NNs face with not only impertinent classification accuracy but also getting stuck in local minima as well as lowconvergence speed. To lift defections, this study uses Adaptive Best Mass Gravitational Search Algorithm (ABGSA) to train MLP NN. This algorithm develops marginal disadvantage of the GSA using the bestcollected masses within iterations and expediting exploitation phase. To test the proposed classifier, this algorithm along with the GSA, GD, GA, PSO and compound method (PSOGSA) via three datasets in various dimensions will be assessed. Assessed metrics include convergence speed, fail probability in local minimum and classification accuracy. Finally, as a practical application assumed network classifies sonar dataset. This dataset consists of the backscattered echoes from six different objects: four targets and two non-targets. Results indicate that the new classifier proposes better output in terms of aforementioned criteria than whole proposed benchmarks.

Słowa kluczowe

EN

MLP NN; Multi-Layer Perceptron Neural Network; ABGSA; Adaptive Best Mass Gravitational Search Algorithm; sonar; classification

• Wydawca: Instytut Podstawowych Problemów Techniki PAN ; Komitet Akustyki PAN ; Polskie Towarzystwo Akustyczne
• Czasopismo: Archives of Acoustics
• Rocznik: 2019
• Tom: Vol. 44, No. 1
• Strony: 137--151
• Opis fizyczny: Bibliogr. 61 poz., rys., tab., wykr.

Twórcy

autor

Mosavi Mohammad Reza

• Department of Electrical Engineering, Iran University of Science and Technology, Narmak, Tehran 16846-13114, Iran

autor

Khishe Mohammad

• Department of Electrical Engineering, Iran University of Science and Technology, Narmak, Tehran 16846-13114, Iran

autor

Naseri Mohammad Jafar

• Department of Electronic and Communication Engineering, University of Marine Sciences, Nowshahr, Iran

autor

Parvizi Gholam Reza

• Department of English, Alborz Institute for Higher Education, Qazvin, Iran

autor

Ayat Mehdi

• Department of Electrical Engineering, Iran University of Science and Technology, Narmak, Tehran 16846-13114, Iran

Bibliografia

• 1. Allahyar M. R., Nemati M. H., Naseri A. S., Golshani A. A. (2012), Monitoring and modelling studies of Iranian coasts phase 5: northern coasts, Ports and Maritime Organization, http://irancoasts.pmo.ir/en/first.
• 2. Aubry A., De Maio A., Piezzo M., Farina A., Wicks M. (2012), Cognitive design of the receive filter and transmitted phase code in reverberating environment, IET Radar, Sonar & Navigation, 6, 9, 822-833, doi: 10.1049/iet-rsn.2012.0029.
• 3. Auer P., Burgsteiner H., Maass W. (2008), A learning rule for very simple universal approximators consisting of a single layer of perceptrons, Neural Networks, 21, 5, 786-795.
• 4. Blumrosen G., Fishman B., Yovel Y. (2014), Noncontact wideband sonar for human activity detection and classification, IEEE Sensors Journal, 14, 11, 4043-4054, doi: 10.1109/JSEN.2014.2328340.
• 5. Chen H., Li S., Tang Z. (2011), Hybrid gravitational search algorithm with random-key encoding scheme combined with simulated annealing, International Journal of Computer Science and Network Security, 11, 6, 208-217.
• 6. Chen J., Qin Z., Liu Y., Lu J. (2005), Particle swarm optimization with local search, IEEE Conference on Neural Networks and Brain, pp. 481-484, Beijing.
• 7. Chen S., Mei T., Luo M., Yang X. (2007), Identification of nonlinear system based on a new hybrid gradient-based PSO algorithm, International Conference on Information Acquisition, pp. 265-268, Seogwipo-si.
• 8. Chu D., Stanto T. K. (2010), Statistics of echoes from a directional sonar beam insonifying finite numbers of single scatterers and patches of scatterers, IEEE Journal on Oceanic Engineering, 35, 2, 267-277.
• 9. Cui X., Geol V., Kingsbury B. (2015), Data augmentation for deep neural network acoustic modelling, IEEE/ACM Transaction on Audio, Speech, and Language Processing, 23, 9, 1496-1477, doi: 10.1109/TASLP.2015.2438544.
• 10. Das A., Kumar A., Bahl R. (2013), Marine vessel classification based on passive sonar data: the spectrum-based approach, IET Radar, Sonar & Navigation, 7, 1, 87-93.
• 11. Derrac J., Garcìa S., Molina D., Herrera F. (2011), A practical tutorial on the use of nonparametric statistical tests as a methodology for comparing evolutionary and swarm intelligence algorithms, Swarm and Evolutionary Computation, 1, 1, 3-18.
• 12. Doraghinejad M., Nezamabadi-Pour H., Mahani A. (2014), Channel assignment in multi-radio wireless mesh networks using an improved gravitational search algorithm, Journal of Network and Computer Applications, 38, 163-171.
• 13. Fei T., Kraus D., Zoubir A. M. (2015), Contributions to automatic target recognition systems for underwater mine classification, IEEE Transaction on Geosciences and Remote Sensing, 53, 1, 505-518.
• 14. Gonzalez-Álvarez D. L., Vega-Rodrìguez M. A., Gómez-Pulido J. A., Sánchez-Pérez J. M. (2011), Applying a multiobjective gravitational search algorithm (MO-GSA) to discover motifs, [in:] Advances in Computational Intelligence, pp. 372-379, Springer, Berlin Heidelberg.
• 15. Gorman R. P., Sejnowski T. J. (1998), Datasets, from http://archive.ics.uci.edu/ml/datasets.
• 16. Gu B., Pan F. (2013), Modified gravitational search algorithm with particle memory ability and its application, International Journal of Innovative Computing, Information and Control, 9, 4531-4544.
• 17. Guo Z. (2012), A hybrid optimization algorithm based on artificial bee colony and gravitational search algorithm, International Journal of Digital Content Technology and Its Applications, 6, 620-626.
• 18. Han K., Wang D. (2014), Neural network based pitch tracking in very noisy speech, IEEE/ACM Transaction on Audio, Speech, and Language Processing, 22, 2158-2168.
• 19. Han X. H., Chang X. M. (2012), A chaotic digital secure communication based on a modified gravitational search algorithm filter, Information Sciences, 208, 14-27.
• 20. Han X. H., Quan L., Xiong X. Y., Wu B. (2013), Facing the classification of binary problems with a hybrid system based on quantum-inspired binary gravitational search algorithm and K-NN method, Engineering Applications of Artificial Intelligence, 26, 2424-2430.
• 21. Hatamlou A., Abdullah S., Nezamabadi-Pour H. (2012), A combined approach for clustering based on K-means and gravitational search algorithms, Swarm and Evolutionary Computation, 6, 47-52.
• 22. Hatamlou A., Abdullah S., Othman Z. (2011), Gravitational search algorithm with heuristic search for clustering problems, 3rd Conference on Data Mining and Optimization (DMO), pp. 190-193, Putrajaya.
• 23. Karayiannis N. B. (1999), Reformulated radial basis neural networks trained by gradient descent, IEEE Transaction on Neural Networks, 10, 657-671.
• 24. Kumar N., Mitra U., Narayanan S. S. (2015), Robust object classification in underwater side scan sonar images by using reliability-aware fusion of shadow features, IEEE Journal on Oceanic Engineering, 40, 592-606.
• 25. Li C., Li H., Kou P. (2014), Piecewise function based gravitational search algorithm and its application on parameter identification of AVR system, Neurocomputing, 124, 139-148.
• 26. Li C., Zhou J. (2011), Parameters identi?cation of hydraulic turbine governing system using improved gravitational search algorithm, Energy Conversion and Management, 52, 374381.
• 27. Li C., Zhou J., Xiao J., Xiao H. (2012), Parameters identification of chaotic system by chaotic gravitational search algorithm, Chaos, Solitons & Fractals, 45, 539-547.
• 28. Li P., Duan H. B. (2012), Path planning of unmanned aerial vehicle based on improved gravitational search algorithm, Science China Technological Sciences, 55, 2712-2719.
• 29. Liu C., Wang H., Yao P. (2014), On terrainaided navigation for unmanned aerial vehicle using b-spline neural network and extended Kalman filter, IEEE Conference on Guidance, Navigation and Control, pp. 2258-2263, Chinese.
• 30. Liu Y., Ma L. (2013), Improved gravitational search algorithm based on free search differential evolution, Journal of Systems Engineering and Electronics, 24, 690-698.
• 31. Meuleau N., Dorigo M. (2002), Ant colony optimization and stochastic gradient descent, Artificial Life, 8, 103-121.
• 32. Mirjalili S. A. (2015), How effective is the grey wolf optimizer in training multi-layer perceptrons, Applied Intelligence, 43, 150-161.
• 33. Mirjalili S. A., Hashim S. Z. M. (2010), A new hybrid PSOGSA algorithm for function optimization, IEEE Conference on Computer and Information Application, pp. 374-377, Tianjin.
• 34. Mirjalili S. A., Lewis A. (2014), Adaptive gbestguided gravitational search algorithm, Neural Computing and Applications, 25, pp. 1569-1584.
• 35. Mirjalili S. A., Mirjalili S. M., Lewis A. (2014), Let a biogeography-based optimizer train your multilayer perceptron, Journal of Information Sciences, 269, 188-209.
• 36. Mirjalili S. A., Mohd Hashim S. Z., Moradian Sardroudi H. (2012), Training feed forward neural networks using hybrid particle swarm optimization and gravitational search algorithm, Applied Mathematics and Computation, 218, 11125-11137.
• 37. Moody J., Darken C. J. (1989), Fast learning in networks of locally-tuned processing units, Neural Computer, 1, 281-294.
• 38. Mosavi M. R., Khishe M., Aghababaee M., Mohammadzadeh F. (2015), Approximation of active sonar clutter’s statistical parameters using array’s effective beam-width, Iranian Journal of Marine Science and Technology [in Persian], 73, 11-22.
• 39. Mosavi M. R., Khishe M., Ebrahimi E. (2015), Classification of sonar targets using OMKC genetic algorithms and statistical moments, Journal of Advance in Computer Research, 7, 50-59.
• 40. Naseri M. J. (2015), Floating buoy controller design and implementation by using special sonobuoys, M.Sc. Thesis, University of Nowshahr Marine Sciences, Iran.
• 41. Noman N., Iba H. (2008), Accelerating differential evolution using an adaptive local search, IEEE Transaction on Evolutionary Computing, 12, 107-125.
• 42. Pailhas Y., Capus C., Brown K. (2012), Dolphin-inspired sonar system and its performance, IET Radar, Sonar & Navigation, 6, 753-763.
• 43. Pan X., Li C., Xu Y., Xu W., Gong X. (2014), Combination of time-reversal focusing and nulling for detection of small targets in strong reverberation environments, IET Radar, Sonar & Navigation, 8, 9-16.
• 44. Parsazad S., Sadoghi Yazdei H., Effati S. (2013), Gravitation based classification, Information Sciences, 220, 319-330.
• 45. Pearce S. K., Bird J. S. (2013), Sharpening side scan sonar images for shallow-water target and habitat classification with a vertically stacked array, IEEE Journal on Oceanic Engineering, 38, 455-469.
• 46. Pei J., Liu X., Pardalos P. M., Fan W., Yang S., Wang L. (2014), Application of an effective modified gravitational search algorithm for the coordinated scheduling problem in a two-stage supply chain, International Journal of Advanced Manufacturing Technology, 70, 335-348.
• 47. Preston J. M. (2004), Resampling sonar echo time series primarily for seabed sediment, United State Patent, US.
• 48. Rahmani Hosseinabadi A. A., Ramzannezhad Ghaleh M. R., Hashemi S. E. (2013), Application of modified gravitational search algorithm to solve the problem of teaching hidden Markov model, International Journal of Computer Science, 10, 3, 1-8.
• 49. Rashedi E., Nezamabadi-Pour H., Saryazdi S. (2009), GSA: A gravitational search algorithm, Information Sciences, 179, 2232-2248.
• 50. Sabri N. M., Puteh M., Mahmood M. R. (2013), A review of gravitational search algorithm, International Journal of Advance in Soft Computing and Application, 5, 1-39.
• 51. Sarafrazi S., Nezamabadi-Pour H., Saryazdi S. (2011), Disruption: A new operator in gravitational search algorithm, Scientia Iranica, 18, 539-548.
• 52. Shaw B., Mukherjee V., Ghoshal S. P. (2012), A novel opposition based gravitational search algorithm for combined economic and emission dispatch problems of power systems, International Journal of Electrical Power & Energy Systems, 35, 21-33.
• 53. Sinaie S. (2010), Solving shortest path problem using gravitational search algorithm and neural networks, M.Sc. Thesis, Faculty of Computer Science and Information Systems, Universiti Teknologi Malaysia (UTM).
• 54. Souza Filho J. B. O., De Seixas J. M. (2016), Classmodular multi-layer perceptron networks for supporting passive sonar signal classification, IET Radar, Sonar & Navigation, 10, 311-317.
• 55. Sun G., Zhang A. (2013), A hybrid genetic algorithm and gravitational using multilevel thresholding, [in:] Pattern Recognition and Image Analysis, Sanches J. M., Mico L., Cardoso J. S. [Ed.], pp. 707-714, Springer Berlin Heidelberg, China University.
• 56. Wilcoxon F. (1945), Individual comparisons by ranking methods, Biometrics Bulletin Society, 1, pp. 80-83.
• 57. Williams D. P., Fakiris E. (2014), Exploring environmental information for improved underwater target classification in sonar imagery, IEEE Transaction on Geosciences and Remote Sensing, 52, 6284-6297.
• 58. Yegireddi S. (2015), A combined approach of generic algorithm and neural networks with an application to geoacoustic inversion studies, Indian Journal of Geo-Marine Sciences, 44, 195-201.
• 59. Zhang Y., Li Y., Xia F., Luo Z. (2012), Immunity-based gravitational search algorithm, 3rd International Conference on Information Computing and Applications, pp. 754-761, Chengde, China.
• 60. Zhang Y., Wu L., Zhang Y., Wang J. (2012), Immune gravitation inspired optimization algorithm, [in:] Advanced Intelligent Computing, Huang D. S., Gan Y., Bevilacqua V., Figueroa J. C. [Ed.], pp. 178-185, Springer Berlin Heidelberg, Haikou, China.
• 61. Zhou J. X., Zhang X. Z. (2005), Shallow-water reverberation level: measurement technique and initial reference values, IEEE Journal on Oceanic Engineering, 30, 832-842.

Uwagi

Opracowanie rekordu w ramach umowy 509/P-DUN/2018 ze środków MNiSW przeznaczonych na działalność upowszechniającą naukę (2019).