Multi-Layer Perceptron Neural Network Utilizing Adaptive Best-Mass Gravitational Search Algorithm to Classify Sonar Dataset
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...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Institute of Fundamental Technological Research Polish Academy of Sciences
2019-01-01
|
| Series: | Archives of Acoustics |
| Subjects: | |
| Online Access: | https://acoustics.ippt.pan.pl/index.php/aa/article/view/1855 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1839604722466553856 |
|---|---|
| author | Mohammad Reza MOSAVI Mohammad KHISHE Mohammad Jafar NASERI Gholam Reza PARVIZI Mehdi AYAT |
| author_facet | Mohammad Reza MOSAVI Mohammad KHISHE Mohammad Jafar NASERI Gholam Reza PARVIZI Mehdi AYAT |
| author_sort | Mohammad Reza MOSAVI |
| collection | DOAJ |
| description | 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 low-convergence 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 best-collected 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. |
| format | Article |
| id | doaj-art-160edb4b758a45fab463730d87a31f6d |
| institution | Matheson Library |
| issn | 0137-5075 2300-262X |
| language | English |
| publishDate | 2019-01-01 |
| publisher | Institute of Fundamental Technological Research Polish Academy of Sciences |
| record_format | Article |
| series | Archives of Acoustics |
| spelling | doaj-art-160edb4b758a45fab463730d87a31f6d2025-08-02T02:08:07ZengInstitute of Fundamental Technological Research Polish Academy of SciencesArchives of Acoustics0137-50752300-262X2019-01-0144110.24425/aoa.2019.126360Multi-Layer Perceptron Neural Network Utilizing Adaptive Best-Mass Gravitational Search Algorithm to Classify Sonar DatasetMohammad Reza MOSAVI0Mohammad KHISHE1Mohammad Jafar NASERI2Gholam Reza PARVIZI3Mehdi AYAT4Iran University of Science and TechnologyIran University of Science and TechnologyUniversity of Marine SciencesAlborz Institute for Higher EducationIran University of Science and TechnologyIn 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 low-convergence 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 best-collected 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.https://acoustics.ippt.pan.pl/index.php/aa/article/view/1855Multi-Layer Perceptron Neural NetworkAdaptive Best Mass Gravitational Search Algorithmsonarclassification |
| spellingShingle | Mohammad Reza MOSAVI Mohammad KHISHE Mohammad Jafar NASERI Gholam Reza PARVIZI Mehdi AYAT Multi-Layer Perceptron Neural Network Utilizing Adaptive Best-Mass Gravitational Search Algorithm to Classify Sonar Dataset Archives of Acoustics Multi-Layer Perceptron Neural Network Adaptive Best Mass Gravitational Search Algorithm sonar classification |
| title | Multi-Layer Perceptron Neural Network Utilizing Adaptive Best-Mass Gravitational Search Algorithm to Classify Sonar Dataset |
| title_full | Multi-Layer Perceptron Neural Network Utilizing Adaptive Best-Mass Gravitational Search Algorithm to Classify Sonar Dataset |
| title_fullStr | Multi-Layer Perceptron Neural Network Utilizing Adaptive Best-Mass Gravitational Search Algorithm to Classify Sonar Dataset |
| title_full_unstemmed | Multi-Layer Perceptron Neural Network Utilizing Adaptive Best-Mass Gravitational Search Algorithm to Classify Sonar Dataset |
| title_short | Multi-Layer Perceptron Neural Network Utilizing Adaptive Best-Mass Gravitational Search Algorithm to Classify Sonar Dataset |
| title_sort | multi layer perceptron neural network utilizing adaptive best mass gravitational search algorithm to classify sonar dataset |
| topic | Multi-Layer Perceptron Neural Network Adaptive Best Mass Gravitational Search Algorithm sonar classification |
| url | https://acoustics.ippt.pan.pl/index.php/aa/article/view/1855 |
| work_keys_str_mv | AT mohammadrezamosavi multilayerperceptronneuralnetworkutilizingadaptivebestmassgravitationalsearchalgorithmtoclassifysonardataset AT mohammadkhishe multilayerperceptronneuralnetworkutilizingadaptivebestmassgravitationalsearchalgorithmtoclassifysonardataset AT mohammadjafarnaseri multilayerperceptronneuralnetworkutilizingadaptivebestmassgravitationalsearchalgorithmtoclassifysonardataset AT gholamrezaparvizi multilayerperceptronneuralnetworkutilizingadaptivebestmassgravitationalsearchalgorithmtoclassifysonardataset AT mehdiayat multilayerperceptronneuralnetworkutilizingadaptivebestmassgravitationalsearchalgorithmtoclassifysonardataset |