Research on Classification and Prediction of Underwater Navigation Adaptation Area Based on BP Neural Network

Haotong Wang; Xijun Gao; Zhiguo Bai

doi:10.54097/skkrag13

Authors

Haotong Wang
Xijun Gao
Zhiguo Bai

DOI:

https://doi.org/10.54097/skkrag13

Keywords:

Significance Analysis, Hierarchical Cluster Analysis, Normalization Processing, BP Neural Network Prediction.

Abstract

Aiming at the problem of classification and prediction of adaptive area for underwater navigation and positioning, this paper studies the processing of gravity anomaly data and the method of adaptive calibration. Aiming at the problem of calibration and recognition of the current adaptation area, this paper proposes a method based on hierarchical clustering analysis and BP neural network. Firstly, a hierarchical clustering analysis model is proposed to divide the suitability of each underwater navigation and positioning area. Through data preprocessing, interpolation encryption and significance analysis, the suitability calibration of the area is completed. Secondly, a BP neural network prediction model is established to predict the adaptability of the region, and the performance of the model is improved by normalization processing and network parameter optimization. Finally, through experimental verification, the classification results of the adaptation area and the prediction results of the BP neural network are obtained. The prediction accuracy is 82.7929% and the correlation coefficient is 0.94641, which verifies the effectiveness of the proposed method. This method provides theoretical support and decision-making basis for the navigation accuracy improvement of underwater vehicles and marine economic development planning.

References

[1] Ma H, Mu X, He B. Adaptive navigation algorithm with deep learning for autonomous underwater vehicle[J]. Sensors, 2021, 21(19): 6406.

[2] Xu Q, Kong W. Research on forecast model based on BP neural network algorithm[C]//Journal of Physics: Conference Series. IOP Publishing, 2021, 1982(1): 012065.

[3] Zhang D, Lou S. The application research of neural network and BP algorithm in stock price pattern classification and prediction[J]. Future Generation Computer Systems, 2021, 115: 872-879.

[4] Ran X, ** Y, Lu Y, et al. Comprehensive survey on hierarchical clustering algorithms and the recent developments[J]. Artificial Intelligence Review, 2023, 56(8): 8219-8264.

[5] Hohmann M, Devriendt K, Coscia M. Quantifying ideological polarization on a network using generalized Euclidean distance[J]. Science Advances, 2023, 9(9): eabq2044.

[6] Song S, **ong X, Wu X, et al. Modeling the SOFC by BP neural network algorithm[J]. International Journal of Hydrogen Energy, 2021, 46(38): 20065-20077.

[7] Huang L, Qin J, Zhou Y, et al. Normalization techniques in training dnns: Methodology, analysis and application[J]. IEEE transactions on pattern analysis and machine intelligence, 2023, 45(8): 10173-10196.

[8] Grabski I N, Street K, Irizarry R A. Significance analysis for clustering with single-cell RNA-sequencing data[J]. Nature Methods, 2023, 20(8): 1196-1202.

[9] Hodson T O. Root mean square error (RMSE) or mean absolute error (MAE): When to use them or not[J]. Geoscientific Model Development Discussions, 2022, 2022: 1-10.

[10] Zhou J, Li X, Ding T, et al. On the optimization landscape of neural collapse under mse loss: Global optimality with unconstrained features[C]//International Conference on Machine Learning. PMLR, 2022: 27179-27202.

[11] Malburg L, Hoffmann M, Bergmann R. Applying MAPE-K control loops for adaptive workflow management in smart factories[J]. Journal of Intelligent Information Systems, 2023, 61(1): 83-111.