Fast and Robust RBF Neural Network Based on Global K-means Clustering with Adaptive Selection Radius for Sound Source Angle Estimation
Authors:
- 11 April 2018
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Antennas and Propagation
- Vol. PP (0018926X) , 1
Abstract
The sound source localization technique is widely applied to target detection and localization. However, the application of conventional sound source localization methods is limited in actual environment because of estimation accuracy, computational complexity and flexibility of the environment. In order to improve the sound source localization performance in actual environment, a fast and robust radial basis function (RBF) neural network based on global K-means clustering with adaptive selection radius is proposed in this paper. In the proposed method, an adaptive selection radius is calculated according to the population density sampling method to remove unnecessary points around cluster centers during the global K-means clustering, thus compared with conventional neural network, a fast optimization of hidden layer neuron parameters can be achieved. Afterwards, the RBF neural network is trained to locate the sound source by solving non-linear equations of the time difference of arrival (TDOA) and sound source location. Because of the adoption of adaptive selection radius in global K-means clustering, the proposed method can provide desirable performance with low computational complexity. Based on the simulated and actual experimental data, the proposed method is verified and an improved performance is achieved compared with that of conventional neural network sound source localization methods.Keywords
This publication has 18 references indexed in Scilit:
- Radial Basis Function Interpolation for Signal-Model-Independent LocalizationIEEE Sensors Journal, 2015
- Lagrange Programming Neural Network Approach for Target Localization in Distributed MIMO RadarIEEE Transactions on Signal Processing, 2015
- BP neural network based localization for a front-wheel drive and differential steering mobile robot2015
- TDOA-Based Source Localization With Distance-Dependent NoisesIEEE Transactions on Wireless Communications, 2014
- A Geometric Approach to Sound Source Localization from Time-Delay EstimatesIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2014
- Identification of artifacts in scenery images using color and line information by RBF network - Segmentation by K-means algorithm and edge information2011
- Deterministic Convergence of an Online Gradient Method for BP Neural NetworksIEEE Transactions on Neural Networks, 2005
- The global k-means clustering algorithmPattern Recognition, 2003
- On the problem of local minima in backpropagationIEEE Transactions on Pattern Analysis and Machine Intelligence, 1992
- Multiple emitter location and signal parameter estimationIEEE Transactions on Antennas and Propagation, 1986