ChainNet: Neural Network-Based Successive Spectral Analysis
arXiv:2105.03742
Abstract
We discuss a new neural network-based direction of arrival estimation scheme that tackles the estimation task as a multidimensional classification problem. The proposed estimator uses a classification chain with as many stages as the number of sources. Each stage is a multiclass classification network that estimates the position of one of the sources. This approach can be interpreted as the approximation of a successive evaluation of the maximum a posteriori estimator. By means of simulations for fully sampled antenna arrays and systems with subarray sampling, we show that it is able to outperform existing estimation techniques in terms of accuracy, while maintaining a very low computational complexity.
arXiv commentReworked argumentation and added more simulation results
References in corpus (8)
- Adam: A Method for Stochastic Optimization
- Deep Networks for Direction-of-Arrival Estimation in Low SNR
- Multi-Speaker DOA Estimation Using Deep Convolutional Networks Trained with Noise Signals
- Broadband DOA estimation using Convolutional neural networks trained with noise signals
- DeepMUSIC: Multiple Signal Classification via Deep Learning
- Classifier Chains: A Review and Perspectives
- A Machine Learning Approach to DoA Estimation and Model Order Selection for Antenna Arrays with Subarray Sampling
- Model Order Selection in DoA Scenarios via Cross-Entropy based Machine Learning Techniques