基于贝叶斯优化的自动化多层感知区分神经网络实现了高精度的一源单一快照到达方向估计
Bin Zhang1, Jiawen He1, Peishun Liu1
1Department of Computer Science and Technology, Ocean University of China, Qingdao, 266100, China.
本研究介绍了自动化的多层感知区分神经网络 (AutoMPDNN),用于精确的水下稀疏到达方向 (DOA) 估计. 在单一源,单一快照场景中,AutoMPDNN显著优于现有方法.
科学领域:
- 信号处理 信号处理
- 机器学习 机器学习
- 水下声学 水下声学
背景情况:
- 稀少的采样对水下到达方向 (DOA) 估计提出了挑战.
- 传统的方法在复杂的水下环境中难以准确.
研究的目的:
- 开发一种创新的自动化机器学习解决方案,用于高精度的稀疏水下DOA估计.
- 为了解决经典和当前深度学习DOA估计技术的局限性.
主要方法:
- 提出了基于贝叶斯优化的自动化多层感知区分神经网络 (AutoMPDNN).
- 将稀疏的时间域信号转换为复杂的域,以增强功能保存.
- 将超参数集成到损失函数中,使用贝叶斯优化原理来解决最大概率问题.
主要成果:
- 自动MPDNN在单一源,单一快照场景中表现出卓越的预测性能.
- 与经典稀疏表示和当代深度学习DOA方法相比,实现了更高的精度.
- 探索了AutoMPDNNs_ln (n=2,3,4) 变种,在不同的条件下显示出强大的性能.
结论:
- 自动MPDNN为稀疏的水下DOA估计提供了先进和有效的解决方案.
- 自动化方法提高了精度,克服了现有方法的局限性.
- 这项工作推动了水下声信号处理和机器学习应用领域的发展.
更多相关视频
11:14A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants
Published on: October 4, 2015
09:47Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
Published on: December 15, 2023
相关概念视频
Multi-input and Multi-variable systems
In the absence...
Reducing Line Loss
With a step-up transformer at the source, the voltage is increased, thereby reducing the current in the transmission lines since power loss...
Improving Translational Accuracy
Propagation of Uncertainty from Random Error
Calibration Curves: Linear Least Squares
For data that follow a straight line, the standard method for fitting is the linear...
Model Approaches for Pharmacokinetic Data: Distributed Parameter Models
The distributed parameter models are specifically designed to account for variations and differences in some drug classes. This model is particularly useful for assessing regional concentrations of anticancer or...
