To minimize the major decline in direction of arrival (DOA) estimation performance for an acoustic vector sensor array (AVSA) with the coexistence of axial deviation and non-uniform noise, a two-step iterative minimization (TSIM) method is proposed in this paper. Initially, the axial deviation measurement model of an AVSA is formulated by incorporating the disturbance parameter into the signal model, and then a novel AVSA manifold matrix is defined to estimate the sparse signal power and noise power mutually. After that, to mitigate a joint optimization problem to achieve the sparse signal power, the noise power and the axial deviation matrix, two auxiliary cost functions, are presented based on the covariance matrix fitting (CMF) criterion and the weighted least squares (WLS), respectively. Furthermore, their analytical expressions are also derived. In addition, to further enhance their prediction accuracy, the estimated axial deviation matrix is modified based on its specific structural properties. The simulation results demonstrate the superiority and robustness of the proposed technique over several conventional algorithms.
11 January 2022 in IEEE Transactions on Plasma Science
It is important to study the electron density distribution of plasma sheath to inhibit the blackout phenomenon of reentry vehicle. In this article, we propose a new method to predict the electron density distribution based on a backpropagation neural network (BPNN). We build a dataset based on the hybrid matrix method of computational electromagnetics (EMs) and train a three-layer network to map the relationship between EM wave propagation characteristics and electron density. This method is more accurate than the traditional plasma diagnosis method and reduces the complicated measurement process. Experimental results show that the neural network method has a performance with an average error of less than 3% and can reduce twice the training time using multicore CPU than low computing capability graphics card. This study sheds new light on electron density diagnosis to find more accurate and effective methods.
16 October 2024 in IEEE Antennas and Wireless Propagation Letters
Accurate prediction of the diurnal variations of very low frequency (VLF) waves in the Earth-ionosphere waveguide is still a challenging task. In this letter, a novel method, which consists of a back-propagation neural network (BPNN) and transfer learning (TL) approach known as BPNN-TL, is introduced to predict the diurnal variations of VLF waves. The BPNN is used to pre-train a network model based on theoretical dataset generated by the waveguide mode theory. The parameters of the pre-trained model are later fine-tuned by the TL technique with measured data. By taking the advantages of BPNN and TL, the reality gap caused by inevitable theoretical modeling approximation errors is mitigated.
Pre-trained language models perform well in various natural language processing tasks. However, their large number of parameters poses significant challenges for edge devices with limited resources, greatly limiting their application in practical deployment. This paper introduces a simple and efficient method called Autocorrelation Matrix Knowledge Distillation (AMKD), aimed at improving the performance of smaller BERT models for specific tasks and making them more applicable in practical deployment scenarios. The AMKD method effectively captures the relationships between features using the autocorrelation matrix, enabling the student model to learn not only the performance of individual features from the teacher model but also the correlations among these features. Additionally, it addresses the issue of dimensional mismatch between the hidden states of the student and teacher models. Even in cases where the dimensions are smaller, AMKD retains the essential features from the teacher model, thereby minimizing information loss. Experimental results demonstrate that BERTTINY-AMKD outperforms traditional distillation methods and baseline models, achieving an average score of 83.6% on GLUE tasks. This represents a 4.1% improvement over BERTTINY-KD and exceeds the performance of BERT4-PKD and DistilBERT4 by 2.6% and 3.9%, respectively. Moreover, despite having only 13.3% of the parameters of BERTBASE, the BERTTINY-AMKD model retains over 96.3% of the performance of the teacher model, BERTBASE.
19 June 2025 in Circuits, Systems, and Signal Processing
Enhanced Loran (eLoran) is the most important backup system for Global Navigation Satellite System (GNSS). However, most current eLoran demodulation methods are based on digital signal processing, which may produce large errors under the influence of strong interference or noise. The authors propose an eLoran signal message prediction algorithm based on deep learning. Using time‐frequency (TF) analysis convert one‐dimensional signal into two‐dimensional high‐resolution image. It improves Alexnet by adjusting the convolutional layer structure, adding an attention module, and reducing the pooling layer window to construct the Alexnet‐ECA network. The network is used to identify TF image features and predict signal message. The experimental results show that novel method for eLoran signal message prediction based on Alexnet‐ECA can achieve high accuracy and robustness in various SNR scenarios. The accuracy is more than 90% at SNR greater than 10db and not less than 80% even in the complex environments. Compared with Resnet34 and VGG16 networks, Alexnet‐ECA demonstrates its efficiency and effectiveness using real measurement data. This method can enhance the performance and reliability of eLoran receivers and applications.