Related Experiment Video
Updated: May 28, 2026
08:42
Measurement of the Directional Information Flow in fNIRS-Hyperscanning Data using the Partial Wavelet Transform Coherence Method
Published on: September 3, 2021
A Two-Stage Transformer Framework for Sparse-Array Direction-of-Arrival Estimation via Correlation Vector Recovery
Wenchao He1,2, Yiran Shi2, Hongxi Zhao2
1School of Mechanical and Electrical Engineering, Changchun Humanities and Sciences College, Changchun 130117, China.
Sensors (Basel, Switzerland)
|May 27, 2026
Summary
This study introduces a two-stage Transformer framework for accurate direction-of-arrival (DOA) estimation using sparse arrays. The method reconstructs sensor data, improving performance in low signal-to-noise ratio and limited observation scenarios.
Area of Science:
- Array Signal Processing
- Machine Learning for Signal Processing
Background:
- Accurate direction-of-arrival (DOA) estimation is crucial for array sensing.
- Sparse arrays and limited observations degrade conventional DOA estimator performance.
- Incomplete second-order statistics cause significant performance degradation.
Purpose of the Study:
- Propose a novel two-stage Transformer framework for robust DOA estimation.
- Address challenges posed by sparse arrays and snapshot-limited data.
- Enhance accuracy and stability in low signal-to-noise ratio (SNR) regimes.
Main Methods:
- A two-stage Transformer framework separates correlation recovery and angle inference.
- Stage one reconstructs complete correlation vectors using masking-aware tokenization and global-context modeling.
- Stage two employs a Transformer regressor for direct DOA prediction from recovered features.
Main Results:
- The proposed method demonstrates robust accuracy and improved stability in low-SNR and snapshot-limited conditions.
- Achieves competitive performance at higher SNRs.
- Recovery-based covariance outperforms conventional difference-coarray processing, especially under noise.
Conclusions:
- The Transformer framework effectively reconstructs incomplete sensor data for DOA estimation.
- The approach offers significant advantages in challenging sparse-array scenarios.
- Provides a reliable alternative to traditional methods for DOA estimation.
Related Concept Videos
01:26Linear Approximation in Frequency Domain
Linear systems are characterized by two main properties: superposition and homogeneity. Superposition allows the response to multiple inputs to be the sum of the responses to each individual input. Homogeneity ensures that scaling an input by a scalar results in the response being scaled by the same scalar.
In contrast, nonlinear systems do not inherently possess these properties. However, for small deviations around an operating point, a nonlinear system can often be approximated as linear.
In contrast, nonlinear systems do not inherently possess these properties. However, for small deviations around an operating point, a nonlinear system can often be approximated as linear.
01:08Vector Algebra: Method of Components
It is cumbersome to find the magnitudes of vectors using the parallelogram rule or using the graphical method to perform mathematical operations like addition, subtraction, and multiplication. There are two ways to circumvent this algebraic complexity. One way is to draw the vectors to scale, as in navigation, and read approximate vector lengths and angles (directions) from the graphs. The other way is to use the method of components.
In many applications, the magnitudes and directions of...
In many applications, the magnitudes and directions of...
01:21Linear Approximation in Time Domain
Nonlinear systems often require sophisticated approaches for accurate modeling and analysis, with state-space representation being particularly effective. This method is especially useful for systems where variables and parameters vary with time or operating conditions, such as in a simple pendulum or a translational mechanical system with nonlinear springs.
For a simple pendulum with a mass evenly distributed along its length and the center of mass located at half the pendulum's length, the...
For a simple pendulum with a mass evenly distributed along its length and the center of mass located at half the pendulum's length, the...
01:14Extraction: Partition and Distribution Coefficients
The distribution law or Nernst's distribution law is the law that governs the distribution of a solute between two immiscible solvents. This law, also known as the partition law, states that if a solute is added to the mixture of two immiscible solvents at a constant temperature, the solute is distributed between the two solvents in such a way that the ratio of solute concentrations in the solvents remains constant at equilibrium.
For extracting a solute from an aqueous phase into an organic...
For extracting a solute from an aqueous phase into an organic...
01:10Reconstruction of Signal using Interpolation
Signal processing techniques are essential for accurately converting continuous signals to digital formats and vice versa. When a continuous signal is sampled with a period T, the resulting sampled signal exhibits replicas of the original spectrum in the frequency domain, spaced at intervals equal to the sampling frequency. To handle this sampled signal, a zero-order hold method can be applied, which creates a piecewise constant signal by retaining each sample's value until the next sampling...
01:29Direction Cosines of a Vector
Direction cosines, which help describe the orientation of a vector with respect to the coordinate axes, are an essential concept in the field of vector calculus. Consider vector A that is expressed in terms of the Cartesian vector form using i, j, and k unit vectors. The magnitude of vector A is defined as the square root of the sum of the squares of its components. The direction of this vector with respect to the x, y, and z axes is defined by the coordinate direction angles α, β, and γ,...