For direction-of-arrival estimation problems, deep learning (DL) has shown excellent performance recently owing to the effectiveness and robustness to complicated cases. However, DL is always requiring massive data and lacks explainable theory, which limits its practical application. Fortunately, deep unfolding is able to overcome the disadvantages of DL and empirically achieves fast convergence. Inspired by that, we construct a deep unfolded network according to the famous Sparse Learning via Iterative Minimization (SLIM), yielding a method called learned-SLIM (LSLIM). LSLIM is able to converge efficiently and inherits the advantages of SLIM, such as low computational complexity, excellent sparsity performance. In addition, nested array is further adopted in LSLIM for high estimation accuracy. Extensive simulations are presented to illustrate the superior of the proposed LSLIM beyond other state-of-the-art algorithms.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.