.png){kind=icon}
.png){kind=icon}
Return
Active User Identification Based on Asynchronous Sparse Bayesian Learning With SVM
.png){kind=icon}
OA
AI
DOI：10.1109/ACCESS.2019.2931563.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
In this paper, an asynchronous sparse Bayesian learning (ASBL) algorithm-based receiver for uplink (UL) grant-free transmission is proposed. The time-domain channel estimation is performed by the ASBL algorithm to obtain the channel impulse response (CIR) for each user. Then, the support vector machine (SVM) algorithm is adopted to classify the CIRs of all users. Therefore, the sporadic feature of the massive machine-type communication (mMTC) devices is exploited for identification purpose. The proposed algorithm is verified over asynchronous multipath fading channels and compared with previously compressed sensing (CS)-based algorithms, including the orthogonal matching pursuit (OMP) algorithm and the detecting-based OMP (DOMP) algorithm. Compared with the traditional CS algorithms, the proposed algorithms can reduce the false alarm rate by 70% and obtain a more accurate set of active users.
Keywords:
Massive machine-type communication (mMTC)
asynchronous grant-free multiple access
active user detection
sparse Bayesian learning (SBL)
support vector machine (SVM)
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
3.6
Papers:
9.7W
Citations:
29.4W
Organization
No organization information available