Abstract
In this article, we propose a multi-label convolution neural network (MLCNN)-aided transmit antenna selection (AS) scheme for end-to-end multiple-input multiple-output (MIMO) Internet of Things (IoT) communication systems in correlated channel conditions. In contrast to the conventional single-label multi-class classification ML schemes, we opt for using the concept of multi-label in the proposed MLCNN-aided transmit AS MIMO IoT system, which may greatly reduce the length of training labels in the case of multi-antenna selection. Additionally, applying multi-label concept may significantly improve the prediction accuracy of the trained MLCNN model under correlated large-scale MIMO channel conditions with less training data. The corresponding simulation results verified that the proposed MLCNN-aided AS scheme may be capable of achieving near-optimal capacity performance in real time, and the performance is relatively insensitive to the effects of imperfect CSI.
Highlights
In recent years, as an emerging communication paradigm, the Internet of Things (IoT) has drawn researchers’ substantial attention due to its capability of providing massive low cost connections for a wide range of smart applications [1]
The novel contribution of this work is that we propose a multi-label convolutional neural network (MLCNN)-aided capacity-based AS (CBAS) algorithm for correlated MIMO systems by exploiting the advantages of the machine learning (ML) schemes
IoT system equipped with NT transmit antennas (TAs) and NR receive antennas (RAs), as well as employing Lt transmit RF chains and
Summary
As an emerging communication paradigm, the Internet of Things (IoT) has drawn researchers’ substantial attention due to its capability of providing massive low cost connections for a wide range of smart applications [1]. The optimal performance of CBAS is usually achieved by ergodic search-based methods, which may significantly increase the computational complexity in MIMO systems. With the increase of the antenna scale under the correlated MIMO channel conditions, the complexity of these multi-class classification learning schemes may increase with degraded performance Against this background, the novel contribution of this work is that we propose a multi-label convolutional neural network (MLCNN)-aided CBAS algorithm for correlated MIMO systems by exploiting the advantages of the ML schemes. In contrast to the conventional single-label multi-class classification ML schemes, our proposed MLCNN-based AS scheme may greatly reduce the length of training labels in the case of multi-antenna selection and significantly improve the prediction accuracy of the trained MLCNN model under correlated large-scale MIMO channel conditions with less training data.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
