Optimizing channel capacity for B5G with deep learning approaches in MISO-NOMA-HBF and BFNN 1 of 1
| dc.contributor.author | Masud, M.A. | |
| dc.contributor.author | Al Amin, A., | |
| dc.contributor.author | Islam, Md.S., | |
| dc.contributor.author | Mostafa, V. | |
| dc.contributor.author | Wahiduzzaman, Md. | |
| dc.date.accessioned | 2025-04-25T10:35:30Z | |
| dc.date.issued | 2024-06-25 | |
| dc.description.abstract | This study proposes the integration of a beamforming neural network (BFNN) and multiple-input single-output based non-orthogonal multiple access (MISO-NOMA) with hybrid beamforming (HBF) for cell edge users (CEU) in a millimeter wave (mmWave)-based beyond 5G cellular communication system. This system is referred to as MISO-NOMA-HBFBFNN. The proposed scheme has been implemented to support multiple users simultaneously and also to considerably enhance and significantly improve the overall the sum channel capacity (SC) and user channel capacities. Additionally, the simulation results demonstrate the superiority of the proposed MISO-NOMA-HBF-BFNN scheme over the existing MISO-NOMA with HBF and MISO-OMA with HBFBFNN based schemes in terms of user capacities and SC | |
| dc.identifier.citation | Islam, M. S., Al Amin, A., & Masood, M. A. (2023). Deep Learning-based MISO-NOMA-HBF-BFNN to Improve Channel Capacity for B5G. Authorea Preprints. | |
| dc.identifier.issn | 25024752 | |
| dc.identifier.uri | http://dspace.uttarauniversity.edu.bd:4000/handle/123456789/412 | |
| dc.language.iso | en | |
| dc.publisher | Institute of Advanced Engineering and Science | |
| dc.subject | Beamforming | |
| dc.subject | 5G | |
| dc.subject | deep learning | |
| dc.subject | hybrid beamforming | |
| dc.subject | Machine Learning | |
| dc.title | Optimizing channel capacity for B5G with deep learning approaches in MISO-NOMA-HBF and BFNN 1 of 1 | |
| dc.type | Article |