跳到主要內容

臺灣博碩士論文加值系統

(44.223.39.67) 您好!臺灣時間:2024/05/26 13:30
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

: 
twitterline
研究生:高士淳
研究生(外文):KAO, SHIH-CHUN
論文名稱:上行多天線NOMA視訊傳輸系統下使用 多任務學習方法的用戶選擇
論文名稱(外文):Multi-task Learning Approach for User Selection in Uplink Multi-Antenna Non-Orthogonal Multiple Access Video Transmission System
指導教授:曾恕銘
指導教授(外文):TSENG, SHU-MING
口試委員:曾恕銘曾德峰張立中陳永芳
口試委員(外文):TSENG, SHU-MINGTSENG, DER-FENGCHANG, LI-CHUNGCHEN, YUNG-FANG
口試日期:2019-07-23
學位類別:碩士
校院名稱:國立臺北科技大學
系所名稱:電子工程系
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2019
畢業學年度:107
語文別:中文
論文頁數:22
中文關鍵詞:深度學習多任務學習深度神經網路多天線非正交多重存取用戶選擇
外文關鍵詞:Deep LearningMulti-task LearningDeep Neural NetworksMulti-AntennaNon-orthogonal multiple accessUser selection
相關次數:
  • 被引用被引用:0
  • 點閱點閱:256
  • 評分評分:
  • 下載下載:15
  • 收藏至我的研究室書目清單書目收藏:0
在先前文獻當中,Kim等人提出了次佳的用戶選擇和最優功率分配(限制速率總合),而Fang提出了不同的次佳用戶選擇。然而,在這兩篇文獻當中的性能仍遠低於最佳用戶分組方案。我們為多天線NOMA系統中的用戶組提出了多任務學習(MTL)方式,並針對NOMA用戶分組的損失函數做修改。模擬數值結果表明,本文所提出的方案PSNR數值高於以往的次佳方案,且接近最佳方案。
In prior work, [Kim15] proposed a suboptimal user selection and optimal power allocation(constrain in sum sate) while [Fang18] proposed different suboptimal user select with user substitution. However, the performance of [Kim15] [Fang18] is still much lower than the optimal user grouping scheme. We propose a multi-task learning (MTL) for user group in multi-antenna NOMA systems and propose loss function modification specific for NOMA user grouping. The numerical results show that PSNR of the proposal scheme is higher than the previous suboptimal schemes and close to the optimal scheme.
摘要 i
ABSTRACT ii
誌謝 iii
目錄 iv
表目錄 v
圖目錄 vi
第一章 緒論 1
第二章 上行SIMO NOMA視訊傳輸系統模型 4
2.1 系統架構 4
2.2 接收訊號模型 5
2.3 ZF後置編碼器 6
2.4 接收SINR 6
2.5 視訊失真模型 7
第三章用戶集合選擇方案與功率分配演算法 9
3.1 [7]之用戶集合選擇方案 9
3.2 [9]之用戶集合選擇方案 9
3.3 [7]之功率分配演算法 10
3.4 [9]之功率分配演算法 11
第四章 深度神經網路 12
4.1 神經網路架構 12
4.2神經網路架構 13
4.3訓練/測驗數據 14
第五章 模擬結果 16
第六章 結論 20
參考文獻 21

[1] MediaTek Inc. and CMCC, “Downlink multiuser superposition transmissions for LTE,” 3GPP TSG RAN Meeting #71, Gothenburg, Sweden, Tech. Rep. RP-160680, Mar. 2016.
[2] Study on Downlink Multiuser Superposition Transmission for LTE, document, 3rd Generation Partnership Project (3GPP), Mar. 2015.
[3] Zhang, Liang, et al. “Layered-division-multiplexing: Theory and practice.” IEEE Transactions on Broadcasting, vol. 62, no. 1, pp. 216-232, Jan. 2016.
[4] L. Dai, B. Wang, Y. Yuan, S. Han, C. l. I, and Z. Wang, “Non-orthogonal multiple access for 5G: Solutions, challenges, opportunities, and future research trends,” IEEE Commun. Mag., vol. 53, no. 9, pp. 74–81, Sep. 2015
[5] Zhiguo Ding, Yuanwei Liu, Jinho Choi, Qi Sun, Maged Elkashlan, Chih-Lin I, and H. Vincent Poor "Application of non-orthogonal multiple access in LTE and 5G networks," IEEE Communications Magazine, vol. 55, no. 2, pp. 185-191, 2017.
[6] H. Li, W. He, Q. He, and J. He, ‘‘The application and development of SIC technology in wireless communication system,’’ in Proc. IEEE 9th Int. Conf. Commun. Softw. Netw. (ICCSN), Guangzhou, China, May 2017, pp. 565–570
[7] B. Kim, W. Chung, “Uplink NOMA with Multi-Antenna,” in Proc. Of IEEE VTC 2015-Spring, Scotland, UK.
[8] S. Qureshi and S. A. Hassan, “MIMO uplink NOMA with successive bandwidth division,” IEEE Wireless Communications and Networking Conference (WCNC), Apr. 2016
[9] Hao-Hsin Fang, “User Grouping and Power Allocation for Cross Layer Uplink NOMA Video Communication Systems with Multi-Antenna,” M.S. thesis, Department of Electronic Engineering, National Taipei University of Technology, Jul. 2018, Advisor: Shu-Ming Tseng.
[10] J.-M. Kang and I.-M. Kim, ‘‘Optimal user grouping for downlink NOMA,’’ IEEE Wireless Commun. Lett., vol. 7, no. 5, pp. 724–727, Oct. 2018.
[11] M. S. Ali, E. Hossain, A. Al-Dweik, and D. I. Kim, “Downlink power allocation for CoMP-NOMA in multi-cell networks,” IEEE Trans. Commun., vol. 66, no. 9, pp. 3982–3998, Sep. 2018.
[12] Youngwook Kim, “Application of Machine Learning to Antenna Design and Radar Signal Processing: A Review,” 2018 International Symposium on Antennas and Propagation (ISAP). IEEE, 2018. p. 1-2.
[13] Haoran Sun, Xiangyi Chen, Qingjiang Shi, Mingyi Hong, Xiao Fu, and Nikos D Sidiropoulos. ‘‘Learning to optimize: Training deep neural networks for wireless resource management,’’ In Proc. 18th IEEE International Workshop on Signal Processing Advances in Wireless Communications (SPAWC), pages 1–6, 2017
[14] Guan Gui, Hongji Huang, Yiwei Song, and Hikmet Sari, “Deep Learning for an Effective Non orthogonal Multiple Access Scheme,” IEEE Trans. Vehicular Technology, vol. 67 no. 9, pp. 8440-8450, 2018.
[15] Goutam Mylavarapu, Johnson P Thomas ‘‘A multi-task machine learning approach for comorbid patient prioritization,’’ 2017 IEEE International Conference on Big Data. IEEE, 2017. p. 3877-3881.
[16] Jinlong Ji, Xuhui Chen, Changqing Luo, and Pan Li. ‘‘A deep multi-task learning approach for ECG data analysis,’’Biomedical & Health Informatics (BHI), 2018 IEEE EMBS International Conference on. IEEE, 124--127.
[17] Dawei Wang, Laura Toni, Pamela C. Cosman, and Laurence B. Milstein, “Uplink resource management for multiuser OFDM video transmission systems: analysis and algorithm design,” IEEE Trans. Commun., vol. 61, no. 5, pp. 2060-2073, May 2013.
[18] K. Stuhlmuller, N. Farber, M. Link, and B. Girod, “Analysis of video transmission over lossy channels,” IEEE J. Sel. Areas Commun., vol. 18, no. 6, pp. 1012-1032, Jun 2000.
[19] W. Lee, ‘‘Resource allocation for multi-channel underlay cognitive radio network based on deep neural network,’’ IEEE Commun. Lett., vol. 22, no. 9, pp. 1942–1945, Sep. 2018.

QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
無相關期刊