非正交多重接取 (Non-Orthogonal Multiple Access) 將較於傳統的正交多重接取 (Orthogonal Multiple Access) 具有更高的傳輸效率，是無線通訊系統中提升傳輸 效率的選項，在這種趨勢下，稀疏編碼多重接取 (Sparse Code Multiple Access, SCMA) 是碼域非正交多重接取的一項高度競爭技術。可以使用傳統的消息傳遞算 法 (Message Passing Algorithm, MPA) 在接收端還原資料。
本篇論文著重於無授權 SCMA 場景下的用戶檢測與解碼，傳統是使用解調 參考信號 (Demodulation Reference Signal) 進行活動用戶檢測，再使用 MPA 進行 解碼，這需要多花費資源才能完成訊號傳送，我們提出使用深度神經網絡 (Deep Neural Network) 來直接利用接收訊號進行用戶檢測與解碼。在我們的模擬顯示， 我們提出的解決方法可以有效的偵測出用戶是否在傳送資料的狀態，並且解碼出 傳送的資料。

Non-Orthogonal Multiple Access (NOMA) is higher transmission efficiency than traditional Orthogonal Multiple Access (OMA), and is an option to improve transmission efficiency in wireless communication systems. Under this trend, Sparse Code Multiple Access (SCMA) is a highly competitive technology for non-orthogonal multiple access in the code domain. Data can be restored at the received end using traditional Message Passing Algorithm (MPA).
This paper focuses on user detection and decoding in unlicensed sparse coding multiple access scenarios. Traditionally, the demodulation reference signal (DMRS) is used for active user detection, and then MPA is used for decoding, which requires more resources. In order to complete the signal transmission, we propose to use a deep neural network (DNN) to directly use the received signal for user detection and decoding. In our simulations, our proposed solution can effectively detect whether the user is transmitting data, and decode transmitting data.

論文審定書 i
致謝 ii
摘要 iii
Abstract iv
Chapter 1 介紹 1
1.1 研究動機 3
1.2 論文架構 5
Chapter 2 人工智慧概論與應用 6
2.1 興起與發展 6
2.2 機器學習的分類 8
2.3 類神經網路模型分析 10
Chapter 3 SCMA 系統模型 14
3.1 SCMA 傳送端 14
3.2 SCMA 接收端 15
3.3 Joint Message Passing Algorithm 16
Chapter 4 基於深度學習的活動 UE 檢測和解碼器 18
4.1 活動 UE 檢測和解碼器整體架構 18
4.2 JAUDD 的活動 UE 檢測和解碼模型架構 18
4.3 RAUD 活動 UE 檢測 23
Chapter 5 模擬結果 26
5.1 模型訓練設定 27
5.2 我們方法和 JMPA 檢測錯誤率的比較 28
5.3 Missed Detection and False Alarm 29
5.4 累計不同時間再用戶偵測 31
5.5 是否加入解碼及跳接比較 32
5.6 解碼錯誤率比較 33
5.7 JAUDD 解碼部分損失函數比較 34
5.8 運算速度比較 36
5.9 不同機率為活動的活動用戶檢測率 37
Chapter 6 結論 39
參考文獻 40

[1] J. I. Choi, M. Jain, K. Srinivasan, P. Levis, and S. Katti, “Achieving single channel,full duplex wireless communication,” in Proc. ACM MobiCom, Sep. 2010, pp. 1–12.
[2] B. Farhang-Boroujeny, “OFDM versus filter bank multicarrier,” IEEE Signal Process. Mag., vol. 28, no. 3, pp. 92–112, May 2011.
[3] N. Michailow, M. Matthé, I. S. Gaspar, A. N. Caldevilla, L. L. Mendes, A. Festag, and G. Fettweis, “Generalized frequency division multiplexing for 5th generation cellular networks,” IEEE Trans. Commun., vol. 62, no. 9, pp. 3045–3061, Sep. 2014.
[4] S. M. R. Islam, N. Avazov, O. A. Dobre, and K.-S. Kwak, “Power-domain nonorthogonal multiple access (NOMA) in 5g systems: Potentials and challenges,” IEEE Commun. Surveys Tuts., vol. 19, no. 2, pp. 721–742, Oct. 2016.
[5] H. Nikopour and H. Baligh, “Sparse code multiple access,” in Proc. IEEE 24th Int. Symp. Pers. Indoor Mobile Radio Commun. (PIMRC), London, U.K., Sep. 2013, pp. 332–336.
[6] Y. Zhou, Q. Yu, W. Meng, and C. Li, “SCMA codebook design based on constellation rotation,” in Proc. IEEE Int. Conf. Commun.(ICC), Paris,France, May 2017, pp. 1–6.
[7] L. Yu, P. Fan, D. Cai, and Z. Ma, “Design and analysis of SCMA codebook based on star-QAM signaling constellations,” IEEE Trans. Veh. Technol., vol. 67, no. 11, pp. 10 543–10 553, Nov. 2018.
[8] Y. M. Chen and J. W. Chen, “On the design of near-optimal sparse code multiple access codebooks,” IEEE Trans. Commun., vol. 68, no. 5, pp. 2950–2962, May 2020.
[9] A. Ghaffari, M. Leonardon, Y. Savaria, C. Jego, and C. Leroux, “Improving performance of SCMA MPA decoders using estimation of conditional probabilities,” in Proc. 15th IEEE Int. New Circuits Syst. Conf. (NEWCAS), Strasbourg, France, June 2017, pp. 21–24.
[10] Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning,” Nature, vol. 521, no. 7553, pp. 436–444, May 2015.
[11] C. Zhang, P. Patras, and H. Haddadi, “Deep learning in mobile and wireless networking: A survey,” IEEE Commun. Surveys Tuts., vol. 21, no. 3, pp. 2224–2287, 3rd Quart. 2019.
[12] Q. Luo, Z. Liu, G. Chen, Y. Ma, and P. Xiao, “A novel multitask learning empowered codebook design for downlink scma networks,” IEEE Wireless Communications Letters, vol. 11, no. 6, pp. 1268–1272, June 2022.
[13] A. Bayesteh, E. Yi, H. Nikopour, and H. Baligh, “Blind detection of SCMA for uplink grant-free multiple-access,” in Proc. 11th International Symposium on Wireless Communications System (ISWCS), Barcelona, Spain, Aug. 2014, pp. 853–857.
[14] A. Y. Lin, P. N. Chen, S. L. Shieh, and Y. C. Huang, “Generalized likelihood-ratio enabled machine learning for ue detection over grant-free SCMA,” in Proc. IEEE Global Commun. Conf. (GLOBECOM2020), Taipei, Taiwan, Dec. 2020, pp. 1–6.
[15] M. Kim, N. I. Kim, W. Lee, and D.-H. Cho, “Deep learning-aided SCMA,” IEEE Commun. Lett., vol. 22, no. 4, pp. 720–723, 2018.
[16] J. Lin, S. Feng, Y. Zhang, Z. Yang, and Y. Zhang, “A novel deep neural network based approach for sparse code multiple access,” Neurocomputing, vol. 382, pp. 52–63, 2020.
[17] C. P. Wei, H. Yang, C. P. Li, and Y. M. Chen, “SCMA decoding via deep learning,” IEEE Wireless Commun. Lett., vol. 10, no. 4, pp. 878–881, Apr. 2020.
[18] X. Glorot and Y. Bengio, “Understanding the difficulty of training deep feedforward neural networks,” in Proc. thirteenth international conference on artificial intelligence and statistics, Sardinia, Italy, 2010, pp. 249–256.
[19] Q. Liu and J. Wang, “A one-layer recurrent neural network with a discontinuous hard-limiting activation function for quadratic programming,” IEEE Trans. Neural Netw., vol. 19, no. 4, pp. 558–570, Apr. 2008.
[20] H. Y. Lee, “Machine learning and having it deep and structured,” Jan. 2017. [Online]. Available: http://speech.ee.ntu.edu.tw/~tlkagk/courses.html
[21] J. Wang, S. Li, Z. An, X. Jiang, W. Qian, and S. Ji, “Batch-normalized deep neural networks for achieving fast intelligent fault diagnosis of machines,” Neurocomputing, vol. 329, pp. 53–65, Feb. 2019.
[22] K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proc. IEEE conference on computer vision and pattern recognition, June 2016, pp. 770–778.
[23] Altera Innovate Asia website, “The 1 st 5g algorithm innovation compe titionen SCMA,” May 2017. [Online]. Available: http://www.innovateasia.com/5g/images/pdf/InnovateAsia%20-%201st% 205G%20Algorithm%20Competition%20-%20SCMA.pdf
[24] D. P. Kingma and J. Ba, “Adam: A method for stochastic optimization,” arXiv preprint arXiv:1412.6980, Dec. 2014.
[25] L. Liu, H. Jiang, P. He, W. Chen, X. Liu, J. Gao, and J. Han, “On the variance of the adaptive learning rate and beyond,” arXiv preprint arXiv:1908.03265, Aug. 2019.