隨著網際網路無遠弗屆的應用所伴隨著行動裝置的普及所引導出無線網路通訊應用的迅速發展，因此無線連網裝置速率提升的需求與日俱增。提升無線網路傳輸品質研究更是現階段無線通訊發展的重心。保持現有的硬體裝置中來提升無線網路的傳輸品質是較容易達成且節省費用的做法之一，因此提升天線的效能進而達到穩定地將無線網路傳輸提升的想法應孕而生，其中利用智能天線的場型選擇已是已廣泛的思考並應用於無線設備之中。本研究是利用多樣性天線選擇的方案應用於具有高度移動性的筆記型電腦環境下，不僅利用無線信號建模和預測機器學習在天線選擇解決方案中，更加入數字驅動方式用以强化提升無線網路的傳輸品質反應出實際運用的結果。其中本文首先針對多樣型天線選擇整體的系統設計與學理說明接著對所取得的無線訊號進行分析與探討，利用無線通訊信號資料集並加入標籤化的數據驅動資料數據等，最後以機器學習的智能方法達成提升天線選擇的精確度。本實驗以支援向量機 (SVM)、神經網路 (NN)等學習方式與傳統以誤差向量幅度 (EVM) 套用於數據驅動中在多樣性天線架構選擇做比較。從實驗結果的預測中證明套用機器學習的方式與傳統以誤差向量幅度 (EVM)的天線選擇的精確度結果比較有著明顯的提升，從而實現移動無線通訊設備的精確的天線調整，提高無線傳輸質量。

With the widespread application of the Internet and the popularization of mobile devices, the rapid development of wireless network applications leads to an ever-increasing demand for the speed of wireless networking devices. The research on improving the transmission quality of wireless networks is one of the critical points in developing wireless communication at this stage. Keeping the existing hardware device to improve the transmission quality of the wireless network is cost-effective and easy to achieve. Therefore, enhancing the antenna's efficiency to reach stable wireless network transmission emerged. The field type selection using the smart antenna has been widely considered and applied to wireless devices. In this study, the solution of diversity antenna selection applies to the laptop with high mobility that uses wireless signal data modeling and prediction by machine learning. The wireless communication signal data labeling and data-driven intelligent machine learning method improve antenna selection accuracy. This article starts with leading data-driven strategies to enhance the wireless transmission quality of the network, reflecting the results of actual use. This paper first aims at the overall system design and theoretical explanation of the selection of various antennas. It then analyzes and discusses the obtained wireless signals. In this experiment, the wireless signal data and the data-driven training dataset compare the SVM (Support Vector Machine), NN (Neural Network) learning methods, and EVM (Error Vector Magnitude) in diverse antenna selection mechanisms. The prediction from the experimental results presents that the accuracy of the technique of applying machine learning is significantly improved compared with the traditional EVM antenna selection method. Thus, the accuracy of the antenna adjustment of the mobile wireless communication device is realized, and the wireless transmission quality is improved.

[1] T. Younas, J. Li et al., On Bandwidth Efficiency Analysis for LS-MIMO With Hardware Impairments, IEEE Access, vol. 5, pp. 5994-6001.
[2] F. A. P. d. Figueiredo, An Overview of Massive MIMO for 5G and 6G, IEEE Latin America Transactions, vol. 20, no. 6, pp. 931-940.
[3] C. Wu, C.-F. Lai, A survey on improving the wireless communication with adaptive antenna selection by intelligent method, Computer Communications, vol. 181, pp. 374-403.
[4] G. C. Huang, M. F. Iskander et al., Antenna Array Design and System for Directional Networking, IEEE Antennas and Wireless Propagation Letters, vol. 14, pp. 1141-1144.
[5] L. Jihao, Antenna on board package for 5G millimeter wave phased array antenna, 2020 21st International Conference on Electronic Packaging Technology (ICEPT), pp. 1-5, 12-15 Aug. 2020.
[6] C. Zhao, Y. Liu et al., Broadband Dual Polarization Antenna Array for 5G Millimeter Wave Applications, 2019 International Symposium on Antennas and Propagation (ISAP), pp. 1-3, 27-30 Oct. 2019.
[7] S. Matthie, S. Lindenmeier, A Testing Platform for Investigation of GNSS Antenna Diversity Systems, 2020 14th European Conference on Antennas and Propagation (EuCAP), pp. 1-4, 15-20 March 2020.
[8] I. Ahamed, M. Vijay, Comparison of different diversity techniques in MIMO antennas, 2017 2nd International Conference on Communication and Electronics Systems (ICCES), pp. 47-50, 19-20 Oct. 2017.
[9] R. Bhattacharya, R. Garg et al., Design of a PIFA-Driven Compact Yagi-Type Pattern Diversity Antenna for Handheld Devices, IEEE Antennas and Wireless Propagation Letters, vol. 15, pp. 255-258.
[10] R. Zabihi, R. G. Vaughan, Dual-port Conformal PIFA Diversity Antenna for Small Cylindrical Groundplane Mounting, 2018 IEEE International Symposium on Antennas and Propagation & USNC/URSI National Radio Science Meeting, pp. 29-30, 8-13 July 2018.
[11] S. Chen, Q. Gao et al., A CSI acquisition approach for mmWave massive MIMO, China Communications, vol. 16, no. 9, pp. 1-14.
[12] M. A. v. Wyk, L. Ping et al., Multivaluedness in Networks: Shannon’s Noisy-Channel Coding Theorem, IEEE Transactions on Circuits and Systems II: Express Briefs, vol. 68, no. 10, pp. 3234-3235.
[13] C. Oikonomopoulos-Zachos, E. Stavrou et al., A MIMO antenna array with shaped beam in waveguide technology for WiFi base stations, 2017 International Workshop on Antenna Technology: Small Antennas, Innovative Structures, and Applications (iWAT), pp. 175-178, 1-3 March 2017.
[14] C. Wu, C. Lai, Data-driven diversity antenna selection for MIMO communication using machine learning, Journal of Internet Technology, vol. 23, no. 1, pp. 1-9.
[15] R. Cornelius, A. Narbudowicz et al., Calculating the envelope correlation coefficient directly from spherical modes spectrum, 2017 11th European Conference on Antennas and Propagation (EUCAP), pp. 3003-3006, 19-24 March 2017.
[16] X. Mei, K. L. Wu, Envelope Correlation Coefficient for Multiple MIMO Antennas of Mobile Terminals, 2020 IEEE International Symposium on Antennas and Propagation and North American Radio Science Meeting, pp. 1597-1598, 5-10 July 2020.
[17] Z. Zeng, M. Shao, Impact of EVM on Network Performance, 2018 International Conference on Sensor Networks and Signal Processing (SNSP), pp. 13-16, 28-31 Oct. 2018.
[18] H. Jiang, P. Gong et al., EVM Measurement and Correction for Digitally Modulated Signals, 2018 Conference on Precision Electromagnetic Measurements (CPEM 2018), pp. 1-2, 8-13 July 2018.
[19] M. Jomoto, N. Kikuma et al., Simultaneous estimation of DOA and angular spread of incident radio waves by DOA-Matrix method with SLS and SAGE algorithms, 2015 International Symposium on Antennas and Propagation (ISAP), pp. 1-2, 9-12 Nov. 2015.
[20] W. Yan, DOA Measurement of Moving Targets, 2020 Cross Strait Radio Science & Wireless Technology Conference (CSRSWTC), pp. 1-3, 13-16 Dec. 2020.
[21] C. Ji, F. Zhang, New DOA estimation based on coprime array MIMO radar, 2021 China Automation Congress (CAC), pp. 1041-1045, 22-24 Oct. 2021.
[22] K. E. Ahmed, K. M. Attiah et al., Multiple signal classification algorithm compensated by Extended Kalman Particle Filtering for Wi-Fi through wall multi-target tracking, 2016 IEEE-APS Topical Conference on Antennas and Propagation in Wireless Communications (APWC), pp. 66-69, 19-23 Sept. 2016.
[23] Z. Wang, Z. Yang et al., An Improved Multiple Signal Classification for Nonuniform Sampling in Blade Tip Timing, IEEE Transactions on Instrumentation and Measurement, vol. 69, no. 10, pp. 7941-7952.
[24] Y. Zhou, A. Liu et al., EF-ESPRIT: A simplified ESPRIT algorithm without generalized eigenvalue calculation, Proceedings of 2013 3rd International Conference on Computer Science and Network Technology, pp. 772-776, 12-13 Oct. 2013.
[25] J. Lin, X. Ma et al., Time-Frequency Multi-Invariance ESPRIT for DOA Estimation, IEEE Antennas and Wireless Propagation Letters, vol. 15, pp. 770-773.
[26] A. Barthelme, W. Utschick, A Machine Learning Approach to DoA Estimation and Model Order Selection for Antenna Arrays With Subarray Sampling, IEEE Transactions on Signal Processing, vol. 69, pp. 3075-3087.
[27] X. Wang, P. Wang et al., Adaptive Sparse Array Reconfiguration based on Machine Learning Algorithms, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1159-1163, 15-20 April 2018.
[28] P. Yang, Y. Xiao et al., Adaptive Spatial Modulation MIMO Based on Machine Learning, IEEE Journal on Selected Areas in Communications, vol. 37, no. 9, pp. 2117-2131.
[29] A. M. Elbir, K. V. Mishra et al., CNN-Based Cognitive Radar Array Selection, 2019 IEEE Radar Conference (RadarConf), pp. 1-5, 22-26 April 2019.
[30] M. S. Sim, Y. G. Lim et al., Deep Learning-Based mmWave Beam Selection for 5G NR/6G With Sub-6 GHz Channel Information: Algorithms and Prototype Validation, IEEE Access, vol. 8, pp. 51634-51646.
[31] R. Yao, Y. Zhang et al., Deep Neural Network Assisted Approach for Antenna Selection in Untrusted Relay Networks, IEEE Wireless Communications Letters, vol. 8, no. 6, pp. 1644-1647.
[32] W. T. Li, H. S. Tang et al., Efficient Online Data-Driven Enhanced-XGBoost Method for Antenna Optimization, IEEE Transactions on Antennas and Propagation, vol. 70, no. 7, pp. 4953-4964.
[33] E. M. Lizarraga, G. N. Maggio et al., Hybrid beamforming algorithm using reinforcement learning for millimeter wave wireless systems, 2019 XVIII Workshop on Information Processing and Control (RPIC), pp. 253-258, 18-20 Sept. 2019.
[34] M. S. Ibrahim, A. S. Zamzam et al., Learning-Based Antenna Selection for Multicasting, 2018 IEEE 19th International Workshop on Signal Processing Advances in Wireless Communications (SPAWC), pp. 1-5, 25-28 June 2018.
[35] T. X. Vu, L. Lei et al., Machine Learning based Antenna Selection and Power Allocation in Multi-user MISO Systems, 2019 International Symposium on Modeling and Optimization in Mobile, Ad Hoc, and Wireless Networks (WiOPT), pp. 1-6, 3-7 June 2019.
[36] T. X. Vu, S. Chatzinotas et al., Machine Learning-Enabled Joint Antenna Selection and Precoding Design: From Offline Complexity to Online Performance, IEEE Transactions on Wireless Communications, vol. 20, no. 6, pp. 3710-3722.
[37] X. Chai, H. Gao et al., Reinforcement learning based antenna selection in user-centric massive MIMO, 2020 IEEE 91st Vehicular Technology Conference (VTC2020-Spring), pp. 1-6.
[38] P. Ge, T. Lv, Data enabled Self-Organizing Network with Adaptive Antennas based on Proactive Prediction for Enabling 5G, 2018 IEEE/CIC International Conference on Communications in China (ICCC), pp. 52-56, 16-18 Aug. 2018.
[39] H. H. Huang, Z. Wang et al., Efficient parameter selection for SVM: The case of business intelligence categorization, 2017 IEEE International Conference on Intelligence and Security Informatics (ISI), pp. 158-160, 22-24 July 2017.
[40] L. Duan, Teaching Quality Evaluation System based on Optimal Neural Network and SVM, 2022 International Conference on Information System, Computing and Educational Technology (ICISCET), pp. 83-86, 23-25 May 2022.
[41] Z. Wen, J. Shi et al., Efficient Multi-Class Probabilistic SVMs on GPUs, IEEE Transactions on Knowledge and Data Engineering, vol. 31, no. 9, pp. 1693-1706.
[42] V. K. Singh, Proposing a New ANN model for solving XNOR problem, 2016 International Conference System Modeling & Advancement in Research Trends (SMART), pp. 32-36, 25-27 Nov. 2016.
[43] Z. Stanković, O. Pronić-Rančić et al., ANN Model for DoA Estimation of the Signal Received by Crumpled Textile Wearable Antenna Array, 2022 57th International Scientific Conference on Information, Communication and Energy Systems and Technologies (ICEST), pp. 1-4, 16-18 June 2022.
[44] Y. Pan, H. Yu, Biomimetic Hybrid Feedback Feedforward Neural-Network Learning Control, IEEE Transactions on Neural Networks and Learning Systems, vol. 28, no. 6, pp. 1481-1487.
[45] L. Li, Improvement of Computer Neural Network based on Feedforward Sequence Memory, 2022 IEEE 2nd International Conference on Electronic Technology, Communication and Information (ICETCI), pp. 1068-1071, 27-29 May 2022.
[46] Y. Okawa, T. Nitta, Learning Properties of Feedforward Neural Networks Using Dual Numbers, 2021 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), pp. 187-192, 14-17 Dec. 2021.
[47] S. t. Zhao, X. w. Gao, Neural network adaptive state feedback control of a magnetic levitation system, The 26th Chinese Control and Decision Conference (2014 CCDC), pp. 1602-1605, 31 May-2 June 2014.
[48] J. Toro, Y. K. Choukiker, Design and analysis of meanderline PIFA antenna with MIMO system for mobile handheld device, 2017 International Conference on Trends in Electronics and Informatics (ICEI), pp. 1061-1065, 11-12 May 2017.
[49] A. Verma, D. Punetha et al., A Novel Quad Band Compact Meandered PIFA Antenna for GPS, UMTS, WiMAX, HiperLAN/2 Applications, 2015 Second International Conference on Advances in Computing and Communication Engineering, pp. 404-408, 1-2 May 2015.