本篇論文提出以數據驅動的方式用於適應均勻線性陣列天線(Uniform Linear Array, ULA) 中存在的各種陣列缺陷(Array imperfection) 並估計訊號到達的方向(Direction of Arrival, DOA) 獲得良好的陣列缺陷適應性與增強通用性。在深度學習演算法提出摺積自動編碼器的架構比一般的深度自動編碼器強調了學習局部的結構特徵，自動編碼器的概念類似空間濾波器，將入射訊號的空間範圍分解成多個較小的子空間範圍，在此架構下比起原始的入射訊號每個子空間涵蓋的入射範圍更窄使得入射訊號的的分佈更加集中，有助於減輕後續DOA 估計的負擔。在機器學習演算法中支撐向量機(Support Vector Machine, SVM) 利用核函數將數據映射至高維度的空間進行分類，在對DOA 估計進行分類時，我們使
用有向無環圖(Directed Acyclic Graph, DAG) 改善一般Multiclass SVM 處生的不可辨識區域的問題。在結果分析與比較中，可以看出以數據驅動的方法在各種陣列缺陷下均有令人滿意的性能。

This thesis studies a datadriven approach adapted to various imperfections in uniform linear array (ULA), which can estimate the direction of arrival (DOA) to obtain a good adaptability and enhance versatility for imperfect arrays. The architecture of the convolutional autoencoder in deep learning substantially focuses on the learning of local features of the structure than that of the general deep autoencoder. The autoencoder acts like a group of spatial filters, decomposing the input into multiple small spatial sub-regions. The range of the input covered by each spatial sub-region is narrower than that of the original input, and hence, the distribution of the input is better centralized. In machine learning algorithms, support vector machines (SVM) use kernel functions to map data in a high-dimensional space for classification. For the application of DOA estimation, we apply Directed Acyclic Graph (DAG) to solve the problem of unidentifiable regions with the general multi-class SVM. From simulation analysis and comparison, it can be seen that the data-driven method has satisfactory performance for different cases of imperfect arrays.

[1] R. Schmidt, “Multiple emitter location and signal parameter estimation,”
IEEE Transactions on Antennas and Propagation, vol. 34,
no. 3, pp. 276–280, 1986.
[2] N. Yuen and B. Friedlander, “Asymptotic performance analysis
of esprit, higher order esprit, and virtual esprit algorithms,” IEEE
Transactions on Signal Processing, vol. 44, no. 10, pp. 2537–2550,
1996.
[3] B. Friedlander and A. J. Weiss, “Direction finding in the presence
of mutual coupling,” IEEE Transactions on Antennas and Propagation,
vol. 39, no. 3, pp. 273–284, 1991.
[4] M. Viberg and A. L. Swindlehurst, “Analysis of the combined effects
of finite samples and model errors on array processing performance,”
IEEE Transactions on Signal Processing, vol. 42, no. 11,
pp. 3073–3083, 1994.
[5] W. Xie, C. Wang, F. Wen, J. Liu, and Q. Wan, “Doa and gainphase
errors estimation for noncircular sources with central symmetric array,”
IEEE Sensors Journal, vol. 17, no. 10, pp. 3068–3078, 2017.
[6] B. Porat and B. Friedlander, “Accuracy requirements in offline
array
calibration,” IEEE Transactions on Aerospace and Electronic
Systems, vol. 33, no. 2, pp. 545–556, 1997.
[7] M. Pastorino and A. Randazzo, “A smart antenna system for direction
of arrival estimation based on a support vector regression,”
IEEE Transactions on Antennas and Propagation, vol. 53, no. 7, pp.
2161–2168, 2005.
[8] Z. Liu, C. Zhang, and P. S. Yu, “Directionofarrival
estimation
based on deep neural networks with robustness to array imperfections,”
IEEE Transactions on Antennas and Propagation, vol. 66,
no. 12, pp. 7315–7327, 2018.
[9] A. Randazzo, M. A. AbouKhousa,
M. Pastorino, and R. Zoughi,
“Direction of arrival estimation based on support vector regression:
Experimental validation and comparison with music,” IEEE Antennas
and Wireless Propagation Letters, vol. 6, pp. 379–382, 2007.
[10] X. Xiao, S. Zhao, X. Zhong, D. L. Jones, E. S. Chng, and H. Li, “A
learningbased
approach to direction of arrival estimation in noisy
and reverberant environments,” in 2015 IEEE International Conference
on Acoustics, Speech and Signal Processing (ICASSP), 2015,
pp. 2814–2818.
[11] F. Vesperini, P. Vecchiotti, E. Principi, S. Squartini, and F. Piazza,
“A neural network based algorithm for speaker localization in a
multiroom
environment,” in 2016 IEEE 26th International Workshop
on Machine Learning for Signal Processing (MLSP), 2016, pp.
1–6.
[12] S. Chakrabarty and E. A. P. Habets, “Multispeaker
doa estimation
using deep convolutional networks trained with noise signals,”
IEEE Journal of Selected Topics in Signal Processing, vol. 13, no. 1,
pp. 8–21, 2019.
[13] J. Wang, X. Zhang, Q. Gao, H. Yue, and H. Wang, “Devicefree
wireless localization and activity recognition: A deep learning approach,”
IEEE Transactions on Vehicular Technology, vol. 66, no. 7,
pp. 6258–6267, 2017.
[14] L. Zhao, H. Huang, X. Li, S. Ding, H. Zhao, and Z. Han, “An accurate
and robust approach of devicefree
localization with convolutional
autoencoder,” IEEE Internet of Things Journal, vol. 6, no. 3,
pp. 5825–5840, 2019.
[15] D. Isa, L. H. Lee, V. P. Kallimani, and R. RajKumar, “Text document
preprocessing with the bayes formula for classification using
the support vector machine,” IEEE Transactions on Knowledge and
Data Engineering, vol. 20, no. 9, pp. 1264–1272, 2008.
[16] J. Yousafzai, P. Sollich, Z. Cvetkovic, and B. Yu, “Combined features
and kernel design for noise robust phoneme classification using
support vector machines,” IEEE Transactions on Audio, Speech,
and Language Processing, vol. 19, no. 5, pp. 1396–1407, 2011.
[17] M. Pontil and A. Verri, “Support vector machines for 3d object
recognition,” IEEE Transactions on Pattern Analysis and Machine
Intelligence, vol. 20, no. 6, pp. 637–646, 1998.
[18] F. Ben Abid, S. Zgarni, and A. Braham, “Distinct bearing faults
detection in induction motor by a hybrid optimized swpt and ainetdag
svm,” IEEE Transactions on Energy Conversion, vol. 33, no. 4,
pp. 1692–1699, 2018.
[19] Z. Sun, Z. Guo, C. Liu, X. Wang, J. Liu, and S. Liu, “Fast extended
oneversusrest
multilabel
support vector machine using approximate
extreme points,” IEEE Access, vol. 5, pp. 8526–8535, 2017.
[20] P. Jungwirth and J. V. Monaco, “Digital signal processing: From
complex numbers to the hilbert transform,” in 2019 SoutheastCon,
2019, pp. 1–6.
[21] A. M. Elbir, “A novel data transformation approach for doa estimation
with 3d
antenna arrays in the presence of mutual coupling,”
IEEE Antennas and Wireless Propagation Letters, vol. 16,
pp. 2118–2121, 2017.
[22] W. Wang, R. Wu, J. Liang, and H. C. So, “Phase retrieval approach
for doa estimation with array errors,” IEEE Transactions on
Aerospace and Electronic Systems, vol. 53, no. 5, pp. 2610–2620,
2017.
[23] P. Forster, “Generalized rectification of cross spectral matrices for
arrays of arbitrary geometry,” IEEE Transactions on Signal Processing,
vol. 49, no. 5, pp. 972–978, 2001.
[24] M. Dehghanpour, V. T. Vakili, and A. Farrokhi, “Doa estimation
using multiple kernel learning svm considering mutual coupling,”in 2012 Fourth International Conference on Intelligent Networking
and Collaborative Systems, 2012, pp. 55–61.
[25] N. Cristianini and E. Ricci, Support Vector Machines. Boston,
MA: Springer US, 2008, pp. 928–932. [Online]. Available:
https://doi.org/10.1007/9780387301624_
415
[26] M. Ha Quang, P. Niyogi, and Y. Yao, “Mercer’s theorem, feature
maps, and smoothing.” 01 2006, pp. 154–168.
[27] D. Singh and C. K. Mohan, “Distributed quadratic programming
solver for kernel svm using genetic algorithm,” in 2016 IEEE
Congress on Evolutionary Computation (CEC), 2016, pp. 152–159.