Page 86 - 《应用声学》2021年第5期

730 2021 年 9 月

ocean waveguide using supervised machine learning[J].
The Journal of the Acoustical Society of America, 2017,
参 考 文 献 142(3): 1176–1188.
[12] Wang Y, Peng H. Underwater acoustic source localization
[1] 张旭, 孙翱, 韩旭, 等. 水下垂向运动目标的海底多基站声定 using generalized regression neural network[J]. The Jour-
位方法及精度分析 [J]. 声学学报, 2019, 44(2): 155–169. nal of the Acoustical Society of America, 2018, 143(4):
Zhang Xu, Sun Ao, Han Xu, et al．Acoustic localiza- 2321–2331.
tion scheme and accuracy analysis for underwater vertical [13] Huang Z, Xu J, Gong Z, et al. Source localization using
motion target using multi-stations in the seabed[J]. Acta deep neural networks in a shallow water environment[J].
Acustica, 2019, 44(2): 155–169. The Journal of the Acoustical Society of America, 2018,
[2] 张雪冬, 牛海强, 吴立新. 一种基于序贯估计的直达声区水面 143(5): 2922–2932.
舰船被动测距方法 [J]. 应用声学, 2020, 39(4): 491–500. [14] Liu Y, Niu H, Li Z. Source ranging using ensemble con-
Zhang Xuedong, Niu Haiqiang, Wu Lixin. Passive track- volutional networks in the direct zone of deep water[J].
ing of a surface ship in the direct zone using sequential pa- Chinese Physics Letters, 2019, 36(4): 044302.
rameter estimation[J]. Journal of Applied Acoustics, 2020, [15] Niu H, Gong Z, Ozanich E, et al. Deep-learning source lo-
39(4): 491–500. calization using multi-frequency magnitude-only data[J].
[3] 刘炎堃, 郭永刚, 李整林, 等. 基于路径选择的深海水下运动 The Journal of the Acoustical Society of America, 2019,
目标被动深度估计 [J]. 应用声学, 2020, 39(5): 647–655. 146(1): 211–222.
Liu Yankun, Guo Yonggang, Li Zhenglin, et al. Depth [16] Liu W, Yang Y, Xu M, et al. Source localization in the
estimation of moving underwater source based on routes deep ocean using a convolutional neural network[J]. The
choosing[J]. Journal of Applied Acoustics, 2020, 39(5): Journal of the Acoustical Society of America, 2020, 147(4):
647–655. EL314–EL319.
[4] Bucker H P. Use of calculated sound fields and matched- [17] 张巧力, 刘福臣. 基于 FFNN 的垂直阵被动定位技术研究 [J].
field detection to locate sound sources in shallow water[J]. 声学与电子工程, 2020(1): 32–36.
The Journal of the Acoustical Society of America, 1976, [18] Niu H, Gerstoft P. Source localization in underwater
59(2): 368–373. waveguides using machine learning[J]. The Journal of the
[5] Baggeroer A B. Matched field processing: source localiza- Acoustical Society of America, 2016, 140(4): 3232–3232.
tion in correlated noise as an optimum parameter estima- [19] Ozanich E R, Gerstoft P, Purohit A. Ocean acoustic range
tion problem[J]. The Journal of the Acoustical Society of estimation in noisy environments using convolutional net-
America, 1988, 83(2): 571–587. works[J]. The Journal of the Acoustical Society of Amer-
[6] Michalopoulou Z H, Porter M B. Matched-field process- ica, 2018, 144(3): 1743–1743.
ing for broad-band source localization[J]. IEEE Journal of [20] Ozanich E, Gerstoft P, Niu H. A feedforward neural
Oceanic Engineering, 1996, 21(4): 384–392. network for direction-of-arrival estimation[J]. The Jour-
[7] Soares C, Jesus S M. Broadband matched-field processing: nal of the Acoustical Society of America, 2020, 147(3):
coherent and incoherent approaches[J]. The Journal of the 2035–2048.
Acoustical Society of America, 2003, 113(5): 2587–2598. [21] Muarry J, Ensberg D. The swellex-96 experiment [DB/
[8] 杨坤德, 马远良, 邹士新, 等. 基于环境扰动的线性匹配场处 OL]. [1996-05-31]. [2019-10-15]. http://www.swellex96.
理方法 [J]. 声学学报, 2006, 43(6): 496–505. ucsd.edu/.
Yang Kunde, Ma Yuanliang, Zou Shixin, et al．Linear [22] Porter M B. The KRAKEN normal mode program[R].
matched field processing based on environmental pertur- Naval Research Lab Washington DC, 1992.
bation[J]. Acta Acustica, 2006, 43(6): 496–505. [23] 杨坤德. 水声信号的匹配场处理技术研究 [D]. 西安: 西北工
[9] 贾雨晴, 苏林, 郭圣明, 等. 浅海时变声速环境下的自适应匹 业大学, 2003.
配场定位算法实现 [J]. 应用声学, 2018, 37(4): 518–527. [24] Specht D F. A general regression neural network[J]. IEEE
Jia Yuqing, Su Lin, Guo Shengming, et al. An adaptive Transactions on Neural Networks, 1991, 2(6): 568–576.
matched-field source localization algorithm in coastal wa- [25] Niu H, Ozanich E, Gerstoft P. Ship localization in Santa
ter under the circumstances of time-evolving sound speed Barbara Channel using machine learning classifiers[J]. The
profiles[J]. Journal of Applied Acoustics, 2018, 37(4): Journal of the Acoustical Society of America, 2017, 142(5):
518–527. EL455–EL460.
[10] Steinberg B Z, Beran M J, Chin S H, et al. A neural net- [26] He K, Zhang X, Ren S, et al. Deep residual learning
work approach to source localization[J]. The Journal of the for image recognition[C]. Proceedings of the IEEE Confer-
Acoustical Society of America, 1991, 90(4): 2081–2090. ence on Computer Vision and Pattern Recognition, 2016:
[11] Niu H, Reeves E, Gerstoft P. Source localization in an 770–778.