Page 182 - 201903

464 2019 年 5 月

[14] 陈彦华, 李明轩. 利用人工神经网络实现缺陷的类型识别 [J]. [26] Nasr-Esfahani E, Samavi S, Karimi N, et al. Vessel extrac-
应用声学, 1998, 17(2): 1–4, 10. tion in X-ray angiograms using deep learning[C]. The 38th
Chen Yanhua, Li Mingxuan. Classification of flaws International Conference of the Engineering in Medicine
through an artificial neural network[J]. Applied Acoustics, and Biology Society (EMBC). Orlando, FL, USA: IEEE,
1998, 17(2): 1–4, 10. 2016: 643–646.
[15] 刘镇清, 李成林, 刘江韦, 等. 超声探伤信号的人工神经网络 [27] Second annual data science bowl[EB/OL]. [2018–09–27].
识别 [J]. 应用声学, 1997, 16(2): 14–17. https://www.kaggle.com/c/second-annual-data-science-
Liu Zhenqing, Li Chenglin, Liu Jiangwei, et al. Flaw bowl.
signature recognition in ultrasonic testing using artificial [28] Shen D G, Wu G R, Suk H I. Deep learning in medical
neural network[J]. Applied Acoustics, 1997, 16(2): 14–17. image analysis[J]. Annual Review of Biomedical Engineer-
[16] Simone G, Morabito F C, Polikar R, et al. Feature extrac- ing, 2017, 19: 221–248.
tion techniques for ultrasonic signal classification[J]. In- [29] 余永维, 殷国富, 殷鹰, 等. 基于深度学习网络的射线图像缺
ternational Journal of Applied Electromagnetics and Me- 陷识别方法 [J]. 仪器仪表学报, 2014, 35(9): 2012–2019.
chanics, 2001, 15(1–4): 291–294. Yu Yongwei, Yin Guofu, Yin Ying, et al. Defect recog-
[17] 卢超, 张维, 彭应秋, 等. 小波分析和人工神经网络在金属超 nition for radiographic image based on deep learning net-
声无损检测缺陷分类中的应用 [J]. 南昌航空工业学院学报, work[J]. Chinese Journal of Scientific Instrument, 2014,
2001, 15(3): 51–54. 35(9): 2012–2019.
Lu Chao, Zhang Wei, Peng Yingqiu, et al. Applica- [30] 颜伟鑫. 深度学习及其在工件缺陷自动检测中的应用研
tion of wavelet analysis and artificial neutral networks to 究 [D]. 广州: 华南理工大学, 2016.
flaw classification in ultrasonic non-destructive testing[J]. [31] 郑志远. 焊缝典型缺陷的超声 TOFD-D 扫成像技术研究 [D].
Joural of Nanchang Institute of Aeronautical Technology, 南昌: 南昌航空大学, 2017.
2001, 15(1–4): 291–294. [32] Khumaidi A, Yuniarno E M, Purnomo M H. Welding de-
[18] Veiga J, de Carvalho A A, da Silva I C, et al. The use of fect classification based on convolution neural network
artificial neural network in the classification of pulse-echo (CNN) and Gaussian kernel[C]//Intelligent Technology
and TOFD ultra-sonic signals[J]. Journal of the Brazil- and Its Applications (ISITIA), 2017 International Sem-
ian Society of Mechanical Sciences and Engineering, 2005, inar on. IEEE, 2017: 261–265.
27(4): 394–398. [33] Carneiro G, Nascimento J, Bradley A P. Unregis-
[19] Sambath S, Nagaraj P, Selvakumar N. Automatic de- tered multiview mammogram analysis with pre-trained
fect classification in ultrasonic NDT using artificial in- deep learning models[M]//Medical Image Computing and
telligence[J]. Journal of Nondestructive Evaluation, 2011, Computer-Assisted Intervention. Munich, Germany:
30(1): 20–28. Springer, 2015: 652–660.
[20] Wang B, Saniie J. Ultrasonic target echo detection us- [34] Tajbakhsh N, Shin J Y, Gurudu S R, et al. Convolutional
ing neural network[C]//Proceedings of 2017 IEEE Inter- neural networks for medical image analysis: full training
national Conference on Electro Information Technology or fine tuning?[J]. IEEE Transactions on Medical Imaging,
(EIT), 2017. 2016, 35(5):1299–1312.
[21] Wang B, Saniie J. Ultrasonic flaw detection based on [35] Hinton G E, Srivastava N, Krizhevsky A, et al. Improv-
temporal and spectral signals applied to neural net- ing neural networks by preventing co-adaptation of feature
work[C]//Ultrasonics Symposium (IUS), 2017 IEEE In- detectors[J]. Computer Science, 2012, arXiv: 1207.0580.
ternational. IEEE, 2017: 1–4. [36] Song Y Y, Zhang L, Chen S P, et al. Accurate segmenta-
[22] 施成龙, 师芳芳, 张碧星. 利用深度神经网络和小波包变换进 tion of cervical cytoplasm and nuclei based on multiscale
行缺陷类型分析 [J]. 声学学报, 2016, 41(4): 499–506. convolutional network and graph partitioning[J]. IEEE
Shi Chenglong, Shi Fangfang, Zhang Bixing. Analysis on Transactions on Biomedical Engineering, 2015, 62(10):
defect classification by deep neural networks and wavelet 2421–2433.
packet transform[J]. Acta Acustica, 2016, 41(4): 499–506. [37] Kim Y. Convolutional neural networks for sentence clas-
[23] Arevalo J, Gonzalez F A, Ramos-Pollan R, et al. Rep- sification[J]. Computer Science, 2014, arXiv: 1408.5882.
resentation learning for mammography mass lesion clas- [38] Zikic D, Ioannou Y, Brown M, et al. Segmentation
sification with convolutional neural networks[J]. Com- of brain tumor tissues with convolutional neural net-
puter Methods and Programs in Biomedicine, 2016, 127: works[C]. The 2014 MICCAI Workshop on Multimodal
248–257. Brain Tumor Segmentation Challenge. Boston, Mas-
[24] Xu Y, Mo T, Feng Q W, et al. Deep learning of feature sachusetts, USA, 2014: 36–39.
representation with multiple instance learning for medical [39] Ji S, Xu W, Yang M, et al. 3D convolutional neural
image analysis[C]. The 2014 IEEE International Confer- networks for human action recognition[J]. IEEE Transac-
ence on Acoustics, Speech and Signal Processing. Flo- tions on Pattern Analysis and Machine Intelligence, 2013,
rence, Italy: IEEE, 2014: 1626–1630. 35(1): 221–231.
[25] Dou Q, Chen H, Yu L Q, et al. Multilevel contextual 3-D [40] Lai S, Xu L, Liu K, et al. Recurrent convolutional neural
CNNs for false positive reduction in pulmonary nodule de- networks for text classification[C]. The Association for the
tection[J]. IEEE Transactions on Biomedical Engineering, Advancement of Artificial Intelligence (AAAI), 2015, 333:
2017, 64(7): 1558–1567. 2267–2273.