Leakage Identification of Underground Structures Using Classification Deep Neural Networks and Transfer Learning

被引:1
|
作者
Wang, Wenyang [1 ,2 ]
Chen, Qingwei [1 ,2 ]
Shen, Yongjiang [3 ,4 ]
Xiang, Zhengliang [3 ,4 ]
机构
[1] Shandong Zhiyuan Elect Power Design Consulting Co, Jinan 250021, Peoples R China
[2] State Grid Shandong Elect Power Co, Econ & Technol Res Inst, Jinan 250021, Peoples R China
[3] Cent South Univ, Hunan Prov Key Lab Disaster Prevent & Mitigat Rail, Changsha 410075, Peoples R China
[4] Cent South Univ, Sch Civil Engn, Changsha 410075, Peoples R China
基金
中国博士后科学基金; 中国国家自然科学基金;
关键词
underground structures; water leakage defect; computer vision; transfer learning; deep learning; WATER LEAKAGE; RECOGNITION; CRACK;
D O I
10.3390/s24175569
中图分类号
O65 [分析化学];
学科分类号
070302 ; 081704 ;
摘要
Water leakage defects often occur in underground structures, leading to accelerated structural aging and threatening structural safety. Leakage identification can detect early diseases of underground structures and provide important guidance for reinforcement and maintenance. Deep learning-based computer vision methods have been rapidly developed and widely used in many fields. However, establishing a deep learning model for underground structure leakage identification usually requires a lot of training data on leakage defects, which is very expensive. To overcome the data shortage, a deep neural network method for leakage identification is developed based on transfer learning in this paper. For comparison, four famous classification models, including VGG16, AlexNet, SqueezeNet, and ResNet18, are constructed. To train the classification models, a transfer learning strategy is developed, and a dataset of underground structure leakage is created. Finally, the classification performance on the leakage dataset of different deep learning models is comparatively studied under different sizes of training data. The results showed that the VGG16, AlexNet, and SqueezeNet models with transfer learning can overall provide higher and more stable classification performance on the leakage dataset than those without transfer learning. The ResNet18 model with transfer learning can overall provide a similar value of classification performance on the leakage dataset than that without transfer learning, but its classification performance is more stable than that without transfer learning. In addition, the SqueezeNet model obtains an overall higher and more stable performance than the comparative models on the leakage dataset for all classification metrics.
引用
收藏
页数:23
相关论文
共 50 条
  • [11] Breast cancer masses classification using deep convolutional neural networks and transfer learning
    Shayma’a A. Hassan
    Mohammed S. Sayed
    Mahmoud I Abdalla
    Mohsen A. Rashwan
    Multimedia Tools and Applications, 2020, 79 : 30735 - 30768
  • [12] Breast cancer masses classification using deep convolutional neural networks and transfer learning
    Hassan, Shayma'a A.
    Sayed, Mohammed S.
    Abdalla, Mahmoud, I
    Rashwan, Mohsen A.
    MULTIMEDIA TOOLS AND APPLICATIONS, 2020, 79 (41-42) : 30735 - 30768
  • [13] Deep learning neural networks for acrylamide identification in potato chips using transfer learning approach
    Monika Arora
    Parthasarathi Mangipudi
    Malay Kishore Dutta
    Journal of Ambient Intelligence and Humanized Computing, 2021, 12 : 10601 - 10614
  • [14] Deep learning neural networks for acrylamide identification in potato chips using transfer learning approach
    Arora, Monika
    Mangipudi, Parthasarathi
    Dutta, Malay Kishore
    JOURNAL OF AMBIENT INTELLIGENCE AND HUMANIZED COMPUTING, 2021, 12 (12) : 10601 - 10614
  • [15] Hazards of data leakage in machine learning: A study on classification of breast cancer using deep neural networks
    Samala, Ravi K.
    Chan, Heang-Ping
    Hadjiiski, Lubomir
    Koneru, Sathvik
    MEDICAL IMAGING 2020: COMPUTER-AIDED DIAGNOSIS, 2020, 11314
  • [16] Plant identification using deep neural networks via optimization of transfer learning parameters
    Ghazi, Mostafa Mehdipour
    Yanikoglu, Berrin
    Aptoula, Erchan
    NEUROCOMPUTING, 2017, 235 : 228 - 235
  • [17] Concrete Bridge Defects Identification and Localization Based on Classification Deep Convolutional Neural Networks and Transfer Learning
    Zoubir, Hajar
    Rguig, Mustapha
    El Aroussi, Mohamed
    Chehri, Abdellah
    Saadane, Rachid
    Jeon, Gwanggil
    REMOTE SENSING, 2022, 14 (19)
  • [18] Deep Neural Networks with Transfer Learning Model for Brain Tumors Classification
    Bulla, Premamayudu
    Anantha, Lakshmipathi
    Peram, Subbarao
    TRAITEMENT DU SIGNAL, 2020, 37 (04) : 593 - 601
  • [19] Deep neural networks with transfer learning model for brain tumors classification
    Bulla P.
    Anantha L.
    Peram S.
    Bulla, Premamayudu (drbpm_it@vignan.ac.in), 1600, International Information and Engineering Technology Association (37): : 593 - 601
  • [20] Speech Emotion Recognition Using Deep Neural Networks, Transfer Learning, and Ensemble Classification Techniques
    Mihalache, Serban
    Burileanu, Dragos
    ROMANIAN JOURNAL OF INFORMATION SCIENCE AND TECHNOLOGY, 2023, 26 (3-4): : 375 - 387