{"type":"ScholarlyArticle","title":"Learning in CubeRes Model Space for Anomaly Detection in 3D GPR Data","authors":[{"name":"Xiren Zhou","slug":"xiren-zhou","given":"Xiren","family":"Zhou","affiliation":"University of Science and Technology of China"},{"name":"Shikang Liu","slug":"shikang-liu","given":"Shikang","family":"Liu","affiliation":"University of Science and Technology of China"},{"name":"Ao Chen","slug":"ao-chen","given":"Ao","family":"Chen","affiliation":"University of Science and Technology of China"},{"name":"Huanhuan Chen","slug":"huanhuan-chen","given":"Huanhuan","family":"Chen","affiliation":"University of Science and Technology of China"}],"abstract":"Three-dimensional Ground Penetrating Radar (3D GPR) data offer comprehensive views of the subsurface, yet identifying and classifying underground anomalies from this data is challenging due to limitations like scarce training data and variable underground environments. In response, we introduce learning in the Cube Reservoir Network (CubeRes) model space for efficient and accurate subsurface anomaly detection. CubeRes, incorporating three reservoirs, captures the dynamics in both horizontal and vertical directions inherent in the 3D GPR data. Fitting the data with CubeRes, representing the data with the compact fitted model, and measuring the difference between models by a proposed parameterized model metric, the original data is transformed from the data space to the CubeRes model space. Subsequently, we introduce an optimization strategy in this model space, aimed at bolstering fitting accuracy and improving category discrimination. This enhancement facilitates a more nuanced differentiation of dynamics across various GPR data categories, thereby enabling effective classification on the models rather than the original data. Experiments on real-world data validate our method's effectiveness and superiority, particularly in data-limited scenarios.","doi":"10.24963/ijcai.2024/626","url":"https://ijcai.org/proceedings/2024/626","pdf":"https://ijcai.org/proceedings/2024/0626.pdf","markdown":"https://ijcai.org/proceedings/2024/626.md","bibtex":"https://ijcai.org/proceedings/2024/bibtex/626","volume":{"slug":"2024","title":"Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2024","url":"https://ijcai.org/proceedings/2024/","year":2024,"location":"Jeju, Korea","dates":"3-9 August 2024","editors":"Kate Larson","isbn":"978-1-956792-04-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2024"},"section":"Machine Learning","track":"Main Track","number":626,"pages":{"first":5662,"last":5670},"keywords":["Machine Learning: ML: Applications","Machine Learning: ML: Recurrent networks","Machine Learning: ML: Classification"],"videos":[],"references":[{"position":1,"raw":"[Bai et al., 2023] Xu Bai, Yu Yang, Zhitao Wen, Shouming Wei, Jiayan Zhang, Jinlong Liu, Hongrui Li, Haoxiang Tian, and Guanting Liu. 3d-gpr-rm: A method for under- ground pipeline recognition using 3-dimensional gpr im- ages. Applied Sciences, 13(13), 2023.","title":"3d-gpr-rm: A method for underground pipeline recognition using 3-dimensional gpr images","authors":"Xu Bai, Yu Yang, Zhitao Wen, Shouming Wei, Jiayan Zhang, Jinlong Liu, Hongrui Li, Haoxiang Tian, Guanting Liu","year":"2023","venue":"Applied Sciences","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Bianchi et al., 2020] Filippo Maria Bianchi, Simone Scar- dapane, Sigurd Løkse, and Robert Jenssen. Reservoir computing approaches for representation and classification of multivariate time series. IEEE transactions on neural networks and learning systems, 32(5):2169-2179, 2020.","title":"Reservoir computing approaches for representation and classification of multivariate time series","authors":"Maria Filippo, Simone Bianchi, Sigurd Scardapane, Robert Løkse, Jenssen","year":"2020","venue":"IEEE transactions on neural networks and learning systems","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Chen and Cohn, 2011] Huanhuan Chen and Anthony G Cohn. Buried utility pipeline mapping based on multi- ple spatial data sources: a bayesian data fusion approach. In Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence, volume 11, pages 2411-2417, 2011.","title":"Buried utility pipeline mapping based on multiple spatial data sources: a bayesian data fusion approach","authors":"Chen, Cohn ; ] Huanhuan Chen, Anthony G Cohn","year":"2011","venue":"Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":"/proceedings/2011/402"},{"position":4,"raw":"[Chen et al., 2013] Huanhuan Chen, Peter Tiňo, Ali Rodan, and Xin Yao. Learning in the model space for cognitive fault diagnosis. IEEE transactions on neural networks and learning systems, 25(1):124-136, 2013.","title":"Learning in the model space for cognitive fault diagnosis","authors":"Huanhuan Chen, Peter Tiňo, Ali Rodan, Xin Yao","year":"2013","venue":"IEEE transactions on neural networks and learning systems","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Chen et al., 2014] Huanhuan Chen, Peter Tiňo, and Xin Yao. Cognitive fault diagnosis in tennessee eastman pro- cess using learning in the model space. Computers & chemical engineering, 67:33-42, 2014.","title":"Cognitive fault diagnosis in tennessee eastman process using learning in the model space","authors":"Huanhuan Chen, Peter Tiňo, Xin Yao","year":"2014","venue":"Computers & chemical engineering","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Chen et al., 2015] Huanhuan Chen, Fengzhen Tang, Peter Tino, Anthony G Cohn, and Xin Yao. Model metric co- learning for time series classification. In Proceedings of the twenty-fourth international joint conference on artifi- cial intelligence, pages 3387-3394. AAAI Press, 2015.","title":"Model metric colearning for time series classification","authors":"Huanhuan Chen, Fengzhen Tang, Peter Tino, Anthony G Cohn, Xin Yao","year":"2015","venue":"Proceedings of the twenty-fourth international joint conference on artificial intelligence","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Chen et al., 2023] Ao Chen, Xiren Zhou, Yizhan Fan, and Huanhuan Chen. Underground diagnosis based on gpr and learning in the model space. IEEE Transactions on Pattern Analysis and Machine Intelligence, pages 1-14, 2023.","title":"Underground diagnosis based on gpr and learning in the model space","authors":"Ao Chen, Xiren Zhou, Yizhan Fan, Huanhuan Chen","year":"2023","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Chiu and Minku, 2022] Chun Wai Chiu and Leandro L. Minku. A diversity framework for dealing with multiple types of concept drift based on clustering in the model space. IEEE Transactions on Neural Networks and Learn- ing Systems, 33(3):1299-1309, 2022.","title":"A diversity framework for dealing with multiple types of concept drift based on clustering in the model space","authors":"Chun Wai Chiu, Leandro L Minku","year":"2022","venue":"IEEE Transactions on Neural Networks and Learning Systems","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Dai et al., 2023] Qiqi Dai, Yee Hui Lee, Hai-Han Sun, Genevieve Ow, Mohamed Lokman Mohd Yusof, and Ab- dulkadir C. Yucel. 3dinvnet: A deep learning-based 3d ground-penetrating radar data inversion. IEEE Transac- tions on Geoscience and Remote Sensing, 61:1-16, 2023. Gong et al., 2018] Zhichen Gong, Huanhuan Chen, Bo Yuan, and Xin Yao. Multiobjective learning in the model space for time series classification. IEEE transactions on cybernetics, 49(3):918-932, 2018.","title":"3dinvnet: A deep learning-based 3d ground-penetrating radar data inversion","authors":"Qiqi Dai, Yee Hui Lee, Hai-Han Sun, Genevieve Ow, Mohamed Lokman Mohd, Abdulkadir C Yusof, Yucel","year":"2018","venue":"IEEE Transactions on Geoscience and Remote Sensing","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Goodman et al., 2013] Dean Goodman, Salvatore Piro, Dean Goodman, and Salvatore Piro. Multi-channel gpr. GPR Remote Sensing in Archaeology, pages 175-185, 2013.","title":"Multi-channel gpr","authors":"Dean Goodman, Salvatore Piro, Dean Goodman, Salvatore Piro","year":"2013","venue":"GPR Remote Sensing in Archaeology","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[He et al., 2016] Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Deep residual learning for image recog- nition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770-778, 2016.","title":"Deep residual learning for image recognition","authors":"Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun","year":"2016","venue":"Proceedings of the IEEE conference on computer vision and pattern recognition","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Jaeger, 2001] Herbert Jaeger. The \"echo state\" approach to analysing and training recurrent neural networks-with an erratum note. Bonn, Germany: German National Re- search Center for Information Technology GMD Technical Report, 148(34):13, 2001.","title":"The \"echo state\" approach to analysing and training recurrent neural networks-with an erratum note","authors":"Herbert Jaeger","year":"2001","venue":"German National Research Center for Information Technology GMD Technical Report","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Kang et al., 2019a] Man-Sung Kang, Namgyu Kim, Seok Been Im, Jong-Jae Lee, and Yun-Kyu An. 3d gpr image-based ucnet for enhancing underground cavity detectability. Remote Sensing, 11(21), 2019.","title":"3d gpr image-based ucnet for enhancing underground cavity detectability","authors":"Kang","year":"2019","venue":"Remote Sensing","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Kang et al., 2019b] Man-Sung Kang, Namgyu Kim, Seok Been Im, Jong-Jae Lee, and Yun-Kyu An. 3D GPR image-based UcNet for enhancing underground cavity detectability. Remote Sensing, 11(21):2545, 2019.","title":"3D GPR image-based UcNet for enhancing underground cavity detectability","authors":"Kang","year":"2019","venue":"Remote Sensing","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Liang et al., 2022a] Xingmin Liang, Xin Yu, Chen Chen, Yong Jin, and Jiandong Huang. Automatic classification of pavement distress using 3d ground-penetrating radar and deep convolutional neural network. IEEE Transactions on Intelligent Transportation Systems, 23(11):22269-22277, 2022.","title":"Automatic classification of pavement distress using 3d ground-penetrating radar and deep convolutional neural network","authors":"Liang","year":"2022","venue":"IEEE Transactions on Intelligent Transportation Systems","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Liang et al., 2022b] Xingmin Liang, Xin Yu, Chen Chen, Yong Jin, and Jiandong Huang. Automatic classification of pavement distress using 3d ground-penetrating radar and deep convolutional neural network. IEEE Transactions on Intelligent Transportation Systems, 23(11):22269-22277, 2022.","title":"Automatic classification of pavement distress using 3d ground-penetrating radar and deep convolutional neural network","authors":"Liang","year":"2022","venue":"IEEE Transactions on Intelligent Transportation Systems","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Liu et al., 2021] Zhen Liu, Wenxiu Wu, Xingyu Gu, Shuwei Li, Lutai Wang, and Tianjie Zhang. Application of com- bining yolo models and 3d gpr images in road detection and maintenance. Remote Sensing, 13(6):1081, 2021.","title":"Application of combining yolo models and 3d gpr images in road detection and maintenance","authors":"Zhen Liu, Wenxiu Wu, Xingyu Gu, Shuwei Li, Lutai Wang, Tianjie Zhang","year":"2021","venue":"Remote Sensing","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Liu et al., 2022] Li Liu, Hang Yu, Hang Xu, Bingjie Wang, and Jingxia Li. Underground object classification using deep 3-d convolutional networks and multiple mirror en- coding for gpr data. IEEE Geoscience and Remote Sensing Letters, 19:1-5, 2022.","title":"Underground object classification using deep 3-d convolutional networks and multiple mirror encoding for gpr data","authors":"Li Liu, Hang Yu, Hang Xu, Bingjie Wang, Jingxia Li","year":"2022","venue":"IEEE Geoscience and Remote Sensing Letters","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Ma et al., 2020] Qianli Ma, Sen Li, Wanqing Zhuang, Ji- abing Wang, and Delu Zeng. Self-supervised time series clustering with model-based dynamics. IEEE Transactions on Neural Networks and Learning Systems, 32(9):3942- 3955, 2020.","title":"Self-supervised time series clustering with model-based dynamics","authors":"Qianli Ma, Sen Li, Wanqing Zhuang, Jiabing Wang, Delu Zeng","year":"2020","venue":"IEEE Transactions on Neural Networks and Learning Systems","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Quevedo et al., 2014] Joseba Quevedo, Huanhuan Chen, Miquel À Cugueró, Peter Tino, Vicenc ¸Puig, Diego Garciá, Ramon Sarrate, and Xin Yao. Combining learning in model space fault diagnosis with data validation/recon- struction: Application to the barcelona water network. En- gineering Applications of Artificial Intelligence, 30:18-29, 2014.","title":"Combining learning in model space fault diagnosis with data validation/reconstruction: Application to the barcelona water network","authors":"Joseba Quevedo, Huanhuan Chen, Miquel À Cugueró, Peter Tino, Diego Vicenc ¸puig, Ramon Garciá, Xin Sarrate, Yao","year":"2014","venue":"Engineering Applications of Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Simonyan and Zisserman, 2014] Karen Simonyan and An- drew Zisserman. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556, 2014.","title":"Very deep convolutional networks for large-scale image recognition","authors":"Karen Simonyan, Andrew Zisserman","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Tran et al., 2015] Du Tran, Lubomir Bourdev, Rob Fergus, Lorenzo Torresani, and Manohar Paluri. Learning spa- tiotemporal features with 3d convolutional networks. In Proceedings of the IEEE international conference on com- puter vision, pages 4489-4497, 2015.","title":"Learning spatiotemporal features with 3d convolutional networks","authors":"Du Tran, Lubomir Bourdev, Rob Fergus, Lorenzo Torresani, Manohar Paluri","year":"2015","venue":"Proceedings of the IEEE international conference on computer vision","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Van der Maaten and Hinton, 2008] Laurens Van der Maaten and Geoffrey Hinton. Visualizing data using t-sne. Journal of machine learning research, 9(11), 2008.","title":"Visualizing data using t-sne","authors":"Van Der Maaten, Laurens Hinton, Geoffrey Van Der Maaten, Hinton","year":"2008","venue":"Journal of machine learning research","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Wu et al., 2022] Jiamin Wu, Xiren Zhou, and Qiuju Chen. A characteristic of speaker's audio in the model space based on adaptive frequency scaling. In 2022 8th Interna- tional Conference on Big Data and Information Analytics (BigDIA), pages 99-103. IEEE, 2022.","title":"A characteristic of speaker's audio in the model space based on adaptive frequency scaling","authors":"Jiamin Wu, Xiren Zhou, Qiuju Chen","year":"2022","venue":"2022 8th International Conference on Big Data and Information Analytics (BigDIA)","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Zhou et al., 2018] Xiren Zhou, Huanhuan Chen, and Jin- long Li. An automatic GPR b-scan image interpreting model. IEEE Transactions on Geoscience and Remote Sensing, 56(6):3398-3412, 2018.","title":"An automatic GPR b-scan image interpreting model","authors":"Xiren Zhou, Huanhuan Chen, Jinlong Li","year":"2018","venue":"IEEE Transactions on Geoscience and Remote Sensing","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Zhou et al., 2023] Xiren Zhou, Shikang Liu, Ao Chen, Qi- uju Chen, Fang Xiong, Yumin Wang, and Huanhuan Chen. Underground anomaly detection in GPR data by learning in the c3 model space. IEEE Transactions on Geoscience and Remote Sensing, pages 1-11, 2023.","title":"Underground anomaly detection in GPR data by learning in the c3 model space","authors":"Xiren Zhou, Shikang Liu, Ao Chen, Qiuju Chen, Fang Xiong, Yumin Wang, Huanhuan Chen","year":"2023","venue":"IEEE Transactions on Geoscience and Remote Sensing","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}