{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T20:12:22Z","timestamp":1751400742290,"version":"3.37.3"},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"12","license":[{"start":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T00:00:00Z","timestamp":1710720000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T00:00:00Z","timestamp":1710720000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"German federal state of Rhineland-Palatinate","award":["Forschungskolleg SIVERT"],"award-info":[{"award-number":["Forschungskolleg SIVERT"]}]},{"name":"Hochschule Worms"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2024,12]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>In this work, we propose a visual analytics system to analyze deep reinforcement learning (deepRL) models working on the track reconstruction of charged particles in the field of particle physics. The data of these charged particles are in the form of point clouds with high-dimensional features. We use one of the existing post hoc saliency methods of explainable artificial intelligence (XAI) and extend its adaptation to compute saliency attributions for the input data corresponding to the output of the model. Our proposed system helps users to explore these saliency attributions corresponding to the high-dimensional input data of the machine learning model and interpret the decision-making process of the model. In particular, we provide the users with multiple task-oriented components, different types of linked views and interactive tools to analyze the model. We explain how to use the system by outlining a typical user workflow and demonstrate the system\u2019s usefulness using several case studies which address specific analysis tasks.\n<\/jats:p>","DOI":"10.1007\/s00371-024-03297-3","type":"journal-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T19:01:32Z","timestamp":1710788492000},"page":"9083-9106","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Visual analytics system for understanding DeepRL-based charged particle tracking"],"prefix":"10.1007","volume":"40","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0180-8517","authenticated-orcid":false,"given":"Raju Ningappa","family":"Mulawade","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1669-8549","authenticated-orcid":false,"given":"Christoph","family":"Garth","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6583-3092","authenticated-orcid":false,"given":"Alexander","family":"Wiebel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,3,18]]},"reference":[{"doi-asserted-by":"publisher","unstructured":"Farrell, S., Anderson, D., Calafiura, P., Cerati, G., Gray, L., Kowalkowski, J., Mudigonda, M., Spentzouris, P., Spiropoulou, M., Tsaris, A., et al.: The HEP.TrkX Project: deep neural networks for HL-LHC online and offline tracking. In: EPJ Web of Conferences, vol. 150, p. 00003. EDP Sciences (2017). https:\/\/doi.org\/10.1051\/epjconf\/201715000003","key":"3297_CR1","DOI":"10.1051\/epjconf\/201715000003"},{"doi-asserted-by":"publisher","unstructured":"Biscarat, C., Caillou, S., Rougier, C., Stark, J., Zahreddine, J.: Towards a realistic track reconstruction algorithm based on graph neural networks for the HL-LHC. In: EPJ Web of Conferences, vol. 251, p. 03047. EDP Sciences (2021). https:\/\/doi.org\/10.1051\/epjconf\/202125103047","key":"3297_CR2","DOI":"10.1051\/epjconf\/202125103047"},{"key":"3297_CR3","doi-asserted-by":"publisher","DOI":"10.3389\/fdata.2022.828666","volume":"5","author":"A Elabd","year":"2022","unstructured":"Elabd, A., Razavimaleki, V., Huang, S.-Y., Duarte, J., Atkinson, M., DeZoort, G., Elmer, P., Hauck, S., Hu, J.-X., Hsu, S.-C., et al.: Graph neural networks for charged particle tracking on FPGAs. Front. Big Data 5, 828666 (2022). https:\/\/doi.org\/10.3389\/fdata.2022.828666","journal-title":"Front. Big Data"},{"key":"3297_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s41781-021-00073-z","volume":"5","author":"G DeZoort","year":"2021","unstructured":"DeZoort, G., Thais, S., Duarte, J., Razavimaleki, V., Atkinson, M., Ojalvo, I., Neubauer, M., Elmer, P.: Charged particle tracking via edge-classifying interaction networks. Comput. Softw. Big Sci. 5, 1\u201313 (2021). https:\/\/doi.org\/10.1007\/s41781-021-00073-z","journal-title":"Comput. Softw. Big Sci."},{"unstructured":"Farrell, S., Calafiura, P., Mudigonda, M., Anderson, D., Vlimant, J.-R., Zheng, S., Bendavid, J., Spiropulu, M., Cerati, G., Gray, L., et al.: Novel deep learning methods for track reconstruction. arXiv preprint arXiv:1810.06111 (2018)","key":"3297_CR5"},{"issue":"12","key":"3297_CR6","doi-asserted-by":"publisher","first-page":"15820","DOI":"10.1109\/TPAMI.2023.3305027","volume":"45","author":"T Kortus","year":"2023","unstructured":"Kortus, T., Keidel, R., Gauger, N.R.: on behalf of the Bergen pCT collaboration: towards neural charged particle tracking in digital tracking calorimeters with reinforcement learning. IEEE Trans. Pattern Anal. Mach. Intell. 45(12), 15820\u201315833 (2023). https:\/\/doi.org\/10.1109\/TPAMI.2023.3305027","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"doi-asserted-by":"publisher","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-CAM: visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 618\u2013626 (2017). https:\/\/doi.org\/10.1109\/ICCV.2017.74","key":"3297_CR7","DOI":"10.1109\/ICCV.2017.74"},{"unstructured":"Lundberg, S.M., Lee, S.-I.: A unified approach to interpreting model predictions. In: Guyon, I., Luxburg, U.V., Bengio, S., Wallach, H., Fergus, R., Vishwanathan, S., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 30, pp. 4765\u20134774 (2017). https:\/\/proceedings.neurips.cc\/paper\/2017\/file\/8a20a8621978632d76c43dfd28b67767-Paper.pdf","key":"3297_CR8"},{"doi-asserted-by":"publisher","unstructured":"Mulawade, R.N., Garth, C., Wiebel, A., on behalf of the Bergen pCT collaboration.: Saliency clouds: visual analysis of point cloud-oriented deep neural networks in DeepRL for particle physics. In: Archambault, D., Nabney, I., Peltonen, J. (eds.) Machine Learning Methods in Visualisation for Big Data. The Eurographics Association, Eindhoven (2022). https:\/\/doi.org\/10.2312\/mlvis.20221069","key":"3297_CR9","DOI":"10.2312\/mlvis.20221069"},{"unstructured":"Smilkov, D., Thorat, N., Kim, B., Vi\u00e9gas, F., Wattenberg, M.: SmoothGrad: removing noise by adding noise. arXiv preprint arXiv:1706.03825 (2017)","key":"3297_CR10"},{"key":"3297_CR11","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/s41095-020-0191-7","volume":"7","author":"J Yuan","year":"2021","unstructured":"Yuan, J., Chen, C., Yang, W., Liu, M., Xia, J., Liu, S.: A survey of visual analytics techniques for machine learning. Comput. Vis. Media 7, 3\u201336 (2021). https:\/\/doi.org\/10.1007\/s41095-020-0191-7","journal-title":"Comput. Vis. Media"},{"issue":"6","key":"3297_CR12","doi-asserted-by":"publisher","first-page":"2326","DOI":"10.1109\/TVCG.2022.3165347","volume":"28","author":"X Xuan","year":"2022","unstructured":"Xuan, X., Zhang, X., Kwon, O.-H., Ma, K.-L.: VAC-CNN: a visual analytics system for comparative studies of deep convolutional neural networks. IEEE Trans. Vis. Comput. Graph. 28(6), 2326\u20132337 (2022). https:\/\/doi.org\/10.1109\/TVCG.2022.3165347","journal-title":"IEEE Trans. Vis. Comput. Graph."},{"issue":"1","key":"3297_CR13","doi-asserted-by":"publisher","first-page":"1096","DOI":"10.1109\/TVCG.2019.2934659","volume":"26","author":"F Hohman","year":"2019","unstructured":"Hohman, F., Park, H., Robinson, C., Chau, D.H.P.: Summit: scaling deep learning interpretability by visualizing activation and attribution summarizations. IEEE Trans. Vis. Comput. Graph. 26(1), 1096\u20131106 (2019). https:\/\/doi.org\/10.1109\/TVCG.2019.2934659","journal-title":"IEEE Trans. Vis. Comput. Graph."},{"doi-asserted-by":"publisher","unstructured":"Zheng, T., Chen, C., Yuan, J., Li, B., Ren, K.: Pointcloud saliency maps. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2019). https:\/\/doi.org\/10.48550\/arXiv.1812.01687","key":"3297_CR14","DOI":"10.48550\/arXiv.1812.01687"},{"issue":"7","key":"3297_CR15","doi-asserted-by":"publisher","first-page":"1744","DOI":"10.1109\/TMM.2019.2963592","volume":"22","author":"M Zhang","year":"2020","unstructured":"Zhang, M., You, H., Kadam, P., Liu, S., Kuo, C.-C.J.: Pointhop: an explainable machine learning method for point cloud classification. IEEE Trans. Multimed. 22(7), 1744\u20131755 (2020). https:\/\/doi.org\/10.1109\/TMM.2019.2963592","journal-title":"IEEE Trans. Multimed."},{"doi-asserted-by":"publisher","unstructured":"Tan, H., Kotthaus, H.: Surrogate model-based explainability methods for point cloud NNS. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 2239\u20132248 (2022). https:\/\/doi.org\/10.48550\/arXiv.2107.13459","key":"3297_CR16","DOI":"10.48550\/arXiv.2107.13459"},{"doi-asserted-by":"publisher","unstructured":"Ribeiro, M.T., Singh, S., Guestrin, C.: \u201cWhy Should I Trust You?\u201d: explaining the predictions of any classifier. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. KDD \u201916, pp. 1135\u20131144. Association for Computing Machinery, New York (2016). https:\/\/doi.org\/10.1145\/2939672.2939778","key":"3297_CR17","DOI":"10.1145\/2939672.2939778"},{"unstructured":"Springenberg, J.T., Dosovitskiy, A., Brox, T., Riedmiller, M.: Striving for simplicity: the all convolutional net (2014). arXiv preprint arXiv:1412.6806","key":"3297_CR18"},{"doi-asserted-by":"publisher","unstructured":"Zeiler, M.D., Fergus, R.: Visualizing and understanding convolutional networks. In: European Conference on Computer Vision, pp. 818\u2013833. Springer (2014). https:\/\/doi.org\/10.1007\/978-3-319-10590-1_53","key":"3297_CR19","DOI":"10.1007\/978-3-319-10590-1_53"},{"doi-asserted-by":"publisher","unstructured":"Sundararajan, M., Taly, A., Yan, Q.: Axiomatic attribution for deep networks. In: International Conference on Machine Learning, pp. 3319\u20133328. PMLR (2017). https:\/\/doi.org\/10.48550\/arXiv.1703.01365","key":"3297_CR20","DOI":"10.48550\/arXiv.1703.01365"},{"doi-asserted-by":"publisher","unstructured":"Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., Torralba, A.: Learning deep features for discriminative localization. In: Proceedings of the IEEE CVPR, pp. 2921\u20132929 (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.319","key":"3297_CR21","DOI":"10.1109\/CVPR.2016.319"},{"doi-asserted-by":"publisher","unstructured":"Gupta, A., Watson, S., Yin, H.: 3D point cloud feature explanations using gradient-based methods. In: 2020 International Joint Conference on Neural Networks (IJCNN), pp. 1\u20138. IEEE, Glasgow (2020). https:\/\/doi.org\/10.1109\/IJCNN48605.2020.9206688","key":"3297_CR22","DOI":"10.1109\/IJCNN48605.2020.9206688"},{"key":"3297_CR23","doi-asserted-by":"publisher","first-page":"6571","DOI":"10.1109\/JSTARS.2022.3195200","volume":"15","author":"F Matrone","year":"2022","unstructured":"Matrone, F., Paolanti, M., Felicetti, A., Martini, M., Pierdicca, R.: BubblEX: an explainable deep learning framework for point-cloud classification. IEEE J. Select. Top. Appl. Earth Observ. Remote Sens. 15, 6571\u20136587 (2022). https:\/\/doi.org\/10.1109\/JSTARS.2022.3195200","journal-title":"IEEE J. Select. Top. Appl. Earth Observ. Remote Sens."},{"key":"3297_CR24","doi-asserted-by":"publisher","DOI":"10.3390\/a16070316","author":"M Schwegler","year":"2023","unstructured":"Schwegler, M., M\u00fcller, C., Reiterer, A.: Integrated gradients for feature assessment in point cloud-based data sets. Algorithms (2023). https:\/\/doi.org\/10.3390\/a16070316","journal-title":"Algorithms"},{"key":"3297_CR25","first-page":"11","volume":"9","author":"L Maaten","year":"2008","unstructured":"Maaten, L., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res. 9, 11 (2008)","journal-title":"J. Mach. Learn. Res."},{"issue":"3","key":"3297_CR26","doi-asserted-by":"publisher","first-page":"2153","DOI":"10.1109\/TVCG.2019.2944182","volume":"27","author":"M Espadoto","year":"2021","unstructured":"Espadoto, M., Martins, R.M., Kerren, A., Hirata, N.S.T., Telea, A.C.: Toward a quantitative survey of dimension reduction techniques. IEEE Trans. Vis. Comput. Graph. 27(3), 2153\u20132173 (2021). https:\/\/doi.org\/10.1109\/TVCG.2019.2944182","journal-title":"IEEE Trans. Vis. Comput. Graph."},{"issue":"1","key":"3297_CR27","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6633\/aa8b1d","volume":"81","author":"RP Johnson","year":"2017","unstructured":"Johnson, R.P.: Review of medical radiography and tomography with proton beams. Rep. Prog. Phys. 81(1), 016701 (2017). https:\/\/doi.org\/10.1088\/1361-6633\/aa8b1d","journal-title":"Rep. Prog. Phys."},{"key":"3297_CR28","doi-asserted-by":"publisher","DOI":"10.3389\/fphy.2020.568243","author":"J Alme","year":"2020","unstructured":"Alme, J., Barnaf\u00f6ldi, G.G., Barthel, R., Borshchov, V., Bodova, T., Brink, A., Brons, S., Chaar, M., Eikeland, V., Feofilov, G., et al.: A high-granularity digital tracking calorimeter optimized for proton CT. Front. Phys. (2020). https:\/\/doi.org\/10.3389\/fphy.2020.568243","journal-title":"Front. Phys."},{"key":"3297_CR29","doi-asserted-by":"publisher","first-page":"434","DOI":"10.1016\/j.nima.2015.09.057","volume":"824","author":"M Mager","year":"2016","unstructured":"Mager, M.: ALPIDE, the monolithic active pixel sensor for the alice its upgrade. Nucl. Instrum. Methods Phys. Res. Sect. A 824, 434\u2013438 (2016). https:\/\/doi.org\/10.1016\/j.nima.2015.09.057","journal-title":"Nucl. Instrum. Methods Phys. Res. Sect. A"},{"key":"3297_CR30","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.7426388","author":"T Kortus","year":"2022","unstructured":"Kortus, T., Schilling, A., Keidel, R., Gauger, N.R.: on behalf of the Bergen pCT collaboration: particle tracking data: Bergen DTC prototype. Zenodo (2022). https:\/\/doi.org\/10.5281\/zenodo.7426388","journal-title":"Zenodo"},{"unstructured":"Rosynski, M., Kirchner, F., Valdenegro-Toro, M.: Are gradient-based saliency maps useful in deep reinforcement learning? (2020). arXiv preprint arXiv:2012.01281","key":"3297_CR31"},{"key":"3297_CR32","doi-asserted-by":"publisher","DOI":"10.2312\/vmv.20221210","volume-title":"Vision, Modeling, and Visualization","author":"R Eschbach","year":"2022","unstructured":"Eschbach, R., Messerschmidt, K., Keidel, R., Wiebel, A.: on behalf of the Bergen pCT Collaboration: semi-automatic particle tracking for and visualization of particle detector data. In: Bender, J., Botsch, M., Keim, D.A. (eds.) Vision, Modeling, and Visualization. The Eurographics Association, Eindhoven (2022). https:\/\/doi.org\/10.2312\/vmv.20221210"},{"unstructured":"HoloViz. https:\/\/holoviz.org\/. Accessed 27 Mar 2023","key":"3297_CR33"},{"doi-asserted-by":"publisher","unstructured":"Mulawade, R.N., Garth, C., Wiebel, A., on behalf of the Bergen pCT collaboration.: Source code for paper \u2018Visual analytics system for understanding deeprl-based charged particle tracking\u2019. Zenodo (2024). https:\/\/doi.org\/10.5281\/zenodo.10491504","key":"3297_CR34","DOI":"10.5281\/zenodo.10491504"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-024-03297-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-024-03297-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-024-03297-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,12]],"date-time":"2024-11-12T09:22:02Z","timestamp":1731403322000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-024-03297-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,18]]},"references-count":34,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2024,12]]}},"alternative-id":["3297"],"URL":"https:\/\/doi.org\/10.1007\/s00371-024-03297-3","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"type":"print","value":"0178-2789"},{"type":"electronic","value":"1432-2315"}],"subject":[],"published":{"date-parts":[[2024,3,18]]},"assertion":[{"value":"25 January 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 March 2024","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}