{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T06:07:07Z","timestamp":1782367627757,"version":"3.54.5"},"reference-count":65,"publisher":"Association for Computing Machinery (ACM)","issue":"1","license":[{"start":{"date-parts":[[2023,3,28]],"date-time":"2023-03-28T00:00:00Z","timestamp":1679961600000},"content-version":"vor","delay-in-days":1,"URL":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"the NIH mHealth Center for Discovery, Optimization and Translation of Temporally-Precise Interventions","award":["1P41EB028242"],"award-info":[{"award-number":["1P41EB028242"]}]},{"DOI":"10.13039\/100006754","name":"Army Research Laboratory","doi-asserted-by":"publisher","award":["W911NF2220243, W911NF172-0196"],"award-info":[{"award-number":["W911NF2220243, W911NF172-0196"]}],"id":[{"id":"10.13039\/100006754","id-type":"DOI","asserted-by":"publisher"}]},{"name":"CONIX Research Center"},{"DOI":"10.13039\/100000181","name":"AFOSR","doi-asserted-by":"crossref","award":["FA95502210193"],"award-info":[{"award-number":["FA95502210193"]}],"id":[{"id":"10.13039\/100000181","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["1822935, 2124130"],"award-info":[{"award-number":["1822935, 2124130"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["Proc. ACM Interact. Mob. Wearable Ubiquitous Technol."],"published-print":{"date-parts":[[2023,3,27]]},"abstract":"<jats:p>End-to-end deep learning models are increasingly applied to safety-critical human activity recognition (HAR) applications, e.g., healthcare monitoring and smart home control, to reduce developer burden and increase the performance and robustness of prediction models. However, integrating HAR models in safety-critical applications requires trust, and recent approaches have aimed to balance the performance of deep learning models with explainable decision-making for complex activity recognition. Prior works have exploited the compositionality of complex HAR (i.e., higher-level activities composed of lower-level activities) to form models with symbolic interfaces, such as concept-bottleneck architectures, that facilitate inherently interpretable models. However, feature engineering for symbolic concepts-as well as the relationship between the concepts-requires precise annotation of lower-level activities by domain experts, usually with fixed time windows, all of which induce a heavy and error-prone workload on the domain expert. In this paper, we introduce X-CHAR, an eXplainable Complex Human Activity Recognition model that doesn't require precise annotation of low-level activities, offers explanations in the form of human-understandable, high-level concepts, while maintaining the robust performance of end-to-end deep learning models for time series data. X-CHAR learns to model complex activity recognition in the form of a sequence of concepts. For each classification, X-CHAR outputs a sequence of concepts and a counterfactual example as the explanation. We show that the sequence information of the concepts can be modeled using Connectionist Temporal Classification (CTC) loss without having accurate start and end times of low-level annotations in the training dataset-significantly reducing developer burden. We evaluate our model on several complex activity datasets and demonstrate that our model offers explanations without compromising the prediction accuracy in comparison to baseline models. Finally, we conducted a mechanical Turk study to show that the explanations provided by our model are more understandable than the explanations from existing methods for complex activity recognition.<\/jats:p>","DOI":"10.1145\/3580804","type":"journal-article","created":{"date-parts":[[2023,3,28]],"date-time":"2023-03-28T14:57:51Z","timestamp":1680015471000},"page":"1-28","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":39,"title":["X-CHAR"],"prefix":"10.1145","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0322-7086","authenticated-orcid":false,"given":"Jeya Vikranth","family":"Jeyakumar","sequence":"first","affiliation":[{"name":"University of California Los Angeles, California, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4232-3345","authenticated-orcid":false,"given":"Ankur","family":"Sarker","sequence":"additional","affiliation":[{"name":"University of California Los Angeles, California, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5111-0694","authenticated-orcid":false,"given":"Luis Antonio","family":"Garcia","sequence":"additional","affiliation":[{"name":"University of Southern California, Information Sciences Institute, California, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3782-9192","authenticated-orcid":false,"given":"Mani","family":"Srivastava","sequence":"additional","affiliation":[{"name":"University of California Los Angeles, California, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,3,28]]},"reference":[{"key":"e_1_2_2_1_1","volume-title":"Defense Advanced Research Projects Agency","unstructured":"2016. Defense Advanced Research Projects Agency. Broad Agency Announcement, Explainable Artificial Intelligence (XAI). https:\/\/www.darpa.mil\/attachments\/DARPA-BAA-16-53.pdf. Online; accessed 14-November-2022."},{"key":"e_1_2_2_2_1","volume-title":"Article 15 EU GDPR \"Right of access by the data subject\". https:\/\/www.privacy-regulation.eu\/en\/article-15-right-of-access-by-the-data-subject-GDPR.htm. Online","year":"2022","unstructured":"2018. Article 15 EU GDPR \"Right of access by the data subject\". https:\/\/www.privacy-regulation.eu\/en\/article-15-right-of-access-by-the-data-subject-GDPR.htm. Online; accessed 04-March-2022."},{"key":"e_1_2_2_3_1","volume-title":"Recital 71 EU GDPR. https:\/\/www.privacy-regulation.eu\/en\/r71.htm. Online","year":"2022","unstructured":"2018. Recital 71 EU GDPR. https:\/\/www.privacy-regulation.eu\/en\/r71.htm. Online; accessed 04-March-2022."},{"key":"e_1_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3314388"},{"key":"e_1_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3517224"},{"key":"e_1_2_2_6_1","volume-title":"Counterfactual Explanations for Multivariate Time Series. In 2021 International Conference on Applied Artificial Intelligence (ICAPAI). IEEE, 1--8.","author":"Ates Emre","year":"2021","unstructured":"Emre Ates, Burak Aksar, Vitus J Leung, and Ayse K Coskun. 2021. Counterfactual Explanations for Multivariate Time Series. In 2021 International Conference on Applied Artificial Intelligence (ICAPAI). IEEE, 1--8."},{"key":"e_1_2_2_7_1","volume-title":"Nice: an algorithm for nearest instance counterfactual explanations. arXiv preprint arXiv:2104.07411","author":"Brughmans Dieter","year":"2021","unstructured":"Dieter Brughmans and David Martens. 2021. Nice: an algorithm for nearest instance counterfactual explanations. arXiv preprint arXiv:2104.07411 (2021)."},{"key":"e_1_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jeconom.2018.07.005"},{"key":"e_1_2_2_9_1","volume-title":"Explaining image classifiers by counterfactual generation. arXiv preprint arXiv:1807.08024","author":"Chang Chun-Hao","year":"2018","unstructured":"Chun-Hao Chang, Elliot Creager, Anna Goldenberg, and David Duvenaud. 2018. Explaining image classifiers by counterfactual generation. arXiv preprint arXiv:1807.08024 (2018)."},{"key":"e_1_2_2_10_1","doi-asserted-by":"crossref","unstructured":"Swarat Chaudhuri Kevin Ellis Oleksandr Polozov Rishabh Singh Armando Solar-Lezama Yisong Yue et al. 2021. Neurosymbolic Programming. Foundations and Trends\u00ae in Programming Languages 7 3 (2021) 158--243.","DOI":"10.1561\/2500000049"},{"key":"e_1_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-020-02005-7"},{"key":"e_1_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.2991\/icaita-16.2016.13"},{"key":"e_1_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.3390\/s18041055"},{"key":"e_1_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1999.757481"},{"key":"e_1_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/363958.363994"},{"key":"e_1_2_2_16_1","volume-title":"Explainable Activity Recognition for Smart Home Systems. arXiv preprint arXiv:2105.09787","author":"Das Devleena","year":"2021","unstructured":"Devleena Das, Yasutaka Nishimura, Rajan P Vivek, Naoto Takeda, Sean T Fish, Thomas Ploetz, and Sonia Chernova. 2021. Explainable Activity Recognition for Smart Home Systems. arXiv preprint arXiv:2105.09787 (2021)."},{"key":"e_1_2_2_17_1","volume-title":"Framework for Evaluating Faithfulness of Local Explanations. arXiv preprint arXiv:2202.00734","author":"Dasgupta Sanjoy","year":"2022","unstructured":"Sanjoy Dasgupta, Nave Frost, and Michal Moshkovitz. 2022. Framework for Evaluating Faithfulness of Local Explanations. arXiv preprint arXiv:2202.00734 (2022)."},{"key":"e_1_2_2_18_1","doi-asserted-by":"crossref","unstructured":"Jeffrey De Fauw Joseph R Ledsam Bernardino Romera-Paredes Stanislav Nikolov Nenad Tomasev Sam Blackwell Harry Askham Xavier Glorot Brendan O'Donoghue Daniel Visentin et al. 2018. Clinically applicable deep learning for diagnosis and referral in retinal disease. Nature medicine 24 9 (2018) 1342--1350.","DOI":"10.1038\/s41591-018-0107-6"},{"key":"e_1_2_2_19_1","volume-title":"Bootstrap confidence intervals. Statistical science 11, 3","author":"DiCiccio Thomas J","year":"1996","unstructured":"Thomas J DiCiccio and Bradley Efron. 1996. Bootstrap confidence intervals. Statistical science 11, 3 (1996), 189--228."},{"key":"e_1_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.3390\/s19204474"},{"key":"e_1_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.476"},{"key":"e_1_2_2_22_1","volume-title":"Supervised sequence labelling with recurrent neural networks","author":"Graves Alex","unstructured":"Alex Graves. 2012. Connectionist temporal classification. In Supervised sequence labelling with recurrent neural networks. Springer, 61--93."},{"key":"e_1_2_2_23_1","volume-title":"Unsupervised activity discovery and characterization from event-streams. arXiv preprint arXiv:1207.1381","author":"Hammid Rafay","year":"2012","unstructured":"Rafay Hammid, Siddhartha Maddi, Amos Johnson, Aaron Bobick, Irfan Essa, and Charles Lee Isbell. 2012. Unsupervised activity discovery and characterization from event-streams. arXiv preprint arXiv:1207.1381 (2012)."},{"key":"e_1_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/1409635.1409638"},{"key":"e_1_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3351244"},{"key":"e_1_2_2_26_1","volume-title":"Towards faithfully interpretable NLP systems: How should we define and evaluate faithfulness? arXiv preprint arXiv:2004.03685","author":"Jacovi Alon","year":"2020","unstructured":"Alon Jacovi and Yoav Goldberg. 2020. Towards faithfully interpretable NLP systems: How should we define and evaluate faithfulness? arXiv preprint arXiv:2004.03685 (2020)."},{"key":"e_1_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3356250.3360032"},{"key":"e_1_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3267305.3267529"},{"key":"e_1_2_2_29_1","first-page":"4211","article-title":"How can i explain this to you? an empirical study of deep neural network explanation methods","volume":"33","author":"Jeyakumar Jeya Vikranth","year":"2020","unstructured":"Jeya Vikranth Jeyakumar, Joseph Noor, Yu-Hsi Cheng, Luis Garcia, and Mani Srivastava. 2020. How can i explain this to you? an empirical study of deep neural network explanation methods. Advances in Neural Information Processing Systems 33 (2020), 4211--4222.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_2_30_1","volume-title":"International conference on machine learning. PMLR","author":"Koh Pang Wei","year":"2017","unstructured":"Pang Wei Koh and Percy Liang. 2017. Understanding black-box predictions via influence functions. In International conference on machine learning. PMLR, 1885--1894."},{"key":"e_1_2_2_31_1","volume-title":"International Conference on Machine Learning. PMLR, 5338--5348","author":"Koh Pang Wei","year":"2020","unstructured":"Pang Wei Koh, Thao Nguyen, Yew Siang Tang, Stephen Mussmann, Emma Pierson, Been Kim, and Percy Liang. 2020. Concept bottleneck models. In International Conference on Machine Learning. PMLR, 5338--5348."},{"key":"e_1_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3341163.3347744"},{"key":"e_1_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3341162.3345577"},{"key":"e_1_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11771"},{"key":"e_1_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICOSP.2004.1452759"},{"key":"e_1_2_2_36_1","volume-title":"A unified approach to interpreting model predictions. Advances in neural information processing systems 30","author":"Lundberg Scott M","year":"2017","unstructured":"Scott M Lundberg and Su-In Lee. 2017. A unified approach to interpreting model predictions. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_2_2_37_1","volume-title":"Identifying typical physical activity on smartphone with varying positions and orientations. Biomedical engineering online 14, 1","author":"Miao Fen","year":"2015","unstructured":"Fen Miao, Yi He, Jinlei Liu, Ye Li, and Idowu Ayoola. 2015. Identifying typical physical activity on smartphone with varying positions and orientations. Biomedical engineering online 14, 1 (2015), 32."},{"key":"e_1_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CBMI.2019.8877429"},{"key":"e_1_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICMI.2002.1166960"},{"key":"e_1_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.222"},{"key":"e_1_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.3390\/s16010115"},{"key":"e_1_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jnca.2007.11.002"},{"key":"e_1_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380087"},{"key":"e_1_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3214277"},{"key":"e_1_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"},{"key":"e_1_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2019.06.014"},{"key":"e_1_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3161174"},{"key":"e_1_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939778"},{"key":"e_1_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-019-0048-x"},{"key":"e_1_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00516"},{"key":"e_1_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.4108\/icst.bodynets.2011.247015"},{"key":"e_1_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"e_1_2_2_53_1","volume-title":"Deep inside convolutional networks: Visualising image classification models and saliency maps. arXiv preprint arXiv:1312.6034","author":"Simonyan Karen","year":"2013","unstructured":"Karen Simonyan, Andrea Vedaldi, and Andrew Zisserman. 2013. Deep inside convolutional networks: Visualising image classification models and saliency maps. arXiv preprint arXiv:1312.6034 (2013)."},{"key":"e_1_2_2_54_1","volume-title":"Smoothgrad: removing noise by adding noise. arXiv preprint arXiv:1706.03825","author":"Smilkov Daniel","year":"2017","unstructured":"Daniel Smilkov, Nikhil Thorat, Been Kim, Fernanda Vi\u00e9gas, and Martin Wattenberg. 2017. Smoothgrad: removing noise by adding noise. arXiv preprint arXiv:1706.03825 (2017)."},{"key":"e_1_2_2_55_1","volume-title":"Counterfactual explanations for machine learning: A review. arXiv preprint arXiv:2010.10596","author":"Verma Sahil","year":"2020","unstructured":"Sahil Verma, John Dickerson, and Keegan Hines. 2020. Counterfactual explanations for machine learning: A review. arXiv preprint arXiv:2010.10596 (2020)."},{"key":"e_1_2_2_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/2858036.2858466"},{"key":"e_1_2_2_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/3411836"},{"key":"e_1_2_2_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/3384419.3431158"},{"key":"e_1_2_2_59_1","volume-title":"Yi Yang, Barry Smyth, and Ruihai Dong.","author":"Yang Linyi","year":"2020","unstructured":"Linyi Yang, Eoin M Kenny, Tin Lok James Ng, Yi Yang, Barry Smyth, and Ruihai Dong. 2020. Generating plausible counterfactual explanations for deep transformers in financial text classification. arXiv preprint arXiv:2010.12512 (2020)."},{"key":"e_1_2_2_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/3038912.3052577"},{"key":"e_1_2_2_61_1","volume-title":"Neural-symbolic vqa: Disentangling reasoning from vision and language understanding. Advances in neural information processing systems 31","author":"Yi Kexin","year":"2018","unstructured":"Kexin Yi, Jiajun Wu, Chuang Gan, Antonio Torralba, Pushmeet Kohli, and Josh Tenenbaum. 2018. Neural-symbolic vqa: Disentangling reasoning from vision and language understanding. Advances in neural information processing systems 31 (2018)."},{"key":"e_1_2_2_62_1","volume-title":"Event structure in perception and conception. Psychological bulletin 127, 1","author":"Zacks Jeffrey M","year":"2001","unstructured":"Jeffrey M Zacks and Barbara Tversky. 2001. Event structure in perception and conception. Psychological bulletin 127, 1 (2001), 3."},{"key":"e_1_2_2_63_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_53"},{"key":"e_1_2_2_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00920"},{"key":"e_1_2_2_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.557"}],"container-title":["Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3580804","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3580804","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3580804","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,14]],"date-time":"2025-07-14T04:44:56Z","timestamp":1752468296000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3580804"}},"subtitle":["A Concept-based Explainable Complex Human Activity Recognition Model"],"short-title":[],"issued":{"date-parts":[[2023,3,27]]},"references-count":65,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2023,3,27]]}},"alternative-id":["10.1145\/3580804"],"URL":"https:\/\/doi.org\/10.1145\/3580804","relation":{},"ISSN":["2474-9567"],"issn-type":[{"value":"2474-9567","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,3,27]]},"assertion":[{"value":"2023-03-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}