{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T06:25:45Z","timestamp":1757312745136,"version":"3.41.0"},"reference-count":49,"publisher":"Association for Computing Machinery (ACM)","issue":"3","license":[{"start":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T00:00:00Z","timestamp":1727654400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["J. Data and Information Quality"],"published-print":{"date-parts":[[2024,9,30]]},"abstract":"<jats:p>Human activity recognition (HAR) is an active research field that has seen great success in recent years due to advances in sensory data collection methods and activity recognition systems. Deep artificial intelligence (AI) models have contributed to the success of HAR systems lately, although still suffering from limitations such as data scarcity, the high costs of labelling data instances, and datasets\u2019 imbalance and bias. The temporal nature of human activity data, represented as time series data, impose an additional challenge to using AI models in HAR, because most state-of-the-art models do not account for the time component of the data instances. These limitations have inspired the time-series research community to design generative models for sequential data, but very little work has been done to evaluate the quality of such models. In this work, we conduct a comparative quality analysis of three generative models for time-series data, using a case study in which we aim to generate sensory human activity data from a seed public dataset. Additionally, we adapt and clearly explain four evaluation methods of synthetic time-series data from the literature and apply them to assess the quality of the synthetic activity data we generate. We show experimentally that high-quality human activity data can be generated using deep generative models, and the synthetic data can thus be used in HAR systems to augment real activity data. We also demonstrate that the chosen evaluation methods effectively ensure that the generated data meets the essential quality benchmarks of realism, diversity, coherence, and utility. Our findings suggest that using deep generative models to produce synthetic human activity data can potentially address challenges related to data scarcity, biases, and expensive labeling. This holds promise for enhancing the efficiency and reliability of HAR systems.<\/jats:p>","DOI":"10.1145\/3688393","type":"journal-article","created":{"date-parts":[[2024,8,20]],"date-time":"2024-08-20T11:20:56Z","timestamp":1724152856000},"page":"1-18","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Experience: A Comparative Analysis of Multivariate Time-Series Generative Models: A Case Study on Human Activity Data"],"prefix":"10.1145","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0325-9830","authenticated-orcid":false,"given":"Naif","family":"Alzahrani","sequence":"first","affiliation":[{"name":"School of Computing, Newcastle University, Newcastle upon Tyne, United Kingdom of Great Britain and Northern Ireland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8322-4370","authenticated-orcid":false,"given":"Jacek","family":"Ca\u0142a","sequence":"additional","affiliation":[{"name":"National Innovation Centre for Data at Newcastle University, Newcastle upon Tyne, United Kingdom of Great Britain and Northern Ireland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0978-2446","authenticated-orcid":false,"given":"Paolo","family":"Missier","sequence":"additional","affiliation":[{"name":"School of Computing, Newcastle University, Newcastle upon Tyne, United Kingdom of Great Britain and Northern Ireland"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,4]]},"reference":[{"key":"e_1_3_1_2_2","doi-asserted-by":"crossref","unstructured":"Fl\u00e1via Alves Martin Gairing Frans A. Oliehoek and Thanh-Toan Do. 2020. Sensor data for human activity recognition: Feature representation and benchmarking. 2020 International Joint Conference on Neural Networks (IJCNN). 1\u20138. https:\/\/ieeexplore.ieee.org\/document\/9207068\/citations?tabFilter=papers#citations","DOI":"10.1109\/IJCNN48605.2020.9207068"},{"key":"e_1_3_1_3_2","article-title":"SenseGen: A deep learning architecture for synthetic sensor data generation","author":"Alzantot Moustafa","year":"2017","unstructured":"Moustafa Alzantot, Supriyo Chakraborty, and Mani B. Srivastava. 2017. SenseGen: A deep learning architecture for synthetic sensor data generation. arXiv:1701.08886 [cs] (Jan.2017).","journal-title":"arXiv:1701.08886 [cs]"},{"key":"e_1_3_1_4_2","doi-asserted-by":"publisher","unstructured":"Martin Arjovsky and L\u00e9on Bottou. 2017. Towards principled methods for training generative adversarial networks. (Jan.2017). DOI:10.48550\/arXiv.1701.04862","DOI":"10.48550\/arXiv.1701.04862"},{"key":"e_1_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.5555\/3305381.3305404"},{"key":"e_1_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9534373"},{"key":"e_1_3_1_7_2","volume-title":"Fourier Analysis of Time Series: An Introduction","author":"Bloomfield Peter","year":"2004","unstructured":"Peter Bloomfield. 2004. Fourier Analysis of Time Series: An Introduction. John Wiley & Sons. Google-Books-ID: zQsupRg5rrAC."},{"key":"e_1_3_1_8_2","doi-asserted-by":"publisher","unstructured":"Sam Bond-Taylor Adam Leach Yang Long and Chris G. Willcocks. 2021. Deep generative modelling: A comparative review of VAEs GANs normalizing flows energy-based and autoregressive models. (March2021). DOI:10.1109\/TPAMI.2021.3116668","DOI":"10.1109\/TPAMI.2021.3116668"},{"key":"e_1_3_1_9_2","volume-title":"Time Series Analysis: Forecasting and Control (5th ed.)","author":"Box George","year":"2015","unstructured":"George Box, Gwilym Jenkins, Gregory Reinsel, and Greta Ljung. 2015. Time Series Analysis: Forecasting and Control (5th ed.). John Wiley and Sons Inc. Retrieved from https:\/\/www.wiley.com\/en-gb\/Time+Series+Analysis%3A+Forecasting+and+Control%2C+5th+Edition-p-9781118675021"},{"key":"e_1_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1002\/9781119166092"},{"key":"e_1_3_1_11_2","doi-asserted-by":"publisher","unstructured":"Mason Bretan Gil Weinberg and Larry Heck. 2016. A unit selection methodology for music generation using deep neural networks. (Dec.2016). DOI:10.48550\/arXiv.1612.03789","DOI":"10.48550\/arXiv.1612.03789"},{"key":"e_1_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-020-05399-0"},{"key":"e_1_3_1_13_2","doi-asserted-by":"publisher","unstructured":"Eoin Brophy Zhengwei Wang Qi She and Tomas Ward. 2021. Generative adversarial networks in time series: A survey and taxonomy. (July2021). DOI:10.48550\/arXiv.2107.11098","DOI":"10.48550\/arXiv.2107.11098"},{"key":"e_1_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1007\/s12652-020-02548-0"},{"key":"e_1_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1613\/jair.953"},{"key":"e_1_3_1_16_2","doi-asserted-by":"publisher","unstructured":"Chris Donahue Julian McAuley and Miller Puckette. 2019. Adversarial audio synthesis. (Feb.2019). DOI:10.48550\/arXiv.1802.04208","DOI":"10.48550\/arXiv.1802.04208"},{"key":"e_1_3_1_17_2","doi-asserted-by":"publisher","unstructured":"Florian Eckerli and Joerg Osterrieder. 2021. Generative adversarial networks in finance: An overview. (July2021). DOI:10.48550\/arXiv.2106.06364","DOI":"10.48550\/arXiv.2106.06364"},{"key":"e_1_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3275134"},{"key":"e_1_3_1_19_2","doi-asserted-by":"publisher","unstructured":"Crist\u00f3bal Esteban Stephanie L. Hyland and Gunnar R\u00e4tsch. 2017. Real-valued (medical) time series generation with recurrent conditional GANs. (Dec.2017). DOI:10.48550\/arXiv.1706.02633","DOI":"10.48550\/arXiv.1706.02633"},{"key":"e_1_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.11192"},{"key":"e_1_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.3390\/math10152733"},{"key":"e_1_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/BigData52589.2021.9671280"},{"key":"e_1_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10710-017-9314-z"},{"key":"e_1_3_1_24_2","volume-title":"Advances in Neural Information Processing Systems","author":"Goodfellow Ian","year":"2014","unstructured":"Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. 2014. Generative adversarial nets. In Advances in Neural Information Processing Systems, Vol. 27. Curran Associates, Inc. Retrieved from https:\/\/proceedings.neurips.cc\/paper\/2014\/hash\/5ca3e9b122f61f8f06494c97b1afccf3-Abstract.html"},{"key":"e_1_3_1_25_2","doi-asserted-by":"publisher","unstructured":"Alex Graves. 2014. Generating sequences with recurrent neural networks. (June2014). DOI:10.48550\/arXiv.1308.0850","DOI":"10.48550\/arXiv.1308.0850"},{"key":"e_1_3_1_26_2","doi-asserted-by":"publisher","unstructured":"Martin Heusel Hubert Ramsauer Thomas Unterthiner Bernhard Nessler and Sepp Hochreiter. 2018. GANs trained by a two time-s update rule converge to a local Nash equilibrium. (Jan.2018). DOI:10.48550\/arXiv.1706.08500","DOI":"10.48550\/arXiv.1706.08500"},{"key":"e_1_3_1_27_2","doi-asserted-by":"publisher","unstructured":"Jonathan Ho Ajay Jain and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. (Dec.2020). DOI:10.48550\/arXiv.2006.11239","DOI":"10.48550\/arXiv.2006.11239"},{"key":"e_1_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_3_1_29_2","first-page":"10","volume-title":"Proceedings of the 4th International Workshop on Knowledge Discovery from Sensor Data","author":"Kwapisz Jennifer R.","year":"2010","unstructured":"Jennifer R. Kwapisz, Gary M. Weiss, and Samuel A. Moore. 2010. Activity recognition using cell phone accelerometers. In Proceedings of the 4th International Workshop on Knowledge Discovery from Sensor Data. 10\u201318."},{"key":"e_1_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-70578-7"},{"key":"e_1_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/3410530.3414367"},{"key":"e_1_3_1_32_2","doi-asserted-by":"publisher","unstructured":"David Lopez-Paz and Maxime Oquab. 2018. Revisiting classifier two-sample tests. (Mar.2018). DOI:10.48550\/arXiv.1610.06545","DOI":"10.48550\/arXiv.1610.06545"},{"issue":"86","key":"e_1_3_1_33_2","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Maaten Laurens van der","year":"2008","unstructured":"Laurens van der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE. J. Mach. Learn. Res. 9, 86 (2008), 2579\u20132605. Retrieved from http:\/\/jmlr.org\/papers\/v9\/vandermaaten08a.html","journal-title":"J. Mach. Learn. Res."},{"key":"e_1_3_1_34_2","doi-asserted-by":"publisher","unstructured":"Keiron O\u2019Shea and Ryan Nash. 2015. An introduction to convolutional neural networks. (Dec.2015). DOI:10.48550\/arXiv.1511.08458","DOI":"10.48550\/arXiv.1511.08458"},{"key":"e_1_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/DSAA.2016.49"},{"issue":"8","key":"e_1_3_1_36_2","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford Alec","year":"2019","unstructured":"Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, and Ilya Sutskever. 2019. Language models are unsupervised multitask learners. OpenAI Blog 1, 8 (2019), 9.","journal-title":"OpenAI Blog"},{"key":"e_1_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1002\/widm.1254"},{"key":"e_1_3_1_38_2","doi-asserted-by":"publisher","unstructured":"Masaki Saito Eiichi Matsumoto and Shunta Saito. 2017. Temporal generative adversarial nets with singular value clipping. (Aug.2017). DOI:10.48550\/arXiv.1611.06624","DOI":"10.48550\/arXiv.1611.06624"},{"key":"e_1_3_1_39_2","doi-asserted-by":"publisher","unstructured":"Tim Salimans Ian Goodfellow Wojciech Zaremba Vicki Cheung Alec Radford and Xi Chen. 2016. Improved techniques for training GANs. (June2016). DOI:10.48550\/arXiv.1606.03498","DOI":"10.48550\/arXiv.1606.03498"},{"key":"e_1_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijforecast.2019.07.001"},{"key":"e_1_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1002\/itl2.257"},{"key":"e_1_3_1_42_2","doi-asserted-by":"publisher","unstructured":"Sergey Tulyakov Ming-Yu Liu Xiaodong Yang and Jan Kautz. 2017. MoCoGAN: Decomposing motion and content for video generation. (Dec.2017). DOI:10.48550\/arXiv.1707.04993","DOI":"10.48550\/arXiv.1707.04993"},{"key":"e_1_3_1_43_2","doi-asserted-by":"publisher","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N. Gomez Lukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. (Dec.2017). DOI:10.48550\/arXiv.1706.03762","DOI":"10.48550\/arXiv.1706.03762"},{"key":"e_1_3_1_44_2","doi-asserted-by":"publisher","unstructured":"Carl Vondrick Hamed Pirsiavash and Antonio Torralba. 2016. Generating videos with scene dynamics. (Oct.2016). DOI:10.48550\/arXiv.1609.02612","DOI":"10.48550\/arXiv.1609.02612"},{"key":"e_1_3_1_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2018.8489106"},{"key":"e_1_3_1_46_2","doi-asserted-by":"publisher","unstructured":"Gary Weiss. 2019. WISDM smartphone and smartwatch activity and biometrics dataset. (2019). DOI:10.24432\/C5HK59","DOI":"10.24432\/C5HK59"},{"key":"e_1_3_1_47_2","doi-asserted-by":"publisher","unstructured":"Qiantong Xu Gao Huang Yang Yuan Chuan Guo Yu Sun Felix Wu and Kilian Weinberger. 2018. An empirical study on evaluation metrics of generative adversarial networks. (Aug.2018). DOI:10.48550\/arXiv.1806.07755","DOI":"10.48550\/arXiv.1806.07755"},{"key":"e_1_3_1_48_2","volume-title":"Advances in Neural Information Processing Systems","author":"Yoon Jinsung","year":"2019","unstructured":"Jinsung Yoon, Daniel Jarrett, and Mihaela van der Schaar. 2019. Time-series generative adversarial networks. In Advances in Neural Information Processing Systems, Vol. 32. Curran Associates, Inc. Retrieved from https:\/\/papers.nips.cc\/paper\/2019\/hash\/c9efe5f26cd17ba6216bbe2a7d26d490-Abstract.html"},{"key":"e_1_3_1_49_2","volume-title":"Advances in Neural Information Processing Systems","author":"Yu Hsiang-Fu","year":"2016","unstructured":"Hsiang-Fu Yu, Nikhil Rao, and Inderjit S. Dhillon. 2016. Temporal regularized matrix factorization for high-dimensional time series prediction. In Advances in Neural Information Processing Systems, Vol. 29. Curran Associates, Inc. Retrieved from https:\/\/papers.nips.cc\/paper_files\/paper\/2016\/hash\/85422afb467e9456013a2a51d4dff702-Abstract.html"},{"key":"e_1_3_1_50_2","doi-asserted-by":"publisher","unstructured":"Han Zhang Tao Xu Hongsheng Li Shaoting Zhang Xiaogang Wang Xiaolei Huang and Dimitris Metaxas. 2017. StackGAN: Text to photo-realistic image synthesis with stacked generative adversarial networks. (Aug.2017). DOI:10.48550\/arXiv.1612.03242","DOI":"10.48550\/arXiv.1612.03242"}],"container-title":["Journal of Data and Information Quality"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3688393","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3688393","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:05:56Z","timestamp":1750291556000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3688393"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,30]]},"references-count":49,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2024,9,30]]}},"alternative-id":["10.1145\/3688393"],"URL":"https:\/\/doi.org\/10.1145\/3688393","relation":{},"ISSN":["1936-1955","1936-1963"],"issn-type":[{"type":"print","value":"1936-1955"},{"type":"electronic","value":"1936-1963"}],"subject":[],"published":{"date-parts":[[2024,9,30]]},"assertion":[{"value":"2023-01-26","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-06-28","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-10-04","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}