{ "ok": true, "doi": "10.46243/jst.2023.v8.i12.pp219-229", "events": [ { "seq": 1, "kind": "register", "at": "2026-09-29 22:00:28", "by": "Administrator (admin)", "by_kind": "user", "note": "registered at Crossref; record read from api.crossref.org", "changes": [ { "path": "abstract.lang", "from": null, "to": "en" }, { "path": "abstract.value", "from": null, "to": "Publishing datasets plays an essential role in open data research and promoting transparency of government agencies. However, such data publication might reveal users’ private information. One of the most sensitive sources of data is spatiotemporal trajectory datasets. Unfortunately, merely removing unique identifiers cannot preserve the privacy of users. Adversaries may know parts of the trajectories or be able to link the published dataset to other sources for the purpose of user identification. Therefore, it is crucial to apply privacy preserving techniques before the publication of spatiotemporal trajectory datasets. In this paper, we propose a robust framework for the anonymization of spatiotemporal trajectory datasets termed as machine learning based anonymization (MLA). By introducing a new formulation of the problem, we are able to apply machine learning algorithms for clustering the trajectories and propose to use k-means algorithm for this purpose. A variation of k-means algorithm is also proposed to preserve the privacy in overly sensitive datasets. Moreover, we improve the alignment process by considering multiple sequence alignment as part of the MLA. The framework and all the proposed algorithms are applied to T-Drive, Geolife, and Gowalla location datasets. The experimental results indicate a significantly higher utility of datasets by anonymization based on MLA framework." }, { "path": "agents.0.name.family", "from": null, "to": "C. Gazala Akhtar" }, { "path": "agents.0.name.given", "from": null, "to": "C. Gazala Akhtar" }, { "path": "agents.0.role", "from": null, "to": "author" }, { "path": "agents.0.sequence", "from": null, "to": "first" }, { "path": "agents.1.name.org", "from": null, "to": "Longman Publishers" }, { "path": "agents.1.role", "from": null, "to": "publisher" }, { "path": "characters.0", "from": null, "to": "Language" }, { "path": "container.identifiers.0.medium", "from": null, "to": "electronic" }, { "path": "container.identifiers.0.type", "from": null, "to": "ISSN" }, { "path": "container.identifiers.0.value", "from": null, "to": "2456-5660" }, { "path": "container.issue", "from": null, "to": "12" }, { "path": "container.pages.first", "from": null, "to": "219" }, { "path": "container.pages.last", "from": null, "to": "229" }, { "path": "container.titles.0.type", "from": null, "to": "PrincipalTitle" }, { "path": "container.titles.0.value", "from": null, "to": "Journal of Science & Technology" }, { "path": "container.type", "from": null, "to": "Journal" }, { "path": "container.volume", "from": null, "to": "8" }, { "path": "dates.date_type", "from": null, "to": "PublicationDate" }, { "path": "dates.online", "from": null, "to": "2023-12-12" }, { "path": "dates.published", "from": null, "to": "2023-12-12" }, { "path": "doi", "from": null, "to": "10.46243/jst.2023.v8.i12.pp219-229" }, { "path": "format", "from": null, "to": "smartscholars-doi-metadata/1.0" }, { "path": "identifiers.0.type", "from": null, "to": "DOI" }, { "path": "identifiers.0.value", "from": null, "to": "10.46243/jst.2023.v8.i12.pp219-229" }, { "path": "language", "from": null, "to": "en" }, { "path": "license.applies_to", "from": null, "to": "vor" }, { "path": "license.start", "from": null, "to": "2023-12-12" }, { "path": "license.url", "from": null, "to": "https://creativecommons.org/licenses/by/4.0/" }, { "path": "links.0.primary", "from": null, "to": true }, { "path": "links.0.return_type", "from": null, "to": "text/html" }, { "path": "links.0.url", "from": null, "to": "https://www.jst.org.in/index.php/pub/article/view/902" }, { "path": "links.1.purpose", "from": null, "to": "text-mining" }, { "path": "links.1.return_type", "from": null, "to": "application/pdf" }, { "path": "links.1.url", "from": null, "to": "https://www.jst.org.in/index.php/pub/article/download/902/829" }, { "path": "links.2.purpose", "from": null, "to": "text-mining" }, { "path": "links.2.return_type", "from": null, "to": "application/xml" }, { "path": "links.2.url", "from": null, "to": "https://www.jst.org.in/index.php/pub/article/download/902/1661" }, { "path": "modes.0", "from": null, "to": "Visual" }, { "path": "record.issue_number", "from": null, "to": 1 }, { "path": "record.registered", "from": null, "to": "2024-02-16" }, { "path": "record.registrant", "from": null, "to": "Longman Publishers" }, { "path": "record.source", "from": null, "to": "crossref-api" }, { "path": "record.source_agency", "from": null, "to": "Crossref (member 25296)" }, { "path": "record.updated", "from": null, "to": "2026-09-28" }, { "path": "references.0.doi", "from": null, "to": "10.1109/infocomwkshps47286.2019.9093762" }, { "path": "references.0.key", "from": null, "to": "ref1" }, { "path": "references.0.unstructured", "from": null, "to": "S. Shaham, M. Ding, B. Liu, Z. Lin, and J. Li, “Machine learning aided anonymization of spatiotemporal trajectory datasets,” arXiv preprint arXiv:1902.08934, 2019" }, { "path": "references.1.key", "from": null, "to": "ref2" }, { "path": "references.1.unstructured", "from": null, "to": "A. Government, “New australian government data sharing and release legislation,” 2018. C. Gazala Akhtar, G. Lahari, P. Shruthi, V. Akshitha: PRESERVING PRIVACY IN THE ERA OF BIG DATA: A MACHINE LEARNING-BASED ANONYMIZATION FRAMEWORK FOR SPATIOTEMPORAL TRAJECTORY DATASETS" }, { "path": "references.2.doi", "from": null, "to": "10.1145/2351476.2351486" }, { "path": "references.2.key", "from": null, "to": "ref3" }, { "path": "references.2.unstructured", "from": null, "to": "T. Takahashi and S. Miyakawa, “Cmoa: Continuous moving object anonymization,” in Proceedings of the 16th International Database Engineering & Applications Sysmposium. ACM, 2012, pp. 81–90" }, { "path": "references.3.doi", "from": null, "to": "10.1007/978-3-030-05755-8_44" }, { "path": "references.3.key", "from": null, "to": "ref4" }, { "path": "references.3.unstructured", "from": null, "to": "X. Zhou and M. Qiu, “A k-anonymous full domain generalization algorithm based on heap sort,” in International Conference on Smart Computing and Communication. Springer, 2018, pp. 446–" }, { "path": "references.4.doi", "from": null, "to": "10.1145/1066157.1066164" }, { "path": "references.4.key", "from": null, "to": "ref5" }, { "path": "references.4.unstructured", "from": null, "to": "K. LeFevre, D. J. DeWitt, and R. Ramakrishnan, “Incognito: Efficient full-domain k-anonymity,” in Proceedings of the 2005 ACM SIGMOD international conference on Management of data. ACM, 2005, pp. 49–60" }, { "path": "referent", "from": null, "to": "Creation" }, { "path": "structural_type", "from": null, "to": "Digital" }, { "path": "titles.0.lang", "from": null, "to": "en" }, { "path": "titles.0.type", "from": null, "to": "PrincipalTitle" }, { "path": "titles.0.value", "from": null, "to": "PRESERVING PRIVACY IN THE ERA OF BIG DATA: A MACHINE LEARNING-BASED ANONYMIZATION FRAMEWORK FOR SPATIOTEMPORAL TRAJECTORY DATASETS" }, { "path": "type", "from": null, "to": "JournalArticle" } ], "record_after": { "format": "smartscholars-doi-metadata/1.0", "doi": "10.46243/jst.2023.v8.i12.pp219-229", "referent": "Creation", "type": "JournalArticle", "structural_type": "Digital", "modes": [ "Visual" ], "characters": [ "Language" ], "titles": [ { "value": "PRESERVING PRIVACY IN THE ERA OF BIG DATA: A MACHINE LEARNING-BASED ANONYMIZATION FRAMEWORK FOR SPATIOTEMPORAL TRAJECTORY DATASETS", "type": "PrincipalTitle", "lang": "en" } ], "identifiers": [ { "type": "DOI", "value": "10.46243/jst.2023.v8.i12.pp219-229" } ], "agents": [ { "role": "author", "name": { "given": "C. Gazala Akhtar", "family": "C. Gazala Akhtar" }, "sequence": "first" }, { "role": "publisher", "name": { "org": "Longman Publishers" } } ], "dates": { "published": "2023-12-12", "date_type": "PublicationDate", "online": "2023-12-12" }, "language": "en", "container": { "type": "Journal", "titles": [ { "value": "Journal of Science & Technology", "type": "PrincipalTitle" } ], "identifiers": [ { "type": "ISSN", "value": "2456-5660", "medium": "electronic" } ], "volume": "8", "issue": "12", "pages": { "first": "219", "last": "229" } }, "links": [ { "url": "https://www.jst.org.in/index.php/pub/article/view/902", "return_type": "text/html", "primary": true }, { "url": "https://www.jst.org.in/index.php/pub/article/download/902/829", "purpose": "text-mining", "return_type": "application/pdf" }, { "url": "https://www.jst.org.in/index.php/pub/article/download/902/1661", "purpose": "text-mining", "return_type": "application/xml" } ], "abstract": { "value": "Publishing datasets plays an essential role in open data research and promoting transparency of government agencies. However, such data publication might reveal users’ private information. One of the most sensitive sources of data is spatiotemporal trajectory datasets. Unfortunately, merely removing unique identifiers cannot preserve the privacy of users. Adversaries may know parts of the trajectories or be able to link the published dataset to other sources for the purpose of user identification. Therefore, it is crucial to apply privacy preserving techniques before the publication of spatiotemporal trajectory datasets. In this paper, we propose a robust framework for the anonymization of spatiotemporal trajectory datasets termed as machine learning based anonymization (MLA). By introducing a new formulation of the problem, we are able to apply machine learning algorithms for clustering the trajectories and propose to use k-means algorithm for this purpose. A variation of k-means algorithm is also proposed to preserve the privacy in overly sensitive datasets. Moreover, we improve the alignment process by considering multiple sequence alignment as part of the MLA. The framework and all the proposed algorithms are applied to T-Drive, Geolife, and Gowalla location datasets. The experimental results indicate a significantly higher utility of datasets by anonymization based on MLA framework.", "lang": "en" }, "license": { "url": "https://creativecommons.org/licenses/by/4.0/", "start": "2023-12-12", "applies_to": "vor" }, "references": [ { "key": "ref1", "doi": "10.1109/infocomwkshps47286.2019.9093762", "unstructured": "S. Shaham, M. Ding, B. Liu, Z. Lin, and J. Li, “Machine learning aided anonymization of spatiotemporal trajectory datasets,” arXiv preprint arXiv:1902.08934, 2019" }, { "key": "ref2", "unstructured": "A. Government, “New australian government data sharing and release legislation,” 2018. C. Gazala Akhtar, G. Lahari, P. Shruthi, V. Akshitha: PRESERVING PRIVACY IN THE ERA OF BIG DATA: A MACHINE LEARNING-BASED ANONYMIZATION FRAMEWORK FOR SPATIOTEMPORAL TRAJECTORY DATASETS" }, { "key": "ref3", "doi": "10.1145/2351476.2351486", "unstructured": "T. Takahashi and S. Miyakawa, “Cmoa: Continuous moving object anonymization,” in Proceedings of the 16th International Database Engineering & Applications Sysmposium. ACM, 2012, pp. 81–90" }, { "key": "ref4", "doi": "10.1007/978-3-030-05755-8_44", "unstructured": "X. Zhou and M. Qiu, “A k-anonymous full domain generalization algorithm based on heap sort,” in International Conference on Smart Computing and Communication. Springer, 2018, pp. 446–" }, { "key": "ref5", "doi": "10.1145/1066157.1066164", "unstructured": "K. LeFevre, D. J. DeWitt, and R. Ramakrishnan, “Incognito: Efficient full-domain k-anonymity,” in Proceedings of the 2005 ACM SIGMOD international conference on Management of data. ACM, 2005, pp. 49–60" } ], "record": { "registrant": "Longman Publishers", "registered": "2024-02-16", "updated": "2026-09-28", "issue_number": 1, "source": "crossref-api", "source_agency": "Crossref (member 25296)" } }, "url_after": "https://www.jst.org.in/index.php/pub/article/view/902", "sha256_before": null, "sha256_after": "d679a987738c8c34692091e0a2b99f13a047b6066e52b61f7e2c0ca8abb93b6a" }, { "seq": 2, "kind": "update", "at": "2026-09-29 23:59:47", "by": "Administrator (admin)", "by_kind": "user", "note": "record re-read from api.crossref.org", "changes": [ { "path": "container.titles.0.value", "from": "Journal of Science & Technology", "to": "Journal of Science & Technology" } ], "record_after": { "format": "smartscholars-doi-metadata/1.0", "doi": "10.46243/jst.2023.v8.i12.pp219-229", "referent": "Creation", "type": "JournalArticle", "structural_type": "Digital", "modes": [ "Visual" ], "characters": [ "Language" ], "titles": [ { "value": "PRESERVING PRIVACY IN THE ERA OF BIG DATA: A MACHINE LEARNING-BASED ANONYMIZATION FRAMEWORK FOR SPATIOTEMPORAL TRAJECTORY DATASETS", "type": "PrincipalTitle", "lang": "en" } ], "identifiers": [ { "type": "DOI", "value": "10.46243/jst.2023.v8.i12.pp219-229" } ], "agents": [ { "role": "author", "name": { "given": "C. Gazala Akhtar", "family": "C. Gazala Akhtar" }, "sequence": "first" }, { "role": "publisher", "name": { "org": "Longman Publishers" } } ], "dates": { "published": "2023-12-12", "date_type": "PublicationDate", "online": "2023-12-12" }, "language": "en", "container": { "type": "Journal", "titles": [ { "value": "Journal of Science & Technology", "type": "PrincipalTitle" } ], "identifiers": [ { "type": "ISSN", "value": "2456-5660", "medium": "electronic" } ], "volume": "8", "issue": "12", "pages": { "first": "219", "last": "229" } }, "links": [ { "url": "https://www.jst.org.in/index.php/pub/article/view/902", "return_type": "text/html", "primary": true }, { "url": "https://www.jst.org.in/index.php/pub/article/download/902/829", "purpose": "text-mining", "return_type": "application/pdf" }, { "url": "https://www.jst.org.in/index.php/pub/article/download/902/1661", "purpose": "text-mining", "return_type": "application/xml" } ], "abstract": { "value": "Publishing datasets plays an essential role in open data research and promoting transparency of government agencies. However, such data publication might reveal users’ private information. One of the most sensitive sources of data is spatiotemporal trajectory datasets. Unfortunately, merely removing unique identifiers cannot preserve the privacy of users. Adversaries may know parts of the trajectories or be able to link the published dataset to other sources for the purpose of user identification. Therefore, it is crucial to apply privacy preserving techniques before the publication of spatiotemporal trajectory datasets. In this paper, we propose a robust framework for the anonymization of spatiotemporal trajectory datasets termed as machine learning based anonymization (MLA). By introducing a new formulation of the problem, we are able to apply machine learning algorithms for clustering the trajectories and propose to use k-means algorithm for this purpose. A variation of k-means algorithm is also proposed to preserve the privacy in overly sensitive datasets. Moreover, we improve the alignment process by considering multiple sequence alignment as part of the MLA. The framework and all the proposed algorithms are applied to T-Drive, Geolife, and Gowalla location datasets. The experimental results indicate a significantly higher utility of datasets by anonymization based on MLA framework.", "lang": "en" }, "license": { "url": "https://creativecommons.org/licenses/by/4.0/", "start": "2023-12-12", "applies_to": "vor" }, "references": [ { "key": "ref1", "doi": "10.1109/infocomwkshps47286.2019.9093762", "unstructured": "S. Shaham, M. Ding, B. Liu, Z. Lin, and J. Li, “Machine learning aided anonymization of spatiotemporal trajectory datasets,” arXiv preprint arXiv:1902.08934, 2019" }, { "key": "ref2", "unstructured": "A. Government, “New australian government data sharing and release legislation,” 2018. C. Gazala Akhtar, G. Lahari, P. Shruthi, V. Akshitha: PRESERVING PRIVACY IN THE ERA OF BIG DATA: A MACHINE LEARNING-BASED ANONYMIZATION FRAMEWORK FOR SPATIOTEMPORAL TRAJECTORY DATASETS" }, { "key": "ref3", "doi": "10.1145/2351476.2351486", "unstructured": "T. Takahashi and S. Miyakawa, “Cmoa: Continuous moving object anonymization,” in Proceedings of the 16th International Database Engineering & Applications Sysmposium. ACM, 2012, pp. 81–90" }, { "key": "ref4", "doi": "10.1007/978-3-030-05755-8_44", "unstructured": "X. Zhou and M. Qiu, “A k-anonymous full domain generalization algorithm based on heap sort,” in International Conference on Smart Computing and Communication. Springer, 2018, pp. 446–" }, { "key": "ref5", "doi": "10.1145/1066157.1066164", "unstructured": "K. LeFevre, D. J. DeWitt, and R. Ramakrishnan, “Incognito: Efficient full-domain k-anonymity,” in Proceedings of the 2005 ACM SIGMOD international conference on Management of data. ACM, 2005, pp. 49–60" } ], "record": { "registrant": "Longman Publishers", "registered": "2024-02-16", "updated": "2026-09-28", "issue_number": 1, "source": "crossref-api", "source_agency": "Crossref (member 25296)" } }, "url_after": "https://www.jst.org.in/index.php/pub/article/view/902", "sha256_before": "d679a987738c8c34692091e0a2b99f13a047b6066e52b61f7e2c0ca8abb93b6a", "sha256_after": "b96fcef82144b8bf166cc805d819edbfc39d13ae5560f0f88fbabd794781fc05" } ] }