Conference paper Open Access

Unsupervised Anomaly Detection in Data Quality Control

Poon, Lex; Farshidi, Siamak; Li, Na; Zhao, Zhiming


JSON Export

{
  "files": [
    {
      "links": {
        "self": "https://zenodo.org/api/files/c1f00f80-f8b9-4bb7-9381-2d436ef57cde/2021.workshop.bigdata.midp21.camera.pdf"
      }, 
      "checksum": "md5:51cca856e3286b38b7b738f7d43e9a86", 
      "bucket": "c1f00f80-f8b9-4bb7-9381-2d436ef57cde", 
      "key": "2021.workshop.bigdata.midp21.camera.pdf", 
      "type": "pdf", 
      "size": 2899991
    }
  ], 
  "owners": [
    22243
  ], 
  "doi": "10.1109/BigData52589.2021.9671672", 
  "stats": {
    "version_unique_downloads": 45.0, 
    "unique_views": 28.0, 
    "views": 35.0, 
    "version_views": 35.0, 
    "unique_downloads": 45.0, 
    "version_unique_views": 28.0, 
    "volume": 133399586.0, 
    "version_downloads": 46.0, 
    "downloads": 46.0, 
    "version_volume": 133399586.0
  }, 
  "links": {
    "doi": "https://doi.org/10.1109/BigData52589.2021.9671672", 
    "latest_html": "https://zenodo.org/record/5872438", 
    "bucket": "https://zenodo.org/api/files/c1f00f80-f8b9-4bb7-9381-2d436ef57cde", 
    "badge": "https://zenodo.org/badge/doi/10.1109/BigData52589.2021.9671672.svg", 
    "html": "https://zenodo.org/record/5872438", 
    "latest": "https://zenodo.org/api/records/5872438"
  }, 
  "created": "2022-01-18T12:44:13.333953+00:00", 
  "updated": "2022-01-19T01:49:10.168183+00:00", 
  "conceptrecid": "5872437", 
  "revision": 2, 
  "id": 5872438, 
  "metadata": {
    "access_right_category": "success", 
    "doi": "10.1109/BigData52589.2021.9671672", 
    "version": "camera ready", 
    "license": {
      "id": "CC-BY-4.0"
    }, 
    "title": "Unsupervised Anomaly Detection in Data Quality Control", 
    "relations": {
      "version": [
        {
          "count": 1, 
          "index": 0, 
          "parent": {
            "pid_type": "recid", 
            "pid_value": "5872437"
          }, 
          "is_last": true, 
          "last_child": {
            "pid_type": "recid", 
            "pid_value": "5872438"
          }
        }
      ]
    }, 
    "grants": [
      {
        "code": "860627", 
        "links": {
          "self": "https://zenodo.org/api/grants/10.13039/501100000780::860627"
        }, 
        "title": "CLoud ARtificial Intelligence For pathologY", 
        "acronym": "CLARIFY", 
        "program": "Horizon 2020 Framework Programme - European Training Networks", 
        "funder": {
          "doi": "10.13039/501100000780", 
          "acronyms": [], 
          "name": "European Commission", 
          "links": {
            "self": "https://zenodo.org/api/funders/10.13039/501100000780"
          }
        }
      }, 
      {
        "code": "862409", 
        "links": {
          "self": "https://zenodo.org/api/grants/10.13039/501100000780::862409"
        }, 
        "title": "Blue-Cloud: Piloting innovative services for Marine Research & the Blue Economy", 
        "acronym": "Blue Cloud", 
        "program": "H2020", 
        "funder": {
          "doi": "10.13039/501100000780", 
          "acronyms": [], 
          "name": "European Commission", 
          "links": {
            "self": "https://zenodo.org/api/funders/10.13039/501100000780"
          }
        }
      }, 
      {
        "code": "825134", 
        "links": {
          "self": "https://zenodo.org/api/grants/10.13039/501100000780::825134"
        }, 
        "title": "smART socIal media eCOsytstem in a blockchaiN Federated environment", 
        "acronym": "ARTICONF", 
        "program": "H2020", 
        "funder": {
          "doi": "10.13039/501100000780", 
          "acronyms": [], 
          "name": "European Commission", 
          "links": {
            "self": "https://zenodo.org/api/funders/10.13039/501100000780"
          }
        }
      }, 
      {
        "code": "824068", 
        "links": {
          "self": "https://zenodo.org/api/grants/10.13039/501100000780::824068"
        }, 
        "title": "ENVironmental Research Infrastructures building Fair services Accessible for society, Innovation and Research", 
        "acronym": "ENVRI-FAIR", 
        "program": "H2020", 
        "funder": {
          "doi": "10.13039/501100000780", 
          "acronyms": [], 
          "name": "European Commission", 
          "links": {
            "self": "https://zenodo.org/api/funders/10.13039/501100000780"
          }
        }
      }
    ], 
    "keywords": [
      "data quality", 
      "unsupervised learning", 
      "data quality control", 
      "data quality assessment", 
      "anomaly detection,", 
      "automated data quality control"
    ], 
    "publication_date": "2021-12-15", 
    "creators": [
      {
        "affiliation": "University of Amsterdam", 
        "name": "Poon, Lex"
      }, 
      {
        "affiliation": "University of Amsterdam", 
        "name": "Farshidi, Siamak"
      }, 
      {
        "affiliation": "University of Amsterdam", 
        "name": "Li, Na"
      }, 
      {
        "orcid": "0000-0002-6717-9418", 
        "affiliation": "University of Amsterdam", 
        "name": "Zhao, Zhiming"
      }
    ], 
    "meeting": {
      "acronym": "MIDP-2021", 
      "url": "http://www.midp-info.org/", 
      "dates": "15-18 Dec 2021", 
      "place": "Virtual", 
      "title": "7th International Workshop on Methods to Improve Big Data Science Projects (MIDP-2021), in IEEE BigData 2021"
    }, 
    "access_right": "open", 
    "resource_type": {
      "subtype": "conferencepaper", 
      "type": "publication", 
      "title": "Conference paper"
    }, 
    "description": "<p>Data is one of the most valuable assets of an</p>\n\n<p>organization and has a tremendous impact on its long-term</p>\n\n<p>success and decision-making processes. Typically, organizational</p>\n\n<p>data error and outlier detection processes perform manually and</p>\n\n<p>reactively, making them time-consuming and prone to human errors.</p>\n\n<p>Additionally, rich data types, unlabeled data, and increased</p>\n\n<p>volume have made such data more complex. Accordingly, an</p>\n\n<p>automated anomaly detection approach is required to improve</p>\n\n<p>data management and quality control processes. This study</p>\n\n<p>introduces an unsupervised anomaly detection approach based</p>\n\n<p>on models comparison, consensus learning, and a combination of</p>\n\n<p>rules of thumb with iterative hyper-parameter tuning to increase</p>\n\n<p>data quality. Furthermore, a domain expert is considered a</p>\n\n<p>human in the loop to evaluate and check the data quality and to</p>\n\n<p>judge the output of the unsupervised model. An experiment has</p>\n\n<p>been conducted to assess the proposed approach in the context of</p>\n\n<p>a case study. The experiment results confirm that the proposed</p>\n\n<p>approach can improve the quality of</p>"
  }
}
35
46
views
downloads
Views 35
Downloads 46
Data volume 133.4 MB
Unique views 28
Unique downloads 45

Share

Cite as