Unified Visual-Aware Representations for Data Analytics
One of the characteristics of big data is its internal complexity and variety manifested in many types of datasets that are to be managed, searched, or analyzed. In their natural forms, some data entities are unstructured, such as texts or multimedia objects, while some are structured but too comple...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10854212/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832575626962272256 |
|---|---|
| author | Ladislav Peska Ivana Sixtova David Hoksza David Bernhauer Jakub Lokoc Tomas Skopal |
| author_facet | Ladislav Peska Ivana Sixtova David Hoksza David Bernhauer Jakub Lokoc Tomas Skopal |
| author_sort | Ladislav Peska |
| collection | DOAJ |
| description | One of the characteristics of big data is its internal complexity and variety manifested in many types of datasets that are to be managed, searched, or analyzed. In their natural forms, some data entities are unstructured, such as texts or multimedia objects, while some are structured but too complex (e.g., high-dimensional tabular data). Due to the many different forms of data managed in many domain-specific problems, there are many different data representations used – tailored to a specific data form, domain and task. In this paper, we propose a framework for universal visual representations of complex data. The desired property of the visualizations is the ability to visually encode the semantic features of the original data. Hence, processing of visualizations (images) by generic deep learning models results in deep feature vectors that could be uniformly used in standard data retrieval/analytics tasks. Specifically, we develop a semi-automated transfer learning pipeline for transformation of input arbitrary tabular data into visual representations. The visual representations serve for data analytics tasks performed by human users as well as serve for universal data representations used in machine learning models for automated tasks. We show in large study that visual representations of complex data are effective in a number of domains while we also propose a recommender to help with the parameterization of the entire pipeline for certain domains and use cases. In summary, the proposed framework enables rapid prototyping of data representations (in an arbitrary domain) using a shared concept – visual representations applicable in data analytics using generic deep learning models. |
| format | Article |
| id | doaj-art-f170c1384b164a2280a798a6d4121a5a |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-f170c1384b164a2280a798a6d4121a5a2025-01-31T23:04:57ZengIEEEIEEE Access2169-35362025-01-0113196941971510.1109/ACCESS.2025.353433010854212Unified Visual-Aware Representations for Data AnalyticsLadislav Peska0https://orcid.org/0000-0001-8082-4509Ivana Sixtova1https://orcid.org/0000-0003-2874-1217David Hoksza2https://orcid.org/0000-0003-4679-0557David Bernhauer3https://orcid.org/0000-0003-2368-7506Jakub Lokoc4https://orcid.org/0000-0002-3558-4144Tomas Skopal5https://orcid.org/0000-0002-6591-0879SIRET Research Group, Faculty of Mathematics and Physics, Charles University, Prague, CzechiaSIRET Research Group, Faculty of Mathematics and Physics, Charles University, Prague, CzechiaSIRET Research Group, Faculty of Mathematics and Physics, Charles University, Prague, CzechiaSIRET Research Group, Faculty of Mathematics and Physics, Charles University, Prague, CzechiaSIRET Research Group, Faculty of Mathematics and Physics, Charles University, Prague, CzechiaSIRET Research Group, Faculty of Mathematics and Physics, Charles University, Prague, CzechiaOne of the characteristics of big data is its internal complexity and variety manifested in many types of datasets that are to be managed, searched, or analyzed. In their natural forms, some data entities are unstructured, such as texts or multimedia objects, while some are structured but too complex (e.g., high-dimensional tabular data). Due to the many different forms of data managed in many domain-specific problems, there are many different data representations used – tailored to a specific data form, domain and task. In this paper, we propose a framework for universal visual representations of complex data. The desired property of the visualizations is the ability to visually encode the semantic features of the original data. Hence, processing of visualizations (images) by generic deep learning models results in deep feature vectors that could be uniformly used in standard data retrieval/analytics tasks. Specifically, we develop a semi-automated transfer learning pipeline for transformation of input arbitrary tabular data into visual representations. The visual representations serve for data analytics tasks performed by human users as well as serve for universal data representations used in machine learning models for automated tasks. We show in large study that visual representations of complex data are effective in a number of domains while we also propose a recommender to help with the parameterization of the entire pipeline for certain domains and use cases. In summary, the proposed framework enables rapid prototyping of data representations (in an arbitrary domain) using a shared concept – visual representations applicable in data analytics using generic deep learning models.https://ieeexplore.ieee.org/document/10854212/Data visualizationuniversal data representationsdeep learningdata analyticsuser study |
| spellingShingle | Ladislav Peska Ivana Sixtova David Hoksza David Bernhauer Jakub Lokoc Tomas Skopal Unified Visual-Aware Representations for Data Analytics IEEE Access Data visualization universal data representations deep learning data analytics user study |
| title | Unified Visual-Aware Representations for Data Analytics |
| title_full | Unified Visual-Aware Representations for Data Analytics |
| title_fullStr | Unified Visual-Aware Representations for Data Analytics |
| title_full_unstemmed | Unified Visual-Aware Representations for Data Analytics |
| title_short | Unified Visual-Aware Representations for Data Analytics |
| title_sort | unified visual aware representations for data analytics |
| topic | Data visualization universal data representations deep learning data analytics user study |
| url | https://ieeexplore.ieee.org/document/10854212/ |
| work_keys_str_mv | AT ladislavpeska unifiedvisualawarerepresentationsfordataanalytics AT ivanasixtova unifiedvisualawarerepresentationsfordataanalytics AT davidhoksza unifiedvisualawarerepresentationsfordataanalytics AT davidbernhauer unifiedvisualawarerepresentationsfordataanalytics AT jakublokoc unifiedvisualawarerepresentationsfordataanalytics AT tomasskopal unifiedvisualawarerepresentationsfordataanalytics |