Taking Advantage of Highly-Correlated Attributes in Similarity Queries with Missing Values

Rodrigues, Lucas Santiago; Cazzolato, Mirela T.; Traina, Agma J. M.; Traina-Jr, Caetano

doi:10.1007/978-3-030-60936-8_13

Cited by 5 publications

(5 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…As future work, we aim to assess the subjective quality of our tool with domain specialists, assisted by Sketch-GUI . We also intend to include missing data treatment into the preprocessing module, reducing the impact of incompleteness over similarity queries and EDA [Rodrigues et al 2020].…”

Section: Discussionmentioning

confidence: 99%

Sketch+ for Visual and Correlation-Based Exploratory Data Analysis: A Case Study with COVID-19 Databases

Cazzolato

Rodrigues²,

Ribeiro³

et al. 2022

jidm

View full text Add to dashboard Cite

The amount of data daily generated by different sources grows exponentially and brings new challenges to the information technology experts. The recorded data usually include heterogeneous attribute types, such as the traditional date, numerical, textual, and categorical information, as well as complex ones, such as images, videos, and multidimensional data. Simply posing similarity queries over such records can underestimate the semantics and potential usefulness of particular attributes. In this context, the Exploratory Data Analysis (EDA) technology is well-suited to understand data and perform knowledge extraction and visualization of existing patterns. In this paper, we propose Sketch+ , a technique and a corresponding supporting tool to compare electronic health records (provided by hospitals) by similarity, supporting correlation-based exploratory analysis over attributes of different types and allowing data preprocessing tasks for visualization and knowledge extraction. Sketch+ computes partial and overall data correlation considering distance spaces induced by the attributes. It employs both ANOVA and association rules with lift correlations to study relationships between variables, allowing extensive data analysis. Among the tools provided, a pixel-oriented one drives the analysts to observe visual correlations among dates, categorical and numerical attributes. As a running case study, we employed three open databases of COVID-19 cases, showing that specialists can benefit from the inference modules of Sketch+ to analyze electronic records. The study highlights how Sketch+ can be employed to spot strong correlations among tuples and attributes, with statistically significant results. The exploratory analysis has been shown to be an essential complement for similarity search tasks, identifying and evaluating patterns from heterogeneous attributes.

show abstract

Section: Discussionmentioning

confidence: 99%

Sketch+ for Visual and Correlation-Based Exploratory Data Analysis: A Case Study with COVID-19 Databases

Cazzolato

Rodrigues²,

Ribeiro³

et al. 2022

jidm

View full text Add to dashboard Cite

show abstract

“…Also, in [Maheshwari et al 2021] the authors exploited several visual features to identify COVID-19 in images. However, few existing studies make the employed visual features available for download, e.g., [Chino et al 2015;Rodrigues et al 2020]. Such studies usually limit the provided data to specific sets of images (e.g., [Oliveira et al 2017;Cazzolato et al 2017]), or provide extracted visual representations for a particular computational task or data domain related to the images [Cazzolato et al 2016].…”

Section: Introductionmentioning

confidence: 99%

FeatSet+: Visual Features Extracted from Public Image Datasets

Cazzolato

Scabora

Zabot

et al. 2022

jidm

View full text Add to dashboard Cite

Real-world applications generate large amounts of images every day. With the generalized use of social media, users frequently share images acquired by smartphones. Also, hospitals, clinics, exhibits, factories, and other facilities generate images with potential use for many applications. Processing the generated images usually requires feature extraction, which can be time-consuming and laborious. In this paper, we present FeatSet+, a compilation of color, texture and shape visual features extracted from 17 open image datasets reported in the literature. FeatSet+ provides a collection of 11 distinct visual features, extracted by well-known Feature Extraction Methods (FEMs) such as LBP, Haralick, and Color Layout. We organized the available features in a standard collection, including the metadata and labels, when available. Eleven of the datasets also contain classes, which aid the evaluation of supervised methods such as classifiers and clustering tasks. FeatSet+ is available for download in a public repository as sql scripts and csv files. Additionally, FeatSet+ provides a description of the domain of each dataset, including the reference to the original work and link. We show the potential applicability of FeatSet+ in four computational tasks: multi-attribute analysis and retrieval, visual analysis using Multidimensional Scaling (MDS) and Principal Components Analysis (PCA), global feature classification, and dimensionality reduction. FeatSet+ can be employed to evaluate supervised and non-supervised learning tasks, also widely supporting Content-Based Image Retrieval (CBIR) applications and complex data indexing using Metric Access Methods (MAMs).

show abstract

“…A recuperação de dados complexos é frequentemente realizada a partir de comparações baseadas em Relações de Similaridade -RS, e são amplamente exploradas em diferentes tipos de domínios e em diversos trabalhos de Consultas por Similaridade sobre dados complexos armazenados em SGBDRs (RODRIGUES et al, 2020;ZABOT et al, 2019;CAZZOLATO et al, 2019a;VASCONCELOS et al, 2018). Tradicionalmente, consultas por similaridade executam comparações entre pares de representações extraídas sobre um conjunto de dados complexos, sobre os quais são frequentemente aplicados extratores de características, resultando em vetores de características.…”

Section: Lista De Ilustraçõesunclassified

“…Visão Geral de abordagens selecionadas para tratamento de dados faltantes. et al, 2016) kNNI (BATISTA; MONARD, 2003) DTI (NIKFALAZAR et al, 2020) GAIN (YOON et al, 2018) SDAi (ABIRI et al, 2019) BR-Tree (OOI; GOH; TAN, 1998) MOSAIC (OOI; GOH; TAN, 1998) BEE (CANAHUATE et al, 2006) Hollow-Tree (BRINIS et al, 2019)SOLID(RODRIGUES et al, 2020) …”

unclassified

Explorando Espaços Métricos Correlacionados em Consultas por Similaridade sobre Bases de Dados Incompletos

Rodrigues¹

Self Cite

View full text Add to dashboard Cite

À toda minha família, em especial aos meus pais, Divaldo e Silvana e minha irmã Lara, por todo apoio e incentivo incondicional em todos os momentos e decisões. Obrigado por presenciarem toda a caminhada da minha vida acadêmica até aqui, sei que sempre poderei contar com vocês.Ao meu orientador, Prof. Dr. Caetano Traina Júnior e sua esposa Prof. Dra. Agma Juci Machado Traina por serem grandes pessoas e pesquisadores em suas áreas de trabalho, proporcionando grandes conhecimentos durante os momentos de reuniões, aulas e discussões realizados durante o período deste Mestrado. Tenho certeza que toda a colaboração de vocês é de grande valor para o meu aprendizado profissional e pessoal.Todos os membros do grupo de pesquisa de Bases de Dados e Imagens (GBdI) que sempre cultivaram um ambiente pró-discussão de diversos assuntos pertinentes à pesquisa, além de sempre ajudarem durante todo este Mestrado. Em especial, agradeço a contribuição da Mirela Teixeira Cazzolato, que participou ativamente das tarefas deste projeto com suas ideias, conhecimentos, leituras, questionamentos e revisões, participando sempre com muita dedicação e paciência em todos os momentos.Agradeço aos meus amigos Thábata, Patrícia, José Maria Clementino, André Toshio, Lucas Scabora e Maxwell Sampaio pelos momentos de diversão durante esse tempo, colaborando para fazer caminhada mais agradável. Meu muito obrigado! Por fim, ao Conselho Nacional de Pesquisa Científica (CNPq) 1 , a Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES) e a Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP) 2 pelo apoio financeiro para a execução deste trabalho.

show abstract

Taking Advantage of Highly-Correlated Attributes in Similarity Queries with Missing Values

Cited by 5 publications

References 9 publications

Sketch+ for Visual and Correlation-Based Exploratory Data Analysis: A Case Study with COVID-19 Databases

Sketch+ for Visual and Correlation-Based Exploratory Data Analysis: A Case Study with COVID-19 Databases

FeatSet+: Visual Features Extracted from Public Image Datasets

Explorando Espaços Métricos Correlacionados em Consultas por Similaridade sobre Bases de Dados Incompletos

Contact Info

Product

Resources

About