An association rule based approach to reducing visual clutter in parallel sets

Zhang, Chong; Yang, Chen; Yang, Jing; Yin, Zhengcong

doi:10.1016/j.visinf.2019.03.006

Cited by 9 publications

(3 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Parallel Sets can also be improved in a semi-automatic way, using machine learning or statistical methods. The interactive approach by Zhang et al [ZCYY19] uses association rule mining to reduce the number of dimensions and categories, requiring user interaction. The approach by Alsakran et al [AHZ * 14] changes the layout and ordering of dimension axes but restricts the dimensionality of the subgroups, i.e., ribbons, to two dimensions.…”

Section: Improvements Of Parallel Setsmentioning

confidence: 99%

“…We note that the number of possible configurations exceeds those of parallel coordinates because the order of categories can be chosen freely. [ZCYY19], which requires user interaction and suffers from summarization that loses information and imposes a biased first view [HD12] by reducing the dimensionality and number of categories. Automatic solutions to designing Parallel Sets do not sufficiently support data analysis in fully exploratory scenarios because they limit the dimensionality of the displayed subsets [AHZ * 14].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

ParSetgnostics: Quality Metrics for Parallel Sets

Dennig

Fischer

Blumenschein

et al. 2021

Computer Graphics Forum

View full text Add to dashboard Cite

While there are many visualization techniques for exploring numeric data, only a few work with categorical data. One prominent example is Parallel Sets, showing data frequencies instead of data points ‐ analogous to parallel coordinates for numerical data. As nominal data does not have an intrinsic order, the design of Parallel Sets is sensitive to visual clutter due to overlaps, crossings, and subdivision of ribbons hindering readability and pattern detection. In this paper, we propose a set of quality metrics, called ParSetgnostics (Parallel Sets diagnostics), which aim to improve Parallel Sets by reducing clutter. These quality metrics quantify important properties of Parallel Sets such as overlap, orthogonality, ribbon width variance, and mutual information to optimize the category and dimension ordering. By conducting a systematic correlation analysis between the individual metrics, we ensure their distinctiveness. Further, we evaluate the clutter reduction effect of ParSetgnostics by reconstructing six datasets from previous publications using Parallel Sets measuring and comparing their respective properties. Our results show that ParSetgostics facilitates multi‐dimensional analysis of categorical data by automatically providing optimized Parallel Set designs with a clutter reduction of up to 81% compared to the originally proposed Parallel Sets visualizations.

show abstract

Section: Improvements Of Parallel Setsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

ParSetgnostics: Quality Metrics for Parallel Sets

Dennig

Fischer

Blumenschein

et al. 2021

Computer Graphics Forum

View full text Add to dashboard Cite

show abstract

“…However, the major challenge with the Apriori algorithm [28] is that it is computationally slow while working on high-dimensional biological data towards generating associative patterns and may truncate the process of pattern discovery before completion [29]. In addition, there is the challenge of data under fitting and inadequate biological result visualization [29,30]. Hence, this work proposed an improved computationally efficient but cost-effective machine-learning algorithm called E_Apriori that will be useful in generating accurate but simple to interpret associative patterns, from high-dimensional biological and clinical data towards malaria control.…”

Section: Introductionmentioning

confidence: 99%

E_Apriori: An Efficient Machine Learning Algorithm for the Control of Malaria

Adegbite

2023

Preprint

View full text Add to dashboard Cite

The discovery of interesting inter-relationships between the different malaria epidemiological parameters is essential towards the disease control. However, existing associative rule-based machine learning algorithms for pattern discovery are slow while working on high-dimensional Malaria Indicator Survey (MIS) data, with the further challenge of data under fitting and inadequate result visualization. Hence, this work proposed a novel and efficient associative rule-based machine-learning algorithm with enhanced graphical visualization capacity for rigorous and confident biological result interpretation for malaria control. Through empirical and asymptotic comparative time-complexity performance evaluations, the proposed algorithm scaled better than other existing associative rule-based machine learning algorithms while maintaining its accuracy. The algorithm was applied to two real MIS data sets obtained from the Demographic and Health Survey repository and other supplementary literature source using Nigeria as a case study. The resulting interesting malaria epidemiological discovered novel trends were: a) the malaria disease might not be associated with the anemia symptom; b) there was no significant association between the anemia symptom and the wealth indices of individuals; c) there were other parameters associated with the insecticide resistance capacity of the malaria vector asides the knock down resistance alleles; d) the population dynamics of the malaria vector was not associated with the malaria disease endemicity. In conclusion, this work developed a computationally efficient and user-friendly associative rule-based machine-learning algorithm called E_Apriori for the control of the malaria disease.

show abstract

Survey of Explainable Machine Learning with Visual and Granular Methods Beyond Quasi-Explanations

Kovalerchuk

Ahmad

Teredesai

2021

Studies in Computational Intelligence

View full text Add to dashboard Cite

This chapter surveys and analyses visual methods of explainability of Machine Learning (ML) approaches with focus on moving from quasi-explanations that dominate in ML to actual domain-specific explanation supported by granular visuals. The importance of visual and granular methods to increase the interpretability and validity of the ML model has grown in recent years. Visuals have an appeal to human perception, which other methods do not. ML interpretation is fundamentally a human activity, not a machine activity. Thus, visual methods are more readily interpretable. Visual granularity is a natural way for efficient ML explanation. Understanding complex causal reasoning can be beyond human abilities without "downgrading" it to human perceptual and cognitive limits. The visual exploration of multidimensional data at different levels of granularity for knowledge discovery is a long-standing research focus. While multiple efficient methods for visual representation of high-dimensional data exist, the loss of interpretable information, occlusion, and clutter continue to be a challenge, which lead to quasiexplanations. This chapter starts with the motivation and the definitions of different forms of explainability and how these concepts and information granularity can integrate in ML. The chapter focuses on a clear distinction between quasi-explanations and actual domain specific explanations, as well as between potentially explainable and an actually explained ML model that are critically important for the further progress of the ML explainability domain. We discuss foundations of interpretability, overview visual interpretability and present several types of methods to visualize the ML models. Next, we present methods of visual discovery of ML models, with the focus on interpretable models, based on the recently introduced concept of General Line Coordinates (GLC). This family of methods take the critical step of creating visual explanations that are not merely quasi-explanations but are also domain specific visual explanations while these methods themselves are domain-agnostic. The chapter includes results on theoretical limits to preserve n-D distances in lower dimensions, based on the Johnson-Lindenstrauss lemma, pointto-point and point-to-graph GLC approaches, and real-world case studies. The chapter also covers traditional visual methods for understanding multiple ML models, which include deep learning and time series models. We illustrate that many of these methods are quasi-explanations and need further enhancement to become actual domain specific explanations. The chapter concludes with outlining open problems and current research frontiers.

show abstract

An association rule based approach to reducing visual clutter in parallel sets

Cited by 9 publications

References 10 publications

ParSetgnostics: Quality Metrics for Parallel Sets

ParSetgnostics: Quality Metrics for Parallel Sets

E_Apriori: An Efficient Machine Learning Algorithm for the Control of Malaria

Survey of Explainable Machine Learning with Visual and Granular Methods Beyond Quasi-Explanations

Contact Info

Product

Resources

About