Compass: Towards Better Causal Analysis of Urban Time Series

Deng, Zikun; Weng, Di; Xie, Xiao; Bao, Jie; Zheng, Yu; Xu, Mingliang; Chen, Wei; Wu, Yingcai

doi:10.1109/tvcg.2021.3114875

Cited by 33 publications

(20 citation statements)

References 84 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A relevant image help users interpret the data. Recently, Compass [17] introduced a compass glyph to facilitate the in-depth understanding of urban problems.…”

Section: Metaphor-based Designsmentioning

confidence: 99%

“…Accordingly, visual metaphors are actively used to draw data-driven glyphs with representative and familiar appearances related to the data [35]. We have seen wide adoption of metaphoric glyphs in various domains, such as sports [32,44], urban application [17,36], and blockchain [68]. Studies have also shown that appropriate metaphors can help people understand glyphs quickly and accurately [13,22,35].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

MetaGlyph: Automatic Generation of Metaphoric Glyph-based Visualization

Lü

Shu

Deng

et al. 2022

IEEE Trans. Visual. Comput. Graphics

Self Cite

View full text Add to dashboard Cite

Fig. 1. Example MGVs generated by MetaGlyph: (a) several attributes of different pokemons; (b) forest area changes in different countries from 1995 to 2020; (c) display of various CDs; (e) multiple hotels' information arranged by price (x) and rate (y); (f) chocolates in different ratings placed on a map; (g) disparate mushrooms. The legends in (a1)(b1)(f1) are also generated by MetaGlyph. The center boxes with yellow backgrounds illustrate the data mappings for each glyph. Encoding channels are represented in icons and (d) shows the annotation. Dashed arrows are used to associate visual elements with the resulting visualizations.

show abstract

“…A relevant image help users interpret the data. Recently, Compass [17] introduced a compass glyph to facilitate the in-depth understanding of urban problems.…”

Section: Metaphor-based Designsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

MetaGlyph: Automatic Generation of Metaphoric Glyph-based Visualization

Lü

Shu

Deng

et al. 2022

IEEE Trans. Visual. Comput. Graphics

Self Cite

View full text Add to dashboard Cite

show abstract

“…To control air pollution, it is important to understand its influence and propagation processes. Various visual analytics techniques have been developed to study its propagation processes based on co-occurrences [85,86], simulation [87], event cascades [65], correlation [88], and causality [52]. Shen et al [89] proposed a visual analytics approach combined with deep learning to predict air quality.…”

Section: Air Qualitymentioning

confidence: 99%

A survey of urban visual analytics: Advances and future directions

et al. 2022

View full text Add to dashboard Cite

Developing effective visual analytics systems demands care in characterization of domain problems and integration of visualization techniques and computational models. Urban visual analytics has already achieved remarkable success in tackling urban problems and providing fundamental services for smart cities. To promote further academic research and assist the development of industrial urban analytics systems, we comprehensively review urban visual analytics studies from four perspectives. In particular, we identify 8 urban domains and 22 types of popular visualization, analyze 7 types of computational method, and categorize existing systems into 4 types based on their integration of visualization techniques and computational models. We conclude with potential research directions and opportunities.

show abstract

“…Causal relations are commonly illustrated with a directed acyclic graph, where a node serves for a type of entities and a link with an arrow encodes the causal relation and direction between two kinds of entities, such as Causalflow [51] and SeqCausal [20] for event sequence dataset, as well as Compass [10], Causality Explorer [50] and the Visual Causality Analyst [49] for multiple dimensional datasets. The above studies are designed for visual exploration of simple directed graph.…”

Section: Visual Causality Analysismentioning

confidence: 99%