VizOPTICS: Getting insights into OPTICS via interactive visual analysis. (April 2023)

• Record Type: Journal Article
• Authors: Wu, Caixia; Chen, Yi; Dong, Yu; Zhou, Fangfang; Zhao, Ying; Liang, Christy Jie
• Is Part Of: Computers & electrical engineering. Volume 107(2023)
• Publication Date: 2023-04
• Subjects: Clustering algorithm -- OPTICS -- Cluster analysis -- Visualization -- Interaction -- Explainable machine learning; Computer engineering -- Periodicals; Electrical engineering -- Periodicals; Electrical engineering -- Data processing -- Periodicals; Ordinateurs -- Conception et construction -- Périodiques; Électrotechnique -- Périodiques; Électrotechnique -- Informatique -- Périodiques; Computer engineering; Electrical engineering; Electrical engineering -- Data processing; Periodicals; Electronic journals; 621.302854
• DOI: 10.1016/j.compeleceng.2023.108624
• Languages: English
• ISSNs: 0045-7906

Abstract

Abstract: Ordering points to identify the clustering structure (OPTICS) is a density-based clustering algorithm that allows the exploration of the cluster structure in the dataset by outputting an ordered queue called cluster ordering. However, this nonexplicit output makes it greatly more difficult for practitioners to identify cluster patterns and obtain high-quality clusters. In this paper, we firstly investigate OPTICS in depth and identify the challenges facing users of OPTICS for cluster analysis through a pilot user study. Then, integrating human intelligence deeply with the machine intelligence of OPTICS, a visual analytics approach, VizOPTICS, is proposed to support practitioners in understanding and applying OPTICS to extract meaningful clustering results. It includes an ordered lattice plot for observing the generation process of cluster ordering, a density scatter plot for analyzing the cluster structure in datasets, and a dynamic reachability plot for optimizing clustering results, and also provides several interaction modes, such as selecting and highlighting, to help users analyze the cluster formation and algorithm operation processes interactively. Finally, we assess our approach through four case studies and a user evaluation study. The results demonstrate the effectiveness and efficiency of the system. Highlights: The challenges for visual cluster analysis are formulated by a pilot user study. A visual design with multiple views is proposed to obtain high-quality clusters. A system VizOPTICS are implemented to support obtaining insights into OPTICS. Pre-study and pro-study demonstrate the effectiveness and efficiency of VizOPTICS.