Visual Exploration of Anomalies in Cyclic Time Series Data with Matrix and Glyph Representations

Suschnigg, Josef; Mutlu, Belgin; Koutroulis, Georgios; Sabol, Vedran; Thalmann, Stefan; Schreck, Tobias

doi:10.1016/j.bdr.2021.100251

Cited by 10 publications

(10 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similarly, Stoffel et al [23] implemented a system capable of visually identifying correlations and anomalies in large datasets, enabling the identification and investigation of security-related events. Suschnigg et al [24] introduced a flexible and extendable visual analytics approach for anomaly detection, with a focus on cycle-dependent data. While these tools offer valuable insights, they may not be specifically tailored to handle big time series data commonly encountered across various applications.…”

Section: Related Workmentioning

confidence: 99%

Anomalyzer: A Visual Interface for Multimodal Time Series Anomaly Analysis

Huang,

Zhang

2024

Preprint

View full text Add to dashboard Cite

Multimodal time series data are pervasive across various applications, providing detailed insights into the evolution of dynamic and complex systems with high-dimensional, high-resolution information. Analyzing the statistical characteristics, detecting changes, and uncovering unexpected behaviors over time from these longitudinal data can yield valuable insights. Traditional anomaly detection methods that rely solely on automated algorithms often overlook the context-specific nature of anomalies. To address this challenge, we introduce Anomalyzer, a novel visual interface for anomaly analysis with multimodal time series data at scale. Anomalyzer integrates sequential transformations to extract, refine, and analyze data representations crucial for anomaly analysis in complex multimodal time series data. Our approach offers a simple yet powerful workflow, a purposeful and step-by-step process meticulously crafted to guide users through the identification and analysis of anomalies with precision and clarity. We evaluate the performance of Anomalyzer with a synthetic multi-variate time series dataset, demonstrating the effectiveness of our novel approach in identifying and analyzing anomalies. The preliminary results have shown that Anomalyzer can help users to perform time series visualization and anomaly detection efficiently using its visualization, aggregation, and anomaly detection capabilities.

show abstract

Section: Related Workmentioning

confidence: 99%

Anomalyzer: A Visual Interface for Multimodal Time Series Anomaly Analysis

Huang,

Zhang

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…There, design studies and resulting VA applications mainly support product design, condition monitoring of stations, the optimization of testing procedures, or the visual support of high cognition tasks. Efforts were carried out to visualize in-car communication networks [41], [42], [43], to facilitate the exploration of multi-criteria alternatives for rotor designs [7],to detect and analyze anomalies in test stations [14], [50], the visual exploration of assembling data to detect inefficiencies [54], and to support mechanical engineers in the analysis of acoustic signatures of electrical engines [12]. Some of the mentioned studies explicitly acknowledge the need for externalizing tacit expert knowledge [14].…”

Section: B Design Studies In Automotive Industrymentioning

confidence: 99%

ManuKnowVis: How to Support Different User Groups in Contextualizing and Leveraging Knowledge Repositories

Eirich

Jäckle

Sedlmair

et al. 2023

IEEE Trans. Visual. Comput. Graphics

View full text Add to dashboard Cite

We present ManuKnowVis, the result of a design study, in which we contextualize data from multiple knowledge repositories of a manufacturing process for battery modules used in electric vehicles. In data-driven analyses of manufacturing data, we observed a discrepancy between two stakeholder groups involved in serial manufacturing processes: Knowledge providers (e.g., engineers) have domain knowledge about the manufacturing process but have difficulties in implementing data-driven analyses. Knowledge consumers (e.g., data scientists) have no first-hand domain knowledge but are highly skilled in performing data-driven analyses. ManuKnowVis bridges the gap between providers and consumers and enables the creation and completion of manufacturing knowledge. We contribute a multi-stakeholder design study, where we developed ManuKnowVis in three main iterations with consumers and providers from an automotive company. The iterative development led us to a multiple linked view tool, in which, on the one hand, providers can describe and connect individual entities (e.g., stations or produced parts) of the manufacturing process based on their domain knowledge. On the other hand, consumers can leverage this enhanced data to better understand complex domain problems, thus, performing data analyses more efficiently. As such, our approach directly impacts the success of data-driven analyses from manufacturing data. To demonstrate the usefulness of our approach, we carried out a case study with seven domain experts, which demonstrates how providers can externalize their knowledge and consumers can implement data-driven analyses more efficiently.

show abstract

“…We initiated our research work with literature analyses on multiple topics, such as visual interactive labeling [12], interactive machine learning [4], knowledge-assisted visualization [81], organizational knowledge creation [88], organizational learning [6], knowledge creation in visual analytics [100], or anomaly detection in manufacturing data [114] to name a view. In this regard, we performed two case studies according to the rationale of Yin [135] to enhance the following two theoretical models:…”

Section: Research Approachmentioning

confidence: 99%

“…Cibulsiki et al [19] developed a VA system to facilitate the exploration of multi-criteria alternatives for rotor designs. Suschnigg et al [114] did build a system to detect and analyze anomalies in test stations, while Xu et al [133] support the visual exploration of assembling data to detect inefficiencies. Gashi et al [40] developed a visualization approach to show the interdependencies of manufacturing stations for predictive maintenance.…”

Section: Applications Of Visual Analytics In the Manufacturing Sectormentioning

confidence: 99%

“…Sedlmair et al [104] show how Visual Analytics can help automotive engineers in debugging masses of traces each consisting of millions of recorded messages from in-car communication networks. Finally, Suschnigg et al [114] show how domain experts can improve the quality of part testing by providing a Visual Analytics system that allows for detecting anomalies in test bench data.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

The Creation, Formalization, and Transfer of Expert Knowledge with Visual Analytics in Industrial Manufacturing Processes of Electrical Vehicles

Eirich¹

View full text Add to dashboard Cite

The 21st century will be heavily impacted by the capability to create value from recorded data of all kinds. In this regard, industrial manufacturing intuitions increasingly rely on new data-driven technologies, such as the Internet of Things or Machine Learning. In terms of data collection, manufacturing processes increasingly include sophisticated sensor equipment, which results in interconnected networks of manufacturing all assembling parts and producing data. However, manufacturing institutions currently face two challenges. First, large amounts of parts and hence data are produced during fully automated manufacturing processes. Second, due to the overwhelming amount of recorded data, it is particularly challenging to efficiently analyze manufacturing data. Hence, it is important to efficiently store and share gained knowledge from performed data analyses. Information visualization and Visual Analytics are two prolific branches of data analysis exploiting sophisticated visualization techniques to support the execution of analytical tasks and to store gained knowledge. This thesis looks at how data visualization approaches can help industrial manufacturing organizations to create value from large amounts of manufacturing data, as well as how to efficiently store and share knowledge from manufacturing data analyses. The goal is to understand how Visual Analytics can improve manufacturing processes in the context of knowledge management. Five Visual Analytics systems were designed, developed, and evaluated to tackle different domain problems that emerged from manufacturing setups. Findings from each system were used to carry out additional studies to enhance established theories of knowledge management. As a result, five success stories are provided of how Visual Analytics can significantly improve manufacturing processes and how knowledge can be efficiently created, formalized, and shared in an organization with Visual Analytics.

show abstract

Visual Exploration of Anomalies in Cyclic Time Series Data with Matrix and Glyph Representations

Cited by 10 publications

References 45 publications

Anomalyzer: A Visual Interface for Multimodal Time Series Anomaly Analysis

Anomalyzer: A Visual Interface for Multimodal Time Series Anomaly Analysis

ManuKnowVis: How to Support Different User Groups in Contextualizing and Leveraging Knowledge Repositories

The Creation, Formalization, and Transfer of Expert Knowledge with Visual Analytics in Industrial Manufacturing Processes of Electrical Vehicles

Contact Info

Product

Resources

About