Identifying, exploring, and interpreting time series shapes in multivariate time intervals

Shirato, Gota; Andrienko, Gennady; Andrienko, Gennady

doi:10.1016/j.visinf.2023.01.001

Cited by 7 publications

(11 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Apart from the SAX method [LKWL07] that we used in our studies, a variety of possibilities exist. One of them is to detect predefined shapes [HÖ2, SAA23] and represent them visually as shapes and symbolically by words ‘increase’, ‘decrease’, ‘peak’, etc. Another possibility is to transform the original values to changes with respect to the previous or initial value apply the SAX method to the transformed data [SAA21].…”

Section: Discussionmentioning

confidence: 99%

“…One of them is to detect predefined shapes [HÖ2, SAA23] and represent them visually as shapes and symbolically by words ‘increase’, ‘decrease’, ‘peak’, etc. Another possibility is to transform the original values to changes with respect to the previous or initial value apply the SAX method to the transformed data [SAA21]. Domain‐specific rules [CC99, AMM*08] or a domain ontology [Sha97] can be employed to assign human‐understandable labels to time series, and these labels can represent the patterns in the following analysis.…”

Section: Discussionmentioning

confidence: 99%

“…Complex patterns can be detected automatically according to predefined rules specifying patterns to be used as building blocks and temporal relationships between these blocks [SLCB07]. Shirato et al [SAA23] propose interactive visual interfaces to identify patterns in the temporal distribution and cooccurrences of patterns of different attributes and transitions between patterns of the same attributes. In that work, higher-level patterns are constructed in the mind of the analyst.…”

Section: Abstraction Of Temporal Datamentioning

confidence: 99%

“…Domain experts may suggest other aggregation methods such as opening and closing prices, minimum and maximum prices for the day, or the difference/ratio between opening and closing prices or between maximum and minimum values. Some of these aggregates were used by Shirato et al [SAA21] to represent trends over parts of time series data.…”

Section: Sax Encodingmentioning

confidence: 99%

“…Thus, there are methods for detecting predefined shapes, such as increase, decrease, constancy, peak, etc. [HÖ2, SAA23]. Abstraction can be done using domain‐specific rules [CC99, AMM*08] or definitions from a domain ontology [Sha97].…”

Section: Related Workmentioning

confidence: 99%

See 4 more Smart Citations

Episodes and Topics in Multivariate Temporal Data

Andrienko,

Shirato

2023

Computer Graphics Forum

Self Cite

View full text Add to dashboard Cite

The term ‘episode’ refers to a time interval in the development of a dynamic process or behaviour of an entity. Episode‐based data consist of a set of episodes that are described using time series of multiple attribute values. Our research problem involves analysing episode‐based data in order to understand the distribution of multi‐attribute dynamic characteristics across a set of episodes. To solve this problem, we applied an existing theoretical model and developed a general approach that involves incrementally increasing data abstraction. We instantiated this general approach in an analysis procedure in which the value variation of each attribute within an episode is represented by a combination of symbols treated as a ‘word’. The variation of multiple attributes is thus represented by a combination of ‘words’ treated as a ‘text’. In this way, the the set of episodes is transformed to a collection of text documents. Topic modelling techniques applied to this collection find groups of related (i.e. repeatedly co‐occurring) ‘words’, which are called ‘topics’. Given that the ‘words’ encode variation patterns of individual attributes, the ‘topics’ represent patterns of joint variation of multiple attributes. In the following steps, analysts interpret the topics and examine their distribution across all episodes using interactive visualizations. We test the effectiveness of the procedure by applying it to two types of episode‐based data with distinct properties and introduce a range of generic and data type‐specific visualization techniques that can support the interpretation and exploration of topic distribution.

show abstract