PSEUDo: Interactive Pattern Search in Multivariate Time Series with Locality-Sensitive Hashing and Relevance Feedback

Simple item page
dc.contributor.authorYu, Yuncongen_US
dc.contributor.authorKruyff, Dylanen_US
dc.contributor.authorJiao, Jiaoen_US
dc.contributor.authorBecker, Timen_US
dc.contributor.authorBehrisch, Michaelen_US
dc.contributor.editorKrone, Michaelen_US
dc.contributor.editorLenti, Simoneen_US
dc.contributor.editorSchmidt, Johannaen_US
dc.date.accessioned2022-06-02T15:29:13Z
dc.date.available2022-06-02T15:29:13Z
dc.date.issued2022
dc.description.abstractWe present PSEUDo, a visual pattern retrieval tool for multivariate time series. It aims to overcome the uneconomic (re- )training with deep learning-based methods. Very high-dimensional time series emerge on an unprecedented scale due to increasing sensor usage and data storage. Visual pattern search is one of the most frequent tasks on such data. Automatic pattern retrieval methods often suffer from inefficient training, a lack of ground truth, and a discrepancy between the similarity perceived by the algorithm and the user. Our proposal is based on a query-aware locality-sensitive hashing technique to create a representation of multivariate time series windows. It features sub-linear training and inference time with respect to data dimensions. This performance gain allows an instantaneous relevance-feedback-driven adaption and converges to users' similarity notion. We are benchmarking PSEUDo in accuracy and speed with representative and state-of-the-art methods, evaluating its steerability through simulated user behavior, and designing expert studies to test PSEUDo's usability.en_US
dc.description.sectionheadersPosters
dc.description.seriesinformationEuroVis 2022 - Posters
dc.identifier.doi10.2312/evp.20221127
dc.identifier.isbn978-3-03868-185-4
dc.identifier.pages87-89
dc.identifier.pages3 pages
dc.identifier.urihttps://doi.org/10.2312/evp.20221127
dc.identifier.urihttps://diglib.eg.org:443/handle/10.2312/evp20221127
dc.publisherThe Eurographics Associationen_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectCCS Concepts: Mathematics of computing --> Time series analysis; Information systems --> Users and interactive retrieval
dc.subjectMathematics of computing
dc.subjectTime series analysis
dc.subjectInformation systems
dc.subjectUsers and interactive retrieval
dc.titlePSEUDo: Interactive Pattern Search in Multivariate Time Series with Locality-Sensitive Hashing and Relevance Feedbacken_US
Files
Original bundle
Now showing 1 - 5 of 5
Thumbnail Image
Name:
087-089.pdf
Size:
684.78 KB
Format:
Adobe Portable Document Format
Download
Thumbnail Image
Name:
9627-file1.pdf
Size:
1.12 MB
Format:
Adobe Portable Document Format
Download
Thumbnail Image
Name:
9627-file2.jpg
Size:
236.12 KB
Format:
Joint Photographic Experts Group/JPEG File Interchange Format (JFIF)
Download
Thumbnail Image
Name:
9627-file3.pdf
Size:
1018.5 KB
Format:
Adobe Portable Document Format
Download
No Thumbnail Available
Name:
9627-file4.mp4
Size:
7.46 MB
Format:
Unknown data format
Download
Collections
EuroVisPosters2022