Proposal of time series data retrieval with user feedback

This paper introduces the concept of relevance feedback for retrieving time series data. Data in medical field handles various kinds of time series data, such as EHR (electronic health record) and consumer health data. Analyzing and accessing such time series data gets to be crucial for doctors to improve the quality of medical treatment. When we are going to develop an interactive interface for supporting a doctor to retrieve time series data of patients, it is supposed that similarity judgment on time series data depends on the knowledge and purpose of a doctor. Therefore, we employs relevance feedback-based retrieval system, which modifies similarity calculation based on the feedback information given by a doctor. In order to obtain enough feedback information from a doctor, we are going to employing two kinds of feedback mechanism: relevance feedback and graphical annotation-based feedback. This paper describes the concept of our relevance feedback-based retrieval system and the feedback mechanisms.

[1]  Eamonn J. Keogh,et al.  Scaling up dynamic time warping for datamining applications , 2000, KDD '00.

[2]  A. Tversky.  Features of Similarity , 1977 .

[3]  Jean-Michel Jolion,et al.  Feature Similarity , 2001, Principles of Visual Information Retrieval.

[4]  Gerard Salton,et al.  The SMART Retrieval System—Experiments in Automatic Document Processing , 1971 .

[5]  Yukio Ohsawa,et al.  KeyGraph: automatic indexing by co-occurrence graph based on building construction metaphor , 1998, Proceedings IEEE International Forum on Research and Technology Advances in Digital Libraries -ADL'98-.

[6]  Rudolf Kruse,et al.  Relevance Feedback for Association Rules by Leveraging Concepts from Information Retrieval , 2007, SGAI Conf..

[7]  Hakan Ferhatosmanoglu,et al.  Diversity based Relevance Feedback for Time Series Search , 2013, Proc. VLDB Endow..

[8]  Yasufumi Takama,et al.  Interactive Context Search System for Exchange Rate Data Using Granularity-Dependent Similarity Calculation of Temporal Data , 2013, 2013 International Conference on Biometrics and Kansei Engineering.

[9]  J. J. Rocchio,et al.  Relevance feedback in information retrieval , 1971 .

[10]  Martin Wattenberg,et al.  Voyagers and voyeurs: supporting asynchronous collaborative information visualization , 2007, CHI.

[11]  Peter McBurney,et al.  Chance Discovery , 2003, Advanced Information Processing.

[12]  Donald J. Berndt,et al.  Using Dynamic Time Warping to Find Patterns in Time Series , 1994, KDD Workshop.

[13]  Mitsunori Matsushita,et al.  Overview of MuST at the NTCIR-7 Workshop - Challenges to Multi-modal Summarization for Trend Information , 2008, NTCIR.

[14]  Eamonn J. Keogh,et al.  An Enhanced Representation of Time Series Which Allows Fast and Accurate Classification, Clustering and Relevance Feedback , 1998, KDD.

[15]  Yasufumi Takama,et al.  VISUAL ANALYSIS OF DISCUSSION FLOW ON KEYGRAPH-BASED BBS , 2010 .

[16]  Nitin Kumar,et al.  Time-series Bitmaps: a Practical Visualization Tool for Working with Large Time Series Databases , 2005, SDM.

[17]  Eamonn J. Keogh,et al.  A symbolic representation of time series, with implications for streaming algorithms , 2003, DMKD '03.

[18]  Eamonn J. Keogh,et al.  Relevance feedback retrieval of time series data , 1999, SIGIR '99.