Similarity Search in Multimedia Time Series Data Using Amplitude-Level Features

Aßfalg, Johannes; Kriegel, Hans‐Peter; Kröger, Peer; Kunath, Peter; Pryakhin, Alexey; Renz, Matthias

doi:10.1007/978-3-540-77409-9_12

Cited by 6 publications

(6 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the presented methodology can be applied for similarity analysis and clustering of other types of time series (since MP profiles can be seen as a specific type of time series). A similar method has been proposed for addressing threshold queries as well as similarity analysis in time series databases by Aßfalg et al (2008). However, their method only considers the deviation (amplitude) of the time series.…”

Section: Discussionmentioning

confidence: 99%

Movement similarity assessment using symbolic representation of trajectories

Dodge

Laube

Weibel

2012

International Journal of Geographical Information Science

111

107

View full text Add to dashboard Cite

This paper describes a novel approach for finding similar trajectories, using trajectory segmentation based on movement parameters such as speed, acceleration, or direction. First, a segmentation technique is applied to decompose trajectories into a set of segments with homogeneous characteristics with respect to a particular movement parameter. Each segment is assigned to a movement parameter class, representing the behavior of the movement parameter. Accordingly, the segmentation procedure transforms a trajectory to a sequence of class labels, that is, a symbolic representation. A modified version of edit distance, called Normalized Weighted Edit Distance (NWED) is introduced as a similarity measure between different sequences. As an application, we demonstrate how the method can be employed to cluster trajectories. The performance of the approach is assessed in two case studies using real movement datasets from two different application domains, namely, North Atlantic Hurricane trajectories and GPS tracks of couriers in London. Three different experiments have been conducted that respond to different facets of the proposed techniques, and that compare our NWED measure to a related method. This paper describes a novel approach for finding similar trajectories, using trajectory segmentation based on movement parameters such as speed, acceleration, or direction. First, a segmentation technique is applied to decompose trajectories into a set of segments with homogeneous characteristics with respect to a particular movement parameter. Each segment is assigned to a movement parameter class, representing the behavior of the movement parameter. Accordingly, the segmentation procedure transforms a trajectory to a sequence of class labels, that is, a symbolic representation. A modified version of edit distance, called Normalized Weighted Edit Distance (NWED) is introduced as a similarity measure between di erent sequences. As an application, we demonstrate how the method can be employed to cluster trajectories. The performance of the approach is assessed in two case studies using real movement datasets from two di erent application domains, namely, North Atlantic Hurricane trajectories and GPS tracks of couriers in London. Three di erent experiments have been conducted that respond to di erent facets of the proposed techniques, and that compare our NWED measure to a related method.

show abstract

Section: Discussionmentioning

confidence: 99%

Movement similarity assessment using symbolic representation of trajectories

Dodge

Laube

Weibel

2012

International Journal of Geographical Information Science

111

107

View full text Add to dashboard Cite

show abstract

“…"However, the computational load of DTW is so expensive that it is intractable for many real-world problems" [23]. "DTW (is) very expensive, and are not applicable for multi-media data" [8]. "computing cost of DTW algorithm is high" [67],"DTW-based techniques suffer for performance inefficiencies" [48].…”

Section: Dtw Is Too Slow To Be Of Practical Usementioning

confidence: 99%

Experimental comparison of representation methods and distance measures for time series data

Wang

Mueen

Ding

et al. 2012

Data Min Knowl Disc

689

463

View full text Add to dashboard Cite

The previous decade has brought a remarkable increase of the interest in applications that deal with querying and mining of time series data. Many of the research efforts in this context have focused on introducing new representation methods for dimensionality reduction or novel similarity measures for the underlying data. In the vast majority of cases, each individual work introducing a particular method has made specific claims and, aside from the occasional theoretical justifications, provided quantitative experimental observations. However, for the most part, the comparative aspects of these experiments were too narrowly focused on demonstrating the benefits of the proposed methods over some of the previously introduced ones. In order to provide a comprehensive validation, we conducted an extensive experimental study re-

show abstract

“…An extension of PAA including a multi-resolution property (MPAA) has been proposed in [Lin and Keogh 2005]. [Aßfalg et al 2008] suggested to extract a sequence of amplitude-levelwise local features (ALF) to represent the characteristics of local structures. It was shown that this proposal provided weak results in [Ding et al 2008].…”

Section: Representationmentioning

confidence: 99%

“…In [Flanagan 2003] weighted histograms of consecutive symbols are used as features. The similarity search based on Threshold Queries (TQuEST) [Aßfalg et al 2006] use a given threshold parameter τ in order to transform a time series into a sequence of threshold-crossing time intervals. It has however been shown to be highly specialized with mitigated results on classical datasets [Ding et al 2008].…”

Section: Similarity Measurementioning

confidence: 99%

Time-series data mining

2012

View full text Add to dashboard Cite

In almost every scientific field, measurements are performed over time. These observations lead to a collection of organized data called time series. The purpose of time series data mining is to try to extract all meaningful knowledge from the shape of data. Even if humans have a natural capacity to perform these tasks, it remains a complex problem for computers. In this paper we intend to provide a survey of the techniques applied for time series data mining. The first part is devoted to an overview of the tasks that have captured most of the interest of researchers. Considering that in most cases, time series task relies on the same components for implementation, we divide the literature depending on these common aspects, namely representation techniques, distance measures and indexing methods. The study of the relevant literature has been categorized for each individual aspects. Four types of robustness could then be formalized and any kind of distance could then be classified. Finally, the study submit various research trends and avenues that can be explored in the near future. We hope that this paper can provide a broad and deep understanding of the time series data mining research field.

show abstract

Similarity Search in Multimedia Time Series Data Using Amplitude-Level Features

Cited by 6 publications

References 11 publications

Movement similarity assessment using symbolic representation of trajectories

Movement similarity assessment using symbolic representation of trajectories

Experimental comparison of representation methods and distance measures for time series data

Time-series data mining

Contact Info

Product

Resources

About