Add to ORKGAbstract. This paper introduces a symbolic time series representation using monotonic sub-sequences and bottom up segmentation. The representation min-imizes the square error between the segments and their monotonic approximations. The representation can robustly classify the direction of a segment and is scale in-variant with respect to the time and value dimensions. This paper describes two experiments. The first shows how accurately the monotonic functions are able to discriminate between different segments. The second tests how well the segmenta-tion technique recognizes segments and classifies them with correct symbols. Fi-nally this paper illustrates the new representation on real-world data.
In this paper, we propose an approach termed segment-based features (SBFs) to classify time series. ...
The present study proposes a new symbolization algorithm for multidimensional time series. We view t...
The time series classification literature has expanded rapidly over the last decade, with many new c...
Time series data-mining algorithms usually scale poorly with regard to dimensionality. Symbolic repr...
International audienceGiven the high data volumes in time series applications, or simply the need fo...
International audienceGiven the high data volumes in time series applications, or simply the need fo...
Many applications in different domains generate time series data at an increasing rate. The continuo...
2017 IEEE International Conference on Data Engineering, San Diego, California, USA, 19-22 April 2017...
Time series representation is one of key issues in time series data mining. Time series is simply a ...
International audienceExisting approaches for time series similarity computing are the core of many ...
Efficiently and accurately searching for similarities among time series and discovering interesting ...
Efficiently and accurately searching for similarities among time series and discovering interesting ...
This paper deals with symbolic time series representation. It builds up on the popular mapping techn...
Abstract. The analysis of time series databases is very important in the area of medicine. Most of t...
The discovery of meaningful change points, finding segments, in both categorical and real-value data...
In this paper, we propose an approach termed segment-based features (SBFs) to classify time series. ...
The present study proposes a new symbolization algorithm for multidimensional time series. We view t...
The time series classification literature has expanded rapidly over the last decade, with many new c...
Time series data-mining algorithms usually scale poorly with regard to dimensionality. Symbolic repr...
International audienceGiven the high data volumes in time series applications, or simply the need fo...
International audienceGiven the high data volumes in time series applications, or simply the need fo...
Many applications in different domains generate time series data at an increasing rate. The continuo...
2017 IEEE International Conference on Data Engineering, San Diego, California, USA, 19-22 April 2017...
Time series representation is one of key issues in time series data mining. Time series is simply a ...
International audienceExisting approaches for time series similarity computing are the core of many ...
Efficiently and accurately searching for similarities among time series and discovering interesting ...
Efficiently and accurately searching for similarities among time series and discovering interesting ...
This paper deals with symbolic time series representation. It builds up on the popular mapping techn...
Abstract. The analysis of time series databases is very important in the area of medicine. Most of t...
The discovery of meaningful change points, finding segments, in both categorical and real-value data...
In this paper, we propose an approach termed segment-based features (SBFs) to classify time series. ...
The present study proposes a new symbolization algorithm for multidimensional time series. We view t...
The time series classification literature has expanded rapidly over the last decade, with many new c...