## Robust Similarity Measures for Mobile Object Trajectories (2002)

Venue: | Proc. of DEXA Workshops |

Citations: | 22 - 1 self |

### BibTeX

@INPROCEEDINGS{Vlachos02robustsimilarity,

author = {Michail Vlachos and Dimitrios Gunopulos and George Kollios},

title = {Robust Similarity Measures for Mobile Object Trajectories},

booktitle = {Proc. of DEXA Workshops},

year = {2002},

pages = {721--728},

publisher = {IEEE Computer Society}

}

### Years of Citing Articles

### OpenURL

### Abstract

We investigate techniques for similarity analysis of spatio-temporal trajectories for mobile objects. Such kind of data may contain a great amount of outliers, which degrades the performance of Euclidean and Time Warping Distance. Therefore, here we propose the use of non-metric distance functions based on the Longest Common Subsequence (LCSS), in conjunction with a sigmoidal matching function. Finally, we compare these new methods to various L p Norms and also to Time Warping distance (for real and synthetic data) and we present experimental results that validate the accuracy and efficiency of our approach, especially under the strong presence of noise.

### Citations

430 | Dynamic programming algorithm optimization for spoken word recognition
- Sakoe, Chiba
- 1978
(Show Context)
Citation Context ...ries data for similarity queries assuming the Euclidean model include [17, 16]. Another approach is based on the time warping technique that first has been used to match signals in speech recognition =-=[26]-=-. Berndt and Clifford [6] proposed to use this technique to measure the similarity of time-series data in data mining. The idea is to allow stretching in time in order to get a better distance. Recent... |

426 | Fast subsequence matching in time-series databases
- Faloutsos, Ranganathan, et al.
- 1994
(Show Context)
Citation Context ...s of similarity of objects is presented in [15]. In another work, Lee et al. [20] propose methods to index sequences of multidimensional points. They extend the ideas presented by Faloutsos et al. in =-=[12]-=- and the similarity model is based on the Euclidean distance. Recently, there has been some work on indexing moving objects to answer spatial proximity queries (range and nearest neighbor queries) [19... |

417 | Similarity search in high dimensions via hashing
- Gionis, Indyk, et al.
- 1999
(Show Context)
Citation Context ...For p = 2 it is the well known Euclidean distance and for p = 1 the Manhattan distance. The advantage of this simple model is that it allows efficient indexing by a dimensionality reduction technique =-=[3, 29, 13]-=-. On the other hand, the model cannot deal well with outliers and is very sensitive to small distortions in the time axis. There are a number of interesting extensions to the above model to support va... |

415 | Efficient similarity search in sequence databases
- Agrawal, Faloutsos, et al.
- 1993
(Show Context)
Citation Context ...For p = 2 it is the well known Euclidean distance and for p = 1 the Manhattan distance. The advantage of this simple model is that it allows efficient indexing by a dimensionality reduction technique =-=[3, 29, 13]-=-. On the other hand, the model cannot deal well with outliers and is very sensitive to small distortions in the time axis. There are a number of interesting extensions to the above model to support va... |

319 | Indexing the positions of continuously moving objects
- Saltenis, Jensen, et al.
(Show Context)
Citation Context ...12] and the similarity model is based on the Euclidean distance. Recently, there has been some work on indexing moving objects to answer spatial proximity queries (range and nearest neighbor queries) =-=[19, 1, 27]-=-. Also in [23], Pfoser et al. present index methods to answer topological and navigational queries in a database that stores trajectories of moving objects. These works do not consider a global simila... |

232 | Locally Adaptive Dimensionality Reduction for Indexing Large Time Series Databases
- Keogh, Chakrabarti, et al.
(Show Context)
Citation Context ...ions such as scaling [9, 25], shifting [9, 14], normalization [14] and moving average [25]. Other recent works on indexing time series data for similarity queries assuming the Euclidean model include =-=[17, 16]-=-. Another approach is based on the time warping technique that first has been used to match signals in speech recognition [26]. Berndt and Clifford [6] proposed to use this technique to measure the si... |

202 | On Indexing Mobile Objects
- Kollios, Gunopulos, et al.
- 1999
(Show Context)
Citation Context ...12] and the similarity model is based on the Euclidean distance. Recently, there has been some work on indexing moving objects to answer spatial proximity queries (range and nearest neighbor queries) =-=[19, 1, 27]-=-. Also in [23], Pfoser et al. present index methods to answer topological and navigational queries in a database that stores trajectories of moving objects. These works do not consider a global simila... |

198 | Fast similarity search in the presence of noise, scaling, and translation in timeseries databases
- Agrawal, Lin, et al.
- 1995
(Show Context)
Citation Context ...ed to make this measure more scalable [18, 21]. A similar technique is to find the longest common subsequences(LCSS) of two sequences and then define the distance using the length of this subsequence =-=[4, 7, 10, 8]-=-. The LCSS shows how well the two sequences can match one another if we are allowed to stretch them but we cannot rearrange the sequence of values. Other techniques to define time series similarity ar... |

172 | Discovering similar multidimensional trajectories
- Vlachos, Kollios, et al.
- 2003
(Show Context)
Citation Context ...ions Outliers Different trajectory lengths In previous work we have extended the LCSS model, in order to perform matching of 2D trajectories within a region ofsin time and a region of in space ([28=-=-=-]). So, whenever the points of two trajectories matched within we increased the similarity by one. This however penalized the points that were marginally outside the matching region (assigning to the... |

169 | Indexing Moving Points
- Agarwal, Arge, et al.
- 2000
(Show Context)
Citation Context ...12] and the similarity model is based on the Euclidean distance. Recently, there has been some work on indexing moving objects to answer spatial proximity queries (range and nearest neighbor queries) =-=[19, 1, 27]-=-. Also in [23], Pfoser et al. present index methods to answer topological and navigational queries in a database that stores trajectories of moving objects. These works do not consider a global simila... |

168 |
Using dynamic time warping to find patterns in time series
- Berndt, Clifford
- 1994
(Show Context)
Citation Context ...ueries assuming the Euclidean model include [17, 16]. Another approach is based on the time warping technique that first has been used to match signals in speech recognition [26]. Berndt and Clifford =-=[6]-=- proposed to use this technique to measure the similarity of time-series data in data mining. The idea is to allow stretching in time in order to get a better distance. Recently, there has been approa... |

151 | On the surprising behavior of distance metrics in high dimensional spaces
- Aggarwal, Hinneburg, et al.
- 1973
(Show Context)
Citation Context ...rping using as the base distance different L p Norms, too. We use lower than L 1 Norms, since for them the extreme values do not dominate to the total distance, therefore are more robust to outliers (=-=[2-=-]). We conducted clustering experiments, using datasets obtained through video tracking, that consisted of various clusters of trajectories in 2D. The datasets are: MobileLong. This is a real dataset... |

148 |
Fast Time Sequence Indexing for Arbitrary Lp Norms
- Yi, Faloutsos
(Show Context)
Citation Context ...For p = 2 it is the well known Euclidean distance and for p = 1 the Manhattan distance. The advantage of this simple model is that it allows efficient indexing by a dimensionality reduction technique =-=[3, 29, 13]-=-. On the other hand, the model cannot deal well with outliers and is very sensitive to small distortions in the time axis. There are a number of interesting extensions to the above model to support va... |

114 |
Novel Approaches in Query Processing for Moving Object Trajectories
- Pfoser, Jensen, et al.
- 2000
(Show Context)
Citation Context ...y model is based on the Euclidean distance. Recently, there has been some work on indexing moving objects to answer spatial proximity queries (range and nearest neighbor queries) [19, 1, 27]. Also in =-=[23]-=-, Pfoser et al. present index methods to answer topological and navigational queries in a database that stores trajectories of moving objects. These works do not consider a global similarity model bet... |

87 | Finding Similar Time Series
- Das, Gunopulos, et al.
- 1997
(Show Context)
Citation Context ...ed to make this measure more scalable [18, 21]. A similar technique is to find the longest common subsequences(LCSS) of two sequences and then define the distance using the length of this subsequence =-=[4, 7, 10, 8]-=-. The LCSS shows how well the two sequences can match one another if we are allowed to stretch them but we cannot rearrange the sequence of values. Other techniques to define time series similarity ar... |

80 | Mobile Computing and Databases - A Survey
- Barbara
- 1999
(Show Context)
Citation Context ...ces in mobile computing, sensor and GPS technology have made it possible to collect large amounts of spatiotemporal data and there is increasing interest to perform data analysis tasks over this data =-=[5]-=-. For example, in mobile computing, users equipped with mobile devices move in space and register their location at different time instances to spatiotemporal databases via wireless links. In environm... |

73 | Landmarks: A New Model for Similarity-based Pattern Querying
- Perng, Wang, et al.
- 2000
(Show Context)
Citation Context ...tch one another if we are allowed to stretch them but we cannot rearrange the sequence of values. Other techniques to define time series similarity are based on extracting certain features (Landmarks =-=[22]-=- or signatures [11]) from each time-series and then use these features to define the similarity. An interesting approach to represent a time series using the direction of the sequence at regular time ... |

67 | Similarity-Based Queries
- Jagadish, Mendelzon, et al.
(Show Context)
Citation Context ...a time series using the direction of the sequence at regular time intervals is presented in [24]. A domain independent framework for defining queries in terms of similarity of objects is presented in =-=[15]-=-. In another work, Lee et al. [20] propose methods to index sequences of multidimensional points. They extend the ideas presented by Faloutsos et al. in [12] and the similarity model is based on the E... |

51 | Scaling up dynamic time warping for datamining applications
- Keogh, Pazzani
- 2000
(Show Context)
Citation Context ...re the similarity of time-series data in data mining. The idea is to allow stretching in time in order to get a better distance. Recently, there has been approached to make this measure more scalable =-=[18, 21]-=-. A similar technique is to find the longest common subsequences(LCSS) of two sequences and then define the distance using the length of this subsequence [4, 7, 10, 8]. The LCSS shows how well the two... |

49 | Variable length queries for time series data
- Kahveci, Singh
(Show Context)
Citation Context ...ions such as scaling [9, 25], shifting [9, 14], normalization [14] and moving average [25]. Other recent works on indexing time series data for similarity queries assuming the Euclidean model include =-=[17, 16]-=-. Another approach is based on the time warping technique that first has been used to match signals in speech recognition [26]. Berndt and Clifford [6] proposed to use this technique to measure the si... |

49 | Similarity search for multidimensional data sequences
- Chung, Lee, et al.
- 2000
(Show Context)
Citation Context ...of the sequence at regular time intervals is presented in [24]. A domain independent framework for defining queries in terms of similarity of objects is presented in [15]. In another work, Lee et al. =-=[20]-=- propose methods to index sequences of multidimensional points. They extend the ideas presented by Faloutsos et al. in [12] and the similarity model is based on the Euclidean distance. Recently, there... |

43 |
Fast time-series searching with scaling and shifting
- Chu, Wong
- 1999
(Show Context)
Citation Context ...deal well with outliers and is very sensitive to small distortions in the time axis. There are a number of interesting extensions to the above model to support various transformations such as scaling =-=[9, 25]-=-, shifting [9, 14], normalization [14] and moving average [25]. Other recent works on indexing time series data for similarity queries assuming the Euclidean model include [17, 16]. Another approach i... |

39 | Efficient Searches for Similar Subsequences of Different Lengths in Sequence Databases
- Park, Chu, et al.
- 2000
(Show Context)
Citation Context ...re the similarity of time-series data in data mining. The idea is to allow stretching in time in order to get a better distance. Recently, there has been approached to make this measure more scalable =-=[18, 21]-=-. A similar technique is to find the longest common subsequences(LCSS) of two sequences and then define the distance using the length of this subsequence [4, 7, 10, 8]. The LCSS shows how well the two... |

38 | Matching and Indexing Sequences of Different Lengths
- Bozkaya, Yazdani, et al.
- 1997
(Show Context)
Citation Context ...ed to make this measure more scalable [18, 21]. A similar technique is to find the longest common subsequences(LCSS) of two sequences and then define the distance using the length of this subsequence =-=[4, 7, 10, 8]-=-. The LCSS shows how well the two sequences can match one another if we are allowed to stretch them but we cannot rearrange the sequence of values. Other techniques to define time series similarity ar... |

36 | Supporting fast search in time series for movement patterns in multiples scales
- Qu, Wang, et al.
- 1998
(Show Context)
Citation Context ...each time-series and then use these features to define the similarity. An interesting approach to represent a time series using the direction of the sequence at regular time intervals is presented in =-=[24]-=-. A domain independent framework for defining queries in terms of similarity of objects is presented in [15]. In another work, Lee et al. [20] propose methods to index sequences of multidimensional po... |

33 | Time-Series Similarity Problems and Well-Separated Geometric Sets
- Bollobas, Das, et al.
(Show Context)
Citation Context |

29 | A signature technique for similarity-based queries
- Faloutsos, Jagadish, et al.
- 1997
(Show Context)
Citation Context ...we are allowed to stretch them but we cannot rearrange the sequence of values. Other techniques to define time series similarity are based on extracting certain features (Landmarks [22] or signatures =-=[11]-=-) from each time-series and then use these features to define the similarity. An interesting approach to represent a time series using the direction of the sequence at regular time intervals is presen... |

18 | Querying Time Series Data Based on Similarity
- Rafiei
(Show Context)
Citation Context ...deal well with outliers and is very sensitive to small distortions in the time axis. There are a number of interesting extensions to the above model to support various transformations such as scaling =-=[9, 25]-=-, shifting [9, 14], normalization [14] and moving average [25]. Other recent works on indexing time series data for similarity queries assuming the Euclidean model include [17, 16]. Another approach i... |

10 |
On Similarity Queries for Time-Series Data
- Goldin, Kanellakis
- 1995
(Show Context)
Citation Context ...liers and is very sensitive to small distortions in the time axis. There are a number of interesting extensions to the above model to support various transformations such as scaling [9, 25], shifting =-=[9, 14]-=-, normalization [14] and moving average [25]. Other recent works on indexing time series data for similarity queries assuming the Euclidean model include [17, 16]. Another approach is based on the tim... |