On the semantics of similarity in deep trajectory representations: Unterschied zwischen den Versionen

Aus SDQ-Institutsseminar
Keine Bearbeitungszusammenfassung
Keine Bearbeitungszusammenfassung
Zeile 2: Zeile 2:
|vortragender=Zdravko Marinov
|vortragender=Zdravko Marinov
|email=ufijd@student.kit.edu
|email=ufijd@student.kit.edu
|vortragstyp=Proposal
|vortragstyp=Bachelorarbeit
|betreuer=Saeed Taghizadeh
|betreuer=Saeed Taghizadeh
|termin=Institutsseminar/2019-05-31
|termin=Institutsseminar/2019-10-11
|kurzfassung=There are many approaches to compute the similarity between two trajectories. In 2018 a novel approach using deep learning had been introduced, which has several advantages against the classical models like Dynamic time warping, Edit distance with real penalty etc. In this thesis, the influence of the parameters of the deep learning approach on the similarity values are investigated. The similarity values are further compared between the novel and the classical models, and in the end the quality of the similarity computation is evaluated via trajectory clustering techniques​ and finding popular routes in cities.
|kurzfassung=With the rapid increase of the number of GPS-enabled devices the amount of accumulated trajectory data is ever increasing. An important task in analyzing trajectory data is investigating which trajectories are similar to each other. Traditional models for trajectory similarity computation are based on dynamic programming. However, they suffer from scalability issues as well as susceptibility to noisy data.  
 
A novel deep learning model for trajectory similarity computation (t2vec) emerged in 2018 and solved these two issues. However, we have no intuitive understanding what the similarity values obtained by t2vec are based on. In order to understand which applications are best suitable for t2vec, we need to analyze the similarity semantics which are captured by the deep learning model.  
 
In this thesis we investigate how the parameters of the deep learning model influence the probability distributions of the similarity values. We already have an intuitive understanding of the traditional dynamic programming models. Therefore, we transfer this intuition onto t2vec by systematically comparing it to the traditional models. In the end we recommend suitable applications for t2vec, based on the results that we have gathered from our experiments.
}}
}}

Version vom 16. September 2019, 13:14 Uhr

Vortragende(r) Zdravko Marinov
Vortragstyp Bachelorarbeit
Betreuer(in) Saeed Taghizadeh
Termin Fr 11. Oktober 2019
Vortragsmodus
Kurzfassung With the rapid increase of the number of GPS-enabled devices the amount of accumulated trajectory data is ever increasing. An important task in analyzing trajectory data is investigating which trajectories are similar to each other. Traditional models for trajectory similarity computation are based on dynamic programming. However, they suffer from scalability issues as well as susceptibility to noisy data.

A novel deep learning model for trajectory similarity computation (t2vec) emerged in 2018 and solved these two issues. However, we have no intuitive understanding what the similarity values obtained by t2vec are based on. In order to understand which applications are best suitable for t2vec, we need to analyze the similarity semantics which are captured by the deep learning model.

In this thesis we investigate how the parameters of the deep learning model influence the probability distributions of the similarity values. We already have an intuitive understanding of the traditional dynamic programming models. Therefore, we transfer this intuition onto t2vec by systematically comparing it to the traditional models. In the end we recommend suitable applications for t2vec, based on the results that we have gathered from our experiments.