Ανακάλυψη επαναληπτικών προτύπων σε δεδομένα κίνησης ψαράδικων
Periodic pattern discovery in fishery vessels
View/
Abstract
In our modern era where massive amounts of information are available, many studies have been made to utilize these data. One way to make use of the available data and come to useful conclusions is by locating some patterns in them. Τo give a quick explanation on this term we could say that a pattern is a recurring module. Patterns can be found in a wide range of different types of data, for example we can find patterns in animal’s behavior, in consumer’s behavior, in meteorology and in many other fields. This thesis is about finding patterns in fishing vessels. The purpose of this study is at first to find periodic patterns in the fishing vessels and then ascertain whether we could or not make some use from those patterns. The data which was used for this study are AIS and VMS type, which refer to two different types of recording the vessel’s location.
In this thesis we can find two different types of data. The first type of data are serial sequences, namely it is two-dimensional data where the information of each recording we have is about its latitude and longitude. The second type of data is space-time sequences, namely it is three-dimensional data where except the latitude and longitude we have as extra info the time of each recording. Along with serial and the space-time sequences it is described some algorithms which can be used to find periodic patterns, according to the type of the data.
In the final chapter an analysis has been made based on the Periodica algorithm to find some periodic patterns in the fishing vessels. The first step was the data cleaning, where only the data which could be used for analysis has been kept. This step was made one time for the AIS data and one time for VMS. Then the data were converted, so each fishing vessel would be consisted of data with a stable time frame. In the end some conclusions collectively for AIS and VMS data has been made.
For the data cleaning was used the R programming language. For the data conversion and Periodica algorithm was used the matlab programming language.
Postgraduate Studies Programme
Εφαρμοσμένη ΣτατιστικήDepartment
Σχολή Χρηματοοικονομικής και Στατιστικής. Τμήμα Στατιστικής και Ασφαλιστικής ΕπιστήμηςNumber of pages
68Language
GreekCollections
Except where otherwise noted, this item's license is described as
Αναφορά Δημιουργού-Μη Εμπορική Χρήση-Όχι Παράγωγα Έργα 3.0 Ελλάδα
Αναφορά Δημιουργού-Μη Εμπορική Χρήση-Όχι Παράγωγα Έργα 3.0 Ελλάδα