Browsing by Author "Sousa, Maria Inês Neves de"
Now showing 1 - 1 of 1
Results Per Page
Sort Options
- Data mining for anomaly detection in maritime traffic dataPublication . Sousa, Maria Inês Neves de; Campos, Aldino Santos de; Lobo, Victor José de Almeida e Sousa; Maia, Rui Filipe PedrosoFor the past few years, oceans have become once again, an important means of communication and transport. In fact, traffic density throughout the globe has suffered a substantial growth, which has risen some concerns. With this expansion, the need to achieve a high Maritime Situational Awareness (MSA) is imperative. At the present time, this need may be more easily fulfilled thanks to the vast amount of data available regarding maritime traffic. However, this brings in another issue: data overload. Currently, there are so many data sources, so many data to obtain information from, that the operators cannot handle it. There is a pressing need for systems that help to sift through all the data, analysing and correlating, helping in this way the decision making process. In this dissertation, the main goal is to use different sources of data in order to detect anomalies and contribute to a clear Recognised Maritime Picture (RMP). In order to do so, it is necessary to know what types of data exist and which ones are available for further analysis. The data chosen for this dissertation was Automatic Identification System (AIS) and Monitorização Contínua das Atividades da Pesca (MONICAP) data, also known as Vessel Monitoring System (VMS) data. In order to store 1 year worth of AIS and MONICAP data, a PostgreSQL database was created. To analyse and draw conclusions from the data, a data mining tool was used, namely, Orange. Tests were conducted in order to assess the correlation between data sources and find anomalies. The importance of data correlation has never been so important and with this dissertation the aim is to show that there is a simple and effective way to get answers from great amounts of data.