“Mircea cel Batran” Naval Academy Scientific Bulletin, Volume XX – 2017 – Issue 1 The journal is indexed in: PROQUEST / DOAJ / Crossref / EBSCOhost / INDEX COPERNICUS / DRJI / OAJI / JOURNAL INDEX / I2OR / SCIENCE LIBRARY INDEX / Google Scholar / Academic Keys/ ROAD Open Access / Academic Resources / Scientific Indexing Services / SCIPIO / JIFACTOR IMPORTANCE OF BIG DATA IN MARITIME TRANSPORT Stefania Loredana NITA 1 Marius Iulian MIHAILESCU 2 1 Integrated Systems Department, Institute for Computers, Bucharest, Romania, stefanialoredanani@gmail.com 2 RLC, Miami, Florida, mihmariusiulian@gmail.com Abstract: As the technology grows fast, big data have become a major topic nowadays. It is interesting due to its nature, namely different types of data combined into one entity, but also because of the opportunities that it brings. Knowledge means power, so a good analysis and mining over huge amounts of data could bring many benefits and decisions could be made based on real time predictions. Maritime transport represents an important part of our lives, and it could be improved integrating big data, because all data is collected and then analyzed, and would help to avoid power failures of different components, based on prediction and different environmental data could be obtained in real time, based on analysis of past data. In this paper we will present the major trends in big data and we will analyze how it could be integrated in maritime transport. Key words: big data, maritime, analysis I. INTRODUCTION Nowadays, the size of digital data is 2.8 trillion gigabytes (GB), and 90% is collected just in the last two years. It is predicted that in 2020 the amount of data will be 40 trillion GB [1]. The sources of data could be anything: communication, transport, social media, wheatear and climate, search engines, GPS signals, online shopping, mobile devices, and many others. It is very important and useful that these data to provide powerful knowledges, which will help to make better decisions in different areas. Maritime transport is a very important aspect of our lives, beginning with defense and ending with trips. All components and sensors of a ship provide powerful data about everything regarded of that ship, which could be analyzed in order to obtain patterns and to find out how that patterns influence the ship over the time. A great opportunity is when more ships are inter- connected and data that is allowed to be provided from every ship is available for others. The data obtained from all ships on the world is so diverse and has a huge amount, becoming big data. It could be analyzed for providing predictions regarding the behavior of ship’s components, digital systems, locations of other ships, customer behavior and so on. The paper is organized in three sections, as follows: the introduction section, big data section, in which we present definitions and tools, and big data in maritime transport, in which we present opportunities and challenged and provide some relevant examples in this area. II. BIG DATA A. Definitions The term of big data is older than we expected. It was used for the first time in 90s, being spread by John Marshey, who considered big data as “storage growing bigger faster DRAM” (Dynamic Random Access Memory) [2]. Today, we refer to big data as data sets that are very large and complex, containing different types of data: structured, unstructured and semi-structured. The sources of big data could be anything, but nowadays database systems cannot handle such datasets. In 2001 in a report of META Group (now Gartner) big data have been defined as a data with three dimensions that grows very fast [3]. Figure 1. The three characteristics of Big Data [4] The three dimensions of big data could be seen in Figure 1 and they are: Volume. This characteristic refers to the large amount of data, obtained from very different and various sources, such as: machines, networks, social interactions. Velocity. It is important to have many datasets, especially for prediction, but another important aspect is the speed at which the data is analyzed. Variety. Data could have different forms, as structured, semi-structured or unstructured. However, the above characteristics represent a first description of big data. Year by year, there 485 DOI: 10.21279/1454-864X-17-I1-079 © 2017. This work is licensed under the Creative Commons Attribution-Noncommercial-Share Alike 4.0 License.