56 M. Mirović et al: Big Data in the... Big Data in the Maritime Industry Veliki skupovi podataka u pomorskoj industriji DOI 10.17818/NM/2018/1.8 UDK 656.61 Review / Pregledni rad Paper accepted / Rukopis primljen: 5. 7. 2017. Maris Mirović Student, Department of Electrical Engineering and Computing University of Dubrovnik e-mail: marism580@gmail.com Mario Miličević Department of Electrical Engineering and Computing University of Dubrovnik e-mail: mario.milicevic@unidu.hr Ines Obradović Department of Electrical Engineering and Computing University of Dubrovnik e-mail: ines.obradovic@unidu.hr Summary Maritime industry is a complex system that requires a quick adaptation to changing conditions and in which decision-making needs to take into account a large number of parameters. As navigation systems become more advanced, there is a signifcant amount of ship performance and navigation data generated. Big Data analytics tools make it possible to analyze these large quantities of data in order to gain the insight that supports decision-making. This paper gives an overview of the applications of Big Data in maritime industry, specifcally in logistics optimization, safety and energy efciency improvement, as well as the challenges that systems involving Big Data face. Sažetak Pomorska industrija je složeni sustav koji zahtijeva brzu prilagodbu u promjenjivim uvjetima u kojima je potrebno uzeti u obzir velik broj parametara prilikom donošenja odluka. Napretkom navigacijskih sustava, generira se znatna količina podataka o performansama broda i navigaciji. Analitički alati za velike skupove podataka omogućuju analizu tih podataka kako bi se dobilo razumijevanje potrebno za podršku donošenju odlukâ. Ovaj članak daje pregled primjene velikih skupova podataka u pomorstvu, posebno u optimizaciji logistike, sigurnosti i poboljšanju energetske učinkovitosti, kao i izazove s kojima se suočavaju sustavi koji koriste velike skupove podataka. KEY WORDS maritime industry big data logistic optimization energy efciency safety KLJUČNE RIJEČI pomorstvo veliki skupovi podataka optimizacija logistike energetska učinkovitost sigurnost 1. INTRODUCTION / Uvod Seaborne trade accounts for over 90 percent of world trade in terms of volume [13]. Due to the size of the network that maritime logistics companies operate, they face large scale planning problems at the strategic, tactical and operational level [5]. Making decisions regarding maritime logistics to ensure safety, minimize cost and improve productivity means taking into account a large number of parameters susceptible to change. This is further complicated by the limitations of ship- to-shore communication, which is why the maritime industry is traditionally not information intensive. However, with the development of navigation systems, sensors and tracking systems following recent advances in technology, the maritime industry is opening up to the benefts of the digital era. The growing amount of available data concerning ship performance and navigation brings a wide range of possibilities, from real-time monitoring of vessels to extracting knowledge through data analysis. The volume and variety of maritime data make this a Big Data problem. The following sections explain the term Big Data and present the way Big Data can be used in logistics and transportation in general and the maritime industry in particular. 2. THE DEFINITION OF BIG DATA / Defnicija pojma velikih skupova podataka With the development of technology, the volume of data generated by countless systems, sensors and devices is growing rapidly. It is estimated that by 2020 the amount of digital data in the world will reach 40 trillion gigabytes [12]. The term Big Data was initially used to describe data sets so large and complex that traditional software is unable to process them [26]. Today, it is a concept that goes beyond the issue of dealing with large quantities of data. Now that Big Data analytics solutions are available, the focus has moved to the value that can be extracted. The term Big Data nowadays refers not only to the data themselves, but also to advancing trends in technology that aim to take advantage of the opportunities that such data ofer, which is a new approach to understanding the world and making decisions [17]. The data involved are often described as high-volume, high- velocity and high-variety (Figure 1) [7]. While volume applies to the magnitude of data, variety entails structural heterogeneity, meaning that the data consist of various types, including unstructured data such as text, images, video and audio. Velocity, on the other hand, refers to the rate at which data are