Big Data in the Maritime Industry

Abstract

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 significant 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, specifically in logistics optimization, safety and energy efficiency improvement, as well as the challenges that systems involving Big Data face.

Full text

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 signicant
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, specically in logistics optimization,
safety and energy eciency 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 eciency
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 benets
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 / Denicija 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
oer, 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

57
“Naše more” 65(1)/2018., pp. 56-62
generated and the speed at which they should be analyzed [11].
The point at which any of these characteristics may be rated
high is relative. Consequently, many denitions instead point
out the requirement for specic technology and analytical
methods as the main characteristic of Big Data [7]. While these
qualities do present challenges when it comes to processing
the data, they are also what makes the data extremely valuable.
It means that, with the right analytical tools, the data can be
analyzed for patterns in order to gain insight that couldn’t be
achieved on a smaller scale.
Figure 1 Big Data characteristics
Slika 1. Karakteristike velikih skupova podataka
There are many examples of Big Data being used in
practice. Companies are expanding their traditional data sets
with social media data, browser logs and similar data to get a
better understanding of their customers, their behaviors and
preferences. Retailers can optimize stock based on predictions
generated from Big Data. Credit card companies use it for fraud
detection. More and more cities use data from road sensors and
cameras to optimize trac ow. Delivery routes are optimized
using geographic positioning and radio frequency identication
sensors. Big Data is also used in medicine. For example, recording
and analyzing heartbeat and breathing patterns of patients in a
specialist premature and sick baby unit has enabled predicting
infections 24 hours before physical symptoms appear [14]. It seems
that there’s no area that wouldn’t benet from the usage of Big
Data. The awareness of its value and potential continues to grow.
3. BIG DATA IN LOGISTICS AND
TRANSPORTATION / Primjena velikih skupova
podataka u logistici i transportu
Big Data analytics brings many benets to logistics and
transportation industry. The data are collected from a very large
network of sensors and devices. Big data analytics tools are
ecient in storing the data and processing them in real time
in order to monitor trac and make predictions that improve
service quality and companies’ revenues [3].
Data generated by trac sensors can be used to identify
issues in real time, which means that road users can make
informed decisions to save time while road authorities may
control trac and intervene quickly when needed [18], [30]. Los
Angeles, for example, uses the data to control trac lights, which
has reduced trac congestion by an estimated 16 percent [14].
In Dublin, the data collected from trac sensors, bus GPS devices
and other sources are used to build a real-time digital map of the
city transportation network. It helps identify trac problems and
make decisions regarding the bus transportation network. As a
result, the trac ow in the city has been improved [3].
The private sector may gain competitive advantage and
increase productivity using Big Data [30]. Tracking vehicles’
locations using satellite navigation and sensors enables
customers to know exactly where their shipment is and when
it will be delivered. The vehicles’ routes can be optimized by
taking into account delivery addresses and data regarding
road conditions, trac jams, weather conditions, locations
of gas stations, etc. Routing optimization saves a lot of fuel,
which reduces nancial cost and environmental impact. Fuel
consumption can also be reduced by optimizing fuel input
based on data from sensors that monitor the engine. Sensors
can also monitor the state of the equipment and vehicle
performance in real time. This helps predict errors and detect
when maintenance is needed. Safety can also be improved
with sensors that monitor vehicle speed, whether the driver is
complying with the trac laws and if the driver has been behind
the wheel for too long [29].
US Xpress, an American logistics company, is an example of
a company taking advantage of Big Data [29]. It has installed
almost 1,000 sensors in each truck to monitor their locations,
driving speed, petrol use, how often they break, if they are
on idle for too long, when maintenance is required and even
the drivers’ capabilities. Hundreds of billions of data records
generated help the company save over $6 million a year.
It is presented in [25] how data regarding the fuel, speed,
acceleration, etc. are collected from vehicles’ sensors and GPS
devices. They are then analyzed, which enables monitoring the
driving behaviors to improve productivity, detecting negative
driving patterns, determining which trucks are idling and wasting
fuel, which trucks have the worst gas mileage and which drivers
have the highest risk factor. The data ow is shown in Figure 2.
Figure 2 System data ow [25]
Slika 2. Tijek podataka sustava [25]
4. BIG DATA IN THE MARITIME INDUSTRY / Primjena
velikih skupova podataka u pomorskoj industriji
4.1. Data sources and utilization strategies / Izvori
podataka i strategije korištenja
There is a signicant amount of data generated in navigation
systems that consist of radar, electronic chart display and

58 M. Mirović et al: Big Data in the...
information system (ECDIS), auto-pilot system and other related
sensors [22]. Moreover, special purpose vessels will require
additional instrumentation relevant for their operations, such
as wave radars, oil spill detectors and high accuracy inertial
navigation sensors [24].
A subset of ship performance and navigation data,
such as the vessel’s unique identication number, position,
course, speed and destination, are transferred by Automatic
Identication System (AIS). Ships on international voyages of
over 300 gross tonnage and all passenger ships are required
to have AIS [28]. An AIS transponder exchanges data with
other nearby ships, land based systems and satellites with the
purpose of collision avoidance.
In addition, the Voyage Data Recorder (VDR), which is
required on all passenger ships and other ships with gross
tonnage of 3000 or more [27], connects to a number of electronic
devices and stores the recorded information of each voyage as
electronic data. Data items include the ship’s position, speed,
heading, audio from bridge microphones, communication
audio, radar data, water depth, wind speed and direction, data
from the alarms, hull openings status, watertight and re door
status, acceleration and hull stresses, the order and response
of the engine and rudder. The volume of data is so large that,
during long voyages, older data have to be overwritten to store
new data. After the voyage is completed, the data are usually
discarded. The main purpose of VDR is data analysis in case of an
accident. However, instead of throwing this information away,
it could be processed and eectively used with the help of Big
Data techniques [15].
Perrera et al. [22] propose the data ow chart as presented
in Figure 3. The data are collected from various onboard sensors
and data acquisition systems, preprocessed and transmitted to
shore based data centers where they are stored and analyzed.
The result of the analysis is information that supports decision-
making, for example to improve energy eciency and system
reliability.
According to [15], DNV-GL and Lloyd’s Register Foundation
(LRF), major worldwide classication societies, have already
published their strategies on Big Data. DNV-GL points out
six main areas in which Big Data is expected to be used:
technical operation and maintenance, energy eciency, safety
performance, management and monitoring of accidents and
environmental risks from shipping trac, commercial operation
and automation of ship operation. DNV-GL also suggests that
the data may be owned and controlled not only by shipowners,
but also ship builders, suppliers of components, the
classication society, etc. LRF predicts that Big Data will enable
condition-based maintenance, smart factories and autonomous
machines. They intend to establish an infrastructure where data
from various resources could be shared, certify the quality of
data and control the rights and responsibilities of players in the
market.
ClassNK is another classication society that has taken
interest in Big Data. In fact, they have established the rst
shared Big Data platform in the maritime industry. The platform
was built in 2016 by Fujitsu Limited. It collects machinery
operational data from moving vessels, such as engine data, and
enables ship operators, shipowners, shipyards, manufacturers
and other maritime businesses to extract data as needed
[10]. The ship’s data are emailed to the onshore data center
where they are converted and stored using IBM’s secure cloud
platform. Stored data can only be accessed strictly according to
the requirements set by each company [16].
4.2. Energy eciency improvement / Unapređenje
energetske učinkovitosti
Ship performance and navigation information can be used to
develop navigation strategies to improve ship energy eciency
[22]. Monitoring fuel consumption, various emissions, the use of
lighting, heating and similar processes can result in insights that
support decision-making.
In [23], data such as wind speed and direction, average draft,
trim, main engine power, shaft speed and fuel consumption
are analyzed and several higher fuel consumption trends
under these parameter variations are noted. The optimal trim
conguration is identied with respect to the fuel consumption
rates. Applying strategies based on this information enables
ships to meet energy eciency and emission control standards.
Along with environmental benets, this is also signicant for
cost reduction.
4.3. Safety improvement / Unapređenje sigurnosti
Safety at sea can also benet from implementing anomaly
detection in marine operations. An overview of several machine
learning techniques that can be used to detect anomalies from
data gathered on vessel movement is presented in [20].
Figure 3 Data ow chart in ship performance and navigation information [22]
Slika 3. Dijagram toka podataka o performansama broda i navigacijskim informacijama [22]

59
“Naše more” 65(1)/2018., pp. 56-62
In [4], an application of sensor-based anomaly detection in
maritime transport is demonstrated. Sensor data, which include
environmental and ship system information, are streamed from
a ship to shore where they are analyzed through a Big Data
analytics platform. Auto Associative Kernel Regression and the
Sequential Probability Ratio Test technique are used to detect
anomalies and trigger alarms so that appropriate action can
be taken as soon as possible. Critical points identied along a
vessel trajectory are shown in Figure 4.
A solution for real time monitoring of sensor data in a seaport
infrastructure implemented in the Puerto de La Luz seaport in
the Canary Islands is described in [9]. The system integrates data
from AIS, various sensors and external sources, and provides
a 3D map showing the ingoing and outgoing vessels, as well
as the environmental conditions. It is equipped with an alert
system which means that the port can easily identify issues
and notify the vessels in order to prevent collisions, help the
vessels avoid high waves, etc. Another example of Big Data
used for anomaly detection is CMAXS, a maintenance system
developed by ClassNK [16]. It uses real-time data collected
from ow, pressure and temperature sensors on all engines and
pumps. The data are analyzed for anomalies in order to detect
potential damage as well as generate recommendations that
help minimize downtime and reduce repairs.
In [6], the arrangement of Precaution Areas, whose purpose
is minimizing the possibility of collisions, is optimized using AIS
data. On the other hand, [1] shows how Big Data can be used
to gain a better understanding of maritime activities, which
is especially useful in remote areas such as the Arctic where
shipping activity needs to be monitored to ensure sustainability
and the information is otherwise dicult to access. It also
discusses anomaly detection, such as detecting when a vessel
deviates from the declared path, falsies its AIS reports or turns
o its AIS transponder to potentially engage in illegal activities.
Figure 5 shows a vessel deviating from the known route (red
dots), approaching a port and then returning to its declared
route.
Figure 4 Critical points identied along a vessel trajectory [2]
Slika 4. Kritičke točke koje su identicirane duž putanje broda [2]
Figure 5 Local anomaly example [1]
Slika 5. Primjerak lokalne anomalije [1]

60 M. Mirović et al: Big Data in the...
4.4. Logistics optimization / Optimizacija logistike
When it comes to logistics and operational cost reduction, [8]
states that Big Data can be used to minimize the time the ships
spend anchored outside harbor waiting for an available slot,
maximize the use of docks and synchronize the ship schedule with
the logistics on shore.
Figure 6 shows vessel position prediction 48 hours in advance
based on historical maritime trac data. The last received AIS
message is represented by the blue star and the destination port is
represented by the green star. Accurate prediction of routes can be
used to better estimate times of arrival in ports [1].
Brouer et al. [5] go into more detail, showing how operational
data can be used to build predictive models that can then provide
input for the decision-making process. Optimization within
maritime logistics is complicated due to the size of the network that
carriers operate and the uncertainty caused by delays, uctuations
in demand, no-show cargo, etc. Machine learning techniques can
provide predictions of delays due to bad weather or congestion,
required maintenance, estimates of future demand and oil prices,
but complex decisions must be made to adjust the transportation
network to the new situation. The paper shows how methods such
as mathematical programming can help make the best choice in
the examples of liner shipping network design, empty container
repositioning, container vessel stowage plans, bunker purchasing
at minimal cost and schedule recovery in case of disruptions. Route
optimization is shown in Figure 7.
Figure 6 Prediction of a vessel track [1]
Slika 6. Predviđanje putanje broda [1]
Figure 7 Route optimization [31]
Slika 7. Optimizacija rute [31]

61
“Naše more” 65(1)/2018., pp. 56-62
5. CONSTRAINTS AND CHALLENGES / Ograničenja
i izazovi
In general, systems involving Big Data face challenges related
to data quality and quantity. Ship performance and navigation
data collected by sensors and data acquisition systems create
both quantity and quality issues. Data may be erroneous, due
to sensor faults or accidental mistakes made during manual
entry. Sometimes, the errors are willful, when operators have
economic interests in reporting misleading data or in an
attempt to disguise illegal activity. One possible solution is
using automated data entry, which may be too costly. Another
solution is extensive validity check [24].
In order to minimize errors, the data have to be cleaned
before being analyzed. Data cleaning includes tasks such
as anomaly detection, conicting values detection and
incomplete data lling. However, [30] points out that many data
cleaning strategies are not suitable for Big Data and that noise
and extreme values rejected in this process may in fact contain
useful information. Another issue is context dependency,
meaning that, in some cases, additional and possibly unavailable
information is needed to interpret the data correctly, such as the
exact location of the sensor [24].
Data quantity results in issues regarding storage and
transfer of data between ship and shore. There are limitations
in maximum available bandwidth and costs of transmissions via
high sea satellite communication, at least in some areas [24].
Using a subset of the large-scale data set, statistical data analysis
and machine intelligence techniques in order to overcome data
quantity issues are proposed in [22]. Koga [15] states that there
is a need for equipment with more capacity and capability, and
expresses the need for standardization of data in order to make
data integration easier.
Furthermore, [21] names model uncertainty as one of the
main issues and states that data driven models may fail due
to quality and quantity issues and proposes to use domain
knowledge to improve the accuracy.
Another major challenge is the shortage of specialists of
data-related engineering, especially in the maritime industry
which is not originally information-intensive [15]. In a survey
released by Sea Asia 2017, the majority of maritime leaders
agreed that a severe skills shortage is preventing the industry
from eectively harnessing Big Data [19].
In all disciplines, Big Data raises serious ethical and
privacy issues, and a legislative framework that will dictate the
boundaries of using data is missing [30]. DNV-GL considers that
well-established governance of data is one of the fundamental
issues. It is pointed out in [15] that, if dierent kinds of data are
concerned, the stakeholders who should have property rights
may dier. The paper also acknowledges the importance of
making sure that the rights of certain data aren’t monopolized.
Any physical connection into networks or systems can
be vulnerable to hostile attacks and reports sent from ship to
shore or vice versa can be intercepted and tampered with [24].
According to [15], LRF points out that the unlawful control of
device/machine and abusive insertion, update and deletion
of data are risks of Big Data security. Systems involving Big
Data have to be secure enough to make a criminal access
unsuccessful and, in the legislative aspect, illegal activities need
to be dened and prohibited [15].
6. CONCLUSION / Zaključak
Big Data techniques can be used to monitor vessels in real time
and analyze ship performance and navigation data collected
from onboard sensors and data acquisition systems. The
insights gained enable development of strategies regarding
optimal logistics network design and energy eciency. Along
with cost reduction and environmental benets, safety at sea
can also be improved. Anomaly detection makes it possible to
identify issues in real time so that they can be resolved as soon
as possible.
However, dealing with Big Data means facing issues
regarding data quantity and quality. The maritime industry
in particular lacks data-related experts. In addition, there
are security and privacy challenges that require setting up a
legislative framework that will dictate the governance of data.
The maritime industry could benet greatly from utilizing
Big Data, but a number of challenges need to be overcome
before it is possible to use it to its full potential.
REFERENCES / Literatura
[1] Alessandrini, A. et al., 2016, “Mining Vessel Tracking Data for Maritime Domain
Applications”, 2016 IEEE 16th International Conference on Data Mining
Workshops (ICDMW), pp. 361-367. https://doi.org/10.1109/ICDMW.2016.0058
[2] Alevizos, E., Artikis, A., Patroumpas, K., Vodas, M., Theodoridis, Y., Pelekis,
N., 2015, “How not to drown in a sea of information: An event recognition
approach”, 2015 IEEE International Conference on Big Data (Big Data), pp.
984-990. https://doi.org/10.1109/BigData.2015.7363849
[3] Ben Ayed, A., Ben Halima, M., Alimi, A. M., 2015, “Big Data Analytics for Logistics
and Transportation”, 4th IEEE International Conference on Advanced logistics
and Transport, pp. 311-316. https://doi.org/10.1109/ICAdLT.2015.7136630
[4] Brandsæter, A., Manno, G., Vanem, E., Glad, I. K., 2016,”An application of
sensor-based anomaly detection in the maritime industry”, IEEE International
Conference on Prognostics and Health Management (ICPHM), pp. 1-8.
https://doi.org/10.1109/ICPHM.2016.7811910, https://doi.org/10.1109/
ICPHM.2016.7754713
[5] Brouer, B. D., Karsten, C. V., Pisinger, D., 2016, “Big Data Optimization in
Maritime Logistics”, Big Data Optimization: Recent Developments and
Challenges, pp. 319–344. https://doi.org/10.1007/978-3-319-30265-2_14
[6] Chen, J., Lu, F., Li, M., Huang, P., Liu, X., Mei, Q., 2016, “Optimization on
Arrangement of Precaution Areas Serving for Ships’ Routeing in the Taiwan
Strait Based on Massive AIS Data”, DMBD 2016: Data Mining and Big Data, pp.
123-133. https://doi.org/10.1007/978-3-319-40973-3_12
[7] De Mauro, A., Greco, M., Grimaldi, M., 2014, “What is Big Data? A Consensual
Denition and a Review of Key Research Topics”, 4th International Conference
on Integrated Information, pp. 97-104.
[8] Domínguez, A. G., 2014, “’Smart Ships’: Smart Mobile Applications, Cloud
and Bigdata on Marine Trac for Increased Safety and Optimized Costs
Operations”, 2014 2nd International Conference on Articial Intelligence,
Modelling and Simulation, pp. 303-308. https://doi.org/10.1109/AIMS.2014.39
[9] Fernández, P. et al., 2017, “Web-Based GIS Through a Big Data Open Source
Computer Architecture for Real Time Monitoring Sensors of a Seaport”, The
Rise of Big Spatial Data, pp. 41-53. https://doi.org/10.1007/978-3-319-45123-
7_4
[10] Fujitsu Limited, 2016, “A shared maritime platform for use by maritime
businesses, which aggregates ship and marine weather data”.
Available: http://www.fujitsu.com/global/about/resources/news/press-
releases/2016/0506-01.html(14.5.2017.)
[11] Gandomi, A., Haider, M., 2015, “Beyond the hype: Big data concepts, methods,
and analytics”, International Journal of Information Management, 35, pp. 137-
144. https://doi.org/10.1016/j.ijinfomgt.2014.10.007
[12] Gantz, J., Reinsel, D., 2012, “The Digital Universe in 2020: Big Data, Bigger
Digital Shadows, and Biggest Growth in the Far East”, IDC IView. Available:
https://www.emc.com/collateral/analyst-reports/idc-the-digital-universe-
in-2020.pdf (12.5.2017.)
[13] International Maritime Organization, 2012, “IMO’s contribution to sustainable
maritime development”. Available: http://www.imo.org/en/OurWork/
TechnicalCooperation/Documents/Brochure/English.pdf (28.6.2017.)
[14] Jain, V. K., 2017, “Big Data and Hadoop”, Khanna Publishing, New Delhi.
[15] Koga, S., 2015, “Major challenges and solutions for utilizing big data in the
maritime industry”, Thesis MSc World Maritime University (Malmö, Sweden).

62 M. Mirović et al: Big Data in the...
[16] Kurashiki, T., 2016, “Maritime Big Data Solutions by ClassNK”. Available:
http://www.mpa.gov.sg/web/wcm/connect/www/c3f96729-2bac-
4c77-9cad-e61954a83e2d/Presentation+-+Toshio+Kurashiki.
pdf?MOD=AJPERES(14.5.2017.)
[17] Lohr, S., 2012, “The Age of Big Data”, The New York Times. Available: http://
www.nytimes.com/2012/02/12/sunday-review/big-datas-impact-in-the-
world.html(12.5.2017.)
[18] Nemscho, M., 2014, “Why the Transportation Industry is Getting on
Board with Big Data & Hadoop”. Available: https://mapr.com/blog/why-
transportation-industry-getting-board-big-data-hadoop/(12.5.2017.)
[19] Network Adria, 2017, “Severe skills shortage preventing maritime industry
from harnessing Big Data”. Available: https://www.networksasia.net/article/
severe-skills-shortage-preventing-maritime-industry-harnessing-big-
data.1487773464 (27.6.2017.)
[20] Obradović, I., Miličević, M., Žubrinić, K., 2014, “Machine Learning Approaches
to Maritime Anomaly Detection”, International Journal of Maritime Science &
Technology “Our Sea”, 61 (5-6), pp. 96-101.
[21] Perera, L. P., 2017, “Handling Big Data in Ship Performance and Navigation
Monitoring”, Smart Ship Technology, pp. 89-97.
[22] Perera, L. P., Mo, B., 2016, “Machine Intelligence for Energy Ecient Ships: A
Big Data Solution”, 3rd International Conference on Maritime Technology and
Engineering (MARTECH 2016), pp. 143-150. https://doi.org/10.1201/b21890-21
[23] Perera, L. P., Mo, B., Kristjánsson, L. A., 2015, “Identication of Optimal Trim
Congurations to improve Energy Eciency in Ships”, 9th IFAC Con-ference
on Manoeuvring and Control of Marine Craft (MCMC 2015), pp. 267-272.
[24] Rødseth, Ø. J., Perera, L. P.; Mo, B., 2016, “Big data in shipping – Challenges
and Opportunities”, Proceedings of the 15th International Conference
on Computer Applications and Information Technology in the Maritime
Industries (COMPIT 2016), pp. 361-373.
[25] Sivan, A. P., Johns, J., Venugopal, J., 2014, “Big Data Intelligence in Logistics
Based On Hadoop And Map Reduce”, IJIRSET, 3, pp. 2634-2640.
[26] Snijders, C., Matzat, U., Reips, U.-D., 2012, “’Big Data’: Big Gaps of Knowledge
in the Field of Internet Science”, International Journal of Internet Science, 7(1),
pp. 1-5.
[27] SOLAS, Guidance on Chapter V – Safety of Navigation (Revision), 2007, Annex
10 - Voyage Data Recorders (VDRs). Available: http://solasv.mcga.gov.uk/
annexes/Annex10.htm (27.6.2017.)
[28] SOLAS, Guidance on Chapter V – Safety of Navigation (Revision), 2007, Annex
17 - Automatic Identication Systems (AIS). Available: http://solasv.mcga.gov.
uk/annexes/Annex17.htm (27.6.2017.)
[29] Van Rijmenam, M., 2014, “Think Bigger: Developing a Successful Big Data
Strategy for Your Business”, Amacom New York, NY.
[30] Vlahogianni, E. I., 2015, “Computational Intelligence and Optimization for
Transportation Big Data: Challenges and Opportunities”, Computational
Methods in Applied Sciences, 38, pp. 107-128.https://doi.org/10.1007/978-3-
319-18320-6_7
[31] Wojnarowicz, K., 2015, “Industrial Internet of Things in the Maritime Industry”.
Available: http://blog.blackducksoftware.com/industrial-internet-of-things-
in-the-maritime-industry/ (28.6.2017.)