Authors

  • Anatoly Matveev
    Technical Superintendent, Tipco Maritime Company Ltd.Bangkok, Thailand

DOI:

https://doi.org/10.37547/tajet/Volume07Issue03-13

Keywords:

artificial intelligence maritime fleet management predictive maintenance route optimization cost reduction

Abstract

The article explores the potential applications of artificial intelligence (AI) in maritime fleet management, focusing on improving operational efficiency and reducing costs. An analysis of key technological solutions is presented, including predictive maintenance, intelligent routing systems, crew performance monitoring tools, and energy consumption optimization. It is demonstrated that machine learning algorithms processing vast datasets, such as Automatic Identification System (AIS) data, weather information, and vessel sensor readings, can predict emergency situations and schedule maintenance based on actual equipment wear.

The study examines case studies from Maersk, Shell, Wärtsilä, and other companies, highlighting fuel savings of up to 15%, reductions in unplanned maintenance events, and improvements in environmental sustainability. Special attention is given to decision-support systems that integrate diverse data sources into a unified information platform, enabling comprehensive analysis and timely decision-making.

The implementation of AI technologies can enhance not only safety levels but also the profitability of maritime transport by optimizing cargo flows and reducing fuel and maintenance costs. The article concludes with practical recommendations for shipping operators transitioning to a "digital" fleet and outlines promising directions for further research. The information presented will be of interest to professionals and researchers in maritime logistics, digital transformation, and operational management who aim to integrate advanced AI-driven models with systems analysis to develop innovative strategies for improving efficiency and reducing costs in maritime fleet management amid global industry dynamics.


background image

The American Journal of Engineering and Technology

133

https://www.theamericanjournals.com/index.php/tajet

TYPE

Original Research

PAGE NO.

133-140

DOI

10.37547/tajet/Volume07Issue03-13



OPEN ACCESS

SUBMITED

22 January 2025

ACCEPTED

19 February 2024

PUBLISHED

12 March 2025

VOLUME

Vol.07 Issue03 2025

CITATION

Anatoly Matveev. (2025). Artificial Intelligence in Maritime Fleet
Management: Enhancing Operational Efficiency and Cost Reduction. The
American Journal of Engineering and Technology, 133

140.

https://doi.org/10.37547/tajet/Volume07Issue03-13

COPYRIGHT

© 2025 Original content from this work may be used under the terms
of the creative commons attributes 4.0 License.

Artificial Intelligence in
Maritime Fleet
Management: Enhancing
Operational Efficiency and
Cost Reduction

Anatoly Matveev

Technical Superintendent, Tipco Maritime Company Ltd.Bangkok,
Thailand


Abstract:

The article explores the potential applications

of artificial intelligence (AI) in maritime fleet
management, focusing on improving operational
efficiency and reducing costs. An analysis of key
technological solutions is presented, including
predictive maintenance, intelligent routing systems,
crew performance monitoring tools, and energy
consumption optimization. It is demonstrated that
machine learning algorithms processing vast datasets,
such as Automatic Identification System (AIS) data,
weather information, and vessel sensor readings, can
predict

emergency

situations

and

schedule

maintenance based on actual equipment wear.

The study examines case studies from Maersk, Shell,
Wärtsilä, and other companies, highlighting fuel savings
of up to 15%, reductions in unplanned maintenance
events,

and

improvements

in

environmental

sustainability. Special attention is given to decision-
support systems that integrate diverse data sources into
a unified information platform, enabling comprehensive
analysis and timely decision-making.

The implementation of AI technologies can enhance not
only safety levels but also the profitability of maritime
transport by optimizing cargo flows and reducing fuel
and maintenance costs. The article concludes with
practical recommendations for shipping operators
transitioning to a "digital" fleet and outlines promising
directions for further research. The information
presented will be of interest to professionals and
researchers in maritime logistics, digital transformation,
and operational management who aim to integrate
advanced AI-driven models with systems analysis to
develop innovative strategies for improving efficiency


background image

The American Journal of Engineering and Technology

134

https://www.theamericanjournals.com/index.php/tajet

The American Journal of Engineering and Technology

and reducing costs in maritime fleet management
amid global industry dynamics.

Keywords:

artificial intelligence, maritime fleet

management,

predictive

maintenance,

route

optimization, cost reduction, operational efficiency,
maritime logistics, maritime safety.

Introduction:

Maritime transport is one of the key

components of global logistics, accounting for up to
90% of international trade volume [1]. However, the
industry faces several critical challenges. First,
operational risks and the high cost of accidents remain
significant concerns. Adverse weather conditions,
heavy vessel traffic, limited visibility, and human
factors frequently lead to incidents that pose threats
to human life and the environment. Second, increasing
demands for environmental sustainability and
emission reduction place additional pressure on the
industry, as maritime transport has a substantial
impact on marine ecosystems. Lastly, fuel costs
represent one of the largest expense categories, with
price fluctuations directly affecting the overall budget
of shipping companies [2].

Artificial intelligence and big data are becoming
integral to the modern maritime industry, enhancing
both safety and cost efficiency through route
optimization, predictive maintenance, and intelligent
fleet management. The emergence of solutions such as

Wärtsilä's Fleet Operations Solution and ABB Ability™

Marine Pilot Vision demonstrates that digital
technologies have the potential to transform ship
management and operational safety [4, 6]. Against this
backdrop, the study of AI integration into maritime
operations is particularly relevant, with the primary
objective being the improvement of economic
performance and the minimization of operational risks.

The literature review includes studies assessing both
environmental and operational efficiency, as well as
the application of advanced methods to minimize
delays and optimize processes. These studies highlight
a research gap related to the insufficient integration of
heterogeneous data into unified management
systems.

One group of publications focuses on the sustainable
development of port regions and the optimization of

route efficiency. Stanković J. J. et al. [1] propose an

MCDM (Multi-Criteria Decision-Making) method for
creating a composite index that comprehensively
evaluates the social, economic, and environmental
sustainability of port regions, with the research
objective of achieving balance among various aspects

of sustainable development. Similarly, Mollaoglu M.,
Altay B. C., and Balin A. [2] conduct a bibliometric
analysis of optimization solutions in maritime transport,
hypothesizing that the application of systemic
optimization approaches can significantly enhance both
operational efficiency and environmental safety.

Additional contributions to this area are made by Fan A.
et al. and Kuroda M., Sugimoto Y., [8] who conduct
empirical studies on the impact of vessel technical
parameters

such as speed, trim, and weather

conditions

on operational performance. Meanwhile,

Zis T. P. V., Psaraftis H. N., and Ding L. [13] systematize
existing routing methods with a focus on meteorological
factors.

The second group of studies focuses on the application
of artificial intelligence methods and AIS data analysis to
enhance safety and optimize navigation processes. Tu E.
et al. [3] provide a comprehensive review of the use of
Automatic

Identification

System

(AIS)

data,

demonstrating the potential of intelligent algorithms in
processing and analyzing navigational information.
Chen X., Ma D., Liu R. W. [4] expand this field by
exploring the application of artificial intelligence in
maritime transport to improve predictive accuracy and
minimize the risk of accidents. The methodology of
these studies is based on a combination of machine
learning techniques, big data processing, and risk
scenario modeling, supporting the hypothesis that AI
integration can significantly enhance navigation
reliability.

Additional contributions to safety analysis are made by
Pallotta G., Vespe M., and Bryan K., [9] who develop
algorithms for detecting anomalous vessel trajectory
patterns. Similarly, Chen J. et al. [6] and Yang Z., Yang Z.,
Yin J. [12] utilize statistical models and Bayesian
networks to assess factors influencing maritime
accidents, highlighting the need for further validation of
these models using empirical data. A review by Durlik I.
et al. [14] summarizes recent advancements in AI-driven
risk management and safety, emphasizing a research
gap related to the lack of a unified approach for
integrating heterogeneous data into comprehensive
monitoring systems.

The third group of publications focuses on training and
human factor management in maritime navigation. Atik
O. and Arslan O. [5] apply eye-tracking technology to
assess electronic navigational competence, allowing for
an objective measurement of operators' training levels
and supporting the hypothesis that biometric methods
can improve training quality. Wahl A. M. and Kongsvik
T., [11] in their review of Crew Resource Management
(CRM) methods, analyze modern crew training


background image

The American Journal of Engineering and Technology

135

https://www.theamericanjournals.com/index.php/tajet

The American Journal of Engineering and Technology

approaches, highlighting the necessity of integrating
simulation-based training and practical exercises to
reduce operational risks.

A separate research direction is represented by the
study of Susto G. A. et al. [10], which explores the
application of machine learning in predictive
maintenance. The authors use a multi-classification
method to identify potential equipment failures,
thereby minimizing vessel downtime.

The analysis of scientific publications indicates that
while safety and anomaly detection have been
extensively studied, systematic research on the overall
economic impact of AI implementation in fleet
management remains limited. This field requires
further exploration, including not only risk assessment
but also economic metrics such as fuel cost reductions,
vessel downtime expenses, and emergency repair
costs, as well as the development of comprehensive
digital ecosystems. The absence of full-scale
comparative

analyses

(before

and

after

AI

implementation) highlights the research gap that
defines the relevance of this study.

The objective of this research is to identify and
systematize key artificial intelligence methods and
tools that significantly improve the economic
efficiency of maritime fleet management while
simultaneously enhancing safety levels.

The scientific novelty lies in examining the role of AI
across multiple domains, including predictive
maintenance, intelligent routing, crew resource
management, and risk analysis, with a focus on
minimizing overall operational costs for shipping
companies. This approach aims to clarify the
relationship between safety and costs while proposing
an optimized strategy for maritime transport
operators.

The hypothesis suggests that integrating AI into
maritime

fleet

management

through

failure

prediction systems, real-time navigational guidance,
vessel load optimization, and other tools

not only

increases safety levels but also leads to a tangible
reduction in operating expenses, averaging a 20

25%

decrease in fuel, maintenance, and downtime costs.

RESEARCH RESULTS

Traditional risk assessment methods in maritime
transport

manual inspections, historical incident

data collection, and expert opinions

do not always

fully reflect the dynamic and complex nature of the
industry [6]. The implementation of artificial
intelligence (AI) algorithms is transforming this

paradigm, as machine learning systems can process
large datasets, including AIS data, weather forecasts,
and vessel sensor readings, to identify hidden patterns
that standard analyses may overlook.

One of the key tools in this process includes neural
networks and ensemble models such as Random Forest
and Gradient Boosting, which are used to assess the
likelihood of accidents and collisions [12]. For example,
Maersk's

AI-based

system

analyzes

real-time

navigational and technical parameters, providing risk
alerts several hours before a critical situation arises.
Such solutions enhance operational efficiency by
preventing downtime and reducing accident-related
costs [5, 7, 9].

The continuous integration of AIS (Automatic
Identification System) data, predictive weather models,
and engine condition sensors enables real-time
recommendations for fleet captains and dispatchers [3].
Decision Support Systems (DSS) generate maneuvering
scenarios, help avoid congested waterways, and
consider high-risk maritime zones [4].

As noted by Pallotta et al. [9], anomaly detection
algorithms provide the ability to identify unusual vessel
movements, which is particularly valuable in areas with
heavy maritime traffic. This allows operators to adjust a

vessel’s course or speed in advance, reducing the risk of

collisions and, consequently, potential financial losses.

AI-driven systems predict problems before they occur.
Instead of reactive measures, where the crew responds
only after a critical event, a proactive strategy is
implemented

[12].

For

example,

preemptive

instructions to the crew regarding mooring or port
departure in adverse weather conditions help minimize
vessel damage and operational delays.

A comprehensive approach that combines big data
analysis, intelligent algorithms, and crew training in
system operations has already demonstrated its
effectiveness.

Predictive maintenance is based on the principle that
equipment failures can be anticipated using historical
inspection data and real-time sensor readings [11]. This
approach differs from scheduled maintenance, where
servicing follows a rigid time-based schedule, and from
reactive maintenance, which involves repairs only after
a failure occurs.

Given the harsh maritime environment

saltwater

exposure, vibrations, and extreme temperatures

frequent equipment failures represent a significant
expense [10]. Predictive maintenance reduces costs by
enabling more accurate planning for repairs, allowing
shipping companies to procure spare parts in advance


background image

The American Journal of Engineering and Technology

136

https://www.theamericanjournals.com/index.php/tajet

The American Journal of Engineering and Technology

and maximize port call efficiency.

Artificial intelligence also improves the allocation of
watchkeeping duties, ensures compliance with rest
period regulations, and provides training simulations
to enhance crew preparedness [5].

Many companies, including Kongsberg Maritime and
Wärtsilä, are developing integrated platforms that
track crew skills, training outcomes, and competency
gaps [1]. Thus, the implementation of AI has a dual
effect: it prevents accidents while also enhancing the
efficient use of human resources.

One of the most significant cost factors in shipping is
fuel consumption, which can account for 40

50% of

total expenses [2]. AI algorithms dynamically adjust
routes based on weather conditions, ocean currents,
and port congestion. According to Tu et al. [3], such
optimization can result in fuel savings of up to 10

15%.

Additionally, intelligent planning systems help avoid
delays when vessels are queuing to enter ports,
particularly during peak periods, further reducing
overall operational costs [4].

Modern propulsion control systems can optimize

engine speed and propeller pitch in real time by
analyzing data on vessel load, current draft, water
resistance, and wind conditions. Machine learning
algorithms, such as LSTM neural networks, assess both
historical and real-time parameters to determine the
most efficient engine operation mode [13].

The integration of these systems enables fuel
consumption reductions of 5

8% under actual operating

conditions. When combined with weather-based
routing, total savings can be even higher [8].

Beyond economic benefits, reducing fuel consumption
also has a significant environmental impact by lowering

CO₂ and other harmful emissions [8, 11]. The

International Maritime Organization (IMO) continues to
set increasingly stringent decarbonization targets, and
operators that effectively utilize AI already gain
advantages in certification and partnerships with
environmentally responsible companies.

As a result, the development of comprehensive AI-
driven "green" solutions allows companies to maintain
a competitive position in the industry, avoid penalties,
and strengthen corporate responsibility (Table 1).

Table 1. Comparison of Traditional and AI-Oriented Approaches in Marine Fleet Management [2-4]

Parameter

Traditional

Approach

AI-Oriented Approach

Key Benefits of AI

Risk
Assessment

Manual

inspection,

historical

case

analysis,

subjective

evaluations

Machine learning models,
big data analysis, real-time
monitoring

Increased accuracy, early
threat

detection,

reduction of accidents
and penalties

Predictive
Maintenance

Preventive
maintenance based on
fixed schedules or
reactive repairs after
failures

Failure

prediction

algorithms

(vibration

analysis, neural networks),
optimized repair planning

Reduced downtime, cost
savings on procurement
and repairs, extended
equipment lifespan

Crew Resource
Management

Minimal

analytics,

shift scheduling based
on

regulations,

infrequent training

Intelligent task distribution,
AI-based

simulations,

fatigue monitoring

Reduced human error,
increased motivation and
crew qualification

Route

and

Energy
Optimization

Planning based on
captain's experience
and weather reports

Continuous

course

optimization using weather
models and ocean currents,

10–15% fuel savings,
reduced

port

delays,

contribution

to


background image

The American Journal of Engineering and Technology

137

https://www.theamericanjournals.com/index.php/tajet

The American Journal of Engineering and Technology

ML-based

engine

adjustments

environmental
sustainability

Environmental
Considerations

Compliance

with

basic

MARPOL

regulations,

low

adaptability

Proactive

decarbonization

strategy, real-time emission
and cost monitoring

Improved environmental
performance,

reduced

fines, enhanced corporate
sustainability image

It is evident that traditional risk assessment methods
in maritime transport, which rely on manual
inspections, historical data, and expert evaluations, no
longer meet the demands of modern industry
conditions, driving the adoption of artificial
intelligence algorithms. The use of neural networks,
ensemble models, and anomaly detection algorithms
allows for the processing of vast datasets and the
development of proactive decision-making strategies.
This not only enhances the accuracy of accident
probability assessments and optimizes predictive
maintenance but also contributes to significant cost
reductions in fuel consumption and repairs.

For further advancements, it is recommended to
implement hybrid models that combine the strengths
of traditional methods with machine learning
capabilities, as well as expand the use of IoT devices to
improve data collection and integration.

Examples of artificial intelligence applications for
fleet management optimization

Fuel costs remain one of the most significant expenses
in the shipping industry. Many companies utilize
machine

learning

algorithms

integrated with

meteorological and oceanographic data to dynamically
adjust vessel routes, reducing overall travel time and
maximizing the use of favorable currents and weather
conditions [3].

More precise control over propulsion systems,
including the propeller, rudder, and main engine
power, also contributes to fuel savings. Modern
systems can manage engine speed in real time, taking
into account vessel load, wind speed, wave height, and
hull fouling [7]. This increases efficiency and prevents
the engine from operating at excessive power levels
for given conditions [8].

AI platforms not only calculate optimal routes between
ports but also plan port arrival times, minimizing idle
time and congestion [4]. Reducing bottlenecks near
port terminals helps decrease unnecessary fuel
consumption and emissions, directly impacting

shippi

ng companies’ budgets.

As previously mentioned, predictive maintenance
enables vessel operators to identify components
requiring repair or replacement in advance. In the
Veracity project by DNV, onboard sensor data

such as

vibration, temperature, and pressure

are continuously

analyzed by AI algorithms. The system predicts failure
timelines and recommends optimal maintenance
windows, reducing the likelihood of unexpected
breakdowns and associated costs for towing or
emergency repairs.

Real-time monitoring of hull condition, propellers, and
power units allows for dock maintenance scheduling
based on actual rather than nominal service intervals
[10].

Shell reports that integrating equipment wear data with
enterprise resource planning (ERP) systems automates
the procurement of spare parts and consumables. This
minimizes the risk of operational downtime due to
delayed deliveries. Coordination between onboard and
shore-based technical teams is simplified through a
unified information system, where AI adjusts
maintenance and logistics schedules as needed [9].

At the fleet level, consisting of dozens or hundreds of
vessels, AI tools optimize vessel allocation based on
their current technical condition, cargo capacity, and
order urgency. Ports are increasingly adopting AI and
IoT-based smart solutions, such as IoT sensors on cranes
and robotic container movers, allowing vessel operators
to synchronize entry and exit schedules. This improves
port throughput and reduces the likelihood of
congestion [2].

Such coordination delivers additional economic
benefits, including shorter transit times, more efficient
use of personnel and equipment, and reduced waiting
times.

Big Data tools aggregate and analyze operational
metrics such as speed, fuel consumption, downtime,
and incidents [9]. The results of this analysis support
strategic decision-making at the management level,
including investments in specific vessel types, additional


background image

The American Journal of Engineering and Technology

138

https://www.theamericanjournals.com/index.php/tajet

The American Journal of Engineering and Technology

crew training, or adjustments to supply chain logistics (Table 2).

Table 2. Summary of Key AI-Based Solutions for Fleet Management [4]

Solution

Key Functions

Application

(Examples)

Main Benefits

Fleet
Operations
Solution
(FOS)

- Weather-based routing -
Engine

performance

monitoring - Draft analysis

Container

ships,

tankers, ferries

5–15%

fuel

savings;

reduced

schedule

deviations

Veracity
DNV

- Predictive maintenance - ERP
integration

-

Technical

condition reports

Cruise

and

commercial

vessels

(integrated

with

maintenance systems)

Reduced

emergency

repairs; accurate planning
of dock maintenance

ABB
Ability™
Marine
Pilot
Vision

- Real-time navigation - AI-
assisted port entry - Obstacle
detection system

Vessels

performing

complex

maneuvers

(docking in congested
ports)

Reduced collision risks,
optimized maneuvering
time

AI-Driven
Logistics

- Fleet distribution optimization
- Integration of shipper data

Large-scale
international
container shipping

Reduced port congestion,
improved delivery time
prediction

Training
Simulators

- Virtual training systems -
Emergency situation modeling -
Crew readiness assessment

Training

centers,

navigation

and

operational

safety

programs

Reduced human error,
increased safety levels

Intelligent
Routing

-

Prediction

of

vessel

movements - Optimal speed
selection - Consideration of
environmental zones

Scientific and test
projects

(partially

autonomous vessels)

Significant reduction in
emissions,

improved

route reliability, and fuel
efficiency

The examples above demonstrate that the
comprehensive implementation of AI technologies in
fleet management can provide:

Fuel cost reduction ranging from 5% to 15%

through optimized routing and engine management
[3].

Decreased downtime due to predictive

maintenance of critical components.

More efficient coordination between maritime

and port operations (automated docking planning,
improved container logistics) [2].

Enhanced

crew

training

and

better

watchkeeping discipline, indirectly reducing human
error risks [11].


background image

The American Journal of Engineering and Technology

139

https://www.theamericanjournals.com/index.php/tajet

The American Journal of Engineering and Technology

It is recommended to develop and implement machine
learning-based

systems

capable

of

analyzing

meteorological, oceanographic, and hydrographic data
in real time. These solutions will not only enable
vessels to adjust their course based on weather
conditions but also optimize engine performance by
regulating speed, power, and load according to real-
time conditions.

Another crucial area is the implementation of
predictive maintenance concepts, which improve fleet
reliability. The use of analytical platforms enables real-
time monitoring of critical components through
vibration, temperature, and pressure sensors, allowing
for early fault detection. Integrating equipment
condition data with ERP systems automates spare
parts and consumables procurement, minimizing
vessel downtime and reducing repair costs.

At the fleet management level, integrated AI solutions
should be developed to coordinate not only internal
vessel processes but also interactions with port
infrastructure. Utilizing Big Data and IoT technologies
to analyze operational metrics such as speed, fuel
consumption, and downtime allows for data-driven
decision-making, optimizing fleet distribution and port
entry schedules. Additionally, the adoption of smart
port systems, including crane sensors and robotic
container handling devices, contributes to reducing
waiting times, lowering emissions, and improving
resource efficiency.

CONCLUSION

The integration of artificial intelligence into marine
fleet management presents new opportunities for
improving efficiency and competitiveness in the
shipping industry. This study examined AI applications
focused on route planning considering weather
conditions,

predictive maintenance

of vessel

equipment, intelligent crew resource allocation, and
automated interaction with port infrastructure.

Through big data analysis and machine learning
methods, fleet operators can anticipate potential
issues, shifting from reactive measures to a proactive
approach. This transition reduces both time and
financial losses associated with unforeseen incidents
and emergency repairs. An additional advantage is the
improvement of environmental performance through
lower emissions and more efficient resource
utilization.

Despite the evident benefits, several challenges
continue to hinder the widespread adoption of AI
technologies, including the lack of high-quality data,

difficulties in integrating with outdated infrastructure,
and

cybersecurity

concerns.

However,

the

recommendations outlined in this study and the
successful implementation examples confirm that the
maritime industry is gradually embracing digital
transformation, with AI emerging as a key tool for
ensuring competitive and safe shipping operations.
Future

advancements

will

require

further

standardization of data collection methodologies and
enhanced collaboration between shipping companies,
ports, and technology providers, enabling the full

realization of artificial intelligence’s potential in the

industry.

REFERENCES

Stanković J. J. et al. Social, economic and environmental

sustainability of port regions: Mcdm approach in
composite index creation //Journal of Marine Science
and Engineering.

2021.

Vol. 9 (1).

pp. 74.

Mollaoglu M., Altay B. C., Balin A. Bibliometric review of
route optimization in maritime transportation:
Environmental sustainability and operational efficiency
//Transportation Research Record.

2023.

Vol. 2677

(6).

pp. 879-890.

Tu E. et al. Exploiting AIS data for intelligent maritime
navigation: A comprehensive survey from data to
methodology //IEEE Transactions on Intelligent
Transportation Systems.

2017.

Vol. 19 (5).

pp.

1559-1582.

Chen X., Ma D., Liu R. W. Application of Artificial
Intelligence in Maritime Transportation //Journal of
Marine Science and Engineering.

2024.

Vol. 12 (3).

pp. 439.

Atik O., Arslan O. Use of eye tracking for assessment of
electronic navigation competency in maritime training
//Journal of eye movement research.

2019.

Vol. 12

(3).

pp. 7-15.

Chen J. et al. Identifying factors influencing total-loss
marine accidents in the world: Analysis and evaluation
based on ship types and sea regions //Ocean
Engineering.

2019.

Vol. 191.

pp. 1-12.

Fan A. et al. Joint optimisation for improving ship energy
efficiency considering speed and trim control
//Transportation Research Part D: Transport and
Environment.

2022.

Vol. 113.

pp. 5-11.

Kuroda M., Sugimoto Y. Evaluation of ship performance
in terms of shipping route and weather condition
//Ocean Engineering.

2022.

Vol. 254.

pp. 1-10.

Pallotta G., Vespe M., Bryan K. Vessel pattern
knowledge discovery from AIS data: A framework for


background image

The American Journal of Engineering and Technology

140

https://www.theamericanjournals.com/index.php/tajet

The American Journal of Engineering and Technology

anomaly detection and route prediction //Entropy.

2013.

Vol. 15 (6).

pp. 2218-2245.

Susto G. A. et al. Machine learning for predictive
maintenance: A multiple classifier approach //IEEE
transactions on industrial informatics.

2014.

Vol.

11. (3).

pp. 812-820.

Wahl A. M., Kongsvik T. Crew resource management
training in the maritime industry: a literature review
//WMU Journal of Maritime Affairs.

2018.

Vol. 17

(3).

pp. 377-396.

Yang Z., Yang Z., Yin J. Realising advanced risk-based
port state control inspection using data-driven
Bayesian networks //Transportation Research Part A:
Policy and Practice.

2018.

Vol. 110.

pp. 38-56.

Zis T. P. V., Psaraftis H. N., Ding L. Ship weather routing:
A taxonomy and survey //Ocean Engineering.

2020.

Vol. 213.

pp. 1-14.

Durlik I. et al. Artificial Intelligence in Maritime
Transportation: A Comprehensive Review of Safety
and Risk Management Applications //Applied Sciences.

2024.

Vol. 14 (18).

pp. 8420.

References

Stanković J. J. et al. Social, economic and environmental sustainability of port regions: Mcdm approach in composite index creation //Journal of Marine Science and Engineering. – 2021. – Vol. 9 (1). – pp. 74.

Mollaoglu M., Altay B. C., Balin A. Bibliometric review of route optimization in maritime transportation: Environmental sustainability and operational efficiency //Transportation Research Record. – 2023. – Vol. 2677 (6). – pp. 879-890.

Tu E. et al. Exploiting AIS data for intelligent maritime navigation: A comprehensive survey from data to methodology //IEEE Transactions on Intelligent Transportation Systems. – 2017. – Vol. 19 (5). – pp. 1559-1582.

Chen X., Ma D., Liu R. W. Application of Artificial Intelligence in Maritime Transportation //Journal of Marine Science and Engineering. – 2024. – Vol. 12 (3). – pp. 439.

Atik O., Arslan O. Use of eye tracking for assessment of electronic navigation competency in maritime training //Journal of eye movement research. – 2019. – Vol. 12 (3). – pp. 7-15.

Chen J. et al. Identifying factors influencing total-loss marine accidents in the world: Analysis and evaluation based on ship types and sea regions //Ocean Engineering. – 2019. – Vol. 191. – pp. 1-12.

Fan A. et al. Joint optimisation for improving ship energy efficiency considering speed and trim control //Transportation Research Part D: Transport and Environment. – 2022. – Vol. 113. – pp. 5-11.

Kuroda M., Sugimoto Y. Evaluation of ship performance in terms of shipping route and weather condition //Ocean Engineering. – 2022. – Vol. 254. – pp. 1-10.

Pallotta G., Vespe M., Bryan K. Vessel pattern knowledge discovery from AIS data: A framework for anomaly detection and route prediction //Entropy. – 2013. – Vol. 15 (6). – pp. 2218-2245.

Susto G. A. et al. Machine learning for predictive maintenance: A multiple classifier approach //IEEE transactions on industrial informatics. – 2014. – Vol. 11. (3). – pp. 812-820.

Wahl A. M., Kongsvik T. Crew resource management training in the maritime industry: a literature review //WMU Journal of Maritime Affairs. – 2018. – Vol. 17 (3). – pp. 377-396.

Yang Z., Yang Z., Yin J. Realising advanced risk-based port state control inspection using data-driven Bayesian networks //Transportation Research Part A: Policy and Practice. – 2018. – Vol. 110. – pp. 38-56.

Zis T. P. V., Psaraftis H. N., Ding L. Ship weather routing: A taxonomy and survey //Ocean Engineering. – 2020. – Vol. 213. – pp. 1-14.

Durlik I. et al. Artificial Intelligence in Maritime Transportation: A Comprehensive Review of Safety and Risk Management Applications //Applied Sciences. – 2024. – Vol. 14 (18). – pp. 8420.