Volume 9, Issue 9, September– 2024 International Journal of Innovative Science and Research Technology

ISSN No:-2456-2165 https://doi.org/10.38124/ijisrt/IJISRT24SEP738

Response Coordination Model for Real Time

Decision Making in Coastal Search and Rescue
Operation Using Fuzzy Logic Technique
1
Charles Juma Mnene; 2Dr Werneld E. Ngongi; 3Dr Tumaini S. Gurumo; 4Miraji Mkwande
Department of Maritime Transport and Nautical Science, Dar es Salaam Maritime Institute,
P.O. Box 6727,1/19 Sokoine Drive, Dar es Salaam.

Abstract:- Coastal search and rescue (SAR) operations (Andreassen et al., 2020). Additionally, the rapid detection of
are complex, involving dynamic and uncertain conditions distress signals, precise situation evaluation, effective
that demand real-time, effective decision-making. This resource deployment, and efficient response unit
paper aimed to analyze response coordination for real- coordination are all necessary for SAR missions to be
time decision-making in coastal SAR operations using the successful (Alsamhi et al., 2022).
fuzzy logic technique. The main aims of this study were to
identify the key parameters and linguistic variables Technological developments over time, especially in the
critical for effective decision-making in SAR operations domains of robotics and artificial intelligence (AI), have
and finally to design a fuzzy logic model tailored to the created new avenues for improving the efficacy and
dynamic and uncertain conditions inherent in coastal efficiency of SAR operations (Soori et al., 2023). One such
SAR operations. The proposed fuzzy logic model technology that shows promise in this domain is fuzzy logic,
demonstrated improved responsiveness and adaptability a computational paradigm that enables the representation and
to changing conditions, offering a more robust framework processing of uncertain and vague information (Sarihi et al.,
for decision-making in SAR operations. However, this 2023). Fuzzy logic has the potential to enhance real-time
study contributes to enhancing the efficiency and decision-making capabilities, which would increase SAR
effectiveness of real time decision making in SAR teams' adaptability and reactivity in difficult and
operations in coastal environments, with broader unpredictable situations (Malyszko, 2022).
implications for maritime safety.
Furthermore, Technology is essential for improving
Keywords:- Fuzzy Logic, Real-Time Decision Making, SAR teams' capabilities and improving outcomes in
Search and Rescue Operations, Coastal Environments, emergency situations through effective, accurate, and timely
Decision Support System, Response Coordination Model, decision-making (Zawawi et al., 2022). Moreover, over the
Fuzzy Model. years, advancements in communication systems, navigation
technologies, remote sensing, and unmanned aerial vehicles
I. INTRODUCTION (UAVs) have revolutionized SAR operations (Mohsan et al.,
2023), enabling responders to access real-time information,
Risks associated with sea transportation and shipping coordinate efforts, and deploy resources more effectively
include fire, collision, grounding, floods, shifting cargo, man (Damaševičius et al., 2023). In recent years, AI-powered
overboard, and, not limited to, piracy (Barzehkar et al., 2021). technology, such as computer vision and machine learning,
Even with the implementation of new safety regulations and and robotics, have emerged as promising tools for enhancing
guidelines, maritime accidents continue to occur (Kosmas et situational awareness, automating decision-making
al., 2022). Search and rescue (SAR) operations play a critical processes, and enhancing the capabilities of SAR teams
role in saving lives and minimizing casualties in emergencies (Byeon et al., 2023; Mathur et al., 2022).
and disasters worldwide (Hasan et al., 2021). Whether
responding to maritime accidents, natural disasters, or Furthermore, Several authors address how to change the
humanitarian crises, SAR teams face immense challenges in procedure such that the ship assessment process which
coordinating efforts, allocating resources, and making timely determines whether a ship is appropriate for a maritime
decisions in dynamic and uncertain environments (Chitikena search and rescue operation makes the best use of fuzzy logic
et al., 2023). (Uflaz et al., 2023). The researcher states that one of the
action planning elements is choosing the most suitable ships.
Search and rescue operations can occur in various Additionally, the allocation of search and rescue resources is
environments, including urban areas, wilderness areas, and done using a multi-objective approach. (Malyszko, 2022).
maritime environments such as oceans, lakes, and rivers Likewise, the location of search and rescue boats is
(Radojević & Kresojević, 2020). In maritime SAR determined by a number of specific elements, including the
operations, responders often face unique challenges, number and nature of incidents handled in the region of
including vast search areas, adverse weather conditions, interest, resource capacities, topography, and operational
limited visibility, and communication difficulties guidelines of the government. Therefore, it is no longer

IJISRT24SEP738 www.ijisrt.com 986

Volume 9, Issue 9, September– 2024 International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165 https://doi.org/10.38124/ijisrt/IJISRT24SEP738

appropriate to use standard models that exclusively take method was chosen for defuzzification, as it provides a crisp
political decisions into account (Malyszko, 2022). output value that represents the priority of SAR operations.
This method averages the output fuzzy set into a single
Finally, while there is literature on fuzzy logic actionable value, facilitating the real-time decision-making
applications in various domains, including robotics, control process crucial to SAR operations.
systems, and decision support, there is a noticeable gap in
research focusing specifically on its application in SAR A critical step in the Mamdani fuzzy system is the
operations at sea (Nasar et al., 2023). Existing studies defuzzification process, which converts the fuzzy output into
primarily focus on traditional decision-making approaches, a crisp value, enabling actionable decisions in real-time
overlooking the potential benefits of fuzzy logic in enhancing search and rescue (SAR) operations.
the adaptability and strength of SAR systems deployed at sea.
Furthermore, the few studies that do explore the application In the Context of Fuzzy Logic, a Fuzzy Variable can be
of fuzzy logic in SAR operations often lack a comprehensive Represented as:
examination of its effectiveness in real-time decision-making
situations, particularly in dynamic and uncertain maritime A = {𝑥, 𝜇𝐴(𝑥)|𝑥𝜖𝑋} (1)
environments (Li et al., 2024). Thus, there is a clear research
gap in understanding the extent to which fuzzy logic can Where μA(x) is the membership function of the fuzzy
improve decision-making processes for SAR operations at set A, and x is an element of the universal set X. Several
sea. defuzzification methods were considered to derive a crisp
output value xˆ, including:
II. LITERATURE REVIEW
 Center of Gravity Method
In recent years, there has been growing interest in
leveraging advanced technologies, such as fuzzy logic ∫ 𝑥𝜇𝐴(𝑥)𝑥𝜕𝑥
xˆ = 𝑥COG = (2)
modeling, to enhance decision-making capabilities in SAR ∫ 𝑥𝜇𝐴(𝑥)𝜕𝑥
operations (Meziani et al., 2023) .
This method is widely used because it provides a
 Fuzzy Systems balanced representation of the fuzzy set, yielding the center
Fuzzy inference systems (FIS) are computational of mass or centroid.
structures based on the theory of fuzzy sets, if-then rules and
fuzzy logic (Meziani et al., 2023). Since fuzzy systems vary  Medium Method (BOA)
in structure and purpose, different names such as fuzzy expert The medium method calculates xˆBOA is such that:-
system, fuzzy model, fuzzy associative memory, fuzzy logic
controller, fuzzy system and others are use. xˆ = 𝑥BOA (3)

 Mamdani-Type Fuzzy Systems Where 𝑥𝐵𝑜𝐴 is such that

In 1975, Ebrahim Mamdani created a fuzzy system for
𝑥𝐵𝑜𝐴 𝛽
operating a steam engine and a boiler in which the linguistic ∫𝛼 𝜇𝐴(𝑥) 𝜕𝑥 = ∫𝑥𝐵𝑜𝐴 𝜇𝐴(𝑥)𝜕𝑥 (4)
rules were tailored to the operators' human experience,
making it one of the earliest fuzzy set theory-based systems For 𝛼 = min{𝑥|𝑥 ∈ 𝑋} and 𝛽 = max{𝑥|𝑥 ∈ 𝑋}
(Vashishtha et al., 2023). A Mamdani-type fuzzy system
varies from other fuzzy systems in its output variables (Iqbal This method finds the point that devides the area under
et al., 2024). the membership functioninto two equal halves.
In a Mamdani-type fuzzy system, the output variables  Average of Maxima Method
are fuzzy and must be defuzzified using various approaches. The Average of Maxima method compute 𝑥𝐴𝑜𝑀 by
The defuzzification operator employs a variety of ways to averaging the values of 𝑥 that correspond to the highest
convert the output fuzzy variable into a crisp value membership degree
(Starczewski et al., 2020). Two choices are typically
employed for the T-norms and T-conorms: an algebraic ∫ 𝑋′𝑥𝜕𝑥
product for the T-norm and max operator for the T-conorm 𝜇xˆ = 𝑥𝐴𝑜𝑀 = (5)
∫ 𝑋′𝜕𝑥
with a max product for the composition; a min operator for
the T-norm and max operator for the T-conorm and a Where
maximin operator for the composition. Literature contains
additional information about T-norms and T-conorms. 𝑥 = 𝑥 ′ = {𝑥|𝜇𝐴(𝑥) = 𝜇 ∗ ∶ 𝜇 ∗ = 𝑀𝑎𝑥 𝑋 (𝜇𝐴(𝑥))} (6)
Although the model can be produced in various ways using
different operators and compositions, Mamdani-type fuzzy This method averages all points with the maximum
models all include fuzzy sets as output variables, membership grade.
necessitating defuzzification. As per (Sii et al., 2004) there
are numerous techniques available for defuzzifying these
aggregated output fuzzy variables. For this study, the centroid

IJISRT24SEP738 www.ijisrt.com 987

Volume 9, Issue 9, September– 2024 International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165 https://doi.org/10.38124/ijisrt/IJISRT24SEP738

 Min of Maxima (LOM) Method logic to enhance decision making under uncertainty in other
The min of maxima method finds the smallest 𝑥 value emergency response scenarios, suggesting that similar
that corresponds to the maximum membership degree. benefits could be realized in maritime SAR operations. This
Study was aimed to bridge this gap by specifically focusing
xˆ = 𝑥𝐿𝑜𝑀 = min{𝑥|𝜇𝐴(𝑥) = 𝜇 ∗ ∶ 𝜇 ∗= max(𝜇𝐴(𝑥))} (7) on the integration of fuzzy logic in the operational protocols
of SAR activities in Dar es Salaam.
 Max of Maxima (MOM) Method
In the contrast, the max of maxima method takes the III. MATERIAL AND METHODS
lagest 𝑥 value that corresponds to the maximum membership
degree. The study was carried out in the coastal waters of Dar
es Salaam. These regions are known for their high incidence
xˆ = 𝑥𝑀𝑜𝑀 = max{𝑥|𝜇𝐴(𝑥) = 𝜇 ∗ ∶ 𝜇 ∗= max(𝜇𝐴(𝑥))} (8) of maritime accidents, presenting an ideal environment for
testing the efficacy of the fuzzy logic model. The study
Existing research on the application of fuzzy logic focused on operations led by the Tanzania Ports Authority,
technique for real-time decision-making in SAR operations Tanzania Naval Force, and various local rescue agencies,
was examined in this literature review. By identifying key with an emphasis on response coordination and resource
concepts, methodologies, and findings from a previous allocation in real-time SAR operations.
research paper, this study seeks to shed light on the current
state of the art and identify potential future research areas. The research employed a mixed-methods approach to
ensure both depth and breadth in data collection and analysis.
The review was commenced with an analysis of the Qualitative data was collected via in-depth interviews with
fundamental principles of fuzzy logic and its applicability to SAR personnel to gain insights into the challenges and
decision-making in unpredictable environments, with a decision-making frameworks used in real-time operations.
particular focus on the marine domain. The section then Quantitative data, on the other hand, was gathered through
investigates into the application of the Fuzzy logic concept to structured surveys aimed at identifying key factors
the coordination of SAR operations involving numerous influencing SAR decision-making.
autonomous agents. Following this, the review was examined
particular implementations of fuzzy logic technique in search Primary data was collected from SAR personnel
and rescue (SAR) at sea. It was emphasized the difficulties, through structured questionnaires and interviews, which
potential advantages, and consequences that arise from the targeted a wide range of respondents, including SAR
integration of these technologies. commanders, operators, and maritime officials. The
qualitative interviews were designed to explore the
Extensive literature highlights the application of fuzzy experiences and perceptions of SAR personnel regarding
logic in various fields requiring real time decision making, decision-making in unpredictable environments. However,
including, heartcare, automotives safety systems, and Secondary data was obtained from SAR operational reports,
financial services. However, its application in maritime SAR previous studies, and maritime accident records, offering a
operations has been limited. Study such as those by comparative backdrop for evaluating the fuzzy logic model.
(Malyszko, 2021) have demonstrated the potential of fuzzy

Table 1 Research Variables and Associated Studies

Variables Literature Source
Weather condition (wind, currant, fog and Rain) (Malkoç & Oskar Eikenbroek ir Eric van Berkum, 2023)
Distance to Distressed Target (Based on time of Distress and speed) (Malkoç & Oskar Eikenbroek ir Eric van Berkum, 2023)
SAR Personnel Equipment (Personal protective equipment, & (Blitch, 1996; Malkoç & Oskar Eikenbroek ir Eric van
personal survival equipment) Berkum, 2023)
Distress Type (Su et al., 2019)
Source : Field Data (2024)

The quantitative data were analyzed using SPSS traditional SAR methods and fuzzy logic-enhanced decision-
(Statistical Package for the Social Sciences) to perform making. Finally, the study utilized MATLAB, specifically the
descriptive statistical analysis, including frequency Mamdani Fuzzy Inference System (FIS), to develop and
distributions and correlation tests. SPSS was used to establish simulate the fuzzy logic model. Mamdani's method was
the relationships between different variables such as weather chosen because it is highly interpretable and allows for
conditions, proximity to distress sites, and the availability of human reasoning to be encoded into the decision-making
resources, offering a baseline for comparison between process through a set of IF-THEN rules.

IJISRT24SEP738 www.ijisrt.com 988

Volume 9, Issue 9, September– 2024 International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165 https://doi.org/10.38124/ijisrt/IJISRT24SEP738

 Methodological Flow Chart

Fig 1 Model Methodological Framework

Source : Field Data (2024)

IV. RESULTS Indian ocean at Dar es salaam. These factors were gathered
through interviews with SAR personnel. Reseacher were
 Variable to Consider in Response Coordination for using this factor as the variable in designing a model for real
Search and Rescue Operation. time decision making in coastal search and rescue operation.
After data collectin and analysis, in this study identified This factors includes Weather conditions, SAR resource
several key factors that are essential for effective decision available, Distress type, severity of Distress and Distance
making in Roperations, particularly in the context of the from the distressed target.

IJISRT24SEP738 www.ijisrt.com 989

Volume 9, Issue 9, September– 2024 International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165 https://doi.org/10.38124/ijisrt/IJISRT24SEP738

Fig 2 Variable to Consider in Response Coordination for Search and Rescue Operation
Source : Field Data (2024)

In order to investigate the frequency with which weather gathered from 44 respondents for the first specified objective
variables (such as wind speed and visibility) are taken into where by the interview and questioner were used to
account when making decisions for SAR operations, data was investigate these parameters.

Fig 3 Weather Conditions

According to (Zhou et al., 2020), the coordination and  Vessel Characteristics

implementation of coastal search and rescue (SAR) In this investigation interview were used to study this
operations are significantly influenced by meteorological variable. The Figure below summarises the responses of 44
conditions. Because coastal areas are dynamic, SAR teams participants. The majority of respondents acknowledged that
must constantly watch the weather and adjust their tactics to vessel characteristics have a substantial impact on decision-
keep their operations safe and effective. SAR personnel may making during SAR operations, according to the report.
find it challenging to locate victims or manoeuvre safely According to (Queralta et al., 2020), the response
when there is severe visibility reduction due to fog, snow, or coordination and real-time decision-making process in search
rain. Poor visibility can cause response times to be delayed, and rescue (SAR) operations are greatly impacted by vessel
as SAR units may need to wait for conditions to improve parameters, including size, type, speed, and manoeuvrability.
before beginning their search (Fjørtoft & Berg, 2020),.

IJISRT24SEP738 www.ijisrt.com 990

Volume 9, Issue 9, September– 2024 International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165 https://doi.org/10.38124/ijisrt/IJISRT24SEP738

Fig 4 Vessel Characteristics

Source: Field Data (2024)

The size of a vessel determines its stability in rough rescues. Finally, Real-time decision-making entails
seas, the number of survivors it can accommodate, and the determining the appropriate type of vessel based on the
type of equipment it can carry. Larger vessels offer more circumstances of the situation. Specialised vessels may be
space and stability but may have limitations in shallow waters prioritised for operations that need specific skills, such as
or tight spaces. Additionally, the type of vessel, including its medical evacuations or deep-sea rescues.
design and purpose (e.g., rescue boat, patrol boat, or
helicopter), influences its capability for various SAR  Distance of the SAR Boat to the Distressed Vessel
scenarios. Specialised vessels outfitted with innovative According to the data, most responders take the
technology, medical facilities, or diving equipment can Distance into account when making decisions about SAR
considerably improve the success of rescue operations. missions. this indicates that a sizable majority (73.8%)
However, vessel's speed and manoeuvrability determine how regularly takes distance proximity to distressed vessel into
soon it can reach the emergency area and navigate through account, highlighting the crucial role that Distance to
difficult conditions. High-speed vessels can travel long distressed vessel play in search and rescue operations.
distances quickly, which is essential for time-sensitive

Fig 5 Proximity of the Distressed Vessel.

Source: Field Data (2024)

IJISRT24SEP738 www.ijisrt.com 991

Volume 9, Issue 9, September– 2024 International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165 https://doi.org/10.38124/ijisrt/IJISRT24SEP738

According to Storvik, (2020), the closer a vessel is to weather. Additionally, the availability of necessary
the coast; the faster rescue workers can get there. This can equipment and resources such as firefighting gear, medical
have a substantial influence on the outcome of the rescue supplies and towing capability is one of the factors to
attempt, especially in time-critical scenarios. This indicate consider based on the type of distress. However, Weather,
that distance is one of the factors that the rescue team consider sea state and visibility can significantly impact the feasibility
before acknowledge the message of SAR missions. and safety of the SAR operation. In certain scenarios, like
Additionally, proximity to the coastline affects the type and piracy or terrorism coordination with security forces and
number of resources required. other agencies is crucial and will require time and lead for
delay in search and rescue operation, Finally, Effective
 Distress Type communication with the distressed vessel and accurate
The response coordination and real-time decision- navigation are essential for successful SAR operations. By
making process in search and rescue (SAR) operations are considering these factors, SAR teams can make informed,
greatly impacted by vessel parameters, including Fire, real-time decisions to effectively respond to various types of
collision, Grounding, Flooding, shifting of cargo, man marine distress and enhance the chances of a successful
overboard, Piracy, Engine Failure, Capsizing, Sinking, rescue operation.
Medical Emergency, Severe Weather, Lost of
communication, Navigation Hazard, Structure Damage, Fuel  Response Coordination Model
shortage, Unmanned Vessel, Terrorism, Pollution Incident In this study, the SAR fuzzy logic model was designed
and Mechanical Failure. using MATLAB's Fuzzy Inference System (FIS) toolbox
using Mamdani minimum-maximum inference engine based
According to (Caulfield et al., 2023) the extent and on linguistic variables and membership functions
severity of the distress impact the urgency and type of (MathWorks, 2016). This system was using IF-THEN rules
response required. Ensuring the safety of the SAR team is formulated using expert knowledge and domain-specific
paramount, especially in case like fire, piracy and severe heuristics to make decisions in SAR operations.

Table 2 Input and Output Variables used in the Model Design in Fuzzy Control
Input Variables Output Variable
Proximity Distance to Distressed vessel
Distress Severity Urgency level (Low, Medium and High)
Environmental Visibility
Resource Availability
Source: Research Data, 2024

The input and output variables that were considered in also was categorized based on the number of variables
fuzzy model was Weather condition, Distance to Distressed obtained from the questioner to characterize all the possible
Target, Severity of distress and Resource availability fuzzy output. Additionally, the fuzzy model was trained using
according to interview made from the experts. The numerical the triangular membership function for both the input and
input and output variables were transformed in fuzzy output parameters. The choice of the number of membership
variables then were described using linguistic terms, which functions and their initial values were based on the
was used to describe all the possible fuzzy inputs. The output knowledge of the system and experimental conditions.

Fig 6 Input and Output Variables and Parameter in the Fuzzy Logic Designer
Source: Research (2024)

IJISRT24SEP738 www.ijisrt.com 992

Volume 9, Issue 9, September– 2024 International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165 https://doi.org/10.38124/ijisrt/IJISRT24SEP738

The developed fuzzy model was relied on number of  IF the weather is Good AND proximity is Near AND
fuzzy roles generated by the rule editor to describe all resources are High, THEN the urgency level is High.
relationships between the input and output variables.  IF the weather is Bad AND proximity is Far AND
Moreover, the knowledge and experience of SAR operators resources are Low, THEN the Urgency level is Low.
and Experts from Dar es salaam Search and rescue were  IF the vessel is Large AND proximity is Medium, THEN
adopted to develop rules, Construct Rule Base and Formulate the response priority is Medium.
a set of fuzzy if-then rules. The fuzzy logic system employed
a set of IF-THEN rules to model the decision-making These rules allowed the system to infer appropriate
process. Examples of rules included: rescue actions under various SAR conditions.

Fig 7 Fuzzy Rules Set in the Fuzzy Rule Editor.

Finally, Center of Gravity (COG) was used, which is the SAR operations as it ensured that decisions were made based
most popular defuzzification method for obtaining a real on comprehencive assessment of the input variables. Other
value (numerical) output.. methods such as min of maxima and max of maxima, were
considered but deemed less suitable as they focus on extremes
For this study, the centre of gravity method was chosed rather than the overall distribution of the membership
for defuzzification due to its stability to provide a balanced function. The resulting clipped membership functions of all
and well representative output, considering the entire shape the consequents were taken and combined into a single
of the fuzzy set. This method was deal for our application in aggregated output.

Table 3 The Linguistic Variables for Both Inputs and Outputs were Distribute
Input Variables Linguistic Variables Membership Functions Common Type
Distance Close 0 0 25 Triangular
Medium 25 50 75
Far 50 100 100
Weather condition Poor 0 0 25 Triangular
Fair 25 50 75
Good 50 100 100
Distress Severity Low 0 0 25 Triangular
Medium 25 50 75
High 50 100 100
Resource Availability Limited 0 0 25 Triangular
Adequate 25 50 75
Abundant 50 100 100
Output Variable
Urgency Level Low 0 0 25 Trapezoidal Function
Medium 25 50 75
High 50 100 100
Source: Field Data: (2024)

IJISRT24SEP738 www.ijisrt.com 993

Volume 9, Issue 9, September– 2024 International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165 https://doi.org/10.38124/ijisrt/IJISRT24SEP738

The range of value for the corresponding Severity of team required to take other alternative action in order to
distress, Weather conditions and urgency level is shown in ensure safety for him/herself. Rescue operation in this rescue
the figure 8 The result in the figure with value ranges indicate vessel should be avoided because of the occurrence of risk to
that if Urgency level in term of probability of risk to occur their vessel is high. The relay of massage to nearable ship is
and weather conditions is poor and Severity of distress is high preferable. the following key findings were observed.
the urgency level will be high. This indicate that the Rescue

Fig 8 Fuzzy viewer Indicating how the Input Variable Control the Output

 Simulink Model to Run and Testing a Search and Rescue environment for modelling, simulating and analyzing multi
Model domain dynamic systems. Where by the input variable are
After the model design accomplished, the SAR fuzzy Composite and sent to the fuzzy logic controller while the
model was simulated in the Simulink environment of the output is captured in the display box. If it apparent that there
MATLAB software which is a graphical programing is a close.

Fig 9 Simulink Model Blockto Run and Test the SAR Response Coordination Model

The model demonstrated a high level of adaptability to SAR scenarios. This led to more reliable decision-making
changing conditions, crucial for real-time SAR operations. outcomes compared to traditional methods. Moreover, the
The simulations showed that the model could adjust decision integration with Simulink provided a powerful platform for
outputs in real-time, improving response efficiency. testing and validating the model in various simulated
Additionally, the fuzzy logic model effectively managed environments, highlighting its practical application in real-
uncertainty and imprecise data, which are common in coastal world SAR operations.

IJISRT24SEP738 www.ijisrt.com 994

Volume 9, Issue 9, September– 2024 International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165 https://doi.org/10.38124/ijisrt/IJISRT24SEP738

Fig 10 Simulink Model Display the SAR Response Coodination Model

Additionally, Further investigation could explore why decision support systems, hurdles such as training, system
some SAR operations have adopted fuzzy logic and others availability, and awareness may need to be addressed.
have not. Factors such as cost, ease of implementation, and Furthermore, establishing the efficacy of these technologies
perceived benefits versus limitations could be relevant. through case studies and comparative research may drive
Finally, in order to increase acceptance of fuzzy logic-based wider use.

Fig 11 Severity of Distress, Weather Conditions and Urgency level in the Surface Rule Display Window

IJISRT24SEP738 www.ijisrt.com 995

Volume 9, Issue 9, September– 2024 International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165 https://doi.org/10.38124/ijisrt/IJISRT24SEP738

Table 4 Model Analysis Formula

Parameter Description Equation
Coefficient of Measure a degree of correlation between the [∑𝑁
𝑖−1(𝑃1 −𝑃)(𝑄1 −𝑄)]
2
𝑅2 = ∑𝑁
(1)
Determination (R2) experimental and predicted values 2
𝑖−1(𝑃1 −𝑃) (𝑄1 −𝑄)
2

Root mean square error Measure the error in the same units as the variable 1
between the experimental and predicted values 𝑅𝑀𝑆𝐸 = √ ∑𝑁
𝑖−1(𝑃1 − 𝑄1 )
2
(2)
𝑁
Mean absolute error Measure the average magnitude of the errors in a set of 1
𝑀𝐴𝐸 = 𝑁 ∑𝑁
𝑖−1|𝑃1 − 𝑄1 | (3)
(MAE) forecasts without taking into consideration their direction
Model efficiency (ME) Measures the efficiency between the experimental and ∑𝑁
𝑖−1(𝑄1 −𝑃1 )
2
𝑀𝐸 = 1 − ∑𝑁 2 (4)
predicted values 𝑖−1(𝑄1 −𝑄)
Overall Index (OI) Measure the performance of the mathematical models 1 𝑅𝑀𝑆𝐸
𝑂𝐼 = (1 − ( ) + 𝑀𝐸) (5)
and fitting between the experimental and predicted values 2 𝑄𝑚𝑎𝑥 −𝑄𝑀𝐼𝑁

V. DISCUSSION This study also highlights the potential for further

development of fuzzy logic models within SAR frameworks.
The findings of this study illustrate the significant Refining the input parameters and enhancing the integration
advantages of employing fuzzy logic for decision-making in of real-time data streams, such as meteorological updates or
coastal search and rescue (SAR) operations, particularly vessel tracking systems, could further optimize the decision-
when contrasted with traditional methodologies. Traditional making process. The promising results obtained suggest that
SAR decision-making frameworks often rely on rigid, binary the adoption of fuzzy logic systems in SAR operations could
processes that are ill-equipped to handle the complexities and markedly improve outcomes, potentially leading to faster
uncertainties characteristic of maritime environments. These response times and more lives saved.
conventional methods frequently lead to delays and
suboptimal outcomes, especially under rapidly changing VI. CONCLUSION
conditions.
This research underscores the transformative potential
The fuzzy logic model developed in this study, by of fuzzy logic in refining real-time decision-making for
contrast, proved adept at managing multiple, interrelated coastal search and rescue (SAR) operations. By incorporating
variables simultaneously, providing a level of flexibility that a diverse set of critical parameters ranging from
is critical in dynamic SAR contexts. The model’s ability to meteorological conditions to resource availability the fuzzy
incorporate parameters such as weather conditions, proximity logic model demonstrated superior adaptability and precision,
to distressed vessels, and resource availability allowed for a significantly outpacing traditional SAR methodologies. Its
more nuanced approach to prioritizing rescue operations. ability to dynamically respond to the inherent uncertainties of
Notably, the use of fuzzy sets and inference rules enabled the maritime environments underscores its relevance as a robust
system to make real-time adjustments, improving the overall decision-support tool.
responsiveness of SAR efforts.
The findings suggest that integrating such
The application of the Mamdani-type Fuzzy Inference computational intelligence could drastically elevate SAR
System (FIS) and defuzzification through the Center of efficiency, with future studies warranted to explore its
Gravity (COG) method provided actionable output values practical deployment in live operational contexts and further
that were representative of the broader context in which refine its algorithms for optimized performance. Moreover,
decisions were made. This approach contrasts sharply with based on the time limit and financial constraint this study
traditional binary models, which are often forced to make focused on the coastal waters of the Indian ocean near Dar es
decisions based on incomplete or static data. In scenarios salaam and made the design of a simple SAR fuzzy model for
simulated using Simulink, the fuzzy logic model real time decision making for response coordination in search
demonstrated its capability to adapt in real time, dynamically and rescue operation. However, Father research and
recalculating decision priorities as variables fluctuated. development should undertake to explore the integration of
fuzzy logic with existing SAR technologies, such as GPS,
However, despite these advantages, certain challenges Automatic Identification Systems (AIS), ECDS,
persist. The practical deployment of fuzzy logic in real-world communication systems, Artificial Intelligence, data feed
SAR operations necessitates access to advanced from sensor, satellite and machine learning Algorithms. This
computational resources and extensive training for personnel, could enhance the model’s predictive capabilities and lead to
who must be able to interpret and act on the system’s outputs. creation of more sophisticated decision support system that
Additionally, while the simulations provided robust evidence enhance the overall efficiency of SAR operations.
of the model’s efficacy, further field tests in live SAR
scenarios are essential to fully validate its utility under the
unpredictable conditions typical of maritime emergencies.

IJISRT24SEP738 www.ijisrt.com 996

Volume 9, Issue 9, September– 2024 International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165 https://doi.org/10.38124/ijisrt/IJISRT24SEP738

REFERENCES [13]. Li, Y., Song, G., Yip, T.-L., & Yeo, G.-T. (2024).
Fuzzy Logic-Based Decision-Making Method for
[1]. Alsamhi, S. H., Shvetsov, A. V, Kumar, S., Shvetsova, Ultra-Large Ship Berthing Using Pilotage Data.
S. V, Alhartomi, M. A., Hawbani, A., Rajput, N. S., Journal of Marine Science and Engineering, 12(5),
Srivastava, S., Saif, A., & Nyangaresi, V. O. (2022). 717.
UAV computing-assisted search and rescue mission [14]. Malkoç, S., & Oskar Eikenbroek ir Eric van Berkum,
framework for disaster and harsh environment ir. (2023). Fuzzy Logic Modelling of Route Choice in
mitigation. Drones, 6(7), 154. a Transportation Network.
[2]. Andreassen, N., Borch, O. J., & Sydnes, A. K. (2020). [15]. Malyszko, M. (2021). Fuzzy logic in selection of
Information sharing and emergency response maritime search and rescue units. Applied Sciences,
coordination. Safety Science, 130, 104895. 12(1), 21.
[3]. Barzehkar, M., Parnell, K. E., Soomere, T., [16]. Malyszko, M. (2022). Fuzzy Logic in Selection of
Dragovich, D., & Engström, J. (2021). Decision Maritime Search and Rescue Units. Applied Sciences
support tools, systems and indices for sustainable (Switzerland), 12(1), 1–18.
coastal planning and management: A review. Ocean & https://doi.org/10.3390/app12010021
Coastal Management, 212, 105813. [17]. Mathur, G. C. A., Srivastava, M. S. K., & Prabu, M. I.
[4]. Blitch, J. G. (1996). Artificial intelligence (2022). LEVERAGING TECHNOLOGICAL
technologies for robot assisted urban search and ADVANCES IN C4ISR TO ENHANCE
rescue. Expert Systems with Applications, 11(2), 109– SITUATIONAL AWARENESS AND DECISION
124. https://doi.org/10.1016/0957-4174(96)00038-3 MAKING. SYNERGY, 59.
[5]. Byeon, H., Thingom, C., Keshta, I., Soni, M., Hannan, [18]. Meziani, A., Bourouis, A., & Chebout, M. S. (2023).
S. A., & Surbakti, H. (2023). A logic Petri net model NeutroMAS4SCRM: a combined multi-agent system
for dynamic multi-agent game decision-making. with neutrosophic data analytic hierarchy process
Decision Analytics Journal, 9(June), 100320. framework for supply chain risk management. Journal
https://doi.org/10.1016/j.dajour.2023.100320 of Intelligent & Fuzzy Systems, 44(3), 3695–3716.
[6]. Caulfield, R., Wiseman, T., Gullick, J., & Ogilvie, R. [19]. Mohsan, S. A. H., Othman, N. Q. H., Li, Y., Alsharif,
(2023). Factors preceding occupational distress in M. H., & Khan, M. A. (2023). Unmanned aerial
emergency nurses: An integrative review. Journal of vehicles (UAVs): Practical aspects, applications, open
Clinical Nursing, 32(13–14), 3341–3360. challenges, security issues, and future trends.
[7]. Chitikena, H., Sanfilippo, F., & Ma, S. (2023). Intelligent Service Robotics, 16(1), 109–137.
Robotics in search and rescue (SAR) operations: An [20]. Nasar, W., Da Silva Torres, R., Gundersen, O. E., &
ethical and Design Perspective Framework for Karlsen, A. T. (2023). The Use of Decision Support in
Response Phase. Applied Sciences, 13(3), 1800. Search and Rescue: A Systematic Literature Review.
[8]. Damaševičius, R., Bacanin, N., & Misra, S. (2023). ISPRS International Journal of Geo-Information,
From sensors to safety: Internet of Emergency 12(5), 182.
Services (IoES) for emergency response and disaster [21]. Queralta, J. P., Taipalmaa, J., Pullinen, B. C., Sarker,
management. Journal of Sensor and Actuator V. K., Gia, T. N., Tenhunen, H., Gabbouj, M.,
Networks, 12(3), 41. Raitoharju, J., & Westerlund, T. (2020). Collaborative
[9]. Fjørtoft, K., & Berg, T. E. (2020). Handling the multi-robot systems for search and rescue:
preparedness challenges for maritime and offshore Coordination and perception. ArXiv Preprint
operations in Arctic waters. Arctic Marine ArXiv:2008.12610.
Sustainability: Arctic Maritime Businesses and the [22]. Radojević, S., & Kresojević, M. (2020). Saving
Resilience of the Marine Environment, 187–212. migrants from the sea: improving training for search
[10]. Hasan, M. M., Rahman, M. A., Sedigh, A., Khasanah, and rescue operations. TransNav, International
A. U., Asyhari, A. T., Tao, H., & Bakar, S. A. (2021). Journal on Marine Navigation and Safety Od Sea
Search and rescue operation in flooded areas: A survey Transportation, 14(1), 129–133.
on emerging sensor networking-enabled IoT-oriented [23]. Sarihi, M., Shahhosseini, V., & Banki, M. T. (2023).
technologies and applications. Cognitive Systems Development and comparative analysis of the fuzzy
Research, 67, 104–123. inference system-based construction labor
[11]. Iqbal, S., Qureshi, A. N., Aurangzeb, K., Alhussein, productivity models. International Journal of
M., Wang, S., Anwar, M. S., & Khan, F. (2024). Construction Management, 23(3), 423–433.
Hybrid Parallel Fuzzy CNN Paradigm: Unmasking [24]. Sii, H. S., Wang, J., Ruxton, T., Yang, J. B., & Liu, J.
Intricacies for Accurate Brain MRI Insights. IEEE (2004). Use of fuzzy logic approaches to safety
Transactions on Fuzzy Systems. assessment in maritime engineering applications.
[12]. Kosmas, V., Acciaro, M., & Besiou, M. (2022). Journal of Marine Engineering and Technology, 3(2),
Saving migrants’ lives at sea: Improving search and 45–58.
rescue operations. Production and Operations https://doi.org/10.1080/20464177.2004.11020182
Management, 31(4), 1872–1889. [25]. Soori, M., Arezoo, B., & Dastres, R. (2023). Artificial
intelligence, machine learning and deep learning in
advanced robotics, a review. Cognitive Robotics.

IJISRT24SEP738 www.ijisrt.com 997

Volume 9, Issue 9, September– 2024 International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165 https://doi.org/10.38124/ijisrt/IJISRT24SEP738

[26]. Starczewski, J. T., Goetzen, P., & Napoli, C. (2020).

Triangular fuzzy-rough set based fuzzification of
fuzzy rule-based systems. Journal of Artificial
Intelligence and Soft Computing Research, 10(4),
271–285.
[27]. Storvik, M. H. R. (2020). Case-Based Reasoning for
Decision Support in Search and Rescue. NTNU.
[28]. Su, C. M., Chang, K. Y., Kao, S. L., & Lin, C. (2019).
A study on seaworthiness of the Kinmen-Xiamen
fairways by fuzzy method. Journal of Marine Science
and Technology (Taiwan), 27(1), 1–7.
https://doi.org/10.6119/JMST.201902_27(1).0001
[29]. Uflaz, E., Celik, E., Aydin, M., Erdem, P., Akyuz, E.,
Arslan, O., Kurt, R. E., & Turan, O. (2023). An
extended human reliability analysing under fuzzy
logic environment for ship navigation. Australian
Journal of Maritime & Ocean Affairs, 15(2), 189–209.
[30]. Vashishtha, S., Gupta, V., & Mittal, M. (2023).
Sentiment analysis using fuzzy logic: A
comprehensive literature review. Wiley
Interdisciplinary Reviews: Data Mining and
Knowledge Discovery, 13(5), e1509.
[31]. Zawawi, A. A., Ab Halim, N., Kamarunzaman, N. Z.,
& Zawawi, A. A. (2022). The Roles of Technology
Compatibility and Relational Boundary on the
Performance of Rescue Frontliners. Global Business
& Management Research, 14(1).
[32]. Zhou, X., Cheng, L., Min, K., Zuo, X., Yan, Z., Ruan,
X., Chu, S., & Li, M. (2020). A framework for
assessing the capability of maritime search and rescue
in the south China sea. International Journal of
Disaster Risk Reduction, 47, 101568.

IJISRT24SEP738 www.ijisrt.com 998