Authors :
James, G. G.; Chukwu, E. G.; Ekwe, P. O.; ASOGWA, E. C.; DARLINGTON, C. H
Volume/Issue :
Volume 8 - 2023, Issue 6 - June
Google Scholar :
https://bit.ly/3TmGbDi
Scribd :
https://tinyurl.com/3kmu8zbc
DOI :
https://doi.org/10.5281/zenodo.8126451
Abstract :
The search for quick detection and solution of
Lung cancer is traced back to the Stone Age by medical
experts and health workers. Often time, patients are
confronted with the challenges of running through
different medical outfits and spending a lot of money to
fight the deadly disease and still ended up in their
untimely grave. This is not because the medical experts
could not handle the patient appropriately, but because
the disease has gotten to the final or terminal stage, and
at this point it is irreversible. The quest to reduce the
challenges faced by patients and medical experts to get a
timely solution to the diagnosis or detection of lung
cancer in other to save the life of the patient has
motivated this research. The work aims at designing and
implementing an intelligent-based system for the
diagnosis of lung cancer driven by fuzzy c-means
algorithm.The methodology used was Object-Oriente
Analysis and Design (OOAD). The fuzzy model was
designed in three main stages includingfuzzification,
FCM inference system, and defuzzification. The
triangular membership (Tmf) function was used to map
the input parameters to the output parameter. The FIS
model was designed using Mamdani’s inference
mechanism. C# programming language was used on a
windows 10 platform to integrate the Matlab FIS output
for better performance and MySQL database 5.7.14
from WAMP server 3.0.6 was used as the back-end
engine. To validate this work, data was captured directly
from the 50 volunteers. The training, testing, and
checking FCM KMSI values of 0.00123, 0.03123, and
0.06301 respectively were observed in the process at 150
epochs and an average error of 0.0002102 was observed
at 300 epochs.
Keywords :
Fuzzy Cluster Means Algorithm, Cancer Detection, Fuzzification, Intelligent System.
The search for quick detection and solution of
Lung cancer is traced back to the Stone Age by medical
experts and health workers. Often time, patients are
confronted with the challenges of running through
different medical outfits and spending a lot of money to
fight the deadly disease and still ended up in their
untimely grave. This is not because the medical experts
could not handle the patient appropriately, but because
the disease has gotten to the final or terminal stage, and
at this point it is irreversible. The quest to reduce the
challenges faced by patients and medical experts to get a
timely solution to the diagnosis or detection of lung
cancer in other to save the life of the patient has
motivated this research. The work aims at designing and
implementing an intelligent-based system for the
diagnosis of lung cancer driven by fuzzy c-means
algorithm.The methodology used was Object-Oriente
Analysis and Design (OOAD). The fuzzy model was
designed in three main stages includingfuzzification,
FCM inference system, and defuzzification. The
triangular membership (Tmf) function was used to map
the input parameters to the output parameter. The FIS
model was designed using Mamdani’s inference
mechanism. C# programming language was used on a
windows 10 platform to integrate the Matlab FIS output
for better performance and MySQL database 5.7.14
from WAMP server 3.0.6 was used as the back-end
engine. To validate this work, data was captured directly
from the 50 volunteers. The training, testing, and
checking FCM KMSI values of 0.00123, 0.03123, and
0.06301 respectively were observed in the process at 150
epochs and an average error of 0.0002102 was observed
at 300 epochs.
Keywords :
Fuzzy Cluster Means Algorithm, Cancer Detection, Fuzzification, Intelligent System.
