Development of Diagnostic System for Brain MRI Scanning Based on Robust Information Clustering

Brain problem has led to the death of many people in our society. The causes of brain problem are hard drugs, taking Indian hem, accidents and not having a good identifying machine that could scan and identify this problem fast before it could be worst. This can be overcome by development of diagnostic system for brain MRI scanning based on robust information clustering. This is done by designing a membership function that would analyze the symptoms in the brain, designing a rule that enhances the diagnosization of the brain symptoms, training these rules in ANN to enhance the efficiency of the diagnosization, designing an intelligent sensor for brain MRI scanning based on robust information clustering, designing a visual basic for development of diagnostic system for brain MRI Scanning based on robust information clustering and designing a Simulink model for development of diagnostic system for brain MRI scanning based on robust information clustering. The result obtained shows that using robust information gives faster identification of problem in the brain than any other conventional one.


INTRODUCTION
Development of diagnostic system for brain MRI scanning based on robust information clustering is the topic of this project. Brain problem has become a severe threat to human lives due to its prevalence. According to the British brain Society, the estimated number of new cases, for all types of brain problem in the world for the year 2017 is over 2,550,110, and the estimated number of deaths from brain problem is 780,350. In men, brain fake is the most prevalent brain problem which has arisen as a result of smoking Indian hem and taking dangerous drugs. The estimated new cases of men brain problem are 1,550,90, which is the highest number among all types of brain problem (Which is at about 60%.).

Literature Review
Alzheimer's Disease (AD) is a neurological disorder that mostly affects people over 65 years old and whose incidence rate grows exponentially with age, almost doubling in every 5 years. (Brookmeyer, 2015). Although it has been described for the first time more than 100 years ago, by Alois Alzheimer, only in the last 30 years its causes, symptoms, risk factors and treatment have been intensively investigated. Still, apart from a few exceptions, the factors that trigger the onset of AD remain unknown (Alzheimer's,2016). It is a progressive disease, meaning that it worsens over time, and for which there is currently no cure, leading eventually to death. The very early stages are often mistakenly confused with the normal process of ageing or linked to stress and it is often characterized by episodic losses of short term memory and difficulty to grasp new ideas. This preclinical stage is also known as Mild Cognitive Impairment (MCI). As the brain damage progresses, other cognitive impairments appear and the disease becomes obvious. In the late stages, individuals are completely dependent on caregivers even for the most basic daily tasks such as eating, bathing or dressing. Moreover, motor skills are affected and patients become more vulnerable to infections. Pneumonia, a lung infection, is one of the most frequent direct causes of death (Wimo, 2016).
Finally, a lot of authors have used different diagnostic approaches on brain; some of these renowned authors are (Samphson,2014) who used optimized method in computerized diagnostic system for brain MRI scanning based on robust information cluster and could only get 32% achievement. (Donard,2016) used genetic approach in

IJTSRD23184
International Journal of Trend in Scientific Research and Development (IJTSRD) @ www.ijtsrd.com eISSN: 2456-6470 Page: 866 computerized diagnostic system for brain MRI scanning based on robust information cluster and achieved at about 41% efficiency. (Leo, 2015) used proportional integral in the same diagnostic system but could only achieve 38%. This inefficiency in the diagnostic approach has led to the death of many innocent Nigerians. This ugly situation that has led to the death of some Nigerians can be overcome by development of diagnostic system for brain MRI scanning based on robust information clustering using intelligent agent.

Methodology
To design a membership function that would analyze the symptoms in the brain To design a rule that enhances the diagnosization of the brain symptoms To design an intelligent sensor for brain MRI scanning based on robust information clustering.  Fig 4 also shows that when the sensor indicates green light, it shows that no brain symptom is observed by the sensor. To design a Simulink model for development diagnostic system for brain MRI scanning without robust information clustering  Table 1 shows the simulated result obtained in designed Simulink model for development diagnostic system for brain MRI scanning without robust information.

To design a visual basic development of diagnostic system for brain MRI Scanning based on robust information clustering
To design a Simulink model for development diagnostic system for brain MRI scanning based on robust information clustering  Table 2 shows the simulated result gotten when robust information clustering is incorporated in the system.      6). With this result obtained using robust information identifies brain problem faster than when robust information is not used.

Conclusion
The not identifying brain problem at a faster rate has led to the dying of some innocent souls in our country Nigeria. This unfortunate incidence can be overcome by development of diagnostic system for brain MRI scanning based on robust information clustering. This is done by designing a membership function that would analyze the symptoms in the brain, designing a rule that enhances the diagnosization of the brain symptoms, training these rules in ANN to enhance the efficiency of the diagnosization, designing an intelligent sensor for brain MRI scanning based on robust information clustering, designing a visual basic for development of diagnostic system for brain MRI Scanning based on robust information clustering and designing a Simulink model for development of diagnostic system for brain MRI scanning based on robust information cluster