BRAIN AGE PREDICTION USING MACHINE LEARNING
1SOWMIYA S R, 2GAYITRI N, 3SRAVYA P, 4HANNA P, 5NAGASUDHA P
1Faculty of Computer Science & Engineering, Dhanalakshmi Srinivasan Engineering College, Perambalur.
2Computer Science & Engineering, Dhanalakshmi Srinivasan Engineering College, Perambalur.
3Computer Science & Engineering, Dhanalakshmi Srinivasan Engineering College, Perambalur.
4Computer Science & Engineering, Dhanalakshmi Srinivasan Engineering College, Perambalur.
5Computer Science & Engineering, Dhanalakshmi Srinivasan Engineering College, Perambalur.
Dhanalakshmi Srinivasan Engineering College (AUTONOMOUS),Perambalur-621212
ABSTRACT: Aging is the process of getting older but when we discuss about ageing the main theme to know about the chronological age and biological age. Chronological age is the time that has passed from an individual’s birth. Biological age is the aging occurs moderately accumulating damage to various tissues and cells. There is a connection between chronological age and biological age. In addition to biological aging it is a concept of normal ageing and abnormal ageing i.e., experiencing abnormal ageing or ageing faster. Aging has a impact on the brain and with increasing age it can cause degenerative disease like Alzheimer’s disease. The effects of age on the brain or any abnormal activities in brain can be detected by some parameters like (gender, age factor, stress level, based on smoking, BMI, glucose). There are many methods in predict the brain age, by extracting the values from resources like (MRI and CT scan). Convolutional neural networks and Machine learning are the methods that are popular in computer vision. The prediction accuracy level in the brain age estimation frameworks is associated with different Machine learning algorithms such as Decision Tree, SVC (Support Vector Classifier), Passive Aggressive, Adaboost Classifier.
KEYWORDS: Aging, Chronological Age, SVC, Decision Tree, Passive Aggressive, Adaboost Classifier.
