Classification of Cerebral Infarction Data Using K-Means and Kernel K-Means

A cerebral infarct is a circumscribed focus or area of brain tissue that dies as a result of localized hypoxia or ischemia due to cessation of blood flow. To diagnose the presence of cerebral infarction, it needs a CT scan result from the patient. But, in this study not only CT scan result will be used, machine learning also will be proposed to diagnosing cerebral infarction. Machine learning can be used to detect and classify of infarcts in the brain using features and label that obtained from the results of the CT scan. In this study, the machine learning method that will be used is K-Means and K-Means based on kernel or kernel K-Means. Kernel K-Means is the application of K-Means that modified by changing the inner product with kernel function. The CT scan result data used in this study was obtained from the Department of Radiology at Dr. Cipto Mangunkusumo Hospital (RSCM). The best result reached with kernel K-Means, it performed with different percentage of training data, started with 50%, 55%, until 95% data training. The average accuracy score of the kernel K-Means method attained an accuracy rate of 95.28%.

[1]  T. Velmurugan,et al.  Performance based analysis between k-Means and Fuzzy C-Means clustering algorithms for connection oriented telecommunication data , 2014, Appl. Soft Comput..

[2]  Radford M. Neal.  Pattern Recognition and Machine Learning , 2007, Technometrics.

[3]  Zuherman Rustam,et al.  Hybrid Preprocessing Method for Support Vector Machine for Classification of Imbalanced Cerebral Infarction Datasets , 2019 .

[4]  Development Ischemic Stroke Model by Right Unilateral Common Carotid Artery Occlusion (RUCCAO) Method , 2018, Folia Medica Indonesiana.

[5]  Aristidis Likas,et al.  The global kernel k-means clustering algorithm , 2008, 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence).

[6]  Israa Abdzaid Atiyah,et al.  KC-Means: A Fast Fuzzy Clustering , 2018, Adv. Fuzzy Syst..

[7]  Richard Weber,et al.  Kernel Penalized K-means: A feature selection method based on Kernel K-means , 2015, Inf. Sci..

[8]  V. Feigin,et al.  Global and regional burden of stroke during 1990–2010: findings from the Global Burden of Disease Study 2010 , 2014, The Lancet.

[9]  Narayanaswamy Venketasubramanian,et al.  Stroke Epidemiology in South, East, and South-East Asia: A Review , 2017, Journal of stroke.

[10]  M. Owolabi,et al.  Stroke: a global response is needed , 2016, Bulletin of the World Health Organization.

[11]  Zuherman Rustam,et al.  Kernel Spherical K-Means and Support Vector Machine for Acute Sinusitis Classification , 2019, IOP Conference Series: Materials Science and Engineering.

[12]  Zuherman Rustam,et al.  Classification of Breast Cancer using Fast Fuzzy Clustering based on Kernel , 2019, IOP Conference Series: Materials Science and Engineering.