Abstract
With current technological developments, machine learning has become one of the most popular methods, one of the popular machine learning algorithms is k-nearest neighbors (KNN). Machine learning has been widely used in the medical field to analyze medical datasets, in this study the k-nearest neighbors (KNN) machine learning algorithm will be used because of its good level of accuracy in recognition and is included in the supervised learning algorithm group. The results showed the k-nearest neighbors (KNN) method in recognizing x-ray images of tuberculosis (TB) using SURF feature extraction with an average accuracy of 73%.
Highlights
Tuberculosis (TB) is still a major public health problem in many countries that can cause death [1]
Tuberculosis is a bacterial infection in the air caused by Mycobacterium tuberculosis (MTB) which attacks any part of the body and is generally the lungs, the signs of tuberculosis are: cough often lasts longer than 3 weeks with or without sputum production, coughing up blood, chest pain, loss of appetite, unexpected weight loss, night sweats, fever and fatigue [3]
Machine learning has been widely used in the medical field to analyze medical datasets, [10] to analyze cancer gene datasets in patients using supervised machine learning algorithms to classify cancer cells based on microRNA gene expression. [11] analyzed the breast cancer dataset using the support vector machine (SVM) algorithm, the SVM algorithm in ML is used to look for a pattern of data from a set of data that can produce predictions to determine whether live breast cancer cells are malignant or benign. [12] analyzed the breast cancer dataset using a sequential minimal optimization algorithm
Summary
Tuberculosis (TB) is still a major public health problem in many countries that can cause death [1]. The x-ray image files used for training and testing were taken from http://openi.nlm.nih.gov/imgs/collections/ChinaSet_AllFile s.zip with a total sampling of 1000 images of tuberculosis (TB), there are several studies related to implementing K-Nearest Neighbor (KNN) algorithm and SURF feature extraction: [14] Classify Hernia Disc disease and Spondylolisthesis of the spine. [15] used the K-Nearest Neighbor (KNN) algorithm to predict patients with diabetes at many public health centers in Bulukumba district, the results of the accuracy obtained from the test were 68.30%. [19] in his research using SURF and SIFT feature extraction to obtain the characteristics of a person's feet where the test results have been obtained, SURF feature extraction is better used than SIFT feature extraction in an individual identification system using foot images based on accuracy in grouping images.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
