Awang Harsa Kridalaksana

Automatic Glaucoma Detection Method Applying a Statistical Approach to Fundus Images

Objectives Glaucoma is an incurable eye disease and the second leading cause of blindness in the world. Until 2020, the number of patients of this disease is estimated to increase. This paper proposes a glaucoma detection method using statistical features and the k-nearest neighbor algorithm as the classifier. Methods We propose three statistical features, namely, the mean, smoothness and 3rd moment, which are extracted from images of the optic nerve head. These three features are obtained through feature extraction followed by feature selection using the correlation feature selection method. To classify those features, we apply the k-nearest neighbor algorithm as a classifier to perform glaucoma detection on fundus images. Results To evaluate the performance of the proposed method, 84 fundus images were used as experimental data consisting of 41 glaucoma image and 43 normal images. The performance of our proposed method was measured in terms of accuracy, and the overall result achieved in this work was 95.24%, respectively. Conclusions This research showed that the proposed method using three statistics features achieves good performance for glaucoma detection.

Performance of Decision Tree C4.5 Algorithm in Student Academic Evaluation

Student academic evaluation is part of academic information system (AIS) performance, in order to control student learning progress is necessary. Furthermore, the evaluation showing whether the student will pass or fail would benefit the student/instructor and act as a guide for future recommendations/evaluations on performance. An in depth study on the student academic evaluation technique by using Decision Tree C4.5 has been conducted. Specific parameters including age, place of birth, gender, high school status (public or private), department in high school, organization activeness, age at the start of high school level, and progress GPA (pGPA) and Total GPA (tGPA) from semester 1–4 with three times graduation criteria (i.e., fast, on, and delay) times have been defined and tested. The scope of the paper has been set for undergraduate programs. The experimental results show that accuracy algorithm (AC) of 78.57% with true positive rate (TP) of 76.72% by using quality training data of 90% have best performance accuracy value.