Claim Missing Document
Check
Articles

Found 2 Documents
Search

Preprocessing Using SMOTE and K-Means for Classification by Logistic Regression on Pima Indian Diabetes Dataset Akbar, Ahmad Taufiq; Husaini, Rochmat; Prapcoyo, Hari
Telematika Vol 20 No 2 (2023): Edisi Juni 2023
Publisher : Jurusan Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31315/telematika.v20i2.9676

Abstract

Purpose: Our study aims to combine pre-processing methods to develop a training data model from the Indian diabetic Pima dataset so that it can improve the performance of machine learning in recognizing diabetesDesign/methodology/approach: This research was started through several stages such as collecting the Pima indian diabetes dataset, pre-processing including k-means clustering, oversampling using SMOTE, then undersampling the dataset whose cluster is a minority in each class. Furthermore, the dataset is classified using machine learning namely logistic regression through 10 cross validationFindings/result: The results of this classification performance show that the accuracy reaches 99.5% and is higher than the method in previous studies.Originality/value/state of the art:The method in this study uses SMOTE to handle data imbalances and k-means clustering to remove outliers by removing labels that do not match the majority cluster in each class so that clean data is produced and validation using logistic regression is more accurate than previous studies.Tujuan: Penelitian ini bertujuan untuk menerapkan metode pre-processing untuk membentuk model data latih dari dataset Pima Indian diabetes sehingga dapat meningkatkan performa mesin pembelajaran dalam mengenali diabetes.Perancangan/metode/pendekatan: Riset ini dimulai melalui beberapa tahap yakni pengumpulan dataset Pima Indian diabetes, pre-processing meliputi clustering, oversampling menggunakan SMOTE, kemudian undersampling pada dataset pada klasterĀ  minoritas pada setiap kelas. Selanjutnya dataset diklasifikasikan menggunakan machine learning yakni metode regresi logistik melalui 10 cross validationHasil: Hasil dari performa klasifikasi ini menunjukkan akurasi mencapai 99,5% dan lebih tinggi daripada metode pada penelitian sebelumnya.Keaslian/ state of the art: Metode dalam penelitian ini menggunakan SMOTE untuk menangani ketidakseimbangan data dan k-means klastering untuk membuang outlier dengan cara menghapus label yang tidak sesuai dengan klaster mayoritas pada setiap kelas sehingga dihasilkan data yang bersih dan pada validasi menggunakan logistic regression lebih akurat daripada penelitian sebelumnya.
Evaluation of waiting time for outpatient services at Respira Hospital Yogyakarta using discrete system simulation Astanti, Yuli Dwi; Rahmawati, Berty Dwi; Akbar, Ahmad Taufiq; Rysnalendra, Alya Pangesti
OPSI Vol 16 No 2 (2023): ISSN 1693-2102
Publisher : Jurusan Teknik Industri, Fakultas Teknologi Industri UPN "Veteran" Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31315/opsi.v16i2.11536

Abstract

The Ministry of Health of the Republic of Indonesia has established standard rules for the quality of outpatient service in hospitals. One indicator of the quality of outpatient services at a hospital is the patient's waiting time to be served either by a specialist or other services such as a pharmacy. Respira Hospital Yogyakarta is a special pulmonary and respiratory hospital in Yogyakarta that continues to improve the quality of its services. Based on the results of observations and interviews it is known that in terms of waiting time, patients at Respira Hospital Yogyakarta still have to wait to get service. Examples of queues that occur include patients waiting for a specialist doctor's examination for around 75 to 90 minutes. waiting at the pharmacy and cashier for up to 60 minutes or more. This study attempts to evaluate the waiting time for outpatient services at Respira Hospital Yogyakarta using a simulation. Based on the simulation results, it is known that the patient's waiting time in the system is 217.33 minutes and the longest waiting time is in the pediatric polyclinic and pharmacy departments. After the scenario implementation were made, namely in the pediatric polyclinic and pharmacy sections, the waiting time decreased to 177.19 minutes. This means that evaluations carried out using simulations can help hospitals reduce waiting time for outpatients