Article Per Year (5 Year)
p-Index From 2020 - 2025
0.408
P-Index
This Author published in this journals
All Journal Journal of Natural Sciences and Mathematics Research Jurnal Matematika UNAND
Aqsha, Masjidil
Unknown Affiliation
Agriculture, Biological Sciences & Forestry Biochemistry, Genetics & Molecular Biology Chemistry Computer Science & IT Materials Science & Nanotechnology Mathematics Physics

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
PERFORMA KLASIFIKASI DATA TIDAK SEIMBANG DENGAN PENDEKATAN MACHINE LEARNING (STUDI KASUS: DIABETES INDIAN PIMA) Aqsha, Masjidil; Sunusi, Nurtiti
Jurnal Matematika UNAND Vol. 12 No. 2 (2023)
Publisher : Departemen Matematika dan Sains Data FMIPA Universitas Andalas Padang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25077/jmua.12.2.176-193.2023

Abstract

Diabetes merupakan suatu penyakit atau gangguan metabolisme kronis dengan multi etiologi yang ditandai dengan tingginya kadar gula darah disertai dengan gangguan metabolisme karbohidrat, lipid, dan protein sebagai akibat insufisiensi fungsi insulin. Faktor risiko diabetes berhubungan dengan status diabetes sesorang. Berbagai pendekatan machine learning menjadi alternatif dalam memprediksi status diabetes. Namun, dalam banyak kasus, data yang tersedia tidak cukup seimbang dalam kelas datanya. Adanya ketidakseimbangan data dapat menyebabkan hasil prediksi menjadi tidak akurat. Tujuan penelitian dalam paper ini adalah untuk mengatasi masalah ketidakseimbangan data dan membandingkan kinerja model dalam memprediksi status diabetes. Secara umum, metode seperti Synthetic Minority Over-sampling Technique (SMOTE) dan Adaptive Synthetic (ADASYN) dapat digunakan untuk menyeimbangkan data. Data Diabetes Indian Pima yang telah diseimbangkan kemudian diprediksi dengan metode machine learning seperti metode Bagging, Random Forest, dan XGBoost. Hasil penelitian menunjukkan bahwa performa model machine learning meningkat setelah menangani ketidakseimbangan data dan model terbaik adalah model XGBoost. 
Early detection model of Parkinson's Disease using Random Forest Method on voice frequency data Rifqah Fahira, Nurul; Lawi, Armin; Aqsha, Masjidil
Journal of Natural Sciences and Mathematics Research Vol. 9 No. 1 (2023): June
Publisher : Faculty of Science and Technology, Universitas Islam Negeri Walisongo Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Parkinson's disease is the most common nervous system disease that affects all ethnicities, genders, and ages, with a higher prevalence in the elderly and men. Developing countries tend to have higher cases of Parkinson's. The prevalence of death due to Parkinson's in Indonesia reaches the fifth highest cases in Asia and 12th in the world. This neurodegenerative disease affects a person's ability to control movement. Currently, the diagnosis of Parkinson's disease is only based on observation of motor symptoms. Therefore, early detection of the disease cannot be done. His paper proposes an efficient way to detect Parkinson's disease symptoms by comparing the fundamental frequencies of patients' voices using the random forest method. Random forest is a Machine Learning method that applies the ensemble concept, which aims to improve the performance of the classification by combining several decision trees as a basis. Random forests have shown superior algorithm performance in numerous health studies. In this study, the dataset consisted of 20 patients with Parkinson's and 20 normal patients. Data for each patient was taken from 26 types of voice records, and thus, the total data was 1,040 observations. The obtained data is prepared by filtering and rescaling. Then, the data is split and modelled using the Random Forest Method. The random forest model obtained accuracy results of 72.50%, precision (normal) of 72.28%, precision (Parkinson's) of 72.73%, sensitivity (normal) of 73.00%, sensitivity (Parkinson's) of 72.00% and AUC is 80.70%. The built random forest model is quite good at Parkinson's disease detection.
Co-Authors Armin Lawi NURTITI SUNUSI Rifqah Fahira, Nurul