Article Per Year (5 Year)
p-Index From 2021 - 2026
1.886
P-Index
This Author published in this journals
All Journal Jurnal Informatika dan Teknik Elektro Terapan INTI Nusa Mandiri JE-Unisla Jurnal Pengabdian kepada Masyarakat Nusantara Best : Journal of Applied Electrical, Science and Technology Prima Abdika: Jurnal Pengabdian Masyarakat Jurnal Riset Perbankan, Manajemen dan Akuntansi Wallaby: Jurnal Manajemen, Bisnis & Akuntansi Papsel Economic Journal
Mohamad Ilham
Universitas PGRI Adi Buana Surabaya
Arts Humanities Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Energy Engineering Environmental Science Languange, Linguistic, Communication & Media Mathematics Physics Social Sciences Other

Published : 12 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 12 Documents
Search

 1   2 
Enhancing Cluster-Based SMOTE with kNN-Based Post-Oversampling Cleaning for Robust Health Risk Prediction Ilham, Mohamad; Solikin, Akhmad; Patmanthara, Syaad
BEST Vol 8 No 1 (2026): BEST
Publisher : Universitas PGRI Adi Buana Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36456/a9k8xq74

Abstract

Class imbalance is a common problem in health datasets and often leads to poor recognition of the minority (disease) class. NR-Clustering-SMOTE is a cluster-based oversampling method that combines noise reduction, K-Means clustering, and SMOTE with a modified distance metric to improve classification performance on imbalanced health data. However, the original method only performs noise reduction before SMOTE, so noisy synthetic samples generated around borderline or highly overlapped regions may still degrade classifier performance and introduce epistemological bias in the learned decision rules. This paper proposes a lightweight extension called NR-CluSMOTE-KNC (NR-Clustering-SMOTE with Post-SMOTE k-NN Cleaning). After the standard NR-Clustering-SMOTE pipeline, a k-nearest neighbour filter is applied solely to synthetic minority samples; synthetic points that are surrounded predominantly by majority neighbours are identified as extreme noise and removed. On the Pima Indians Diabetes dataset using Random Forest, the proposed method improves accuracy from 0.8481 (baseline NR-Clustering-SMOTE) to 0.8589 with NR-CluSMOTE-KNC, accompanied by consistent gains in G-Mean and AUC. These results indicate that a simple post-SMOTE cleaning step can epistemologically refine the representation of minority concepts in the data, producing more reliable and fair predictive models for health decision support.
PENDEKATAN HYBRID TSR-NN UNTUK PERAMALAN INFLOW OUTFLOW UANG KARTAL REGIONAL JAWA TIMUR Artanti Indrasetianingsih; Elvira Mustikawati Putri Hermanto; Mohamad Ilham; Novi Rahmawati; Intan Amelia Hariyanto
INTI Nusa Mandiri Vol. 19 No. 2 (2025): INTI Periode Februari 2025
Publisher : Lembaga Penelitian dan Pengabdian Pada Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/inti.v19i2.5283

Abstract

The availability of currency circulating in society can influence the economic conditions of a country. The need for money increases when religious holidays approach, such as Eid al-Fitr and Christmas, as well as school holidays and the end of the year. Therefore, it is necessary to plan the need for currency, one of which is by forecasting the circulation of currency, both inflow and outflow. Forecasting is done to predict a value in the future based on historical data. This research aim was to predict the inflow and outflow of regional currency in East Java using the hybrid Time Series Regression (TSR) – Neural Network (NN) method. The methods in time series analysis used to predict are increasingly developing, as are hybrid methods, namely methods that combine several models to produce more accurate forecasts. The analysis results obtained show that the prediction of incoming and outgoing cash flows is better using the hybrid TSR-NN method because it produces a smaller RMSE value, namely 1,656.62, with a MAPE of 0.28 compared to the TSR method. The results of this study are expected to contribute to a hybrid approach for forecasting the regional currency inflow and outflow of East Java.
Co-Authors Abidin, Zainil Adi Winarno Agus Nisfur Romdioni Akhmad Solikin Aryani, Reni Cuhenda, Cuhenda Day, Wa Ode Siti Hamsinah Elvira Mustikawati Putri Hermanto Elvira Mustikawati Putri Hermanto Epin, Maria Natalia Wainip Fredy Fredy Hafsemi Rapsanjani Hariyanto, Intan Amelia Indrasetianingsih, Artanti Intan Amelia Hariyanto Ismail, My Jodhy Satria Ramadhan Kastanya, Mensy Otelyo Kurniasih, Milla Listiani Safitri, Devi Moch. Lutfi Muhamad Anang Sucipto Noverina, Yolla Novi Rahmawati Novi Rahmawati Rizki Adri Yohanes Rusnani, Adila Sagita Rochman Syaad Patmanthara Tri Suratno