Article Per Year (5 Year)
p-Index From 2021 - 2026
0.408
P-Index
This Author published in this journals
All Journal International Journal of Innovation in Mechanical Engineering and Advanced Materials Jurnal Pengabdian Masyarakat dan Riset Pendidikan
Priyo Haryoko
Universitas Pancasakti Tegal
Humanities Automotive Engineering Education Energy Engineering Languange, Linguistic, Communication & Media Materials Science & Nanotechnology Mathematics Mechanical Engineering Other

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

Found 2 Documents
Search

 1 
Benchmarking Nine SMOTE-Balanced Classifiers Including Artificial Neural Network for CNC Predictive Maintenance Didiek Trisatya; Priyo Haryoko
International Journal of Innovation in Mechanical Engineering and Advanced Materials Vol. 8 No. 1 (2026)
Publisher : Universitas Mercu Buana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22441/ijimeam.v8i1.38645

Abstract

Unplanned equipment failure in CNC manufacturing causes significant economic losses, driving demand for effective predictive maintenance (PdM). A critical research gap persists: existing studies on the AI4I 2020 Predictive Maintenance Dataset apply isolated classifiers under inconsistent preprocessing pipelines, preventing fair algorithmic comparison. No prior study has benchmarked nine diverse classifier families under a unified pipeline integrating SMOTE oversampling with domain-driven feature engineering. This study addresses that gap by systematically evaluating nine ML classifiers—Logistic Regression, K-Nearest Neighbors, Decision Tree, Random Forest, Gradient Boosting, AdaBoost, SVM (RBF kernel), Naive Bayes, and MLP Neural Network—on the AI4I 2020 dataset (10,000 records; 3.4% failure rate; 1:28 class imbalance). Two domain-engineered features were constructed: mechanical power (P = n × T × (π/30)) and thermal gradient (ΔT = T_process - T_air). Features were normalized; SMOTE was applied to training folds only; and 10-fold stratified cross-validation assessed six performance metrics. Three novel contributions are presented: (1) the first nine-classifier benchmark on AI4I 2020 under a unified SMOTE-and-feature-engineering pipeline enabling fair model comparison; (2) empirical demonstration that Average Precision is a more discriminating evaluation metric than AUC-ROC under severe 1:28 class imbalance; and (3) physical interpretation of feature importance linking dominant predictors to CNC failure mechanisms. Gradient Boosting achieved the best-balanced performance (F1-score: 0.6782, Accuracy: 97.20%, AUC-ROC: 0.9723); Random Forest attained the highest AUC-ROC (0.9772). Mechanical power (25.51%) and tool wear (23.91%) were dominant predictors, corresponding to tribological, fatigue loading, and thermal failure mechanisms. These findings support cost-effective condition-based maintenance strategies in industrial CNC environments.
Penerapan Algoritma k-Nearest Neighbor untuk Klasifikasi Kondisi Lingkungan Pertanian Berbasis IoT : Penelitian Panji Pangestu Saputra; Hasbi Firmansyah; Rizki Prasetyo Tulodo; Priyo Haryoko; Wahyu Asriyani
Jurnal Pengabdian Masyarakat dan Riset Pendidikan Vol. 4 No. 3 (2026): Jurnal Pengabdian Masyarakat dan Riset Pendidikan Volume 4 Nomor 3 (Januari 202
Publisher : Lembaga Penelitian dan Pengabdian Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31004/jerkin.v4i3.4566

Abstract

The development of the Internet of Things (IoT) has encouraged the adoption of smart technologies in agriculture to enable real-time environmental monitoring. This study aims to apply the k-Nearest Neighbor (k-NN) algorithm to classify agricultural environmental conditions into ideal and non-ideal categories based on IoT sensor data. The dataset used in this research was obtained from an open-source repository and consists of several environmental parameters, including temperature, humidity, and soil moisture. The research stages include data preprocessing, attribute and label determination, data normalization using the z-transformation method, and model evaluation through cross validation. The performance of the classification model was assessed using accuracy, precision, recall, and F-measure metrics. The experimental results indicate that the k-NN algorithm is capable of providing good classification performance in identifying agricultural environmental conditions. However, limitations were observed in detecting minority class instances, suggesting the need for further parameter optimization and model enhancement. This research is expected to serve as a foundation for the development of IoT-based smart agriculture systems to support more effective decision-making in agricultural environmental management.
Co-Authors Asriyani, Wahyu Didiek Trisatya Hasbi Firmansyah Panji Pangestu Saputra Rizki Prasetyo Tulodo