cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Yuhefizar
Contact Email
jurnal.resti@gmail.com
Phone
+628126777956
Journal Mail Official
ephi.lintau@gmail.com
Editorial Address
Politeknik Negeri Padang, Kampus Limau Manis, Padang, Indonesia.
Location
,
INDONESIA
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi)
Published by Ikatan Ahli Informatika Indonesia
ISSN : 25800760     EISSN : 25800760     DOI : https://doi.org/10.29207/resti.v2i3.606
Core Subject : Science, Engineering,
Computer Science & IT Engineering
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) dimaksudkan sebagai media kajian ilmiah hasil penelitian, pemikiran dan kajian analisis-kritis mengenai penelitian Rekayasa Sistem, Teknik Informatika/Teknologi Informasi, Manajemen Informatika dan Sistem Informasi. Sebagai bagian dari semangat menyebarluaskan ilmu pengetahuan hasil dari penelitian dan pemikiran untuk pengabdian pada Masyarakat luas dan sebagai sumber referensi akademisi di bidang Teknologi dan Informasi. Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) menerima artikel ilmiah dengan lingkup penelitian pada: Rekayasa Perangkat Lunak Rekayasa Perangkat Keras Keamanan Informasi Rekayasa Sistem Sistem Pakar Sistem Penunjang Keputusan Data Mining Sistem Kecerdasan Buatan/Artificial Intelligent System Jaringan Komputer Teknik Komputer Pengolahan Citra Algoritma Genetik Sistem Informasi Business Intelligence and Knowledge Management Database System Big Data Internet of Things Enterprise Computing Machine Learning Topik kajian lainnya yang relevan
Arjuna Subject : Ilmu Komputer (semua kategori) - Ilmu Komputer (Lain-Lain)
Articles 1,113 Documents
 108   109   110   111   112 
Development of Hidden Markov Model Based Hydrometeorological Disaster Prediction Model for More Effective Preparedness Joko Sutopo; Burhanuddin Mohd Aboobaider; Mustaqim Pabbajah; Juhansar Juhansar; Aprijanto Aprijanto; RB Hendri Kuswantoro
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 10 No 3 (2026): Juni 2026 (in progress)
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v10i3.6359

Abstract

Hydrometeorological disasters, such as floods, are significant threats that require an accurate prediction system to improve preparedness and risk mitigation. This research aims to develop a Hidden Markov Model (HMM)-based hydrometeorological disaster prediction model by utilizing hydrological data from Kelambu Dam in Demak Regency. The data used includes water levels upstream (Level Up), downstream (Level Down), and water discharge (Q Serang), as well as information on flood events in the period 2022-2024. The methods applied include data collection and preprocessing, model training using the Baum-Welch algorithm, and performance evaluation with accuracy, precision, recall, and F1-score metrics. The results showed that the HMM model was able to identify hydrological change patterns and predict flood events with a high level of accuracy, reaching 94.29% at the best iteration. The performance evaluation also indicated that the model has a good balance between precision and recall, making it a potential tool in early warning systems. Thus, the implementation of this prediction model can improve community preparedness and support decision-making in hydrometeorological disaster management.
A Hybrid PCA, MPK Method for Multi-Objective Human Resource Analytics in Plantation Management Gilang Ramadhan; Rahmad Syah; Ahmad Rafiki
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 10 No 3 (2026): Juni 2026 (in progress)
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v10i3.6903

Abstract

This study presents a hybrid framework combining Principal Component Analysis (PCA) and Multi‐Objective Complexity Prediction (MPK) to extract actionable insights from multidimensional human resource (HR) data in plantation companies. Initially, PCA reduces nine original HR variables including age, tenure, absenteeism, leave, harvest yield, and performance scores to four principal components that capture over 90 % of total variance. These reduced features form the solution space for MPK agents, each of which simultaneously optimizes three objectives: absenteeism risk (predicted via SVR), performance score (via linear regression), and workload imbalance. The model is tuned with 5-fold cross-validation on 80 % of the data, yielding MAE ≈ 6.5 days and R² ≈ 0.82 for absenteeism, MAE ≈ 4.2 points and R² ≈ 0.78 for performance, MAPE ≈ 15 % for workload imbalance, and a Pareto‐front hypervolume of ≈ 0.90. Validation on the remaining 20 % hold-out set confirms similar generalization (hypervolume ≈ 0.88). Sensitivity analysis with ± 10 % input noise demonstrates the approach’s robustness under moderate perturbations. These results illustrate that PCA–MPK can both streamline high-dimensional HR datasets and deliver reliable, multi-objective forecasts to inform strategic workforce planning.
Improving Data Completeness in SINTA Publication Scraping Using an Iterative Method Muhammad Arfah Asis; St. Hajrah Mansyur; Nia Kurniati
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 10 No 3 (2026): Juni 2026 (in progress)
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v10i3.6952

Abstract

The structure of publication data on lecturer profiles in SINTA, particularly those indexed by SCOPUS, often results in data duplication and missing records. This issue arises because articles are distributed by year across multiple pages, making standard single-pass scraping methods unable to guarantee data completeness. This study aims to develop and evaluate the effectiveness of an iterative scraping method in improving the accuracy of publication data retrieval from SINTA. The proposed method involves a series of ten experimental trials, in which the results of single-pass scraping are compared with those of iterative scraping. The evaluated parameters include the level of data completeness and the number of iterations required to achieve optimal results. The findings indicate that single-pass scraping captures only an average of 70.7% of publications in the first iteration, with frequent occurrences of duplicated and missing data. In contrast, the iterative scraping method consistently achieves 100% publication retrieval across all trials, although it requires a varying number of iterations ranging from four to eleven. Therefore, it can be concluded that iterative scraping is a more reliable approach for ensuring the completeness and accuracy of publication data. Although this approach demands greater computational resources than standard methods, it is well suited for large-scale bibliometric studies, institutional evaluations, and more comprehensive monitoring of research trends.
Impact of Dataset Background on Deep Learning-Based Waste Classification Nazzua Azzahra; Aditiya Hermawan; Junaedi; Yusuf Kurnia; Edy
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 10 No 3 (2026): Juni 2026 (in progress)
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v10i3.6965

Abstract

Accurate waste classification plays a vital role in supporting effective waste management and promoting environmental sustainability, especially amid the continuing increase in global waste generation. This study investigates how the presence and removal of image backgrounds influence the performance of deep learning models in automated waste classification. Two Convolutional Neural Network architectures, namely MobileNetV2 and DenseNet169, were evaluated using a dataset comprising 5,054 images across six waste categories: cardboard, glass, metal, paper, plastic, and trash. Each architecture was trained and tested on two dataset variants: original images with backgrounds and images with the backgrounds removed. Model performance was assessed using accuracy, precision, recall, F1-score, and ROC AUC. The results indicate that DenseNet169 consistently outperformed MobileNetV2 across all evaluation metrics. The highest accuracy, reaching 88.33%, was achieved by DenseNet169 when trained on images retaining their original backgrounds. This suggests that background information may provide meaningful contextual features that enhance classification performance. Conversely, removing backgrounds can limit the visual information available to the model and potentially reduce predictive effectiveness. These findings emphasize the importance of carefully considering background characteristics during dataset preparation and model training. Moreover, the study demonstrates that selecting an appropriate model architecture in relation to dataset properties is essential for optimizing classification outcomes. Overall, this research offers practical insights for improving dataset design and model selection in future automated waste classification systems, while contributing to the advancement of scalable and intelligent deep learning-based waste management solutions.
Enhanced Loan Prediction Performance Using Blending Model Approach Nur Haryadi; Siti Juwariyah; Muhammad Ricky Perdana Putra
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 10 No 3 (2026): Juni 2026 (in progress)
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v10i3.7242

Abstract

The loan approval process at financial institutions is carried out manually in a conventional manner by looking at the customer's track record. This process is ineffective because it takes a considerable amount of time. As a result, a machine learning (ML) model has been developed that can recognize certain patterns in datasets for automatic and rapid prediction. However, the problem is that a single ML model is still not optimal, so it needs to be improvised, one of which is with Ensemble Learning (EL), which combines more than one model. This study uses Blending EL (BEL), which is built on two layers: the first layer as a base model with KNN, DT, and NB algorithms, and the second layer as a meta layer built with XGBoost. Pre-processing uses MinMaxScaler for data normalization and SMOTE-ENN for data class balancing. Testing uses a confusion matrix covering accuracy, recall, precision, and F1-Score, as well as Area Under Curve (AUC) and execution time, then combined with K-Fold cross validation with k=10. The BEL model prediction results were 96.42% accuracy, 96.29% precision, 96.29% recall, 96.29% F1-Score, and 98.72% AUC. Meanwhile, the average matrix in K-Fold cross validation is accuracy 96.84%, precision 98.09%, recall 95.57%, F1-Score 96.70%, and AUC 99.32% as well as execution time 0.261 seconds.
Stock Price Prediction Using SVR: A Feature Engineering and Hyperparameter Tuning Approach Alfian Ramadhan; Yoga Pristyanto; Anggit Dwi Hartanto; Donni Prabowo
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 10 No 3 (2026): Juni 2026 (in progress)
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v10i3.7249

Abstract

Stock price prediction in Indonesia's volatile mining sector poses significant forecasting challenges driven by commodity price dynamics and structural market shifts. This study proposes a systematic prediction framework for PT Indo Tambangraya Megah Tbk (ITMG.JK) integrating technical and market-derived non-technical feature engineering, LightGBM-based feature selection, multilevel TimeSeriesSplit cross-validation, and hyperparameter optimization. Support Vector Regression (SVR) is benchmarked against LightGBM, XGBoost, and Random Forest under 5-fold, 10-fold, and 15-fold schemes. SVR achieves the best performance at 10-fold, with RMSE of 0.0121, MAE of 0.0090, MAPE of 1.1457%, and R² of 0.9249. Generalization experiments across four additional stocks in banking, automotive, and mining sectors confirm SVR's robustness, maintaining R² above 0.89 and MAPE below 2.65% in all cases while tree-based models produce negative R² on certain datasets. Statistical validation via Wilcoxon signed-rank test (p < 0.05) and Cohen's d (|d| > 0.8) confirms the significance of SVR's advantage. These findings indicate that SVR consistently outperforms the evaluated models under the proposed experimental framework.
Reward Scheme Analysis for DQN-Based Adaptive Traffic Signal Control in Road Repair Zones Yoanda Alim Syahbana; Muhammad Wahyudi; Fikri Muhaffizh Imani; Ardianto Wibowo; Fatur Rizky Al-Farisz
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 10 No 3 (2026): Juni 2026 (in progress)
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v10i3.7381

Abstract

Traffic congestion caused by temporary road repairs often forces bidirectional traffic to alternate through a single lane, leading to increased delays and imbalanced traffic flow. This study investigates the impact of reward scheme design on the performance of a Deep Q-Network (DQN)-based adaptive traffic signal control system in such constrained environments. Using the Simulation of Urban Mobility (SUMO), a traffic scenario involving 1,656 vehicles over 1,800 seconds was modeled to evaluate six reward scheme configurations combining Traffic Flow (TF), Waiting Time (WT), and Average Speed (AS): TF-TF, TF-WT, WT-TF, WT-WT, AS-TF, and AS-WT. The DQN agent, implemented with a two-layer neural network and trained for 50 epochs, dynamically adjusted signal timing to balance traffic from opposing directions. Experimental results indicate that the AS-WT configuration achieved the most balanced performance, producing the best fairness index (1.04) while maintaining stable traffic flow. In contrast, schemes with misaligned or redundant metrics showed significantly poorer performance. These findings highlight the importance of reward design in reinforcement learning-based traffic signal control and suggest that carefully selected reward schemes can improve fairness and efficiency in temporary road repair zones.
Trajectory Tracking of a Pioneer P3DX Robot Using Model Predictive Control Azam Zamhuri Fuadi; Ahmad Rizal Miftah Awali Sofyan; Angga Rusdinar
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 10 No 3 (2026): Juni 2026 (in progress)
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v10i3.7383

Abstract

Trajectory tracking of nonholonomic mobile robots using Model Predictive Control (MPC) has attracted significant attention due to its capability to explicitly handle system dynamics and actuator constraints within an optimization framework. However, limited studies specifically investigate the computational consistency of constrained Nonlinear Model Predictive Control (NMPC) under fixed-sampling closed-loop simulation environments. This study presents the implementation of a constrained NMPC framework for trajectory tracking of a Pioneer P3DX differential-drive robot using a discrete-time kinematic model and Sequential Least Squares Quadratic Programming (SLSQP) optimization. The controller is integrated with the CoppeliaSim environment through a ZeroMQ based communication interface operating at a fixed sampling time of 0.1 s. Controller performance is evaluated using circular, lemniscate, and square reference trajectories to analyze predictive behavior under varying curvature conditions. The simulation results demonstrate cumulative Root Mean Square Error (RMSE) values of 0.3868 m for the circular trajectory, 0.0942 m for the lemniscate trajectory, and 0.4911 m for the square trajectory. In the square trajectory case, the controller autonomously reduces linear velocity before sharp corners and generates smooth feasible turning maneuvers while satisfying actuator constraints. These behaviors indicate that the implemented NMPC framework is capable of maintaining stable and constraint-aware trajectory tracking performance within a structured closed-loop simulation environment. The study, therefore, provides a preliminary validation of computational feasibility prior to hardware level implementation.
Comparative Performance of YOLOv12 in Detecting Fungal Skin Diseases in Cats Bradika Almandin Wisesa; Vivin Mahat Putri; Evvin Faristasari; Sirlus Andreanto Jasman Duli; Satria Agus Darma
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 10 No 3 (2026): Juni 2026 (in progress)
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v10i3.7446

Abstract

Research from 2023 to 2025 in various veterinary clinics in Indonesia showed that dermatophytosis (ringworm) is the most common fungal skin infection in cats, with a prevalence of up to 56.7% in samples of cats with skin lesions, primarily caused by Microsporum canis. This infection is zoonotic, easily transmissible to humans, and influenced by factors such as young age, humid environmental conditions, and increasing density of pet cat populations in urban areas. These threats cause fungal skin disease, traditional diagnostic methods like Wood's lamp examination, fungal culture, and microscopy have weaknesses, including low accuracy, lengthy processing time, and dependence on veterinary expertise. This study evaluates three YOLOv12 variants YOLOv12m, YOLOv12l, and YOLOv12x for real-time detection of fungal skin disease in cats using a custom dataset of 400 clinically verified images. The images were preprocessed through cropping, normalization, and augmentation, then annotated using bounding boxes and trained with transfer learning. Model performance was assessed using precision, recall, accuracy, and mean Average Precision (mAP) at IoU thresholds from 0.50 to 0.95. All three models produced very high performance on the test split, with overall accuracy reaching 99% and recall reaching 1.00. Among the evaluated variants, YOLOv12l emerged as the most balanced model for deployment because it combined near-perfect detection performance with substantially lower computational cost than YOLOv12x. Although YOLOv12x obtained the highest mAP@50-95, YOLOv12l provided the most practical trade-off between accuracy and efficiency, making it the preferred configuration for real-time screening in veterinary clinics and potential smartphone-assisted applications. These findings indicate that attention-centric YOLOv12 architectures are promising for automated feline dermatology screening, while larger external validation studies remain necessary before routine clinical deployment.
Lightweight CNN Feature Extraction and PSO-Weighted Ensemble for Retinal OCT Classification Neisa Hibatillah Alif; Anggun Dwi Rizkika; Feiticeira Zulkarnaen; Nanik Suciati
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 10 No 3 (2026): Juni 2026 (in progress)
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v10i3.7451

Abstract

Retinal diseases are a primary cause of visual impairment, requiring accurate and efficient automated classification. This study proposes a multi-class classification approach for detecting retinal disease from Optical Coherence Tomography (OCT) images using the OCT-C8 dataset, which consists of 24,000 images across eight balanced classes. Pretrained lightweight convolutional neural networks (EfficientNet-B0, ShuffleNetV2, and RegNetY-400MF) are used as feature extractors to leverage transfer learning while reducing computational cost. Instead of end-to-end deep learning, extracted features are classified using traditional machine learning models (KNN, RF, SVM, and MLP), which are more efficient for moderate-sized datasets. To improve robustness, a weighted ensemble is applied, where classifier contributions are optimized using Particle Swarm Optimization (PSO). Experimental results show that the proposed method achieves a classification accuracy of 97.35%, outperforming conventional hard and soft voting methods, while maintaining a balance between computational efficiency and performance with potential for practical deployment.

Page 111 of 112 | Total Record : 1113

 108   109   110   111   112 

Filter by Year

2017 2026


Reset
Filter By Issues
All Issue Vol 10 No 3 (2026): Juni 2026 (in progress) Vol 10 No 2 (2026): April 2026 Vol 10 No 1 (2026): February 2026 Vol 9 No 6 (2025): December 2025 Vol 9 No 5 (2025): October 2025 Vol 9 No 4 (2025): August 2025 Vol 9 No 3 (2025): June 2025 Vol 9 No 2 (2025): April 2025 Vol 9 No 1 (2025): February 2025 Vol 8 No 6 (2024): December 2024 Vol 8 No 5 (2024): October 2024 Vol 8 No 4 (2024): August 2024 Vol 8 No 3 (2024): June 2024 Vol 8 No 2 (2024): April 2024 Vol 8 No 1 (2024): February 2024 Vol 7 No 6 (2023): December 2023 Vol 7 No 5 (2023): October 2023 Vol 7 No 4 (2023): August 2023 Vol 7 No 3 (2023): Juni 2023 Vol 7 No 2 (2023): April 2023 Vol 7 No 1 (2023): February 2023 Vol 6 No 6 (2022): Desember 2022 Vol 6 No 5 (2022): Oktober 2022 Vol 6 No 4 (2022): Agustus 2022 Vol 6 No 3 (2022): Juni 2022 Vol 6 No 2 (2022): April 2022 Vol 6 No 1 (2022): Februari 2022 Vol 5 No 6 (2021): Desember 2021 Vol 5 No 5 (2021): Oktober2021 Vol 5 No 4 (2021): Agustus 2021 Vol 5 No 3 (2021): Juni 2021 Vol 5 No 2 (2021): April 2021 Vol 5 No 1 (2021): Februari 2021 Vol 4 No 6 (2020): Desember 2020 Vol 4 No 5 (2020): Oktober 2020 Vol 4 No 4 (2020): Agustus 2020 Vol 4 No 3 (2020): Juni 2020 Vol 4 No 2 (2020): April 2020 Vol 4 No 1 (2020): Februari 2020 Vol 3 No 3 (2019): Desember 2019 Vol 3 No 2 (2019): Agustus 2019 Vol 3 No 1 (2019): April 2019 Vol 2 No 3 (2018): Desember 2018 Vol 2 No 2 (2018): Agustus 2018 Vol 2 No 1 (2018): April 2018 Vol 1 No 3 (2017): Desember 2017 Vol 1 No 2 (2017): Agustus 2017 Vol 1 No 1 (2017): April 2017 More Issue