cover
Contact Name
Andri Nofiar.
Contact Email
garuda@apji.org
Phone
+6285726173515
Journal Mail Official
isbn@yayasandpi.or.id
Editorial Address
Pusat Penelitian dan Pengadian pada Masyarakat Kampus Politeknik Kampar JL. Tengku Muhammad KM 2 Bangkinang - Riau
Location
Kab. kampar,
Riau
INDONESIA
Jurnal Elektronika dan Teknik Informatika Terapan
Published by Politeknik Kampar
ISSN : 29880866     EISSN : 29880874     DOI : 10.59061
Core Subject : Science,
Bidang Ilmu Komputer dan Informatika Bidang Ilmu Internet Of Thinks Bidang Ilmu Mikrokontroller Bidang Ilmu Animasi dan Multimedia
Articles 118 Documents
Perbandingan Algoritma Random Forest dan Support Vector Machine untuk Klasifikasi Penyakit Ginjal Kronis Berbasis Machine Learning Edison Ulung Panggabean Simanihuruk; Arifin Tua Purba; Hasanuddin Sirait
Jurnal Elektronika dan Teknik Informatika Terapan ( JENTIK ) Vol. 3 No. 4 (2025): Desember: Jurnal Elektronika dan Teknik Informatika Terapan (JENTIK)
Publisher : Politeknik Kampar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59061/jentik.v3i4.1613

Abstract

Chronic kidney disease (CKD) is a progressive renal disorder that affects approximately 10–15% of the global population and represents a significant contributor to morbidity and mortality worldwide. Early and accurate diagnosis of CKD is essential to enable timely clinical intervention and prevent progression to end-stage renal disease. This study presents a comparative analysis of two machine learning algorithms, namely Random Forest (RF) and Support Vector Machine (SVM), for the classification of CKD using clinical and laboratory data. The dataset was obtained from the UCI Machine Learning Repository, comprising 400 instances with 24 features and 1 binary target variable. Data preprocessing steps included missing value imputation, categorical encoding, outlier detection using the Interquartile Range method, and feature normalization. Both algorithms were implemented using their default hyperparameters to ensure a fair comparison without optimization bias. The dataset was split into 80% training (320 samples) and 20% testing (80 samples) using stratified sampling. Model performance was evaluated using five metrics: accuracy, precision, recall, F1-score, and area under the receiver operating characteristic curve (AUC-ROC). The experimental results demonstrated that Random Forest achieved perfect classification performance with 100% across all evaluation metrics, while SVM attained 98.75% accuracy, 100% precision, 97.87% recall, 98.92% F1-score, and 100% AUC-ROC. The superior performance of Random Forest is attributed to its ensemble learning mechanism that aggregates predictions from multiple decision trees, effectively reducing overfitting and enhancing model robustness. These findings suggest that Random Forest is a highly reliable algorithm for CKD classification and holds significant potential as a clinical decision support tool for early disease detection.
Analisis Path Selection Border Gateway Protocol (BGP) pada Jaringan IPv6 Salman Fari; Kurniadin Abdul Latif; Ondi Asroni; Lalu Zazuli Azhar
Jurnal Elektronika dan Teknik Informatika Terapan ( JENTIK ) Vol. 4 No. 3 (2026): September: Jurnal Elektronika dan Teknik Informatika Terapan ( JENTIK )
Publisher : Politeknik Kampar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59061/jentik.v4i3.1619

Abstract

The development of Internet Protocol Version 6 (IPv6) networks requires routing mechanisms that can determine the preferred path while maintaining connectivity when network conditions change. Border Gateway Protocol (BGP) determines routes through a set of path-selection attributes. This study analyzes BGP Path Selection on IPv6 networks, examines the effect of Weight, Local Preference, and AS-Path Prepending on route selection, and evaluates Failover and recovery when the main path is disrupted. The study applies three phases of the Network Development Life Cycle (NDLC): analysis, design, and simulation prototyping. The simulation was conducted in GNS3 using four Autonomous Systems (AS 65001, AS 65002, AS 65003, and AS 65004) with primary and alternative IPv6 paths. Testing was performed under normal, failure, and recovery conditions using ping and traceroute, with comparisons between default and modified BGP attributes. The results show that the three attributes can control Path Selection according to the configured policy. Under normal conditions, the primary path produced an average latency of 61.97 ms with 0% packet loss. When the main path was disconnected, BGP successfully failed over to the alternative path. In the AS-Path scenario, the alternative path started responding at approximately 45 seconds after the disruption, with 44% packet loss during transition, and then returned to 0% after stabilization. The recovery test reported a transition period of approximately 2.007 seconds until the connection became stable.
Pengelompokan Kabupaten/Kota Berdasarkan Jumlah dan Persentase Penduduk Miskin di Provinsi Sumatera Utara menggunakan Algoritma K-Means Fahmi Firzada; Saifullah Saifullah; Eka Irawan; Wendi Robiansyah
Jurnal Elektronika dan Teknik Informatika Terapan ( JENTIK ) Vol. 4 No. 3 (2026): September: Jurnal Elektronika dan Teknik Informatika Terapan ( JENTIK )
Publisher : Politeknik Kampar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59061/jentik.v4i3.1620

Abstract

Poverty is a social problem that has widespread impacts on society and remains a major concern for governments in their efforts to improve public welfare. This study aims to cluster districts and cities in North Sumatra Province based on the number and percentage of poor people using the K-Means Clustering algorithm. The data were obtained from Statistics Indonesia (BPS) and cover the period from 2019 to 2023. The K-Means algorithm was applied to group regions according to similarities in their poverty characteristics, particularly the number and percentage of poor people. The clustering process was implemented using RapidMiner software to facilitate data processing, analysis, and visualization of the resulting clusters. The findings indicate that K-Means can group districts and cities with similar poverty characteristics, providing an overview of the distribution of poverty across North Sumatra Province. The resulting clusters can serve as supporting information for the regional government in identifying areas that require greater attention and developing more targeted poverty alleviation policies. This study is expected to support more effective resource allocation and contribute to the formulation of sustainable poverty reduction strategies tailored to regional conditions and development priorities.
Desain dan Implementasi Aplikasi Pengelolaan Sumber Daya Virtual pada Cloud Provider Berbasis Web Eka Bayu Suputra; Kurniadin Abd. Latif; Ondi Asroni
Jurnal Elektronika dan Teknik Informatika Terapan ( JENTIK ) Vol. 4 No. 3 (2026): September: Jurnal Elektronika dan Teknik Informatika Terapan ( JENTIK )
Publisher : Politeknik Kampar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59061/jentik.v4i3.1621

Abstract

Provisioning of Virtual Private Servers (VPS) on Proxmox Virtual Environment (VE) is still performed manually by administrators through the native dashboard, which is time-consuming and prone to configuration errors, while end users cannot order and manage virtual resources independently. This study aims to design and implement ONEVPS, a web-based application integrated with Proxmox VE through its REST API to automate VPS ordering, provisioning, and management in a self-service manner. The system was developed using the Agile method with Planning, Design, Development, and Testing stages, using native PHP with the Model-View-Controller (MVC) pattern, MySQL as the database, and Linux Container (LXC) as the VPS virtualization environment. Black Box Testing on 11 scenarios showed that all tested functions, including authentication, VPS ordering, automatic container provisioning with IP address allocation, power control, and real-time resource monitoring, worked as expected. In the comparison scenario, creating a VPS through the application was faster than manual creation and required no manual configuration on the Proxmox dashboard. ONEVPS offers cloud providers a more structured VPS service workflow with reduced administrator intervention.
Konfigurasi Backpropagation Neural Network Ringan untuk Klasifikasi Kesuburan Tanah Berbasis Nilai NPK: Analisis Hyperparameter dan Uji Derau Simulasi Marzuarman Marzuarman; Agustiawan Agustiawan; Mus Ali Alsabah; Azizul Azizul; M. Afridon; Jefri Lianda; Fandy Octafiandri; Cindy Witra Nuansa
Jurnal Elektronika dan Teknik Informatika Terapan ( JENTIK ) Vol. 4 No. 3 (2026): September: Jurnal Elektronika dan Teknik Informatika Terapan ( JENTIK )
Publisher : Politeknik Kampar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59061/jentik.v4i3.1622

Abstract

Soil fertility classification from nitrogen (N), phosphorus (P), and potassium (K) values can be embedded in low-cost devices, but the architecture and hyperparameters of a Backpropagation Neural Network (BPNN) are often chosen by trial and error, and the effect of sensor uncertainty is rarely examined. This study aims to find a lightweight BPNN configuration and evaluate it under simulated sensor noise. A dataset of 200 soil samples from Bengkalis Island and Sungai Pakning, labeled into three fertility classes, was used. Hidden-layer size, learning rate, and number of epochs were explored by grid search with 5-fold stratified cross-validation repeated three times, and Gaussian noise of 0–20% of each feature's range was added to the test data. Networks with at least two hidden neurons reached 100.00% accuracy without noise, whereas one hidden neuron reached 94.50%. Within 25 epochs, accuracy rose from 32.00% at a learning rate of 0.0001 to 100.00% at 0.1. The lightweight 3–2–3 configuration (17 parameters) matched the 3–12–8–3 reference (179 parameters) at every noise level, with 95.87% versus 95.57% accuracy at 10% noise, and trained about 30 times faster. A two-neuron BPNN is therefore sufficient for this dataset. The findings are limited to simulated noise and 200 samples, so validation with real RS485 sensor readings is required.  
Model Pengambilan Keputusan Multikriteria AHP-TOPSIS Berbasis Data Dasar Jalan (DD1) untuk Penanganan Jalan Provinsi di Riau Octadino Haryadi; Imam Rangga Bakti; Andi Saputra
Jurnal Elektronika dan Teknik Informatika Terapan ( JENTIK ) Vol. 4 No. 2 (2026): Juni: Jurnal Elektronika dan Teknik Informatika Terapan (JENTIK)
Publisher : Politeknik Kampar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59061/jentik.v4i2.1623

Abstract

The provincial road network in Riau covers 2897.46 km across 115 sections. About 37.4 percent of the network is in unstable condition, while limited funding prevents all damaged sections from being treated at the same time. This study develops a road treatment priority model using the Analytical Hierarchy Process and the Technique for Order Preference by Similarity to Ideal Solution. The model uses three criteria from Basic Road Data, namely road damage level, traffic volume, and accessibility. The Analytical Hierarchy Process determines the criteria weights and evaluates their consistency. The Technique for Order Preference by Similarity to Ideal Solution ranks 114 road sections based on their relative closeness values. The results show that road damage level is the most influential criterion. Severely damaged sections receive the highest priority, and 26 sections are recommended for reconstruction. The proposed model provides an objective and transparent priority ranking and can support provincial road treatment planning using existing data without additional surveys.
Experimental Evaluation of Smartphone GNSS Position Stability for Fisherman’s Trap Tracking under Different Update Intervals Teguh Junian Kuswanto; Mustika Kurnia Mayangsari; Santi Febrianti; Imam Nur Rokhim; Deanissa Azzahra Ramadhani
Jurnal Elektronika dan Teknik Informatika Terapan ( JENTIK ) Vol. 4 No. 2 (2026): Juni: Jurnal Elektronika dan Teknik Informatika Terapan (JENTIK)
Publisher : Politeknik Kampar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59061/jentik.v4i2.1624

Abstract

Smartphone-based Global Navigation Satellite System (GNSS) positioning provides an accessible solution for location tracking in small-scale fishing activities, particularly for recording and retrieving the locations of fisherman’s traps. However, the position generated by smartphone GNSS may fluctuate over time due to receiver characteristics, signal conditions, environmental effects, and the frequency of location updates. This study experimentally evaluates the stability of smartphone GNSS positions for fisherman’s trap tracking under different location update intervals. An Android-based tracking application was developed using React Native CLI and tested on a Xiaomi Redmi Note 12. Three location update intervals, namely 5, 10, and 30 seconds, were evaluated under controlled outdoor conditions. The collected data consisted of latitude, longitude, timestamp, and GNSS accuracy information, while reference coordinates were used to assess positional deviation. Position stability was evaluated using Haversine distance, Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), standard deviation, positional variance, and error distribution. The analysis was designed to determine how changes in update intervals affect the consistency and dispersion of smartphone-derived GNSS positions. The results are expected to identify the update interval that provides the most stable positioning performance for fisherman’s trap tracking while maintaining an appropriate temporal resolution for field operation. The findings can provide an empirical basis for configuring location update intervals in Android-based tracking applications for small-scale maritime activities.
Evaluasi Efisiensi Komputasi Model MobileNetV2 Berbasis TensorFlow Lite untuk Klasifikasi Kesegaran Tiga Spesies Ikan pada Perangkat Edge Aisyah Nur Nabila; Teguh Junian Kuswanto; Santi Febrianti; Nuke Amalia; Riyan Bagus Prihandanu; Rudy Suryadi; Emy Sofia
Jurnal Elektronika dan Teknik Informatika Terapan ( JENTIK ) Vol. 4 No. 2 (2026): Juni: Jurnal Elektronika dan Teknik Informatika Terapan (JENTIK)
Publisher : Politeknik Kampar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59061/jentik.v4i2.1627

Abstract

Fish freshness classification using computer vision offers a potential approach for rapid visual assessment. However, deploying deep learning models on edge devices requires consideration of both classification performance and computational efficiency. This study evaluates MobileNetV2 implemented with TensorFlow Lite for six-class image classification representing fresh and non-fresh conditions in three fish species: Johnius heterolepis, Rastrelliger brachysoma, and Nemipterus bathybius. The dataset described in this study consists of 372 images, comprising 300 training images and 72 validation images. Based on the confusion matrix presented, the model correctly classified 69 of the 72 validation images, yielding an accuracy of 95.83%. Misclassifications occurred in the non-fresh short mackerel class and the fresh large-scale croaker class. The computational evaluation framework considers model size, inference latency, throughput, and classification accuracy across Float32, Float16, and INT8 configurations. However, the efficiency values currently presented are illustrative scenarios rather than verified measurements obtained from converted models on a specified edge device. Therefore, no definitive conclusion can yet be drawn regarding the most computationally efficient configuration. Further experiments involving actual model conversion, consistent evaluation procedures, and device-level measurements are required. This study highlights the importance of evaluating classification performance alongside computational requirements when developing image-based fish freshness classification systems for edge deployment. The findings should be interpreted within the limitations of the available dataset and its labeling procedure.

Page 12 of 12 | Total Record : 118