cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Nuris Dwi Setiawan
Contact Email
elkom@stekom.ac.id
Phone
+6285641386859
Journal Mail Official
elkom@stekom.ac.id
Editorial Address
Jalan Majapahit No 605 Semarang
Location
Kota semarang,
Jawa tengah
INDONESIA
Elkom: Jurnal Elektronika dan Komputer
Published by Universitas Sains Dan Teknologi Komputer
ISSN : 19070012     EISSN : 27145417     DOI : https://doi.org/10.51903/elkom.v14i1
Core Subject : Education,
Education
Elkom : Jurnal Elektronika dan Komputer merupakan Jurnal yang diterbitkan oleh SEKOLAH TINGGI ELEKTRONIKA DAN KOMPUTER (STEKOM). Jurnal ini terbit 2 kali dalam setahun yaitu pada bulan Juli dan Desember. Misi dari Jurnal ELKOM adalah untuk menyebarluaskan, mengembangkan dan menfasilitasi hasil penelitian mengenai Ilmu bidang informatika, sebagai media bagi para dosen, guru, peneliti dan para praktisi dalam bidang teknologi informasi dari seluruh Indonesia, dalam melakukan pertukaran informasi tentang hasil-hasil penelitian terbaru yang telah dilakukan.
Arjuna Subject : -
Articles 661 Documents
 62   63   64   65   66 
Analisis Kinerja Metode Long Short-Term Memory (LSTM) dalam Klasifikasi Sentimen Ulasan Pengguna Shopee Muhimatul Ifadah; Bambang Irawan
Elkom: Jurnal Elektronika dan Komputer Vol. 18 No. 2 (2025): Desember : Jurnal Elektronika dan Komputer
Publisher : STEKOM PRESS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51903/elkom.v18i2.3407

Abstract

User reviews on the Shopee e-commerce platform represent an important source of information for understanding consumer perceptions of products and services. Sentiment analysis is commonly applied to classify user opinions into positive, neutral, and negative sentiment categories based on textual data. This study aims to analyze the performance of the Long Short-Term Memory (LSTM) method in sentiment classification of Shopee user reviews. The dataset used in this study consists of Indonesian-language user reviews that have undergone preprocessing stages, including case folding, text cleaning, tokenization, and stopword removal. The LSTM model was trained using preprocessed text represented as word sequences. Model performance was evaluated using overall accuracy and class-wise classification results. The experimental results indicate that the LSTM method achieved an overall accuracy of 87.62%. In addition, the classification performance for the positive sentiment class reached 95.27%, the neutral class achieved 4.96%, and the negative class reached 74.26%. These results demonstrate that the LSTM method performs well in classifying sentiment in Shopee user reviews, particularly for positive sentiment. This study is expected to provide insights and references for the application of deep learning methods in sentiment analysis of Indonesian e-commerce review data.
Implementasi Kontrol PID Pada Alat Negative Pressure Wound Therapy Naufal Adkha; Eka Nuryanto Budisusila
Elkom: Jurnal Elektronika dan Komputer Vol. 19 No. 1 (2026): Juli : Jurnal Elektronika dan Komputer
Publisher : STEKOM PRESS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51903/elkom.v19i1.3457

Abstract

This study aims to implement Proportional-Integral-Derivative (PID) control in a Negative Pressure Wound Therapy (NPWT) device to improve the precision and stability of negative pressure applied to wounds. NPWT is a standard therapy for complex wounds that applies subatmospheric pressure to accelerate healing. The developed system consists of three operating modes, namely continuous, intermittent, and dynamic, to tailor therapy based on wound type and patient needs. The prototype was built using main components including the XGZP101DB1R pressure sensor, ESP32 microcontroller, DC vacuum motor, and LCD Nextion interface. The PID algorithm was optimized through a trial-and-error method to achieve a stable response with minimal overshoot and fast response time. Test results show that the system can operate in a pressure range of -25 mmHg to -150 mmHg with very high accuracy, as indicated by an error percentage below 2% across all modes. PID control proved effective in maintaining pressure according to the setpoint, with a response time ranging from 12.8 to 15.8 seconds depending on the target pressure. Thus, this research successfully developed a precise, stable, and adaptive NPWT system, ready for further testing in clinical applications.
Development of a Digital-Based 360-Degree Performance Appraisal System to Enhance the Objectivity of Employee Evaluation Abdul Tahir; Jasman Jasman
Elkom: Jurnal Elektronika dan Komputer Vol. 19 No. 1 (2026): Juli : Jurnal Elektronika dan Komputer
Publisher : STEKOM PRESS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51903/elkom.v19i1.3665

Abstract

Employee performance appraisal is a strategic instrument in human resource management that directly influences competency development, job promotion, and remuneration policies. However, conventional top-down appraisal systems are often confronted with issues of subjectivity, evaluator bias, and limited transparency in the evaluation process. This study aims to develop a digital-based 360-degree performance appraisal system that integrates multi-source perspectives, including supervisors, peers, subordinates, and self-assessment, within a unified platform. The study employed an Agile-based system development method using an iterative approach, supported by data collection techniques consisting of literature review, business process observation, and in-depth interviews with stakeholders within higher education institutions. The system was designed using a web-based architecture with role-separated modules, a role-based access control (RBAC) authentication mechanism, and score normalization algorithms to ensure assessment consistency. The testing results indicate that the system successfully improves evaluation objectivity through standardized weighting distribution, enhances transparency through audit trail and real-time reporting features, and accelerates the recapitulation process by up to 78% compared to manual methods. Furthermore, the system effectively reduces single-evaluator bias and strengthens accountability in human resource management decision-making. This study concludes that the digitalization of 360-degree performance appraisal functions not merely as an automation tool, but as a strategic instrument for establishing a fair, transparent, and data-driven evaluation culture. 
Implementasi Convolutional Neural Network berbasis Transfer Learning untuk Klasifikasi Acute Lymphoblastic Leukemia Rana Adinda Manalus Fata; Jenny Putri Hapsari
Elkom: Jurnal Elektronika dan Komputer Vol. 19 No. 1 (2026): Juli : Jurnal Elektronika dan Komputer
Publisher : STEKOM PRESS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51903/elkom.v19i1.3679

Abstract

Leukemia is a cancer that originates in human blood cells. The most common type of leukemia (97%), with an incidence of 4–4.5 cases per 100,000 children per year, is Acute Lymphoblastic Leukemia (ALL). This indicates that leukemia can progress rapidly and become fatal for the patient within a few months. Therefore, a supporting method is needed that can classify blood cells automatically, quickly, and accurately. This method is a Convolutional Neural Network (CNN) using the EfficientNet-B3 architecture as a pre-trained model or for transfer learning. This dataset consists of 3,527 blood cell images that have been preprocessed to a size of 224x224x3 and image enhancement has been applied. The images were trained on the pre-trained model and then combined with Global Average Pooling (GAP), Batch Normalization, Dense, and Softmax layers until the model could classify the images into the ALL or HEM classes. The results of the study show that the EfficientNet-B3 architecture is capable of classifying white blood cell images into the ALL and HEM classes through the transfer learning process. The best hyperparameter configuration for optimal results includes a learning rate of 0.0001 and the RMSProp optimizer. The model achieved the best training accuracy of 100% at epoch 30 and a batch size of 16, while the best testing accuracy was 96% at epoch 50 and a batch size of 16. Additionally, the precision, recall, and F1-score were 96%, 94%, and 95%, respectively.
Perbandingan Metode Random Forest dan Convolutional Neural Network dalam Deteksi Website Phishing pada Lingkungan Universitas XYZ Elang Prasakti Ghani; Ria Putri Sunaryo
Elkom: Jurnal Elektronika dan Komputer Vol. 19 No. 1 (2026): Juli : Jurnal Elektronika dan Komputer
Publisher : STEKOM PRESS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51903/elkom.v19i1.3602

Abstract

Phishing attacks are a cybersecurity threat often used to steal sensitive user information through fake websites that resemble legitimate sites. Therefore, this study aims to analyze and compare the performance of the Random Forest and Convolutional Neural Network (CNN) algorithms in detecting phishing websites based on Uniform Resource Locator (URL) features. The dataset used was obtained from Web Application Firewall (WAF) security logs on the network infrastructure at XYZ University, which record URL access activities on the web system. The data was then processed and labeled into two categories: phishing and legitimate websites. The dataset used in this study consists of 549,346 URL records. The research stages include data exploration (Exploratory Data Analysis / EDA), URL text preprocessing, character-based feature extraction and URL tokenization, and model training using the Random Forest algorithm and a 1D Convolutional Neural Network (1D-CNN) architecture. Model evaluation was conducted using accuracy, precision, recall, and F1-score metrics as well as confusion matrix analysis. The results showed that the Random Forest model achieved an accuracy of 82.69%, while the 1D-CNN model achieved a higher accuracy of 95.94%. Furthermore, the CNN training process demonstrated a steady increase in accuracy and a decrease in loss values in each epoch. Based on these results, it can be concluded that the deep learning approach using CNN outperforms the Random Forest method in detecting URL-based phishing websites
Evaluasi dan Manajemen Infrastruktur Jaringan Lokal (LAN) pada Badan Penanggulangan Bencana Daerah (BPBD) Kabupaten Ciamis Muhammad Rofik Aprizani; Najwa Syafa Syahidah; Helmy Dzulfikar
Elkom: Jurnal Elektronika dan Komputer Vol. 19 No. 1 (2026): Juli : Jurnal Elektronika dan Komputer
Publisher : STEKOM PRESS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51903/elkom.v19i1.3606

Abstract

The Regional Disaster Management Agency (BPBD) of Ciamis Regency is an emergency institution that heavily relies on internet connectivity to support its operational functions, particularly in accessing disaster reporting applications. However, the existing local area network (LAN) infrastructure faces structural issues, including the absence of a structured failover mechanism, bandwidth management that lacks operational priority, and network segmentation without logical separation at the network layer. This study aims to evaluate the existing LAN infrastructure and formulate improvement recommendations using the first two stages of the Network Development Life Cycle (NDLC): Analysis and Design. Data were collected through direct observation and interviews with network administrators at the site. Evaluation results indicate that the primary issue lies not in bandwidth capacity, but in the governance layer and network distribution architecture. The proposed recommendations include implementing a Dual WAN topology with automatic Netwatch-based failover, tiered Simple Queue based on operational priority, VLAN-based network segmentation, and replacement of the hub with a managed switch. All recommendations are designed to be implemented using existing devices without requiring comprehensive new infrastructure procurement.
Pengembangan Sistem Backup Server EPrint dengan Ubuntu 24.04 ke Cloud Storage Nextcloud (Studi Kasus: Sekolah Tinggi Pariwisata (STP) Sahid Surakarta): Studi Kasus: Sekolah Tinggi Pariwisata (STP) Sahid Surakarta Paryanta Paryanta; Ernes Cahyo N.; Muhammad Johan Fatoni
Elkom: Jurnal Elektronika dan Komputer Vol. 19 No. 1 (2026): Juli : Jurnal Elektronika dan Komputer
Publisher : STEKOM PRESS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51903/elkom.v19i1.3638

Abstract

Managing scientific archive data on the EPrints Server at STP Sahid Surakarta faces issues with manual backups using WinSCP. This procedure leads to potential human error and the risk of data loss due to local storage, thus threatening important institutional information. The purpose of this research is to develop a scheduled automatic backup system for an Ubuntu 24.04-based Eprints server, utilizing two Virtual Private Servers (VPS) and Nextcloud as cloud storage. The development method used is the Software Development Life Cycle (SDLC) Waterfall model, which includes analysis, design, implementation, and testing. The system implementation involves using bash scripts, cron, mysqldump, tar, and rclone for backup and restore functions. The system's functionality is verified through Black Box Testing. The test results show that the automatic backup system works consistently and as planned. Additionally, the restore function successfully recovered the entire data component and rolled back old data, complete with satisfactory activity log recording. This system provides a more efficient and controlled backup solution, addressing the weaknesses of the old system analyzed using the PIECES framework (performance, information, economy, control, efficiency, and service).
Penyeimbangan Beban Jaringan 20kV Terhadap Rugi-Rugi Daya Menggunakan Perangkat Lunak ETAP PT PLN (Persero) ULP Cijawura ridwan Muhamad ridwan
Elkom: Jurnal Elektronika dan Komputer Vol. 19 No. 1 (2026): Juli : Jurnal Elektronika dan Komputer
Publisher : STEKOM PRESS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51903/elkom.v19i1.3642

Abstract

Ketidakseimbangan beban pada sistem distribusi tenaga listrik merupakan salah satu permasalahan yang dapat menurunkan kualitas daya serta meningkatkan rugi-rugi daya pada jaringan. Penelitian ini bertujuan untuk menganalisis kondisi ketidakseimbangan beban serta melakukan upaya penyeimbangan beban pada sisi sekunder transformator distribusi berdasarkan data hasil pengukuran di lapangan. Metode yang digunakan meliputi pengumpulan data arus pada masing-masing fasa, perhitungan persentase ketidakseimbangan beban, serta evaluasi terhadap pembagian beban sebelum dan sesudah dilakukan penyeimbangan. Hasil analisis menunjukkan bahwa sebelum dilakukan penyeimbangan, terdapat perbedaan arus yang cukup signifikan antar fasa yang mengindikasikan kondisi tidak seimbang. Setelah dilakukan redistribusi beban, nilai ketidakseimbangan mengalami penurunan sehingga arus pada masing-masing fasa menjadi lebih merata. Kondisi ini berdampak pada peningkatan efisiensi sistem serta penurunan rugi-rugi daya pada jaringan distribusi. Dengan demikian, penyeimbangan beban merupakan langkah yang efektif dalam meningkatkan kinerja dan keandalan sistem distribusi tenaga listrik.
Perancangan Smart Server System Berbasis Monitoring Suhu, Kelembapan, dan Keamanan Akses di CV Gundara Solusi Bersama Ungaran Aizaas Vianansa Rochmawan; Priyadi Priyadi; Candra Supriadi
Elkom: Jurnal Elektronika dan Komputer Vol. 19 No. 1 (2026): Juli : Jurnal Elektronika dan Komputer
Publisher : STEKOM PRESS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51903/elkom.v19i1.3659

Abstract

Server rack management at CV Gundara Solusi Bersama Ungaran previously relied on conventional room cooling and manual door locking mechanisms without environmental monitoring and access logging. This condition increases the risk of hardware overheating, excessive humidity, and unauthorized physical access. This study proposes a Smart Server System based on the ESP32 microcontroller to integrate temperature and humidity monitoring, automatic thermal control, electronic access security, and cloud-based logging within a single Internet of Things (IoT) platform. The system utilizes an SHT21 sensor, dual DC cooling fans controlled through a relay module, a 4×4 keypad for PIN authentication, a solenoid door lock, an LCD 20×4 I2C display, and Google Sheets integration through an HTTPS REST API. The cooling mechanism activates automatically when the temperature exceeds 27°C or humidity exceeds 65% RH, while access events are recorded in real time to cloud storage. The system was developed using an iterative Research and Development (R&D) prototyping approach and evaluated through functional, performance, and reliability testing. Experimental results show that the proposed system achieved a temperature measurement MAE of 0.220°C, humidity MAE of 0.724% RH, average response times below 3 seconds for cooling and access control operations, logging completeness of 100%, and system uptime of 99.7% during a 72-hour continuous test. The proposed system provides an affordable and integrated solution for thermal management and physical security monitoring of server infrastructure in small and medium enterprises (SMEs).
Pengembangan Sistem Kendali Cerdas Alat Pemberi Isyarat Lalu Lintas (APILL) Berbasis Machine Learning Saut Mampetua Siregar; Enry Firmana
Elkom: Jurnal Elektronika dan Komputer Vol. 19 No. 1 (2026): Juli : Jurnal Elektronika dan Komputer
Publisher : STEKOM PRESS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51903/elkom.v19i1.3667

Abstract

In modern cities, population growth directly contributes to an increase in the number of vehicles, leading to significant traffic problems and a decline in road service quality and capacity. Conventional traffic light control systems (APILL) that rely on fixed-time scheduling often fail to adapt to the dynamic nature of traffic conditions, potentially exacerbating congestion. This study proposes an innovative approach to traffic management by utilizing the YOLO (You Only Look Once) object detection algorithm. By analyzing CCTV streaming data at intersections, the system dynamically assesses traffic density, identifies vehicle types, and adjusts signal timings in real-time. Leveraging YOLO's ability to perform fast and accurate object detection, the system can respond to traffic conditions in a timely manner. This approach integrates Artificial Intelligence (AI) and Machine Learning techniques to address the urgent need for adaptive traffic management strategies in urban areas. The primary goals of this solution are to reduce congestion, improve traffic flow, and minimize environmental impact. Therefore, the integration of YOLO technology with adaptive traffic signal control algorithms represents a strategic step toward addressing the complex challenges of urban traffic congestion.

Page 64 of 67 | Total Record : 661

 62   63   64   65   66 

Filter by Year

2007 2026


Reset
Filter By Issues
All Issue Vol. 19 No. 1 (2026): Juli : Jurnal Elektronika dan Komputer Vol. 18 No. 2 (2025): Desember : Jurnal Elektronika dan Komputer Vol. 18 No. 1 (2025): Juli : Jurnal Elektronika dan Komputer Vol. 17 No. 2 (2024): Desember : Jurnal Elektronika dan Komputer Vol 17 No 1 (2024): Juli : Jurnal Elektronika dan Komputer Vol. 17 No. 1 (2024): Juli : Jurnal Elektronika dan Komputer Vol. 16 No. 2 (2023): Desember : Jurnal Elektronika dan Komputer Vol 16 No 2 (2023): Desember : Jurnal Elektronika dan Komputer Vol. 16 No. 1 (2023): Juli : Jurnal Elektronika dan Komputer Vol 16 No 1 (2023): Juli : Jurnal Elektronika dan Komputer Vol 15 No 2 (2022): Desember : Jurnal Elektronika dan Komputer Vol. 15 No. 2 (2022): Desember : Jurnal Elektronika dan Komputer Vol 15 No 1 (2022): Juli : Jurnal Elektronika dan Komputer Vol. 15 No. 1 (2022): Juli : Jurnal Elektronika dan Komputer Vol 14 No 2 (2021): Desember: Jurnal Elektronika dan Komputer Vol 14 No 1 (2021): Juli: Jurnal Elektronika dan Komputer Vol 13 No 2 (2020): Desember: Jurnal Elektronika dan Komputer Vol 13 No 1 (2020): Juli: Jurnal Elektronika dan Komputer Vol 12 No 2 (2019): Desember: Jurnal Elektronika dan Komputer Vol 12, No 1 (2019) Vol 12 No 1 (2019): Juli: Jurnal Elektronika dan Komputer Vol 11 No 2 (2018): Desember: Jurnal Elektronika dan Komputer Vol 11 No 1 (2018): Juli: Jurnal Elektronika dan Komputer Vol 11, No 1 (2018) Vol 10, No 1 (2017) Vol 9, No 1 (2016) Vol 9, No 1 (2016) Vol 8, No 1 (2015) Vol 8, No 1 (2015) Vol 7, No 2 (2014) Vol 7, No 2 (2014) Vol 6, No 2 (2013) Vol 6, No 2 (2013) Vol 5, No 2 (2012) Vol 4, No 1 (2007) More Issue