cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Andik Yulianto
Contact Email
andik@uib.ac.id
Phone
+62811693767
Journal Mail Official
andik@uib.ac.id
Editorial Address
Jl. Gajah Mada, Baloi Permai, Kec. Sekupang, Kota Batam, Kepulauan Riau
Location
Kota batam,
Kepulauan riau
INDONESIA
Telcomatics
Published by Universitas Internasional Batam
ISSN : -     EISSN : 25415867     DOI : http://dx.doi.org/10.37253/telcomatics.v5i1.838
Core Subject : Science, Engineering,
Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering
Telcomatics is a peer reviewed Journal in English or Bahasa Indonesia published two issues per year (June and December). The aim of Telcomatics is to publish articles dedicated to all aspects of the latest outstanding developments in the field of Electrical Engineering and Information System. Telcomatics Journal welcomes full research articles in the following engineering subject areas: Telecommunication and Information Technology Applied Computing and Computer Instrumentation and Control Electronic Computer Security Computer Network Image Processing Mechatronic and Robotic Network Traffic Modeling Game Technology Intelligent System
Arjuna Subject : Teknik (semua kategori) - Teknik (Lain-Lain)
Articles 99 Documents
 6   7   8   9   10 
Perancangan dan Pengembangan Smart Pet Feeder dengan Aplikasi Mobile Blynk dan ESP8266 Haris Sulthan; Jerry Beltsazar Nainggolan; Muhammad Rafli Alamsyah; Mohammad Rabby Afrizie; Andik Yulianto
Telcomatics Vol. 11 No. 1 (2026)
Publisher : Universitas Internasional Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37253/telcomatics.v11i1.11051

Abstract

This research presents the design and development of a Smart Pet Feeder system based on the Internet of Things (IoT) using the Blynk platform to simplify pet feeding management. The primary goal of this system is to ensure consistent feeding schedules, reduce manual intervention, and provide remote control and monitoring capabilities. The system utilizes the ESP8266 microcontroller integrated with a load cell sensor and servo motor to dispense pet food accurately. Real-time data on remaining food levels is transmitted to the Blynk Cloud, allowing users to monitor food stock, schedule feeding times, and receive notifications when the stock is running low.The methodology involves a multi-layer communication architecture: perception layer for data acquisition, communication layer for connectivity, data processing layer for cloud-based analysis, and application layer for user interaction. The load cell measures food weight, while the servo motor dispenses food based on user input via the Blynk interface. The implementation results demonstrate that the system effectively reduces manual feeding tasks, prevents overfeeding, and optimizes food efficiency. This innovative approach not only enhances convenience for pet owners but also promotes sustainable pet care practices by ensuring precise and timely feeding.
Pendekatan Klasifikasi Random Forest untuk Identifikasi URL Berbahaya yang Akurat Haeruddin Haeruddin; Elvert; Andik Yulianto; Sabariman Sabariman
Telcomatics Vol. 10 No. 2 (2025)
Publisher : Universitas Internasional Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37253/telcomatics.v10i2.11173

Abstract

Internet users currently face significant risks from malicious URLs that facilitate phishing attacks, malware distribution, and data theft. Traditional blacklisting methods have become ineffective against evolving cyberattack techniques. This study proposes a Random Forest classification approach for more accurate malicious URL detection, focusing on critical URL features including URL length, presence of special keywords, subdomain structure, and special character usage. these features train the Random Forest model to distinguish between safe and malicious URLs. We evaluate model effectiveness using accuracy, precision, and recall metrics. This research aims to develop a Random Forest-based malicious URL detection system that is more accurate and adaptive than conventional methods. The study examines both the advantages and limitations of this approach, along with its potential as a reliable detection solution for dynamic digital environments. Evaluation results demonstrate an overall accuracy of 94%, weighted average F1-score of 0.94, and macro average F1-score of 0.94.
Penerapan Algoritma K-Means untuk Pengelompokan Halte Transjakarta Berdasarkan Aktivitas Harian Penumpang Esteria Rohanauli Sidauruk; Anisa Fitriyani; Akmal Faiz Abdillah; M Syamsuddin Wisnubroto; Fajri Farid
Telcomatics Vol. 11 No. 1 (2026)
Publisher : Universitas Internasional Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37253/telcomatics.v11i1.11462

Abstract

Ketidakseimbangan aktivitas di halte bus Transjakarta, yang menyebabkan kemacetan dan penumpukan penumpang pada titik-titik tertentu, menjadi tantangan penting dalam peningkatan efisiensi layanan transportasi publik perkotaan. Penelitian ini bertujuan untuk mengelompokkan halte bus Transjakarta berdasarkan pola aktivitas penumpang harian (pagi, siang, sore, dan malam) menggunakan algoritma K-Means Clustering pada dataset transaksi Transjakarta. Setelah tahap pra-pemrosesan data dan penentuan jumlah klaster optimal dengan metode Elbow, diperoleh dua klaster (K=2) yang menunjukkan perbedaan signifikan.Klaster 0 merepresentasikan halte dengan tingkat aktivitas rendah yang menandakan pemanfaatan minimal, sedangkan Klaster 1 mencakup halte dengan volume aktivitas tinggi, terutama padaperiode sore hari. Visualisasi peta interaktif menunjukkan distribusi geografis yang jelas: halte dengan aktifitas sibuk (berwarna merah) terkonsentrasi di pusat kota Jakarta, sementara halte dengan aktifitas rendah (berwarna biru) tersebar di wilayah pinggiran. Hasil pengelompokan ini dapat dimanfaatkan oleh manajemen Transjakarta dan Dinas Perhubungan DKI Jakarta sebagai dasar dalam pengambilan keputusan strategis, seperti pengalokasian armada dan penyesuaian jadwal keberangkatan yang lebih adaptif terhadap tingkat permintaan di Klaster 1, serta evaluasi efektivitas operasional halte di Klaster 0. Evaluasi model menghasilkan nilai Silhouette Score sebesar 0.7205 yang menandakan pemisahan klaster yang baik, dan Davies-Bouldin Index sebesar 0.8763, yang mengindikasikan klaster yang cukup kompak dan terpisah. Penelitian ini memberikan kontribusi praktis bagi perencanaan transportasi publik berbasis data dalam mendukung kebijakan distribusi layanan yang lebih merata di seluruh jaringan Transjakarta.
Implementasi K-Means Mengelompokkan Kabupaten/Kota Berdasarkan Faktor Sosial-Ekonomi untuk Prioritas Alokasi Bantuan Sumatera Selatan 2023 Asa Do'a Uyi; Siti Nur Aarifah; Dwi Ratna Anggraeni; M. Syamsuddin Wisnubroto; Fajri Farid
Telcomatics Vol. 11 No. 1 (2026)
Publisher : Universitas Internasional Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37253/telcomatics.v11i1.11546

Abstract

Pembangunan manusia merupakan salah satu indikator utama keberhasilan pembangunan suatu daerah yang menjadi dasar perencanaan pembangunan berkelanjutan. Penelitian ini bertujuan mengelompokkan kabupaten/kota di Provinsi Sumatera Selatan berdasarkan indikator sosial-ekonomi yang membentuk Indeks Pembangunan Manusia (IPM) dengan menerapkan algoritma K-Means Clustering. Data yang digunakan berasal dari Badan Pusat Statistik (BPS) tahun 2023. Kualitas hasil klasterisasi dievaluasi melalui Davies-Bouldin Index dan Silhouette Score untuk menilai tingkat pemisahan antar klaster dan konsistensi data. Hasil analisis menunjukkan terbentuknya tiga kelompok wilayah rendah, sedang, dan tinggi dengan distribusi masing-masing 3, 13, dan 1 daerah. Temuan ini mengindikasikan masih adanya ketimpangan kualitas pembangunan manusia di Sumatera Selatan, terutama pada aspek pendidikan dan pengeluaran riil per kapita. Nilai Davies-Bouldin Index sebesar 0,9698 dan Silhouette Score sebesar 0,3313 menunjukkan bahwa hasil pengelompokan cukup baik dan dapat digunakan sebagai acuan dalam penentuan prioritas alokasi bantuan. Dengan demikian, penerapan algoritma K-Means dapat membantu pemerintah daerah dalam memetakan kondisi pembangunan manusia secara objektif dan mendukung pengambilan kebijakan yang lebih tepat sasaran.
Public Sentiment Analysis Toward the Ministry of Finance 2025 Using Recurrent Neural Network Methods Based on Data from Sosial Media X Muhammad Regi Abdi Putra Amanta; M. Syamsuddin Wisnubroto; Fajri Farid; Aditya Rahman; Sofyan Fauzi Dzaki Arif
Telcomatics Vol. 11 No. 1 (2026)
Publisher : Universitas Internasional Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37253/telcomatics.v11i1.11645

Abstract

The Ministry of Finance plays a strategic role in maintaining national economic stability through fiscal policy management, taxation, public debt administration, and state budget control. In today’s digital era, social media platforms such as X have become important channels for the public to express opinions about government policies. This study analyzes public perceptions of the Ministry of Finance’s performance using machine-learning-based sentiment analysis and identifies the most effective classification model. Data were collected from public posts on X and processed using text mining and Natural Language Processing (NLP). Three Recurrent Neural Network (RNN) models were tested: Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and an improved variant, LSTM_G. The findings show that negative sentiment dominates at 43.0%, followed by neutral at 33.9% and positive at 23.1%. Among the models, LSTM_G achieved the highest accuracy of 78.98%, indicating strong capability in capturing sequential patterns in dynamic, unstructured social media text. These results reflect substantial public concerns regarding fiscal policies and demonstrate the usefulness of sentiment analysis as a data-driven tool for decision-making and for strengthening public communication strategies to enhance the Ministry’s digital reputation.
Evaluasi Komparatif Model Transferlearning untuk Klasifikasi Tanaman Aquascape Muhammad Ilham Ashiddiq Tresnawan; Ni'matul Ma'muriyah; Sabariman; Lesley Peterson Lee
Telcomatics Vol. 11 No. 1 (2026)
Publisher : Universitas Internasional Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37253/telcomatics.v11i1.12440

Abstract

The popularity of aquascaping has increased significantly in recent years. However, beginners often face difficulties in identifying aquatic plant species due to their highly similar visual characteristics, which may lead to improper plant care. This study evaluates and compares the performance of three Convolutional Neural Network (CNN) architectures, namely MobileNetV3 Large, ResNet18, and EfficientNet-B0, for classifying six aquascape plant species: Anubias, Bucephalandra, Cryptocoryne Wendtii, Floaters, Hornwort, and Vallisneria Spiralis. The dataset consists of 1,998 images resized to 224 × 224 pixels and enhanced through data augmentation techniques, including rotation, horizontal flip, color jitter, and Gaussian blur, to improve model generalization. The models were trained using the PyTorch framework with transfer learning, fine-tuning based on ImageNet pretrained weights, the AdamW optimizer, class weighting, and an early stopping strategy. Experimental results show that ResNet18 achieved the highest test accuracy of 92.7%, followed by EfficientNet-B0 with 90.3% and MobileNetV3 Large with 88.7%. These findings indicate that the residual learning architecture of ResNet18 is particularly effective for aquatic plant classification on the proposed dataset, while MobileNetV3 Large remains a suitable alternative for deployment on resource-constrained devices.
Analisis Pengaruh Seo dan Iklan Online Terhadap Keputusan Pembelian Konsumen Kerry, Winson John; Elisa, Lilis; Hoverio, Auron Rafael; Dalon, Dalon; Jaya, Oki
Telcomatics Vol. 10 No. 2 (2025)
Publisher : Universitas Internasional Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37253/telcomatics.v10i2.11310

Abstract

The use of Search Engine Optimization (SEO) technology and online advertising as a marketing medium shows how marketing strategies have shifted in the digital era. Although both are widely used, the effectiveness of this strategy on purchasing decisions is not fully clear yet. This study tries to find out how much influence SEO and online advertising have on online purchasing decisions. The method used is a quantitative approach with a survey technique by distributing questionnaires to 400 students of Universitas Internasional Batam (UIB) class of 2023–2024. Data analysis was carried out using the Structural Equation Modeling (SEM) method using SmartPLS 3.2.9 software. The results of the study show that both SEO and online advertising have a real effect on online purchasing decisions. SEO contributes to increasing visibility and trust in a product, while online advertising helps catch the consumer attention and buying interest. Hopefully, this research can be a helpful guide for for business actors in developing effective digital marketing strategies, as well as increasing public understanding of the importance of the role of SEO and online advertising in influencing purchasing decisions in the digital era.
Product Quality Classification Based on Machine Learning in the Quality Control System of the Laser Metal Deposition Process Elok Fiola; Rahma Neliyana; Try Yani Rizki Nur Rohmah; M. Syamsuddin Wisnubroto; Fajri Farid
Telcomatics Vol. 10 No. 2 (2025)
Publisher : Universitas Internasional Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37253/telcomatics.v10i2.11432

Abstract

Industry 4.0 revolutionizes modern manufacturing by enabling the active integration of smart sensors and machine learning to optimize product quality control systems. This research focuses on classifying product quality in the Laser Metal Deposition (LMD) process by applying three machine learning algorithms, namely Decision Tree (DT), Random Forest (RF), and Support Vector Machine (SVM). The dataset consists of four numerical sensor variables, including Optical Sensor, Laser Power, Pressure, and Temperature, with Defect Label as the binary target variable. The Synthetic Minority Oversampling Technique (SMOTE) is used to balance the class distribution. Correlation analysis reveals weak linear relationships among all variables, suggesting the presence of complex non-linear interactions. The Random Forest model produces the best performance with accuracy of 0.88, recall of 0.79, and AUC of 0.80, outperforming Decision Tree and SVM. These findings indicate that ensemble-based methods effectively capture complex patterns within sensor data and offer reliable predictions for quality control in metal manufacturing industries, particularly within Laser Metal Deposition processes.
Analisis Sentimen Review Aplikasi Chat GPT dengan Memanfaatkan Algoritma Support Vector Machine Alit Damar Prabadaru; Ashifa Zahrawati; Muhammad Agmal Jibran; Salsabila Nurulita; Nadya Cantika Apriani Dewana
Telcomatics Vol. 10 No. 2 (2025)
Publisher : Universitas Internasional Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37253/telcomatics.v10i2.11759

Abstract

This study analyses user sentiment toward the ChatGPT application based on reviews collected from the Google Play Store. The goal of this research is to classify user opinions into positive and negative categories using the Support Vector Machine (SVM) algorithm. The dataset was obtained through web scraping and processed using several text preprocessing steps, including case folding, tokenization, stopword removal, and stemming. The TF-IDF method was applied to convert the text into numerical feature vectors suitable for machine learning models. A linear SVM model was used to perform sentiment classification due to its effectiveness in handling high-dimensional text data. The results of the evaluation show that the linear SVM provides stable and accurate performance when identifying sentiment in user reviews. The findings also indicate that TF-IDF features contribute significantly to improving model accuracy. Overall, this research concludes that SVM is a suitable and reliable method for sentiment analysis of application reviews. The outcomes can help developers understand user perceptions and improve the quality of the ChatGPT application based on the insights obtained

Page 10 of 10 | Total Record : 99

 6   7   8   9   10 

Filter by Year

2016 2026


Reset
Filter By Issues
All Issue Vol. 11 No. 1 (2026) Vol. 10 No. 2 (2025) Vol. 10 No. 1 (2025) Vol. 9 No. 2 (2024) Vol. 9 No. 1 (2024) Vol. 8 No. 2 (2023) Vol 8 No 1 (2023) Vol. 8 No. 1 (2023) Vol 7 No 2 (2022) Vol 7 No 1 (2022) Vol 7 No 1 (2022): (in press) Vol 6 No 2 (2021) Vol 6 No 1 (2021) Vol 5 No 2 (2020) Vol 5 No 1 (2020) Vol 4 No 2 (2019) Vol. 4 No. 2 (2019) Vol. 4 No. 1 (2019) Vol 4 No 1 (2019) Vol 3 No 2 (2018) Vol 2 No 2 (2017) Vol. 2 No. 2 (2017) Vol. 1 No. 1 (2016) Vol 1 No 1 (2016) More Issue