cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Hafiz Irsyad
Contact Email
hafizirsyad@mdp.ac.id
Phone
+6281373740969
Journal Mail Official
hafizirsyad@mdp.ac.id
Editorial Address
Universitas Multi Data Palembang, Kampus Rajawali. Jl. Rajawali no 14 Palembang
Location
Kota palembang,
Sumatera selatan
INDONESIA
Algoritme Jurnal Mahasiswa Teknik Informatika
Published by Universitas Multi Data Palembang
ISSN : -     EISSN : 27758796     DOI : https://doi.org/10.35957/algoritme.v2i2
Core Subject : Science,
Computer Science & IT
Jurnal Algoritme menjadi sarana publikasi artikel hasil temuan Penelitian orisinal atau artikel analisis. Bahasa yang digunakan jurnal adalah bahasa Inggris atau bahasa Indonesia. Ruang lingkup tulisan harus relevan dengan disiplin ilmu seperti: - Machine Learning - Computer Vision, - Artificial Inteledence, - Internet Of Things, - Natural Language Processing, - Image Processing, - Cyber Security, - Data Mining, - Game Development, - Digital Forensic, - Pattern Recognization, - Virtual & AUmented Reality,. - Cloud Computing, - Game Development, - Mobile Application, dan - Topik kajian lainnya yang relevan dengan ilmu teknik informatika.
Arjuna Subject : Ilmu Komputer (semua kategori) - Kecerdasan Buatan
Articles 120 Documents
 8   9   10   11   12 
Pengelompokan Komoditas Ekspor Laut Indonesia Berbasis K-Means Clustering dalam Sistem Informasi WEB Juseka, Christien Julio; Fibriani, Charitas
Algoritme Jurnal Mahasiswa Teknik Informatika Vol 6 No 2 (2026): April 2026 || Algoritme Jurnal Mahasiswa Teknik Informatika
Publisher : Program Studi Teknik Informatika Universitas Multi Data Palembang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35957/algoritme.v6i2.13737

Abstract

This research presents the design of a web-based information system (SILAUTINA) for clustering Indonesia's marine export commodities based on their economic potential. The dataset was obtained from the Ministry of Marine Affairs and Fisheries, containing attributes such as commodity name, export volume (tons), and export value (million USD). Data preprocessing involved cleaning, normalization, and clustering using the K-Means algorithm with K=3, which was determined objectively through the Elbow and Silhouette methods. The results yielded three main clusters: superior, potential, and super superior, classified based on average export volume and value. The system was built using the Flask framework and visualized the results through interactive Scatter plots. Evaluation using Silhouette Score (0.62) and Davies–Bouldin Index (0.49) demonstrated that the applied method effectively maps the economic potential of marine commodities. The SILAUTINA system can be utilized as a data-driven decision-making tool for policymakers in strategic marine export planning. Thus, this research not only provides a validated clustering methodology but also delivers an operational platform that can be readily adopted by stakeholders in the maritime sector.
Classification of Smoking Addiction Levels Among Universitas Malikussaleh Students Using the C4.5 Algorithm Mundirawati, Cut; Qamal, Mukti; Rosnita, Lidya
Algoritme Jurnal Mahasiswa Teknik Informatika Vol 6 No 2 (2026): April 2026 || Algoritme Jurnal Mahasiswa Teknik Informatika
Publisher : Program Studi Teknik Informatika Universitas Multi Data Palembang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35957/algoritme.v6i2.13809

Abstract

This study addresses the subjective determination of smoking addiction levels among students at Malikussaleh University by implementing the C4.5 algorithm. Using a data mining approach based on entropy and gain ratio, the research objectively classifies addiction levels. Data was gathered from 300 respondents, divided into 240 training and 60 testing samples, covering attributes such as cigarettes per day, smoking duration, and the first cigarette after waking. Analysis reveals that cigarettes per day yielded the highest gain ratio (0.2717), serving as the decision tree's root. The classification identified 95 students with mild, 148 moderate, 55 severe, and 2 very severe addiction. Model evaluation via a confusion matrix showed 80% accuracy, 64.5% precision, 56.8% recall, and a 58.9% F1-score. The C4.5 algorithm proved effective in building an interpretative model using IF–THEN rules. These findings provide a solid foundation for university health policies, prevention programs, and early identification of high-addiction risks among students.
Klasterisasi Kategori Judul Buku Pada Perpustakaan Dengan Menggunakan Metode HDBSCAN Laksono, Ivan Luthfi; Pribadi, Muhammad Rizky
Algoritme Jurnal Mahasiswa Teknik Informatika Vol 6 No 2 (2026): April 2026 || Algoritme Jurnal Mahasiswa Teknik Informatika
Publisher : Program Studi Teknik Informatika Universitas Multi Data Palembang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35957/algoritme.v6i2.14011

Abstract

To assist in library collection management, this study aims to create a system that can automatically classify book titles. Previous studies have mostly used K-Means and DBSCAN because they have limitations in determining the number of clusters and are less responsive to varying densities of text data. Furthermore, HDBSCAN is still limited to clustering Indonesian-language book titles. The dataset consists of 1044 book titles that were processed through text preprocessing, TF-IDF weighting, and dimension reduction using Singular Value Decomposition (SVD). When HDBSCAN was used for clustering and compared with DBSCAN, the results showed that the combination of SVD and HDBSCAN had better cluster quality with a Silhouette value of 0.158 and a lower noise level. This study scientifically demonstrates that improving the stability of cluster structures in large book title data can be achieved through the integration of dimension reduction and density-based clustering.
Klasifikasi Suara Lingkungan Berbasis ResNet-50 untuk Penyandang Gangguan Pendengaran Berbasis Android Kurniawan, Felix; Rahman, Abdul
Algoritme Jurnal Mahasiswa Teknik Informatika Vol 6 No 2 (2026): April 2026 || Algoritme Jurnal Mahasiswa Teknik Informatika
Publisher : Program Studi Teknik Informatika Universitas Multi Data Palembang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35957/algoritme.v6i2.14281

Abstract

Individuals with hearing impairments often have difficulty recognizing environmental sounds that are important for daily activities. This study presents an Android-based environmental sound classification application built on a Convolutional Neural Network (CNN) using the ResNet-50 architecture. The model was trained on the ESC-50 dataset (2,000 samples across 50 classes); each audio file was converted into three-channel images (log-Mel spectrogram, delta, delta-delta) as model input. Hyperparameter tuning identified an optimal configuration (epoch=100, batch size=16, learning rate=0.001). The trained model achieved strong performance with training accuracy ≈ 93.19% and testing accuracy ≈ 92%, and average precision ≈ 0.93, recall ≈ 0.92, and F1-score ≈ 0.92. Field tests revealed degraded performance under high noise levels and at increased distances; usability evaluation yielded Usefulness = 90.30%, Satisfaction = 87.57%, and Ease of Use = 89.09% (mean = 88.98%). These results indicate ResNet-50 is effective for environmental sound classification in controlled settings, while enhanced pre-processing (noise handling) is recommended for robust real-world deployment.
Analisis Performa Model Klasifikasi Otomatis Beragam Jenis Jeruk Menggunakan Pendekatan Metode YOLOv5-CNN Halawa, Paskah Lina; Himamunanto, Agustinus Rudatyo
Algoritme Jurnal Mahasiswa Teknik Informatika Vol 6 No 2 (2026): April 2026 || Algoritme Jurnal Mahasiswa Teknik Informatika
Publisher : Program Studi Teknik Informatika Universitas Multi Data Palembang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35957/algoritme.v6i2.15554

Abstract

Manual classification of citrus fruit varieties is time-consuming and error-prone, making an automated digital image-based system essential to support farmers and traders in distribution, pricing, and quality standardization. Previous research has shown that CNN and YOLO are effective in fruit classification, but the models still have difficulty distinguishing classes with visual similarities and under different lighting conditions. This research focuses on analyzing the performance of a YOLOv5-CNN-based citrus fruit classification model, with YOLOv5 used to detect objects and generate bounding boxes, and then the detected areas are classified by EfficientNet-B0. Testing on an independent dataset of 960 images showed an accuracy of 96%. These results indicate that the developed model is effective for automatic citrus fruit classification, providing a basis for the development of a digital image-based fruit sorting and identification system.
Analisis Sentimen Berbasis ASOQE dan Taksonomi pada Program MBG di X mendrofa, victor crisman; Berutu, Sunneng Sandino; Budiati, Haeni
Algoritme Jurnal Mahasiswa Teknik Informatika Vol 6 No 2 (2026): April 2026 || Algoritme Jurnal Mahasiswa Teknik Informatika
Publisher : Program Studi Teknik Informatika Universitas Multi Data Palembang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35957/algoritme.v6i2.15636

Abstract

The Free Nutritious Meal (MBG) program faces implementation challenges regarding distribution, menu quality, and budget sustainability, sparking diverse public discourse on social media. This study analyzes public sentiment toward the MBG program using an Aspect-Opinion-Qualifier Extraction (ASOQE) approach based on policy taxonomy. The dataset was obtained from X (formerly Twitter) via web scraping and processed through standardized text preprocessing. Automatic annotation used a lexicon-based BIO labeling approach to generate a silver-standard dataset. The classification model was trained using an IndoBERT-BiLSTM architecture to identify contextual aspects and opinions. Inference results were mapped into five sentiment classes and five policy dimensions: nutritional quality, implementation, social impact, policy, and effectiveness. Evaluation showed excellent performance, with F1-scores exceeding 0.98. Findings reveal that social impact and implementation dimensions dominate public discourse, showing significantly positive sentiment. This research demonstrates the potential of Aspect-Based Sentiment Analysis as a data-driven tool for comprehensive public policy evaluation.
Analisis Sentimen Berbasis Aspek Program Koperasi Desa Merah Putih Menggunakan IndoBERT gea, yuris mardayani; Berutu, Sunneng Sandino; Jatmika, Jatmika
Algoritme Jurnal Mahasiswa Teknik Informatika Vol 6 No 2 (2026): April 2026 || Algoritme Jurnal Mahasiswa Teknik Informatika
Publisher : Program Studi Teknik Informatika Universitas Multi Data Palembang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35957/algoritme.v6i2.15711

Abstract

The Koperasi Desa Merah Putih program is a strategic initiative requiring evaluation through public perception monitoring. This study employs Aspect-Based Sentiment Analysis (ABSA) using the IndoBERT transformer model via a two-stage approach: aspect-opinion extraction using BIO labeling (Token Classification) and sentiment polarity determination (Sequence Classification). A dataset of 12,013 entries from Platform X underwent systematic preprocessing and was trained using an 80:20 stratified split to ensure label balance. Model performance, evaluated through accuracy, precision, recall, and F1-score, demonstrated high reliability with 79% accuracy. Collectively, the analysis identified 4,917 neutral, 3,961 negative, and 3,135 positive opinions. Specifically, the "Economy" aspect recorded 1,673 positive opinions, reflecting public optimism regarding the program's economic impact. These results confirm that Deep Learning-based approaches provide granular insights into policy effectiveness, serving as an accurate decision-support instrument for cooperative program managers at the village level to improve policy implementation based on data-driven evidence.
Evaluasi Implementasi PWA terhadap Performa Website dengan Lighthouse dan Chrome DevTools Siregar, Master Edison
Algoritme Jurnal Mahasiswa Teknik Informatika Vol 6 No 2 (2026): April 2026 || Algoritme Jurnal Mahasiswa Teknik Informatika
Publisher : Program Studi Teknik Informatika Universitas Multi Data Palembang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35957/algoritme.v6i2.15712

Abstract

Website performance is a critical determinant of user experience and digital service efficiency. This study evaluates the impact of Progressive Web App (PWA) implementation on performance using Google Lighthouse and Chrome DevTools. Employing a comparative experimental method, tests were conducted across initial and repeat visit scenarios with three iterations ($K=3$). Evaluation parameters included total requests, data transferred, finish time, DOMContentLoaded, load time, and Lighthouse performance scores.The results demonstrate significant improvements following PWA integration. Average data transfer decreased substantially from 3.9 MB to 320.07 kB, while finish time dropped from 8.42 to 7.26 seconds. Furthermore, load time accelerated from 190.33 ms to 59.00 ms. The Google Lighthouse performance score rose from 71 to 91, shifting the classification from "medium" to "good." These findings confirm that PWA effectively enhances website performance by optimizing data transfer efficiency and accelerating repeat access through service worker-based caching mechanisms.
Implementasi Aspect-Based Sentiment Analysis Berbasis IndoBERT Pada Program Sekolah Rakyat Marunduri, Tik Tanika; Berutu, Sunneng Sandino; Jatmika, Jatmika
Algoritme Jurnal Mahasiswa Teknik Informatika Vol 6 No 2 (2026): April 2026 || Algoritme Jurnal Mahasiswa Teknik Informatika
Publisher : Program Studi Teknik Informatika Universitas Multi Data Palembang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35957/algoritme.v6i2.15734

Abstract

The Sekolah Rakyat program is a strategic Ministry of Social Affairs initiative requiring continuous evaluation through public perception monitoring. This study employs Aspect-Based Sentiment Analysis (ABSA) using the IndoBERT transformer model via a two-stage approach: aspect-opinion extraction using BIO labeling (Token Classification) and sentiment polarity determination (Sequence Classification). A dataset of 14,787 entries from Platform X underwent systematic preprocessing and was trained using an 80:20 stratified split to ensure label balance. Model performance demonstrated high reliability, achieving 86% accuracy and stable F1-scores. Collectively, the analysis identified 8,454 neutral, 4,062 positive, and 2,271 negative sentiments. The results reveal that educational aspects, specifically regarding students, are the primary focus of public discourse, dominated by neutral sentiment. These findings confirm that Deep Learning-based approaches provide granular insights into policy effectiveness, serving as an accurate decision-support instrument for the government to evaluate educational policies comprehensively based on data-driven evidence.
Klasifikasi Kualitas Telur Ayam Ras Berdasarkan Cangkang Menggunakan You Only Look Once Hasan, Nicholas Jacky Pratama; Al Rivan, Muhammad Ezar
Algoritme Jurnal Mahasiswa Teknik Informatika Vol 6 No 2 (2026): April 2026 || Algoritme Jurnal Mahasiswa Teknik Informatika
Publisher : Program Studi Teknik Informatika Universitas Multi Data Palembang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35957/algoritme.v6i2.15742

Abstract

Chicken eggs are one of the most popular food ingredients in Indonesia, with demand increasing every year. However, the quality of chicken eggs sold to consumers must be ensured to be safe for consumption. This study utilized the You Only Look Once (YOLO) method from a Convolutional Neural Network (CNN) architecture to detect chicken eggs and determine their quality based on eggshell images. The dataset used in this research included variations in eggshell color corresponding to their quality. Based on the model training results, the best model achieved optimal performance with a mean Average Precision (mAP) of 99.287% for mAP50 and 93.317% for mAP50-95. The results of the study demonstrate that YOLO is capable of detecting the quality of chicken eggs, making it applicable for improving efficiency in the egg-sorting process. This research is expected to contribute significantly to the development of more advanced and effective egg-sorting technology to support the distribution of high-quality eggs to the public.

Page 12 of 12 | Total Record : 120

 8   9   10   11   12 

Filter by Year

2020 2026


Reset
Filter By Issues
All Issue Vol 6 No 2 (2026): April 2026 || Algoritme Jurnal Mahasiswa Teknik Informatika Vol 6 No 1 (2025): Oktober 2025 || Algoritme Jurnal Mahasiswa Teknik Informatika Vol 5 No 2 (2025): April 2025 || Algoritme Jurnal Mahasiswa Teknik Informatika Vol 5 No 1 (2024): Oktober 2024 || Algoritme Jurnal Mahasiswa Teknik Informatika Vol 4 No 2 (2024): April 2024 || Algoritme Jurnal Mahasiswa Teknik Informatika Vol 4 No 1 (2023): Oktober 2023 || Algoritme Jurnal Mahasiswa Teknik Informatika Vol 3 No 2 (2023): April 2023 || Algoritme Jurnal Mahasiswa Teknik Informatika Vol 3 No 1 (2022): Oktober 2022 || Algoritme Jurnal Mahasiswa Teknik Informatika Vol 2 No 2 (2022): April 2022 || Algoritme Jurnal Mahasiswa Teknik Informatika Vol 2 No 1 (2021): Oktober 2021 || Algoritme Jurnal Mahasiswa Teknik Informatika Vol 1 No 2 (2021): April 2021 || Algoritme Jurnal Mahasiswa Teknik Informatika Vol 1 No 1 (2020): Oktober 2021 || Algoritme Jurnal Mahasiswa Teknik Informatika More Issue