cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Yosep Septiana
Contact Email
yseptiana@itg.ac.id
Phone
+6282124588750
Journal Mail Official
algoritma@itg.ac.id
Editorial Address
Jl. Mayor Syamsu No.1, Jayaraga, Kec. Tarogong Kidul, Kabupaten Garut, Jawa Barat 44151
Location
Kab. garut,
Jawa barat
INDONESIA
Jurnal Algoritma
Published by Institut Teknologi Garut
ISSN : 14123622     EISSN : 23027339     DOI : https://doi.org/10.33364/algoritma
Core Subject : Science,
Computer Science & IT
Jurnal Algoritma merupakan jurnal yang digunakan untuk mempublikasikan hasil penelitian dalam bidang Teknologi Informasi (TI), Sistem Informasi (SI), dan Rekayasa Perangkat Lunak (RPL), Multimedia (MM), dan Ilmu Komputer (Computer Science).
Arjuna Subject : Ilmu Komputer (semua kategori) - Ilmu Komputer (Lain-Lain)
Articles 1,150 Documents
 111   112   113   114   115 
Manajemen Risiko Trading Aset Kripto Melalui Pendekatan Bet Sizing yang Diadaptasi dari Game Theory Jason Evan Hendarko; Kristoko Dwi Hartomo
Jurnal Algoritma Vol 23 No 1 (2026): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.23-1.3440

Abstract

The high volatility and fat-tailed return distribution of cryptocurrency markets require a more adaptive risk management approach than conventional static models. This study aims to implement and evaluate the effectiveness of a bet-sizing model adapted from Game Theory using the Kelly Criterion as an adaptive risk management framework. A quantitative approach was applied to four major cryptocurrencies—Bitcoin (BTC), Ethereum (ETH), Solana (SOL), and XRP—using 2020 to 2022 as the in-sample period and 2023 to 2025 as the out-of-sample evaluation period. The out-of-sample results demonstrate that the Kelly Criterion-based bet-sizing model outperformed the traditional risk management approach, generating a total return of one hundred thirty-eight point sixty percent and a Sharpe Ratio of 1.34, compared with twelve point eleven percent and 1.22, respectively, for the conventional model. However, this superior performance was accompanied by a substantially larger Maximum Drawdown (MDD) of thirty-three point thirty-three percent, compared with four point twenty-three percent under the traditional approach. These findings indicate that an adaptive transaction-level risk allocation strategy is better able to respond to the dynamic characteristics of cryptocurrency markets. Nevertheless, the relatively limited number of trades and the restricted evaluation period make the bet-sizing model sensitive to changes in sample characteristics, particularly under more extreme market conditions. Despite these limitations, the study incorporates in-sample and out-of-sample validation, as well as transaction costs and slippage, into the performance evaluation, providing a more realistic assessment of the proposed adaptive risk management strategy.
Pengelompokan Tipe Pemain Indonesian Basketball League Berbasis Pca dan Algoritma Clustering Junindra Yuga Pamungkas; Berlilana
Jurnal Algoritma Vol 23 No 1 (2026): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.23-1.3462

Abstract

The professional basketball industry, including the Indonesian Basketball League (IBL), is increasingly adopting data-driven analytics to support strategic decision-making. However, previous studies on domestic basketball leagues have largely relied on individual performance statistics without applying dimensionality reduction techniques, making traditional player position classifications insufficient for objectively representing the characteristics of modern basketball players. To address this limitation, this study integrates Principal Component Analysis (PCA) with clustering algorithms to analyze 160 IBL players from the 2025 season who met the inclusion criteria (GP >= 5 and MP>= 8 minutes) from a total of 246 registered players. Seven statistical variables were used as input features, including Points Per Game (PPG), Rebounds Per Game (RPG), Assists Per Game (APG), Steals Per Game (SPG), Blocks Per Game (BPG), Field Goal Percentage (FGpercen), and Three-Point Field Goal Percentage (3Ppercen). Principal Component Analysis (PCA) was applied prior to clustering to address multicollinearity among variables and reduce data dimensionality while preserving the essential information contained in the original dataset. The PCA results indicate that two principal components explained seventy-one point six percent of the total data variance. The first principal component (PC1) accounted for forty-eight point six percent of the variance and was primarily influenced by PPG and RPG, whereas the second principal component (PC2) explained twenty-three point zero percent of the variance and was dominated by APG, BPG, and 3P percen. Based on internal validation metrics using the optimal number of clusters (k = 4), four distinct player archetypes were identified: All-Around, Bigman, Role Player, and Three-Point Shooter. The K-Means algorithm produced more compact clusters than Ward's Hierarchical Clustering, achieving a Silhouette Score of 0.25, a Davies–Bouldin Index of 1.36, and a Calinski–Harabasz Index of 74.8, with an agreement rate of 81.9 percent between the two clustering algorithms. The moderate Silhouette Score suggests that the boundaries between player archetypes are gradual rather than sharply defined. This study contributes to the academic literature by proposing a player classification framework that combines dimensionality reduction with comparative clustering validation. The proposed approach provides an empirical basis for professional basketball organizations to support player performance evaluation, talent identification, and recruitment decision-making.
Naïve Bayes Berbasis TF-IDF Meningkatkan Kinerja Klasifikasi Berita Hoaks Program Makan Bergizi Gratis Putri Wulandari; Kustiyono
Jurnal Algoritma Vol 23 No 1 (2026): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.23-1.3484

Abstract

The rapid advancement of information technology has led to an increase in the spread of fake news in digital media, which has the potential to influence public opinion; therefore, an automated system is needed to distinguish between fake news and facts. This study aims to classify fake news and facts using a text mining approach with the TF-IDF method for feature extraction and the K-Nearest Neighbor (KNN) and Naïve Bayes algorithms as classification methods. The dataset consists of 1,121 news items obtained from text sources, which underwent preprocessing, word weighting using TF-IDF, and handling of data imbalance using the Synthetic Minority Oversampling Technique (SMOTE), applied to the training data during the cross-validation process to prevent data leakage. Model evaluation was conducted using the metrics accuracy, precision, recall, and F1-score. The results of the study show that the Naïve Bayes algorithm outperforms KNN with an accuracy of 95.74%, precision of 94.98%, recall of 95.23%, and an F1-score of 95.10%, while KNN achieved an accuracy of 48.97%, precision of 68.59%, recall of 62.46%, and an F1-score of 65.32%. Based on these results, it can be concluded that Naïve Bayes is more effective and stable in classifying hoax and factual news based on TF-IDF representation.
Smart Waste Detection: Implementasi Machine Learning pada Aplikasi Android untuk Identifikasi Jenis dan Estimasi Volume Sampah Agus Supriatman; Teguh Ikhlas Ramadhan; Aji Ahmad Baehaki
Jurnal Algoritma Vol 23 No 1 (2026): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.23-1.3496

Abstract

Waste management in Indonesia remains a challenge, particularly in monitoring waste volume and classifying waste types, which are generally still carried out manually and are therefore less efficient. This study aims to develop a Machine Learning-based Android application to estimate waste volume and detect waste types using Convolutional Neural Network (CNN) and You Only Look Once (YOLO) models. The research method includes image data collection and labeling, pre-processing, model training, evaluation, and model implementation into an Android application using TensorFlow Lite. The dataset used consists of 1,584 images for waste volume estimation and 3,168 images for waste type detection, which were divided into training, validation, and testing data. The test results show that the CNN model achieved an accuracy of 90 percent in estimating waste volume. Meanwhile, the YOLO model achieved a precision of 96.59 percent, recall of 97.51 percent, and mAP@50 of 98.39 percent in detecting waste types. Implementation on the Advan Tab 7 Android device showed that the models were successfully run in TFLite format, with a CNN model size of 12,919 KB and a YOLO model size of 11,994 KB, as well as application memory usage of 80.34 MB during operation. In addition, testing using external data outside the training and testing datasets showed that limitations still exist under certain conditions. Overall, the developed system has the potential to serve as a technology-based solution to support more efficient waste management.
Digitalisasi Sistem Monitoring Kedisiplinan Siswa Menggunakan Pendekatan Human Centered Design untuk Meningkatkan Transparansi Sekolah Shofiyah Nur Jannah; A. Ferico Octaviansyah Pasaribu
Jurnal Algoritma Vol 23 No 1 (2026): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.23-1.3506

Abstract

Digital transformation in education has become an essential requirement for improving data management efficiency and information transparency in the era of Industry 4.0. MTs Al-Ikhlas continues to face challenges in monitoring student discipline, as records of violations and achievements are still maintained manually using physical record books. This condition increases the risk of data loss, reporting inaccuracies, and delays in delivering information to relevant stakeholders. This study aims to design the User Interface (UI) and User Experience (UX) of the E-POIN application as a digital student discipline monitoring system using the Human-Centered Design (HCD) approach. The HCD methodology applied in this research consists of three main phases: Inspiration, Ideation, and Implementation. During the Inspiration phase, observations and interviews were conducted with Guidance and Counseling (GC) teachers and parents to identify user needs. The Ideation phase involved the development of wireframes and high-fidelity designs tailored to user requirements and school regulations. Subsequently, the Implementation phase was carried out through prototype testing using the System Usability Scale (SUS) method, involving 10 respondents consisting of 3 GC teachers and 7 other teachers. The results indicate that the proposed E-POIN application successfully provides digital features for recording student violations and achievements, integrated data monitoring, and notification services for parents via WhatsApp. Usability testing demonstrated a task completion rate of 100% and an average SUS score of 85, which falls within the Excellent category. These findings suggest that the Human-Centered Design approach is effective in producing an application design with a high level of usability and strong alignment with user needs within the MTs Al-Ikhlas educational environment.
Penerapan Algoritma Decision Tree dalam Analisis Sentimen Penerima MBG di Indonesia untuk Menilai Pandangan dan Preferensi Penerima Maulidia Safitri; Kustiyono
Jurnal Algoritma Vol 23 No 1 (2026): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.23-1.3510

Abstract

The Free Nutritious Meals Program (MBG) is one of the government’s efforts to improve the public’s nutritional status, making it important to analyze public opinion regarding this program on social media. This study aims to classify public sentiment toward the MBG Program using the Decision Tree algorithm. The research data was obtained from Instagram and X (Twitter), comprising 1,016 data points collected through scraping, preprocessing, and sentiment labeling. The research stages included text preprocessing, feature extraction using TF-IDF, and the application of k-fold cross-validation during model training and testing. The evaluation results show that the Decision Tree model achieved an accuracy of 89.07%, with a precision of 85.16% for the positive class and 95.93% for the negative class, as well as a recall of 97.35% for the positive class and 78.67% for the negative class. The classification results show that positive sentiment is slightly more dominant than negative sentiment on both social media platforms. These findings indicate that public opinion on social media tends to respond positively to the MBG Program, although the model still has limitations in recognizing negative sentiment in a balanced manner. This study also has limitations because the data comes from only two social media platforms, and the sentiment labeling process still has the potential to contain bias despite manual validation.
Klasifikasi Sentimen Opini Publik pada Isu Anggaran DPR Menggunakan Support Vector Machine Berbasis Pembobotan Kelas Julio Siringoringo; Sapril Perdamean Tanjung; Hery Budi Santoso Lukito; Jackleenius Prancis Rumapea; Yennimar
Jurnal Algoritma Vol 23 No 1 (2026): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.23-1.3539

Abstract

This study classifies YouTube users’ sentiment toward the issue of the Indonesian House of Representatives’ allowance increase using a TF-IDF-based Support Vector Machine (SVM). The dataset consists of 26,074 cleaned comments, with a class distribution of 74.61 percent negative and 25.39 percent positive. Initial labeling was performed using a lexicon-based approach and was validated on a limited scale through manual annotation of 150 samples, with a Cohen’s Kappa value of 0.8298. The Linear Kernel SVM model with `class_weight=‘balanced’` achieved an accuracy of 97.10 percent, an F1-score of 98.05 percent for the negative class, and 94.40 percent for the positive class. Using `class_weight=‘balanced’` did not improve all metrics, but it increased the positive class recall from 95.47 percent to 96.15 percent. The comparison results show that the Linear Kernel outperforms the RBF Kernel on high-dimensional data. Despite the high classification performance, 151 misclassified data points were found, influenced by contextual ambiguity, sarcasm, slang, and lexical coverage limitations. Further research is recommended to expand manual validation and utilize contextual semantic features.
Analisis Konseptual Pendeteksian Tingkat Rasa Sakit Pada Penderita Penyakit Jantung Koroner Berdasarkan Ekspresi Wajah Menggunakan Systematic Literature Review (SLR) Maruansa Iruanto Sianipar; Fredy Vico Ardian Purba; Daniel Roppu Ganda Panjaitan; Jeges Martunas Manik; Christnatalis HS
Jurnal Algoritma Vol 23 No 1 (2026): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.23-1.3557

Abstract

Pain assessment is a critical aspect of healthcare delivery, particularly for patients with Coronary Artery Disease (CAD), who often experience communication difficulties during acute episodes. This study aims to analyze the current state of research on facial expression-based pain detection through a Systematic Literature Review (SLR) conducted in accordance with the PRISMA guidelines. A total of 86 articles published between 2020 and 2025 were retrieved from the Google Scholar database and systematically reviewed. The critical synthesis reveals that studies specifically investigating facial expressions for pain assessment in patients with coronary artery disease remain highly limited. Existing research is predominantly focused on the development of pain detection technologies for general clinical settings, including the use of physiological indicators, experimental datasets such as the BioVid Heat Pain Database, and the application of generic machine learning algorithms. The primary scientific contribution of this review is the identification of a substantial methodological gap within the current literature. Existing studies are largely characterized by descriptive qualitative research designs and a strong reliance on secondary laboratory datasets rather than real-world clinical data collected from patients. The novelty of this study lies in its comprehensive mapping of the existing literature and its proposal to adapt generic pain detection models to the specific characteristics of chest pain (angina pectoris) experienced by patients with coronary artery disease. The findings highlight the need for future research to shift toward integrating computational methods with real-world clinical data from cardiology patients in order to improve the external validity and practical applicability of pain detection systems within actual healthcare environments.
Implementasi Metode Algoritma Random Forest Untuk Deteksi Risiko Depresi Pada Mahasiswa Franklin Rado Sinurat; Naufal Taqy Abriyan Nasution; Obed David Sinaga; Jeliana Damanik; Syarifah Atika
Jurnal Algoritma Vol 23 No 1 (2026): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.23-1.3559

Abstract

Depresi merupakan salah satu masalah kesehatan mental yang banyak dialami mahasiswa dan dapat memengaruhi kualitas hidup serta prestasi akademik. Identifikasi awal terhadap mahasiswa yang berisiko mengalami depresi penting dilakukan untuk mendukung upaya pencegahan dan penanganan yang lebih tepat. Penelitian ini bertujuan mengimplementasikan algoritma Random Forest untuk mengklasifikasikan tingkat depresi mahasiswa, mengevaluasi kinerja model, serta mengidentifikasi fitur yang paling berkontribusi terhadap prediksi depresi. Penelitian menggunakan pendekatan kuantitatif eksperimental dengan data yang diperoleh dari 153 mahasiswa Universitas Prima Indonesia Medan melalui kuesioner daring. Model Random Forest dibangun menggunakan parameter terbaik hasil Grid Search, yaitu n_estimators = 50 dan max_depth = 10. Data dibagi menggunakan metode stratified split dengan rasio 80:20 dan dievaluasi menggunakan confusion matrix, kurva ROC, serta validasi silang 5-lipat. Hasil penelitian menunjukkan bahwa model Random Forest memperoleh akurasi 93,55%, presisi 85,71%, recall 85,71%, F1-score 85,71%, dan AUC 87,80%, yang menunjukkan kemampuan klasifikasi yang baik pada dataset penelitian. Analisis feature importance menunjukkan bahwa kondisi kesehatan, IPK, dan biaya per bulan merupakan fitur dengan kontribusi terbesar dalam prediksi depresi mahasiswa. Hasil penelitian menunjukkan potensi Random Forest sebagai pendekatan komputasional untuk membantu identifikasi awal mahasiswa yang berisiko mengalami depresi. Namun, temuan ini masih terbatas pada dataset dari satu universitas dan belum melalui validasi klinis menggunakan instrumen psikologis standar.
Evaluasi Aksesibilitas Sistem POLINDA Kabupaten Garut Berdasarkan Standar WCAG 2.2 Akmala Akmala
Jurnal Algoritma Vol 23 No 1 (2026): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.23-1.3714

Abstract

The digitization of social services must be accessible to all citizens, including people with disabilities. This study evaluates the accessibility of POLINDA (Social Assistance Services of the Garut Regency Social Affairs Office) using WCAG 2.2 Levels A and AA. The subjects consist of a portal and four services based on Google Forms and Google Drive. The method adapts WCAG-EM as an initial evidence-based audit of 32 indicators under the principles of perceivable, operable, understandable, and robust. Indicators requiring DOM inspection, contrast testing, keyboard navigation, or screen reader testing—and which could not yet be verified—were assigned a “U” status. The results showed a verified indicator index of 78.6 percent: 19 met the criteria, six partially met the criteria, three did not meet the criteria, and four were not yet verified. The lowest score was in the “understandable” category (62.5 percent), influenced by mixed languages, Google authentication, inconsistent help, and cross-platform fragmentation. Priorities for improvement include access without login, language standardization, consistent help, labels and error messages, contrast and keyboard focus audits, and integration with the official portal. These results serve as a baseline that needs to be confirmed through technical audits and user testing.

Page 115 of 115 | Total Record : 1150

 111   112   113   114   115 

Filter by Year

2012 2026


Reset
Filter By Issues
All Issue Vol 23 No 1 (2026): Jurnal Algoritma Vol 22 No 2 (2025): Jurnal Algoritma Vol 22 No 1 (2025): Jurnal Algoritma Vol 21 No 2 (2024): Jurnal Algoritma Vol 21 No 1 (2024): Jurnal Algoritma Vol 20 No 2 (2023): Jurnal Algoritma Vol 20 No 1 (2023): Jurnal Algoritma Vol 19 No 2 (2022): Jurnal Algoritma Vol 19 No 1 (2022): Jurnal Algoritma Vol 18 No 2 (2021): Jurnal Algoritma Vol 18 No 1 (2021): Jurnal Algoritma Vol 17 No 2 (2020): Jurnal Algoritma Vol 17 No 1 (2020): Jurnal Algoritma Vol 16 No 2 (2019): Jurnal Algoritma Vol 16 No 1 (2019): Jurnal Algoritma Vol 15 No 2 (2018): Jurnal Algoritma Vol 15 No 1 (2018): Jurnal Algoritma Vol 14 No 2 (2017): Jurnal Algoritma Vol 14 No 1 (2017): Jurnal Algoritma Vol 13 No 2 (2016): Jurnal Algoritma Vol 13 No 1 (2016): Jurnal Algoritma Vol 12 No 2 (2015): Jurnal Algoritma Vol 12 No 1 (2015): Jurnal Algoritma Vol 11 No 2 (2014): Jurnal Algoritma Vol 11 No 1 (2014): Jurnal Algoritma Vol 10 No 2 (2013): Jurnal Algoritma Vol 10 No 1 (2013): Jurnal Algoritma Vol 9 No 2 (2012): Jurnal Algoritma Vol 9 No 1 (2012): Jurnal Algoritma More Issue