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 1,026 Documents
 95   96   97   98   99 
Arsitektur Model SSDMobileNet V2 untuk Klasifikasi Bahasa Isyarat BISINDO Nurzaman, Muhammad Zein; Fitriani, Leni
Jurnal Algoritma Vol 22 No 2 (2025): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.22-2.2850

Abstract

In this study, we used a commonly used object detection algorithm to classify sign language gestures, namely BISINDO or Indonesian Sign Language. The process of learning sign language is still limited, especially with the use of traditional methods such as direct conversation or using a dictionary. However, there are still obstacles with this approach, for example, some students have difficulty interpreting what they see in the dictionary. Therefore, this study aims to overcome this problem by using a real-time image classification model. The dataset used in this study was collected by the researchers themselves, with a total of 520 images consisting of 26 classes of BISINDO alphabet gestures. We also used transfer learning in this study to utilize the pre-trained SSDMobileNet V2 architecture. Using the COCO evaluation metric, the results show that this model achieved 94% mean average precision, 91% average precision, and 85% recall. This model can also classify sign language gestures in real-time.
Perancangan Antarmuka Website Smart System Academy untuk Pembelajaran Dipersonalisasi Dengan Metode Design Thinking Tresnawati, Dewi; Mujakki, Akmal
Jurnal Algoritma Vol 22 No 2 (2025): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.22-2.2856

Abstract

Perkembangan teknologi pendidikan mendorong lahirnya berbagai platform pembelajaran daring, namun banyak di antaranya belum mampu memberikan pengalaman belajar yang benar-benar personal. Sering kali, antarmuka yang kurang intuitif menyebabkan siswa kesulitan memahami progres belajar, menavigasi materi, maupun mengakses informasi penting secara efisien. Kondisi ini berpotensi menurunkan motivasi dan efektivitas pembelajaran. Penelitian ini bertujuan untuk merancang ulang antarmuka (user interface) pada platform pembelajaran daring Smart System Academy (SSA) agar lebih ramah pengguna dan mendukung pembelajaran yang dipersonalisasi. Proses ini mencakup lima langkah utama, yaitu Empathize, Define, Ideate, Prototype, serta Test. Pada tahap Empathize, kegiatan dilakukan dengan wawancara dan observasi, kemudian dilanjutkan dengan penyusunan user persona serta user journey map pada tahap Define. Pada tahap Ideate dilakukan analisis pesaing serta penyusunan user flow dan wire flow untuk memetakan alur interaksi. Hasilnya diwujudkan dalam bentuk prototipe hi-fi menggunakan Figma pada tahap Prototype. Prototipe yang dihasilkan meliputi fitur utama: login, verifikasi wajah, dashboard akademis, course, dan chatbot. Fitur-fitur ini memberikan kemudahan navigasi, meningkatkan keamanan, serta memperkaya pengalaman belajar yang dipersonalisasi. Evaluasi dilakukan dengan instrumen System Usability Scale (SUS) terhadap 26 responden yang terdiri dari pengelola SSA dan pengguna akhir. Hasil pengujian menunjukkan rata-rata skor 70,19 yang termasuk kategori acceptable usability. Hasil penelitian menunjukkan bahwa penggunaan metode Design Thinking terbukti mampu menghasilkan desain antarmuka yang lebih mudah dipahami, fleksibel, serta mendukung proses pembelajaran daring yang ter personalisasi.
Optimalisasi Jaringan MikroTik Dengan Menggunakan Load Balancing PCC dengan Pendekatan PPDIOO Ahmadi, Meisandi Naufal; Risqiwati, Diah; Muthohirin, Bashor Fauzan
Jurnal Algoritma Vol 22 No 2 (2025): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.22-2.2878

Abstract

The need for a stable and high-performance network is essential to support real-time data transmission. One common challenge faced is the effective management of two or more internet connections to avoid bottlenecks on a single link. This study aims to optimize network performance by implementing the Load Balancing PCC (Per Connection Classifier) method on Mikrotik routers to evenly distribute traffic load across two available ISP links. The research methodology used is PPDIOO (Prepare, Plan, Design, Implement, Operate, Optimize), an approach that encompasses all network management activities. The testing environment is simulated using PNETLab, with performance monitoring conducted using tools such as Zabbix Server Monitoring and Speedtest.net. The parameters tested include Quality of Services such as throughput, response time, bandwidth utilization, and traffic load distribution across each ISP link. The test results show that the application of the PCC method significantly improves network performance. The average throughput increased from 1.49 Mbps to 2.08 Mbps, response time decreased from 3.6 ms to 1.6 ms, and download bandwidth utilization increased from 0.43 Mbps to 0.96 Mbps. Furthermore, the traffic load, which was initially concentrated on a single ISP link, was successfully distributed evenly across both links, demonstrating that PCC load balancing is effective in balancing connections. Therefore, this method is highly recommended for network implementations that require high efficiency and stability in traffic management.
Analisis Kerangka Kerja Scrum pada Sistem Informasi SIGAP sebagai Model Transformasi Digital Kepolisian Hartomo, Kristoko; Arthur, Christian; Waliyuddin Rabbani, Imam
Jurnal Algoritma Vol 22 No 2 (2025): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.22-2.2882

Abstract

The advancement of information technology has driven law enforcement institutions to pursue digital transformation in order to enhance the effectiveness and accountability of public services. One of the initiatives undertaken by the Magelang City Police is the development of the Security Guard Information System (SIGAP), designed to support activity recording, field monitoring, personnel management, and security reporting. Common challenges in similar system developments include excessive backlog, release delays, and limited user involvement. This study aims to analyze the application of the Scrum framework in the development of SIGAP, evaluate its impact on team performance and stakeholder engagement, and provide practical contributions to the adoption of Agile methods in the public sector. This research employed a case study approach using Scrum, conducted through four sprints of two weeks each. Data were collected through observation, interviews, questionnaires, and application log analysis. Evaluation indicators included backlog completion rate, average cycle time, user satisfaction, and stakeholder participation. The findings indicate that backlog completion increased from 24% in the first sprint to 100% in the fourth sprint, accompanied by a 65% reduction in cycle time. User satisfaction improved from a moderate level to a very good level, while stakeholder participation increased from 60% to 93%. These results demonstrate that the Scrum framework is effective in enhancing the development of police information systems and can serve as a replicable model for adaptive, transparent, and accountable digital transformation in other public institutions.
Perbandingan Algoritma K-means, Fuzzy C-means, dan Hierarchical clustering pada Klasterisasi Tingkat Pemahaman Siswa dalam Pembelajaran Berdiferensiasi Ripai, Ahmad; Baskoro, Yudha; Imelda
Jurnal Algoritma Vol 22 No 2 (2025): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.22-2.2890

Abstract

Differentiated learning is a teaching and learning process tailored to the unique characteristics of each student. The main challenge in implementing differentiated learning lies in teachers’ difficulty in understanding the varying levels of students’ comprehension, particularly in informatics subjects. This study aims to compare the K-means, Fuzzy C-means, and Hierarchical Clustering algorithms in grouping students based on academic performance, using daily scores, knowledge, and skill scores of grade X students at SMK Citra Nusantara. The contribution of this research is the application of weighting on the parameters used to improve clustering results. The assigned weights are 0.2 for daily scores, 0.4 for knowledge, and 0.4 for skills when using three parameters, giving a smaller weight to daily scores. If only two parameters are used, the weighting is adjusted so that the total weight equals 1. The evaluation metrics applied are the Silhouette Index, Calinski-Harabasz Index, and Davies-Bouldin Index. The results show that the K-means method outperforms Fuzzy C-means and Hierarchical Clustering. The Silhouette Index is considered the most ideal because it evaluates two aspects simultaneously: cohesion (compactness within clusters) and separation (distinctness between clusters). However, a combination of the Silhouette Index, Davies-Bouldin Index, and Calinski-Harabasz Index is still required to achieve optimal results. The testing results for K-means, evaluated using the Silhouette Index, Davies-Bouldin Index, and Calinski-Harabasz Index, respectively, are 0.350125, 0.822452, and 1157.806. The best clustering outcome with two clusters categorized students into “very good” and “good” groups.
Deteksi Penyakit Daun Padi Menggunakan Deep Learning untuk mendukung Produktivitas dan Pertanian Berkelanjutan Ratnasari; Feriyanto, Dwi
Jurnal Algoritma Vol 22 No 2 (2025): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.22-2.2900

Abstract

Rice is a major food commodity that is susceptible to leaf diseases, such as blast, bacterial leaf blight, and tungro, which can significantly reduce productivity if not detected early. This study aims to develop an early detection method for rice leaf diseases using a deep learning approach with a VGG16-based Convolutional Neural Network (CNN) architecture. The data used came from the Rice Leaf Dataset (Kaggle) and field images in Pringsewu Regency. The training process was carried out through transfer learning. The results showed that the model was able to achieve an accuracy of 99.75% on the training data, 96.08% on the validation data, and 100% on the test data. Field tests also proved the model's ability to generalize to real conditions, although there were still some cases with prediction confidence levels that were close between classes. These findings confirm that VGG16-based CNNs are effective for accurate and efficient detection of rice leaf diseases. The application of this model has the potential to support faster decision-making, reduce pesticide use, and encourage environmentally friendly sustainable agricultural practices.
Implementasi Business Intelligence untuk Prediksi Produksi Perikanan Budidaya Berbasis Web Dashboard Visualisasi Vistiyawati, Vanessa; Budy Santoso, Cahyono
Jurnal Algoritma Vol 22 No 2 (2025): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.22-2.2902

Abstract

Aquaculture plays an essential role in supporting food security and meeting the protein needs of the population, particularly in urban areas such as Jakarta. However, data management in aquaculture production is often still performed manually, making analysis and prediction difficult. This study aims to design a web-based visualization dashboard integrated with Business Intelligence implementation to predict aquaculture production in the Jakarta region. The research employs the CRISP-DM (Cross Industry Standard Process for Data Mining) methodology, which consists of six main stages: business understanding, data understanding, data preparation, modeling, evaluation, and deployment. Aquaculture production data were processed through cleaning and integration stages, followed by the application of predictive models using Random Forest and Linear Regression algorithms, with Python as the data processing tool. The prediction and analysis results are visualized in an interactive web-based dashboard for easy access and interpretation. Evaluation results indicate that the predictive models used were able to provide an overview of production trends with a satisfactory level of accuracy. The contribution of this research lies in the integration of predictive methods with interactive web-based visualization, which has rarely been applied in the context of urban aquaculture, offering a new approach to supporting strategic decision-making. Through this dashboard, stakeholders can obtain more comprehensive information to enhance strategic decisions in aquaculture management in Jakarta.
Aplikasi Presensi Digital Berbasis GPS dengan Leaflet JS Afrina, Nisa; Habiba, Azifa
Jurnal Algoritma Vol 22 No 2 (2025): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.22-2.2905

Abstract

Manual internship attendance recording is inefficient and prone to manipulation. This study aims to develop a web-based internship attendance system integrated with GPS location validation and digital document management to improve accuracy and simplify administration. The system was developed using a prototype model with PHP Native and LeafletJS for real-time location visualization. The results of implementation and qualitative evaluation show that the system functions effectively, significantly improving the efficiency of attendance recording and improving internship documentation. The main contribution of this study is to provide an integrated digital solution that combines robust location verification and document management in a single platform. The implication is the achievement of higher data accuracy and transparency, as well as significant operational efficiency, improving the discipline of interns.
Game Edukasi Trash Sorter Untuk Meningkatkan Kesadaran Pemilahan Sampah Berbasis Model Addie Nugraha, Nur Budi; Santosa, Yaqutina Marjani; Puspaningrum, Alifia
Jurnal Algoritma Vol 22 No 2 (2025): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.22-2.2911

Abstract

The low level of public awareness regarding waste sorting is one of the major contributing factors to flooding in various regions of Indonesia. This condition indicates the need for interactive and engaging learning media to foster environmental awareness from an early age. This study aims to develop the Trash Sorter educational game as a web-based learning medium that introduces waste-sorting concepts within the context of flood-mitigation efforts. The development process followed the ADDIE model (Analysis, Design, Development, Implementation, Evaluation) systematically. At the implementation stage, the game was tested on 20 participants consisting of elementary school students and community members living in flood-prone areas. Evaluation was conducted through pre-tests and post-tests to measure improvements in user understanding. The results showed an increase in the average score from 56.75 on the pre-test to 87.25 on the post-test. In addition, internal alpha testing successfully fixed several bugs and improved application performance. Thus, Trash Sorter has proven effective as an educational medium for increasing waste-sorting awareness as part of flood-mitigation efforts. Moving forward, the game has the potential to be implemented as environmental education media in elementary schools and community organizations to support learning based on environmental literacy and disaster mitigation.
Implementasi Business Intelligence dan Machine Learning untuk Prediksi dan Visualisasi Donasi di Komunitas Sedekah Barokah Dewi, Putu Candra; Widjaja, Yunus
Jurnal Algoritma Vol 22 No 2 (2025): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.22-2.2913

Abstract

Transformasi digital memberikan peluang baru bagi organisasi sosial untuk meningkatkan transparansi dan akurasi pengelolaan keuangan. Penelitian ini bertujuan mengembangkan sistem prediksi keuangan berbasis machine learning yang terintegrasi dengan business intelligence pada Komunitas Sedekah Barokah. Permasalahan utama komunitas ini adalah keterbatasan dalam memantau arus kas, memprediksi donasi, serta menjaga keseimbangan antara pemasukan dan pengeluaran akibat ketergantungan pada donasi masyarakat. Penelitian dilakukan melalui lima tahapan, yaitu pengumpulan data keuangan Januari 2022 – Maret 2025, pra-pemroresan data, penerapan business intelligence menggunakan Tableau, pengembangan model prediksi menggunakan regresi linear dengan python dan evaluasi. Hasil penelitian menunjukkan bahwa dashboard interaktif mampu menyajikan perkembangan saldo, distribusi donasi, dan pola pengeluaran secara transparan serta mudah dipahami oleh pengurus maupun donatur. Sementara itu, model regresi linear menghasilkan performa baik dan akurat dalam memprediksi keuangan komunitas. Penelitian ini menegaskan bahwa integrasi business intelligence dan machine learning prediktif dapat meningkatkan akurasi estimasi pemasukan, pengeluaran, dan saldo, sekaligus memperkuat akuntabilitas serta mendukung pengambilan keputusan strategis. Penelitian ini juga berkontribusi pada literatur dengan menawarkan pendekatan integratif yang dapat direplikasi pada organisasi sosial lain yang menghadapi tantangan serupa dalam pengelolaan dana berbasis donasi. Selain kontribusi praktis tersebut, penelitian ini juga memperkaya literatur mengenai integrasi business intelligence dan machine learning di sektor nonprofit yang sebelumnya masih jarang diteliti.

Page 97 of 103 | Total Record : 1026

 95   96   97   98   99 

Filter by Year

2012 2025


Reset
Filter By Issues
All Issue 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