cover
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
ISSN : 14123622     EISSN : 23027339     DOI : https://doi.org/10.33364/algoritma
Core Subject : Science,
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).
Articles 1,145 Documents
Implementasi Augmented Reality Untuk Media Promosi Program Gaya Hidup Sehat di Santiana Nutrition Club Menggunakan Metode MDLC Asep Deddy Supriatna; Erika Puspa Dewi
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.23-1.3159

Abstract

Driven by the need for more effective promotion at Santiana Nutrition Club (Santiana NC), this study aims to design and develop an Augmented Reality (AR) application as a promotional tool for healthy living programs at Santiana Nutrition Club (Santiana NC) using the Multimedia Development Life Cycle (MDLC) method, which includes the concept, design, content collection, application development, testing, and distribution phases. The application was developed to provide more interactive promotions compared to conventional methods. Testing was conducted via Black Box Testing to ensure the system functions properly, followed by Alpha Testing by the developers and Beta Testing using the System Usability Scale (SUS) with Santiana NC customers and owners. The test results showed that all features functioned optimally with a SUS score of 72.67, which falls into the “good” category; thus, the application was deemed suitable for use as an effective and easily accessible interactive promotional medium for the public.
Perancangan dan Evaluasi Usability Aplikasi Talentgo Untuk Karier Bidang Informatika Menggunakan Metode Design Thinking Solihatun Havidah; Purwadi; M. Syaiful Amin
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.23-1.3161

Abstract

This study aims to develop a prototype of the TalentGo application as a career mapping and job search platform specifically for the Informatics field, capable of providing relevant job vacancy recommendations, competency-based career pathways, and a user-friendly interface. The development process uses the Design Thinking approach through the stages of empathize, define, ideate, prototype, and test to ensure that the design aligns with user needs and behavior. The resulting prototype is evaluated using the System Usability Scale (SUS), the User Experience Questionnaire (UEQ), and a five-point Likert scale–based questionnaire to assess interface aspects, user experience, satisfaction, and user loyalty. The results show that the user flow on both the applicant and company sides runs efficiently with minimal obstacles, and key features such as one-click apply and application status tracking are considered helpful in the job search process. Quantitative evaluation produces average scores above 4.00 across all assessment aspects, indicating that the application interface is attractive, navigation is easy to understand, and features are relevant to user needs. Overall, the TalentGo prototype meets modern UI/UX standards and is suitable for further development as a digital recruitment platform for users in the Informatics field.
Peningkatan Akurasi Sistem Rekomendasi E-Commerce Collaborative Filtering dan Negative Sampling untuk Mengatasi Masalah Sparsity Gilang Miftkahul Fahmi Fahmi; Imam Tahyudin; Fandy Setyo Utomo
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.23-1.3198

Abstract

The rapid growth of e-commerce presents challenges in delivering relevant product recommendations to users. This study develops a deep learning–based recommendation system by comparing the performance of Neural Collaborative Filtering (NCF) and Autoencoder models with the classical User-Based Collaborative Filtering approach using the RetailRocket dataset, which contains 2,756,101 user–product interactions. The research focuses on the application of negative sampling techniques to address the extremely high level of data sparsity. The experimental results show that NCF achieves the best performance, outperforming both the Autoencoder and the classical method in terms of Precision@10, Recall@10, and F1@10 metrics. The main contribution of this study lies in the application of NCF to a large-scale and highly sparse e-commerce dataset, demonstrating its superiority in handling extreme sparsity and producing more relevant and accurate recommendations. In addition, the study confirms the effectiveness of negative sampling techniques in improving recommendation prediction quality. These findings have theoretical implications by reinforcing the role of neural architectures in modern recommendation systems and practical implications for deploying more efficient and accurate models in real-world e-commerce platforms, potentially enhancing user experience and customer satisfaction.
Penerapan Decision Support System (DSS) menggunakan Metode TOPSIS untuk Seleksi Mahasiswa Berprestasi Irawati; Sugiarti; Lilis Nur Hayati; Herman; Siti Safira Tawetubun; Nur Asy Syams Sam Ahmad
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.23-1.3200

Abstract

The diversity of students in Indonesian universities requires an objective and transparent selection mechanism for high-achieving students, while manual selection practices remain prone to subjectivity and inconsistency in assessment. This study developed a Decision Support System (DSS) based on the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) with a methodological innovation in the form of integrating eight multidimensional criteria that combine academic and non-academic aspects into a single structured decision-making framework. The implementation results show that the system is capable of increasing the consistency of selection decisions by up to 87% and reducing the selection process time by around 60% compared to conventional methods. These findings confirm that the TOPSIS-based DSS not only improves the objectivity of assessments but also provides significant operational efficiency, thus having the potential to become an adaptive and applicable decision support model for standardizing the selection of outstanding students in higher education.
Perbandingan Genetic Algorithm, Nearest Neighbour, dan Particle Swarm Optimization untuk Penentuan Rute Pengiriman Barang Sandy Achmadi; Prabowo Murti Saputro; Luhur Bayuaji
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.23-1.3201

Abstract

The goods distribution process carried out by PT Saqo Putra Utama, a logistics transportation service company that delivers goods from warehouses to customers in the Jabodetabek area, is still performed manually. As a result, its effectiveness cannot be measured based on the travel distance from one location to another, leading to high operational costs for the company. This study aims to determine the shortest route for goods delivery by minimizing travel distance. The study compares and analyzes route determination results using three methods: Genetic Algorithm, Nearest Neighbour, and Particle Swarm Optimization. The comparison of these three algorithms in goods distribution routing aims to find a balance between processing speed and solution quality, namely the shortest distance or lowest cost. This research was conducted in the Jabodetabek area at PT Saqo Putra Utama, a logistics transportation service company that distributes goods from warehouses to customers. Based on the average calculation results of the three compared methods, it can be concluded that the best method for determining goods delivery routes at PT Saqo Putra Utama is the Genetic Algorithm method, with an average total distance of 222.57 km and an average total cost of IDR 355,809.66.
Analisis Sentimen Ulasan Produk Marketplace Indonesia Menggunakan Naive Bayes dan SVM dengan Label Berdasarkan Rating Levi Ardin Gulo; Agung Wibowo
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.23-1.3206

Abstract

Sentiment analysis aims to identify user opinions about products on marketplaces such as Shopee and Tokopedia. This study classifies product review sentiment using Naive Bayes (NB) and Support Vector Machine (SVM). The dataset underwent text preprocessing, including case folding, tokenization, stopword removal, and stemming, then was represented using TF-IDF. The results show that Support Vector Machine (SVM) achieved the highest accuracy of 94.54%, but had a very low negative class recall (5.71%), indicating a strong bias towards the majority class. In contrast, Naïve Bayes (NB) recorded a lower accuracy of 67.88%, but showed more balanced performance with a negative class recall of 48.57%. Conversely, NB provided more balanced performance between positive and negative classes despite its slightly lower accuracy. These findings emphasize the importance of considering class imbalance in sentiment analysis, especially for applications that require consumer complaint detection. This research is expected to serve as a reference for the development of automatic sentiment analysis systems on marketplace platforms with a focus on performance balance between classes.
Efisiensi dan Generalisasi Gated Recurrent Unit pada Pengenalan Bahasa Isyarat Indonesia Berbasis Fitur Rangka Joshua Nathanael Zega; Ida Nurhaida
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.23-1.3221

Abstract

The development of an automatic Indonesian Sign Language (BISINDO) translation system on mobile devices faces major challenges in the form of high computational costs and variability in signing styles across individuals. This study proposes a lightweight approach using MediaPipe Holistic skeletal feature extraction integrated with a Recurrent Neural Network (RNN) architecture. Specifically, the research evaluates and compares the performance of Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) architectures in recognizing 12 classes of dynamic sign words. Unlike most previous studies that employ random data splitting, this research applies a Leave-One-Subject-Out (LOSO) validation scheme to rigorously assess model generalization to unseen users. Experimental results reveal a significant performance gap between the two architectures. The LSTM model exhibits poor generalization capability, achieving an accuracy of only 40.34%, whereas the GRU model demonstrates superior performance with an accuracy of 73.95%. In terms of resource efficiency, GRU is more optimal, with a model size of 0.83 MB (22% smaller than LSTM), 24% fewer parameters, and stable inference speed in the range of 13–14 FPS. This study concludes that GRU is a more effective and efficient architecture for implementing robust BISINDO recognition systems on resource-constrained devices.
Implementasi Tiketing Wisata Berbasis Flutter dan Laravel dengan Fitur Dashboard Analitik Pengunjung Bibit Raikhan Azzaki; Pungkas Subarkah; Nandang Hermanto
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.23-1.3229

Abstract

This study aims to design and implement a digital-based tourism ticketing system at the Curug Pinang tourist attraction as a replacement for the existing manual recording system that still relies on tear-off tickets and conventional bookkeeping. The manual system has the potential to cause errors in recording visitor and transaction data and makes it difficult for managers to compile periodic visitor and revenue reports, particularly monthly reports. The research method used is system development with the Waterfall model, which includes the stages of requirements analysis, system design, implementation, testing, and deployment. The system is developed using the Flutter framework as a mobile-based ticketing and cashier application, and Laravel as the backend integrated with a database and a web-based analytics dashboard. System testing is conducted using the Black Box Testing method to ensure that all system functions operate in accordance with the specified requirements. The results show that the developed digital ticketing system is able to replace manual recording, reduce transaction recording errors, and facilitate the automatic recapitulation of visitor and revenue data. Therefore, this system improves data management efficiency and supports operational decision-making at the Curug Pinang tourist attraction.
Pengembangan Sistem Informasi Verifikasi Data Balita pada Dinas Kesehatan Kota Batu Januar Muiz Triananda; Wildan Suharso
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.23-1.3233

Abstract

Manual management of toddler data at the local health department level is prone to data duplication and inconsistencies; however, information system solutions that integrate technical aspects and organizational capacity are still rarely studied. This study aims to design and evaluate a web-based infant data verification information system for the Batu City Health Department. The system was developed using the Waterfall SDLC method with the Laravel 10 framework and MySQL, and was evaluated through Black Box testing and the System Usability Scale (SUS) with 10 respondents. Test results showed zero data duplication, verification time reduced from approximately 2 days to approximately 4 hours (an efficiency gain of approximately 70%), and a SUS score of 82.5, which falls into the “Excellent” category. These findings indicate that a user-centered design approach effectively enhances system acceptance among non-technical users, and that the combination of the Waterfall SDLC with the SUS constitutes an applicable development framework for health information systems in local government.
Prototype Sistem Ventilasi Pengendalian Kualitas Udara Ruang Laundry Menggunakan Rule-Based Berbasis IoT Kharis Hudaiby Hanif; Widya Ambarwati; Dedy Harto
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.23-1.3245

Abstract

Poor air quality in laundry rooms is generally caused by high temperature and humidity levels as well as potential exposure to carbon monoxide (CO) gas from equipment operations, which can reduce working comfort and increase health risks if not properly managed. This study proposes a prototype of an automatic ventilation system based on the Internet of Things (IoT) using a rule-based approach to support adaptive air quality control. The contribution of this research lies in the design of decision rules that integrate gas concentration, temperature, and humidity parameters into three condition levels (normal, alert, and danger), as well as in the comprehensive evaluation of system performance as a reference for the development of similar systems. The system was developed using an ESP32 microcontroller with MQ-135 and DHT22 sensors, equipped with an exhaust fan actuator and warning devices, and real-time monitoring through the Blynk IoT platform. Testing was conducted over three days with 360 measurement data points. The results show that the DHT22 sensor achieved measurement accuracy of 97.84% for temperature and 84.65% for humidity, while the MQ-135 sensor reached 92.44%. IoT communication performance was also stable, with 0% packet loss and an average latency of 194.25 ms. In the applied testing scenarios, the rule-based classification demonstrated full conformity with the predefined criteria; however, generalization of the findings still requires further validation under broader operational conditions and environmental variations. Overall, the findings indicate that the proposed system is responsive and reliable, and has the potential to serve as a practical and relatively low-cost solution for monitoring and controlling air quality in laundry rooms.