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 1,026 Documents
Peramalan Penjualan Pakaian Berbasis Web Menggunakan Metode Seasonal Adjustment Hazrina, Umi Indah; Sembiring, Muhammad Ardiansyah; Amalia
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.22-2.2459

Abstract

In an increasingly competitive industrial era, companies are required to produce quality products and manage inventory effectively to meet consumer needs. Toko Baju Manisem, a business engaged in the production and sale of clothing, faces challenges in determining optimal stock levels because it still uses manual methods to calculate inventory. This risks causing stock shortages or surpluses, which can lead to additional costs and potential losses. This study aims to develop a web-based sales forecasting system using the seasonal adjustment method to improve the accuracy of demand predictions. Seasonal adjustment is a time series data analysis technique that eliminates seasonal factors so that trend patterns are clearer and forecasts are more accurate. This system was built using the PHP programming language to facilitate the prediction process and more optimal inventory management. The results of this study show that the application of the seasonal adjustment method can improve efficiency in inventory management, reduce the risk of excess or shortage of goods, and help business owners make more informed decisions. With this system in place, it is hoped that Toko Baju Manisem can optimize its sales strategy and improve its business sustainability.
Peningkatan Klasifikasi Serangan DDoS pada SDN Menggunakan XGBoost dan RAMOBoost Badar, Ahmad; Rakhmat Umbara, Fajri; Nurul Sabrina, Puspita
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.22-2.2460

Abstract

The aim of this study is to detect Distributed Denial of Service (DDoS) attacks in Software Defined Networking (SDN) environments using the XGBoost algorithm and the RAMOBoost balancing technique to address the issue of data imbalance. SDN offers flexibility in network management but remains vulnerable to DDoS attacks. The dataset used in this research consists of two classes (normal and attack) with an imbalanced distribution. XGBoost was chosen for its ability to deliver accurate predictions, while RAMOBoost was employed to enhance data representation for the minority class. The results show that before balancing, the model achieved 100% precision for the majority class and 96% precision for the minority class, with recall values of 97% and 100%, respectively. After applying RAMOBoost, precision and recall became more balanced, ranging between 97%–99%, while maintaining a high overall accuracy of 98%. Grouped Feature Importance analysis revealed that randomizing important features reduced accuracy from 97.88% to 49.78%, whereas randomizing unimportant features only slightly decreased accuracy to 97.82%. The main contribution of this study lies in the combined application of RAMOBoost and XGBoost, which proved effective in improving classification performance on imbalanced datasets, and in emphasizing the critical role of feature selection in maintaining model stability. These findings provide valuable insights for network administrators in developing effective attack detection systems for SDN environments.
Optimasi Algoritma Knn Menggunakan Smote Untuk Prediksi Stroke Khairi, Zuriatul; Yanti, Rini; Fitri, Triyani Arita; Fatdha, Eiva
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.22-2.2474

Abstract

Stroke is a disease with a high mortality and disability rate, especially in Indonesia. Early detection of stroke risk is important to prevent serious consequences. This study examines the distribution of stroke cases based on age groups and evaluates the performance of the K-Nearest Neighbors (KNN) algorithm on imbalanced data and after applying the Synthetic Minority Oversampling Technique (SMOTE). The analysis uses two data division scenarios: 80:20 and 70:30 between training and test data. The results show that the risk of stroke increases with age. No cases were found in the 20–30 age group, cases began to appear in the 30–40 age group, and increased sharply above the age of 50. KNN without SMOTE had an accuracy of 95% (80:20) and 94% (70:30), but low recall, 0.04 and f1-score 0.07 (80:20), and recall 0.03 and f1-score 0.05 (70:30). After SMOTE, recall increased to 0.36 and f1-score 0.21 (80:20), and recall 0.28 and f1-score 0.17 (70:30). Accuracy decreased to 86% in both ratios, but recall and f1-score increased, indicating that the model was more sensitive to stroke cases. Overall, SMOTE effectively reduces majority class bias and helps the model recognize overlooked stroke patterns. However, sensitivity still needs to be improved through parameter tuning, selection of relevant features, or alternative algorithms to enhance prediction reliability.
Analisis Sentimen Ulasan Aplikasi CapCut Menggunakan Model RoBERTa Dengan Fitur Ekstraksi Word2vec Budiman, Firman Nur; Witanti, Wina; Nurul Sabrina, Puspita
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.22-2.2480

Abstract

To improve the accuracy of sentiment classification in CapCut app reviews, this study tested a hybrid model built from a combination of RoBERTa and Word2Vec. A total of 5,000 reviews from the Google Play Store were used as a dataset, which was then processed through data cleaning, tokenization, and stopword removal stages. Next, the EDA oversampling technique was used to address the issue of class distribution imbalance. The proposed model architecture works by combining the concatenation of vector features from Word2Vec for local word meaning representation and RoBERTa for overall sentence context understanding. Model evaluation showed an accuracy of 80%, a higher result compared to the 79% accuracy obtained by the single RoBERTa baseline model. This study concludes that combining contextual and semantic feature representations effectively results in better sentiment classification performance.
Pola Pembelian Konsumen Supermarket Menggunakan Algoritma ECLAT Dan Fp-Growth Fahrezi Ahmad, Rafly Fikri; Witanti, Wina; Ramadhan, Edvin
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.22-2.2482

Abstract

This study aims to uncover consumer purchasing patterns in supermarkets to support more targeted sales strategies. The primary focus is on identifying products that are frequently bought together and their relationship with contextual factors such as payment methods, seasons, and discount status. The main challenge lies in handling transactional data that is highly diverse (high cardinality) and sparsely co-occurring, necessitating an approach capable of generating relevant association patterns. To address this, the study implements an integrated approach combining the ECLAT and FP-Growth algorithms in Market Basket Analysis. ECLAT is employed to filter items with low frequency through a TID-List structure, resulting in a more focused set of transactional data for FP-Growth processing. FP-Growth is then used to identify frequently co-occurring product and attribute combinations and to form association rules based on support, confidence, and lift values. The research data comprises 10,000 transactions with 13 attributes, focusing on Product, Payment_Method, Discount_Applied, Season, and City. As a result, ECLAT successfully filtered 81 products and 101 frequently occurring contextual attributes. FP-Growth subsequently discovered 407 itemset patterns, with 13 valid patterns forming association rules between products and contextual attributes. Additionally, three-item patterns were found for watch products associated with discounts and seasons. The contribution of this study lies in demonstrating that the integration of ECLAT and FP-Growth can serve as an effective method for discovering consumer shopping patterns based on transactional context, thereby supporting data-driven business decision-making.
Sistem Deteksi Gerakan Tangan Untuk Pengendalian Kursor Pada Presentasi Berbasis Opencv dan Mediapipe Fitriani, Leni; Nurhakim, Irfan
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.22-2.2485

Abstract

Human-computer interaction continues to evolve, one of which is through device control using hand gestures. In the context of presentations, the use of a mouse as an assistive tool often limits the presenter’s mobility. Therefore, this study aims to develop a hand gesture detection system to control the cursor in real time using the OpenCV and MediaPipe libraries. The system is designed to allow presenters to move freely in front of the audience without being tied to physical input devices. The system development follows the Rational Unified Process (RUP) methodology, encompassing four phases: Inception, Elaboration, Construction, and Transition. The system is implemented using the Python programming language and the Autopy library for cursor control. Testing was conducted under lighting conditions of 100 lux and at a distance of approximately 1 to 1.5 meters. The test results demonstrate excellent system performance: single-click functionality achieved 98% accuracy and 98% precision; double-click functionality reached 99% accuracy and 100% precision; right-click functionality showed 98.04% accuracy and 96.15% precision; and cursor movement achieved 100% accuracy and 100% precision. The system is capable of detecting hand gestures and controlling the cursor with high accuracy and fast response. It also supports light multitasking activities such as opening various types of files. This research contributes to the advancement of human-computer interaction without the need for traditional input devices.
Model Optimalisasi Pemilihan Ekstrakurikuler Menggunakan Algoritma Particle Swarm Optimization (PSO) Urva, Gellysa; Azmi, Khairul; Desriyati, Welly
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.22-2.2488

Abstract

The selection of extracurricular activities is an important element in developing students' character, interests, and potential outside of academic activities. However, this selection process is often not carried out systematically, so it risks not being in accordance with individual student preferences. This study aims to design an extracurricular recommendation model based on the Particle Swarm Optimization (PSO) algorithm, one of the intelligent computing methods that is effective in finding optimal solutions. The model considers four main criteria, namely interests, talents, schedules, and student personalities, which are formulated into an objective function. The PSO algorithm is used to find the best combination of extracurricular activities for each individual based on predetermined preference weights. Testing using data from 50 students shows that the PSO algorithm is able to produce recommendations with the best fitness value that is stable at around 4.5 after the 40th iteration, indicating the algorithm's effectiveness in finding optimal solutions. Correlation analysis between variables shows a strong positive relationship between Interests and Talents (correlation coefficient approaching 0.75), while Personality and Schedule contribute unique information with a correlation below 0.2. The results of this study demonstrate that the PSO algorithm approach is proven to be an adaptive and efficient approach that can be used as an effective method to generate personalized and relevant extracurricular recommendations. It can also be used as a tool in decision-making in educational environments and increase student participation and potential development in a more targeted and optimal manner. The test results show that this model is able to provide more personalized and appropriate recommendations compared to conventional methods. Furthermore, the PSO algorithm provides a relatively fast convergence time with high decision accuracy.
Analisis Segmentasi Pelanggan dengan Algoritma K-Means pada Data Penjualan Nazihah, Fasya; Danniswara, Ahmad; Wibowo, Arief
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.22-2.2489

Abstract

Competition in the world of sales is becoming increasingly fierce, so store owners need the right strategy to understand customer behavior patterns and increase sales. One of the most widely used data analysis methods is K-Means Clustering, which can be used to find patterns and trends in sales data. This study was conducted with the aim of determining customer segmentation based on sales transaction data in order to obtain customer groups with similar characteristics. The method applied in this study was the K-Means algorithm on a sales dataset with a total of 1,289 customer data. Cluster quality was evaluated using the Davies-Bouldin index (DBI), with a DBI result of 0.077, indicating excellent cluster quality. The analysis resulted in three customer clusters, namely: the first cluster (C1) consisting of loyal buyers with 562 customers, the second cluster (C2) consisting of occasional buyers with 279 customers, and the third cluster (C3) consisting of buyers with an average purchase of 448 customers. The implication of these research results is that management can develop more appropriate marketing strategies, such as providing a personal approach to loyal customers and designing specific strategies to attract occasional buyers to become more loyal. Thus, these research results can serve as a basis for more effective marketing decision-making.
Penerapan Internet Of Things dan You Only Look One Pada Sistem Keran Air Wudhu Pintar Sebagai Edukasi Siswa Laksana, Fatih Dwi; Fitri, Zahratul; Suwanda, Rizki
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.22-2.2490

Abstract

This study aims to develop a smart wudhu water tap system based on the Internet of Things (IoT) as an interactive educational medium for students. The system is equipped with object detection sensors, voice guidance, and the YOLOv8 algorithm to detect and classify wudu movements in real-time. Accuracy evaluation was performed using the Fuzzy Takagi-Sugeno-Kang (TSK) method, which categorizes the results into three levels: “Low,” “Medium,” and “High.” Test results show excellent detection performance, with an average mAP50 value of 0.993, mAP50-90 of 0.746, recall of 0.998, and defuzzification results in the “High” category. This system is effective in providing educational feedback and supporting technology-based wudhu learning. In the future, this system has the potential to be implemented in schools on a larger scale and developed to improve its accuracy and functionality.
Aplikasi Rekomendasi Menu Makanan Harian Menggunakan Algoritma Metode KNN Nafi, Tri Maula; Mujiyono, Sri
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.22-2.2491

Abstract

This food menu recommendation app utilizes the K-Nearest Neighbors (KNN) algorithm to provide menu suggestions that suit the nutritional needs and preferences of users. The system analyzes various factors, including calories, protein, fat, and carbohydrates, in order to generate accurate and relevant recommendations. Users can enter information related to their nutritional needs and food preferences, such as their favorite types of food and allergies, to get the right menu suggestions. Through this application, users are expected to receive healthy menu recommendations that suit their individual needs, which in turn can increase awareness of the importance of a nutritious diet and overall health. With a data-driven approach, this app is an effective solution for those who want to make healthier food choices and support the achievement of their desired health and nutritional goals. In addition, this app can also contribute to building better eating habits among the community.

Page 89 of 103 | Total Record : 1026