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
Analisis Komparatif Akurasi Prediksi Kanker Payudara Menggunakan Algoritma Random Forest dan Logistic Regression Hulaifah Al Abrori, Zahra Zul; Subhiyakto, Egia Rosi
Jurnal Algoritma Vol 22 No 1 (2025): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.22-1.2164

Abstract

This study analyzes the performance of Random Forest and Logistic Regression algorithms in detecting breast cancer using datasets from Kaggle. Evaluation was done based on metrics such as accuracy, precision, recall, and F1-score to classify benign and malignant cancers. Logistic Regression recorded 98% accuracy, with 99% precision for benign class and 98% for malignant class, and 99% recall for both classes. Meanwhile, Random Forest showed an accuracy of 96%, a precision of 96% for benign class and 98% for malignant class, and a recall of 99% for benign class and 93% for malignant class. This study contributes by highlighting the superiority of Logistic Regression in producing more accurate and consistent results on simple datasets, while Random Forest shows greater potential in handling data with more complex patterns. Different from previous studies, this research emphasizes the importance of matching dataset characteristics with the selected algorithm to improve the accuracy of early breast cancer detection. These results are expected to support evidence-based decision-making in the clinical field, especially in choosing the algorithm that best suits the needs and resource constraints.
Implementasi Majority Voting pada Framework Cross-Industry Standard Process for Data Mining untuk Prediksi Kepatuhan Wajib Pajak Binarto, Antonius Jonet; Wibowo, Arief
Jurnal Algoritma Vol 22 No 1 (2025): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.22-1.2165

Abstract

This research aims to predict taxpayer compliance (compliant or non-compliant) using 2,167 rows of tax data. The CRISP-DM (Cross-Industry Standard Process for Data Mining) framework was used to guide the process, as it has a structured framework. Five machine learning algorithms were compared, namely Naive Bayes, Support Vector Machine (SVM), Decision Tree, Logistic Regression, and Deep Learning, trained and tested using RapidMiner tools. To improve the prediction accuracy, the majority voting ensemble method which is the simplest and most efficient ensemble is used by combining the prediction results of these algorithms and evaluated and implemented on Google Collab using Python to validate the performance on new data and successfully provide more stable accuracy than individual models. This research contributes to tax data management, especially policy makers can optimize the use of technology to improve the efficiency of the process of monitoring and evaluating taxpayer compliance. This research also underscores the importance of exploring various machine learning algorithms and ensembles and other parameters to produce effective solutions in the field of taxation.
Analisis Perbandingan Efektivitas Klasterisasi K-Means dan Pengambilan Keputusan Topsis Melalui Pendekatan Anova Juraizah, Nadiah; Ariesta, Atik
Jurnal Algoritma Vol 22 No 1 (2025): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.22-1.2172

Abstract

PT. Saida Indra Panca is a company that manages outsourced labor, such as cleaning services, room attendants, and landscape maintenance. The company often faces difficulties in identifying employees eligible for training and development. Therefore, this study aims to compare the effectiveness of decision-making with and without clustering. The clustering method uses the K-Means algorithm, while the decision-making method uses TOPSIS. The research adopts the CRISP-DM approach, which includes business understanding, data collection, data preparation, modeling, evaluation, and deployment. Evaluation was conducted using ANOVA to compare the variance values of two groups: the first group with clustering and TOPSIS, and the second group with TOPSIS only. The evaluation resulted in an F-value of 5.553025 and a P-value < 0.05, indicating a significant difference between the group means. The study shows that the combination of K-Means and TOPSIS is superior to using TOPSIS alone, as it results in a more structured, efficient, and accurate decision-making process. Clustering helps group employee data based on specific characteristics, making the evaluation and ranking process more targeted. As a result, the company can improve HR management efficiency by up to 25% and enhance the accuracy in selecting employees for training. This approach provides deeper insights for developing effective data-driven HR strategies and supports better decision-making in employee management.
Analisis Perbandingan Algoritma Asosiasi Data Mining Pada Minimarket Adi Poday Dengan Google Collab Arifin, Miftahul; Helmi, Fauzi; Iddrus
Jurnal Algoritma Vol 22 No 1 (2025): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.22-1.2177

Abstract

Data Mining is an important technique in business analysis to discover hidden patterns in transaction data. This study compares the performance of two association rule algorithms, Apriori and FP-Growth, in identifying association patterns between products. This study aims to evaluate the efficiency of processing time and the quality of association rules generated by both algorithms in a retail context. The dataset used comes from transactions of Minimarket Adi Poday, covering 143,523 entries and 97,548 transactions from January to August 2024. The selection of this dataset is based on the relevance to the analysis of customer shopping patterns for marketing strategy optimization. Tests were conducted with a minimum support parameter of 0.01, and the results show that FP-Growth is superior in processing speed to Apriori, with an average execution time difference of 33.33% seconds faster on the same dataset. The implication of this research for minimarket owners is that the use of FP-Growth algorithm for purchasing pattern analysis can help in product arrangement and more effective promotion strategies. In addition, this research contributes to the field of Information Systems by demonstrating the effectiveness of FP-Growth in handling large-scale transaction data, as well as providing insight into the selection of algorithms suitable for retail business needs.
Klasifikasi Penyakit Gagal Jantung Menggunakan Algoritma Naive Bayes Faradeya, Muhammad Az-Zauqy; Subhiyakto, Egia Rosi
Jurnal Algoritma Vol 22 No 1 (2025): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.22-1.2178

Abstract

Heart failure disease shows an alarming increase in global prevalence with significant clinical impact complexity. This study implements the Naive Bayes algorithm to predict heart failure risk, presenting a solution that is more computationally and interpretationally efficient than the high computationally time-consuming Random Forest or SVM with 92% accuracy. The methodological approach includes structured data preprocessing, including missing value handling, feature development, scale normalization, and dataset balancing. The application of K-Fold Cross Validation with K variations (2, 4, 5, 10) achieved optimal performance at K=4 with an accuracy of 85.1%, which enabled a reduction in the misdiagnosis rate to 14.9%. Achieving a precision of 81.1%, recall of 86.1%, and AUC-ROC of 0.914 contributed to savings in treatment costs through early identification accuracy. The system can be integrated in automated screening for efficient allocation of medical resources, resulting in significant operational savings through prioritization of high-risk patients and timely preventive interventions. Performance stability with consistent AUC-ROC (0.91-0.92) makes it a reliable foundation for clinical decision support systems that improve overall patient outcomes.
Wanoja Calakan: Langkah Menuju Digitalisasi Pemberdayaan Kader Perempuan Solihah, Eneng; Wahyudin, Uyu; Saepudin, Asep
Jurnal Algoritma Vol 22 No 1 (2025): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.22-1.2179

Abstract

Women's empowerment is one of the important issues in global development. In Indonesia, the Wanoja Calakan organization strives to empower women through training and activities aimed at forming intelligent and agile female cadres. In facing the challenges of the digital age, it is important for these organizations to transform by utilizing technology. This research discusses the design of the Wanoja Calakan website which aims to improve efficiency in cadre registration, provide information about empowerment programs, and facilitate interaction between members and program managers. Agile methods are used in the design of this website to ensure adaptability to user needs and business processes that continue to evolve continuously. The website was tested using a usability test, resulting in a very good user acceptance score with an average score of 4.8 (96%) with a 95% confidence interval and a margin of error of 10%, using the Lemeshow formula. The result of this design is a user-friendly and responsive platform, which can be used to register cadres and access various information related to the program. In the future, this website is expected to be a more interactive means of empowering women in Indonesia
Klasifikasi Otomatis Korosi Menggunakan Convolutional Neural Network dan Transfer Learning dengan Model MobileNetV2 Rizky Pratama, Muhammad Hafiz; Akrom, Muhamad; Santosa, Akbar Priyo; Rosyid, Muhammad Reesa; Mawaddah, Lubna
Jurnal Algoritma Vol 22 No 1 (2025): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.22-1.2182

Abstract

Corrosion is a major problem that causes significant economic losses in various industries, including transportation, energy, and manufacturing. Early detection of corrosion is essential to reduce its negative impact. This research aims to develop an automatic corrosion classification system based on Convolutional Neural Networks (CNN) with a transfer learning approach. Two models were evaluated, namely a simple CNN architecture and the pre-trained MobileNetV2. The dataset consists of corrosion and non-corrosion images divided into training, validation, and testing data. Data augmentation techniques are applied to increase the variety and number of samples in the training process. The experimental results show that MobileNetV2 achieves a testing accuracy of 95%, which is higher than that of a simple CNN that only reaches 82%. In addition, MobileNetV2 showed better performance in identifying both classes (corrosion and non-corrosion). Despite indications of overfitting due to dataset limitations, the transfer learning approach significantly improved the classification performance. This system has the potential to be applied in real-time industrial applications to reduce economic losses due to corrosion. Further research is recommended to improve the generalization of the model by using a larger dataset and applying more robust regularization techniques.
Monte Carlo Simulation for Seasonal Stock Prediction of Seasoning at AH FOOD Nurhalizah, Ammanda Putri; Ariesta, Atik
Jurnal Algoritma Vol 22 No 1 (2025): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.22-1.2191

Abstract

AH FOOD is a business operating in the food industry, selling various seasoning products such as balado seasoning, balado chili sauce, Miwon, and others. The problem faced involves seasoning products that have specific characteristics, such as a limited shelf life and dependence on the availability of raw materials. This availability is often influenced by general market conditions, weather or seasons, and raw material prices. Therefore, this study aims to predict sales stock at AH FOOD based on Indonesia's seasons, namely the rainy and dry seasons. The method used in this research to predict stock is the Monte Carlo method. This method was chosen due to its ability to handle uncertainty and seasonal variability, making it superior to other methods such as time series regression in predicting seasonal stock. The Mean Absolute Percentage Error (MAPE) was used to measure the accuracy level of the prediction simulation. The results of the accuracy using MAPE showed that the Monte Carlo method is adequate and feasible to use, with an average error value of 26% for the rainy season and 27% for the dry season. This helps AH FOOD optimize stock management, reduce losses due to product expiration, and increase storage efficiency. Based on the MAPE results, the Monte Carlo method is effectively used to predict seasoning stock sales at AH FOOD based on Indonesia's seasonal divisions.
Pendekatan Transfer Learning dengan InceptionResNetV2 dan Augmentasi MixUp untuk Peningkatan Klasifikasi Tumor Otak Mahendra, Randa; Laksana, Eka Angga; Sukenda, Sukenda
Jurnal Algoritma Vol 22 No 1 (2025): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.22-1.2194

Abstract

Diagnosis of brain tumors such as Glioma, Meningioma, and Pituitary using MRI still faces challenges, including reliance on manual interpretation, long evaluation times, and the potential for human error. To address these issues, deep learning-based approaches offer efficient and accurate solutions. This study aims to develop a brain tumor classification model based on deep learning using the InceptionResNetV2 architecture with MixUp augmentation to improve model accuracy and generalization. The model was trained on 7,023 MRI images (Glioma: 1,621; Meningioma: 1,645; Pituitary: 1,757; No-tumor: 2,000), with MixUp proven effective in reducing overfitting and handling data imbalance. The proposed model achieved a highest accuracy of 99.70%, surpassing other models such as CNN with Image Enhancement (97.84%) \[1], Xception (98.00%) \[2], EfficientNet (98.00%) \[3], and ResNet50 (98.47%) \[4]. Evaluation was conducted using metrics including precision, recall, F1-score, as well as MSE, RMSE, and MAE, showing strong performance. These results support the use of transfer learning for medical image classification with limited datasets. This research demonstrates clinical application potential, particularly in improving diagnostic accuracy, speeding up evaluation processes, and reducing human error. Future recommendations include using more diverse datasets, real-world evaluation, and integration into Clinical Decision Support Systems (CDSS).
Penerapan Digitalisasi Pembayaran Pajak Daerah Berbasis QRIS di Daerah Regional melalui Aplikasi “Ayo Balapan” Aminudin, Nur; Aprilia, Fenny; Afanto, Hendri; Sinatria, Naufal; Andika, Tahta Herdian; A, Afnan Zalfa Salsabila
Jurnal Algoritma Vol 22 No 1 (2025): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.22-1.2195

Abstract

Penelitian ini mengevaluasi implementasi aplikasi “Ayo Balapan” berbasis QRIS sebagai inovasi digital dalam sistem pembayaran pajak daerah di daerah regional. Menggunakan metode deskriptif dengan data primer dan sekunder, hasil menunjukkan peningkatan kepatuhan wajib pajak sebesar 20%, pengurangan waktu pembayaran hingga 66,67%, dan peningkatan Pendapatan Asli Daerah (PAD) sebesar 50%. Aplikasi ini membuka peluang pengembangan untuk jenis pajak lain serta penambahan fitur cicilan. Temuan ini berkontribusi pada penguatan sistem informasi pemerintah, khususnya dalam efisiensi administrasi perpajakan berbasis teknologi.

Page 77 of 103 | Total Record : 1026