Article Per Year (5 Year)
p-Index From 2021 - 2026
0.835
P-Index
This Author published in this journals
All Journal Jurnal Dinamika Informatika (JDI) Jurnal Ilmiah Betrik : Besemah Teknologi Informasi dan Komputer International Journal of Advances in Artificial Intelligence and Machine Learning
Lusiana Efrizoni
Universitas Sains dan Teknologi Indonesia
Computer Science & IT

Published : 5 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 5 Documents
Search

 1 
KLASIFIKASI PENJUALAN WALMART MENGGUNAKAN ALGORITMA C4.5 Iftar Ramadhan; Rangga Febrio Waleska; Syarifuddin elmi; Lusiana Efrizoni; Rahmaddeni
BETRIK Vol. 15 No. 02 (2024): Jurnal Ilmiah BETRIK : Besemah Teknologi Informasi dan Komputer
Publisher : PPPM Institut Teknologi Pagar Alam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36050/pjbkse24

Abstract

Penelitian ini bertujuan untuk memprediksi penjualan Walmart dengan menggunakan algoritma C4.5, sebuah metode pohon keputusan yang populer dalam data mining. Prediksi penjualan merupakan aspek krusial bagi strategi bisnis Walmart untuk mengoptimalkan persediaan dan meningkatkan keuntungan. Dataset yang digunakan dalam penelitian ini mencakup data historis penjualan Walmart yang terdiri dari berbagai variabel seperti store, date, weakly sales, holiday flag, temperature, fuel price, uci, unemployment dan faktor-faktor lain yang mempengaruhi penjualan. Dari data variabel tersebut akan melakukan klasifikasi pada data penjualan walmart dari 6.345 record. Hasil pengujian metode dengan evaluasi modeling menunjukkan bahwa metode C4.5 mendapatkan hasil acuracy 0.94, precision 0.43, dan recall 0.75.
PERBANDINGAN ALGORITMA RANDOM FOREST DAN XGBOOST UNTUK KLASIFIKASI PENYAKIT PARU-PARU BERDASARKAN DATA DEMOGRAFI PASIEN Risky Harahap; M. Irpan; M. Azzuhri Dinata; Lusiana Efrizoni; Rahmaddeni
BETRIK Vol. 15 No. 02 (2024): Jurnal Ilmiah BETRIK : Besemah Teknologi Informasi dan Komputer
Publisher : PPPM Institut Teknologi Pagar Alam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36050/3v3xwn06

Abstract

Dalam penelitian ini, algoritma Random Forest dan XGBoost dibandingkan dalam klasifikasi penyakit paru-paru menggunakan data demografi pasien. Dataset yang digunakan terdiri dari 30.000 data pasien dengan 9 atribut dan 1 label yang diambil dari Kaggle. Tahapan penelitian termasuk pengumpulan data, Preprocessing, pembagian data, dan klasifikasi data menggunakan kedua algoritma. Hasil menunjukkan bahwa algoritma XGBoost memiliki akurasi 94% dan AUC 0.98, sedangkan algoritma Random Forest memiliki akurasi 91% dan AUC 0.97. Meskipun Random Forest lebih cepat dan lebih mudah diinterpretasikan, XGBoost bekerja lebih baik dengan data yang kompleks dengan hasil yang lebih konsisten. Melalui penggunaan teknik regularisasi dan penanganan outliers yang lebih baik, XGBoost juga dapat mengatasi masalah overfitting dengan lebih baik. Studi ini memberikan panduan untuk peneliti dan praktisi dalam memilih algoritma terbaik untuk tugas klasifikasi medis, terutama yang berkaitan dengan penyakit paru-paru.
Deep Learning Innovations in Fingerprint Recognition: A Comparative Study of Model Efficiencies Lusiana Efrizoni; Sheeba Armoogum; Mohd Zaki Zakaria
International Journal of Advances in Artificial Intelligence and Machine Learning Vol. 1 No. 1 (2024): International Journal of Advances in Artificial Intelligence and Machine Learni
Publisher : CV Media Inti Teknologi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58723/ijaaiml.v1i1.294

Abstract

Fingerprint recognition technology is integral to biometric security systems, providing secure and reliable identification through unique human fingerprint patterns. However, challenges such as low contrast, high intra-class variability, and partial fingerprints often compromise the efficiency and accuracy of traditional recognition systems. This research addresses these challenges by employing advanced deep learning techniques, specifically Convolutional Neural Networks (CNNs), to enhance fingerprint recognition performance. We propose a methodological approach that leverages state-of-the-art CNN architectures tailored to capture intricate fingerprint details. The study utilizes the Sokoto Coventry Fingerprint Dataset (SOCOFing), which includes diverse fingerprint types and synthetic alterations to evaluate model performance under realistic conditions. Through a comparative analysis of various CNN configurations, we assessed the models based on efficiency and accuracy, using metrics such as accuracy, precision, recall, and F1-score. Our experimental results demonstrate significant improvements in fingerprint recognition capabilities. The optimized CNN model achieved an accuracy of 98.61%, a precision of 97.12%, a recall of 97.46%, and an F1-score of 97.29%. These results validate the effectiveness of CNNs in handling complex biometric data and underscore their potential to enhance the reliability and security of fingerprint recognition systems. The study concludes that deep learning, through the use of CNNs, offers a powerful solution to the limitations of traditional fingerprint recognition techniques. This will pave the way for more sophisticated and accurate biometric security systems in practical applications. The research findings contribute to ongoing advancements in neural network architectures, enhancing their applicability in increasingly automated and data-driven security environments.
Scalability and Efficiency: A Comparative Study of Face Recognition Technologies Mohd Zaki Zakaria; Misinem Misinem; Nyimas Sopiah; Lusiana Efrizoni
International Journal of Advances in Artificial Intelligence and Machine Learning Vol. 1 No. 1 (2024): International Journal of Advances in Artificial Intelligence and Machine Learni
Publisher : CV Media Inti Teknologi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58723/ijaaiml.v1i1.296

Abstract

This article addresses the challenge of selecting the most effective machine learning algorithm for face recognition tasks, a common problem in academic research and practical applications. To tackle this issue, we conducted a comparative analysis of five widely used algorithms: Linear Discriminant Analysis (LDA), Logistic Regression, Naive Bayes, K-Nearest Neighbors (KNN), and Support Vector Machine (SVM). The study involved implementing each algorithm on a standardized dataset, followed by a rigorous evaluation of their performance based on accuracy metrics. The results revealed that LDA, Logistic Regression, and SVM significantly outperformed the other models, each achieving an impressive accuracy of 97%. This high accuracy indicates that these algorithms are well-suited for handling datasets with linearly separable classes. Naive Bayes also showed a strong performance with 90% accuracy, proving effective under the feature independence assumption. However, KNN lagged, with an accuracy of 70%, highlighting its sensitivity to data scale and local structure, which affects its applicability in larger datasets or real-time scenarios. The findings suggest that while LDA, Logistic Regression, and SVM are optimal for datasets with clear class distinctions, the choice of an algorithm should still be guided by specific data characteristics and computational constraints. This study underscores the necessity for carefully considering each algorithm’s strengths and limitations, ensuring that the selected model aligns with the unique demands of the application. Future work could explore ensemble methods and advanced parameter tuning further to enhance the performance and robustness of these models.
Perbandingan Algoritma Naive Bayes dan Decission Tree untuk Prediksi Penyakit Kanker Paru-Paru Mulia Gusti Firmansyah; M. Khairuddin; M fadillah; Lusiana Efrizoni; Rahmaddeni Rahmaddeni
Jurnal Dinamika Informatika Vol. 13 No. 1 (2024): Jurnal Dinamika Informatika
Publisher : Program Studi Informatika Universitas PGRI Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31316/jdi.v13i1.309

Abstract

In this study, we compared the performance of two machine learning algorithms, Naïve Bayes and Decission Tree, for diagnosing lung diseases using patient health datasets. The main objective of this study is to evaluate the accuracy, precision, recall, and F1 score of the two algorithms to determine which method is more effective in predicting lung diseases. The results showed that the tree classification algorithm outperformed Naïve Bayes in terms of accuracy, reaching 95% in an 80:20 split, compared to the 78% accuracy achieved by Naïve Bayes on the same data. Further analysis showed that most patients in this dataset were high risk with 365 patients, followed by risk with 332 patients, and low risk with 303 patients. The decision tree structure proved to be more effective in handling the complexity of the data and produced more accurate predictions, improving efficiency by creating a new "Risk_Score". These results show that decision trees are a better method than Naïve Bayes for diagnosing lung diseases and can provide a solid foundation for developing accurate machine learning models for future health research.
Co-Authors Iftar Ramadhan m fadillah M. Azzuhri Dinata M. Irpan M. Khairuddin Misinem Mohd Zaki Zakaria Mulia Gusti Firmansyah Nyimas Sopiah Rahmaddeni Rahmaddeni Rahmaddeni Rangga Febrio Waleska Risky Harahap Sheeba Armoogum Syarifuddin Elmi