Claim Missing Document
Check
Articles

Found 5 Documents
Search

Perbandingan Metode Random Forest dan Naïve Bayes dalam Email Spam Filtering Maria Anita; Bambang Susanto; Lenox Larwuy
KUBIK Vol 7, No 2 (2022): KUBIK: Jurnal Publikasi Ilmiah Matematika
Publisher : Jurusan Matematika, Fakultas Sains dan Teknologi, UIN Sunan Gunung Djati Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15575/kubik.v7i2.18933

Abstract

Email is an important tool not only for communicating and transferring files but also it can be used for advertising media over the Internet. Since the increase in email user numbers, many users send viruses, fraud, and even pornography contained emails. Those kinds of emails were called spam, where unexpected emails sent in bulk. Many email users are annoyed by the amount of time spent deleting individual spam messages. This study provides a comparison between the Random Forest and Naïve Bayes classification methods for email spam predicting. It aims for searching the most accurate method. The data used in this study is an email dataset totaling 2607 data with two variables, namely the body variable (which shows the contents of the email) and the label variable (which shows labeling) where 1 indicates spam and 0 indicates not spam. From the test result using the confusion matrix, it is known that the random forest method has the highest accuracy value, namely 98%, and Naïve Bayes 73%.
Perbandingan Metode Random Forest dan Naïve Bayes dalam Email Spam Filtering Maria Anita; Bambang Susanto; Lenox Larwuy
KUBIK Vol 7, No 2 (2022): KUBIK: Jurnal Publikasi Ilmiah Matematika
Publisher : Jurusan Matematika, Fakultas Sains dan Teknologi, UIN Sunan Gunung Djati Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15575/kubik.v7i2.18933

Abstract

Email is an important tool not only for communicating and transferring files but also it can be used for advertising media over the Internet. Since the increase in email user numbers, many users send viruses, fraud, and even pornography contained emails. Those kinds of emails were called spam, where unexpected emails sent in bulk. Many email users are annoyed by the amount of time spent deleting individual spam messages. This study provides a comparison between the Random Forest and Naïve Bayes classification methods for email spam predicting. It aims for searching the most accurate method. The data used in this study is an email dataset totaling 2607 data with two variables, namely the body variable (which shows the contents of the email) and the label variable (which shows labeling) where 1 indicates spam and 0 indicates not spam. From the test result using the confusion matrix, it is known that the random forest method has the highest accuracy value, namely 98%, and Naïve Bayes 73%.
Optimasi Parameter Artificial Neural Network (ANN) Menggunakan Particle Swarm Optimization (PSO) Untuk Pengkategorian Nasabah Bank: Optimasi Parameter Artificial Neural Network (ANN) Menggunakan Particle Swarm Optimization (PSO) Lennox Larwuy
Jurnal Matematika Komputasi dan Statistika Vol. 3 No. 3 (2023): September-Desember
Publisher : Jurusan Matematika FMIPA Universitas Halu Oleo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33772/jmks.v3i3.60

Abstract

Artificial Neural Network (ANN), also known as Jaringan Saraf Tiruan, is one of the methods commonly used for pattern recognition, classification, forecasting, and regression, depending on the problem or data used. While the results obtained are generally good, there are often issues with determining the initial parameters as the initial weights, which can lead to non-convergence of results. This is why a method is needed to optimize the ANN parameters to achieve better outcomes. Particle Swarm Optimization (PSO) was chosen as the method to optimize the ANN parameters (PSO-ANN). The best parameter values for PSO were predefined, with w (inertia weight) set to 0.8 and c1 and c2 (acceleration coefficients) set to 1.5. Subsequently, PSO-ANN was trained using a bank customer dataset to determine the categories of customers with credit problems or not. The results were compared with using ANN without parameter optimization. The obtained results showed an Accuracy rate of 82.6%, Precision of 91.1%, and Recall of 37.1%. This represents an improvement compared to the results of ANN without parameter optimization, which had an Accuracy rate of 80.1%, Precision of 89.5%, and Recall of 32.4%.
Analisis Empiris dari Variasi Kontinu dan Lompatan dalam Model Threshold GARCH dengan Ukuran Realized Didit B. Nugroho; Fika M. Hanafi; Agnes D. Puspitasari; Faldy Tita; Lennox Larwuy
Limits: Journal of Mathematics and Its Applications Vol. 21 No. 3 (2024): Limits: Journal of Mathematics and Its Applications Volume 21 Nomor 3 Edisi No
Publisher : Pusat Publikasi Ilmiah LPPM Institut Teknologi Sepuluh Nopember

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Volatilitas adalah ukuran fluktuasi harga aset keuangan yang tak terpisahkan dari dinamika pasar, tidak hanya sebagai indikator risiko tetapi juga sebagai sumber informasi tentang peluang dan ketidakpastian bagi investor. Pendekatan utama dalam mengukur risiko pasar keuangan yaitu dengan pemodelan dan estimasi volatilitas. Studi ini fokus pada pemodelan volatilitas menggunakan kerangka Threshold Generalized Autoregressive Conditional Heteroskedasticity (TGARCH). Pertama kali ini mengkonstruksi model TGARCH-X dan Realized TGARCH (RealTGARCH) yang memperhatikan ukuran Realized Volatility (RV) sebagai variabel eksogen. Selanjutnya, model tersebut dikembangkan menjadi model TGARCH-CJ dan RealTGARCH-CJ dengan cara mendekomposisi komponen RV menjadi komponen kontinu dan lompatan. Analisis empiris didasarkan pada hasil estimasi model menggunakan metode Adaptive Random Walk Metropolis untuk data Tokyo Stock Price Index (TOPIX) Jepang. Perbandingan pencocokan model menunjukkan keunggulan yang signifikan untuk model-model dengan komponen kontinu dan lompatan. Dengan pengaplikasian ukuran RV interval waktu 1 dan 5 menit, model terbaik diberikan oleh RealTGARCH-CJ yang mengadopsi ukuran RV 1 menit.
WORKSHOP PENINGKATAN LITERASI DATA SISWA MELALUI PEMBELAJARAN BERBASIS PROYEK DIGITAL DI SMP KRISTEN SATYA WACANA SALATIGA Adi Setiawan; Faldy Tita; Lennox Larwuy; Amazia Ananta Prabaswara; Harfeley Leipary; Daniel Bramantyo Ranu Bagaskoro
Jurnal Abdi Insani Vol 13 No 1 (2026): Jurnal Abdi Insani
Publisher : Universitas Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29303/abdiinsani.v13i1.3440

Abstract

The development of the digital era demands data literacy skills as a basic 21st-century skill that is important for junior high school students. Based on observations at SMPK Satya Wacana Salatiga, most students still experience difficulties in understanding, interpreting, and using data in learning. This community service activity aims to improve students' data literacy through hands-on practice-based training with an interactive and contextual learning approach. The implementation method includes socialization, data concept training, data processing simulations using spreadsheets and R software, and evaluation through pre-tests and post-tests. The results showed a significant increase in data analysis skills. The average pre-test score of 3.11 increased to 3.84 in the post-test, with an average normalized gain (K) of 0.40, which is included in the medium category. The paired t-test produced a value of t = -12.49 and p-value = 0.000 (p-value < 0.05), indicating a significant difference between the results before and after the training. A total of 44 students were in the medium improvement category, 38 students were low, and 19 students were high. These findings indicate that R-based data literacy training is effective in improving junior high school students' conceptual understanding, self-confidence, and analytical skills, and is relevant to be developed as a 21st-century learning model.