Article Per Year (5 Year)
p-Index From 2020 - 2025
0.444
P-Index
This Author published in this journals
All Journal Jurnal Teknologi Terpadu E-Link: Jurnal Teknik Elektro dan Informatika
Herijanto, Christopher Kevin
Unknown Affiliation
Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering Energy Engineering

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
Perbandingan Klasifikasi Label Tunggal untuk Soal Ujian Fisika menggunakan Naïve Bayes dan K-Fold Cross Validation Herijanto, Christopher Kevin; Wahyuningsih, Yulia
Jurnal Teknologi Terpadu Vol 10 No 1 (2024): Juli, 2024
Publisher : LPPM STT Terpadu Nurul Fikri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54914/jtt.v10i1.1210

Abstract

This research evaluates the use of the Naïve Bayes algorithm in classifying Physics questions with single labels. The main objective is to identify the best algorithm for classifying Physics questions to assist high school students with difficulty understanding them. The research method involves using a dataset containing Physics questions that need to be classified to facilitate learning for high school students. The Naïve Bayes algorithm is implemented using Google Colab to train the classification model using features extracted from the text of the Physics questions. Additionally, several other classification algorithms, such as Support Vector Machine (SVM), Logistic Regression, Decision Tree, and Random Forest, are tested, and their performance is compared. Experimental results show that Naïve Bayes provides competitive results in classifying single-label Physics questions. However, there are significant performance differences between Naïve Bayes and other algorithms, depending on the type and complexity of the classified Physics problems. In this study, SVM achieved higher accuracy, but Naïve Bayes excelled in training time. This research provides a deeper understanding of the strengths and weaknesses of Naïve Bayes in solving the task of classifying single-label Physics problems. These findings guide the development of more accurate classification models for application in the context of Physics learning.
ANALISIS PERBANDINGAN ALGORITMA REGION GROWING DAN OTSU THRESHOLDING PADA SEGMENTASI CITRA BUNGA Siswanto, Paulus William; Riti, Yosefina Finsensia; Herijanto, Christopher Kevin
E-Link: Jurnal Teknik Elektro dan Informatika Vol 18 No 2: Oktober 2023
Publisher : Universitas Muhammadiyah Gresik

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30587/e-link.v18i2.6008

Abstract

Dalam segmentasi citra digital, segmentasi merupakan proses memisahkan objek dari latar belakang yang bertujuan agar objek hasil segmentasi dapat dianalisis lebih lanjut. Untuk mendapatkan hasil citra segmentasi yang baik tentu diperlukan algoritma yang baik. Dalam penelitian ini dilakukan pengujian terhadap kedua algoritma populer yaitu algoritma Otsu Thresholding dan algoritma Region Growing. Tujuan dari penelitian ini adalah untuk membandingkan seberapa baik kedua algoritma bekerja dan menghasilkan segmentasi yang akurat dan efektif. Segmentasi citra dievaluasi berdasarkan kualitasnya dengan mempertimbangkan parameter-parameter seperti waktu komputasi, akurasi segmentasi, MSE (Mean Square Error), dan PSNR (Peak Signal to Noise Ratio). Hasil pengujian dari Algoritma Otsu dan Algoritma Region Growing diperoleh hasil sebagai berikut: dari segi komputasi, Region Growing unggul dengan nilai 0.03 detik dibandingkan Otsu dengan nilai 0.13 detik. Dari segi akurasi, Region Growing unggul dengan nilai 0.8473 dibandingkan Otsu dengan nilai 0.7980. Dari segi MSE, Region Growing unggul dengan nilai 6.35 dibandingkan 28.95.
Co-Authors Riti, Yosefina Finsensia Siswanto, Paulus William Wahyuningsih, Yulia