Article Per Year (5 Year)
p-Index From 2021 - 2026
0.61
P-Index
This Author published in this journals
All Journal Jurnal Pepadun
Didik Kurniawan
Department of Computer Science, Universitas Lampung
Computer Science & IT

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

 1 
Application of MobileNetV1 and DenseNet-121 CNN Architectures for Eye-Based Gender Classification Sinta Nurhalifah; Akmal Junaidi; Didik Kurniawan; M. Iqbal Parabi
Jurnal Pepadun Vol. 7 No. 1 (2026): April
Publisher : Department of Computer Science, Faculty of Mathematics and Natural Sciences, University of Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23960/pepadun.v7i1.296

Abstract

Gender classification is an important field in biometric identification systems that plays a vital role in security, forensics, and human–computer interaction. Human eye images are a promising visual object for gender classification because they contain distinct anatomical features that differ between males and females. This study aims to implement and evaluate two Convolutional Neural Network (CNN) architectures, namely MobileNetV1 and DenseNet-121, for gender classification based on human eye images. The dataset used was obtained from the Kaggle platform, consisting of 11,525 eye images, with 6,323 male and 5,202 female samples. The research process involved several stages, including pre-processing, data splitting, augmentation using Affine transformations (rotation and translation), as well as model training and evaluation. The evaluation was conducted using accuracy, precision, recall, and F1-score metrics. The results showed that both architectures were capable of performing gender classification effectively, although differences in performance were observed. The best accuracy was achieved by MobileNetV1 with a rotation scenario of 92.49%, while DenseNet-121 obtained 86.84% with a combined rotation and translation scenario. This research is expected to contribute to the development of efficient and accurate eye image–based gender classification systems using deep learning approaches.
Detection of Hate Speech in TikTok Comment Sections Using the Naïve Bayes Algorithm with Smoothing Implementation Roy Rafles Matorang Pasaribu; Didik Kurniawan; Muhaqiqin Muhaqiqin; Akmal Junaidi
Jurnal Pepadun Vol. 6 No. 3 (2025): December
Publisher : Department of Computer Science, Faculty of Mathematics and Natural Sciences, University of Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23960/pepadun.v6i3.268

Abstract

Hate speech is a biased, antagonistic, and discriminatory expression that commonly appears on social media platforms, including TikTok. The high volume of comments and varied language styles make manual detection challenging. This research proposes a hate speech detection model using the Multinomial Naïve Bayes algorithm with smoothing to address zero-probability issues and enhance prediction performance. The dataset is split into 80% training and 20% testing portions. The model achieves an accuracy of 88.41%, with precision, recall, and F1-score showing balanced performance. A user evaluation involving 35 participants and 7,415 TikTok comments records a detection accuracy of 68.6%. The model is further implemented into a Google Chrome extension capable of real-time hate speech detection, displaying prediction probabilities and allowing user validation. This study aims to support healthier digital interactions by improving automated hate speech detection on social media.
Structured Systems Analysis and Design (SSADM) Approach in Web-Based Biometric Attendance Systems: A Study at BASARNAS Lampung Az-Zahra Adellia; Didik Kurniawan; Anie Rose Irawati; Bambang Hermanto
Jurnal Pepadun Vol. 7 No. 2 (2026): August
Publisher : Department of Computer Science, Faculty of Mathematics and Natural Sciences, University of Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23960/pepadun.v7i2.278

Abstract

The development of online lectures in Indonesia has encouraged universities to develop more targeted branding strategies, particularly in increasing brand awareness and digital engagement. Public perceptions reflected in open digital sources, particularly online news portals, are important data sources for understanding how online lectures are perceived by the public. This study aims to analyze public opinion on online lectures in Indonesia using web scraping, text mining, TF-IDF Vectorizer, and the K-Means Clustering algorithm. Initial data was obtained through web scraping using several Indonesian keywords related to online lectures and resulted in 108 text documents. After duplicate removal, noise filtering, and text preprocessing, the number of documents used in the analysis was reduced to 60 documents. The analysis stages included text cleaning, normalization, feature extraction using TF-IDF, determining the optimal number of clusters using the Elbow Method and Silhouette Score, and clustering using K-Means. The results showed that the optimal number of clusters was 4 clusters. The formed clusters represent the themes of online lecture academic activities, social and cultural dimensions, distance education and policy, as well as economic, regulatory, and technological aspects. The TF-IDF matrix yielded 1669 features, while the final evaluation yielded a Silhouette Score of 0.0345. PCA visualization showed overlap between clusters, indicating that public perception of online lectures is multidimensional. The conclusion of this study shows that the TF-IDF and K-Means approaches can be used to map public opinion and develop more contextual, data-driven, and relevant online lecture branding recommendations for universities.
Co-Authors Akmal Junaidi Anie Rose Irawati Az-Zahra Adellia Bambang Hermanto M. Iqbal Parabi Muhaqiqin Muhaqiqin Roy Rafles Matorang Pasaribu Sinta Nurhalifah