Article Per Year (5 Year)
p-Index From 2019 - 2024
0.562
P-Index
This Author published in this journals
All Journal JURNAL MEDIA INFORMATIKA BUDIDARMA
Abu Salam
Universitas Dian Nuswantoro, Semarang
Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering

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

Found 3 Documents
Search

 1 
Seleksi Fitur Information Gain untuk Optimasi Klasifikasi Penyakit Tuberkulosis Ardi Caesar Kurniawan; Abu Salam
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 8, No 1 (2024): Januari 2024
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v8i1.7122

Abstract

Tuberculosis (TB), caused by Mycobacterium tuberculosis, is a global health threat that spreads through the air. Factors such as gender, age, and geographical location influence its spread. Indonesia, the country with the second-highest number of TB cases globally, recorded a significant increase in TB cases from 2020 to 2022, especially in Semarang City. To minimize TBs impact, its crucial to identify the factors influencing its progression. Machine Learning techniques like feature selection (Information Gain) and classification algorithms (Random Forest) can be utilized. Feature selection helps determine which factors most influence TB by ranking attribute weights, while Random Forest is used for classification. Oversampling techniques like Synthetic Minority Oversampling Technique (SMOTE) are used to handle data imbalance and improve classification performance. The study concluded that the Random Forest classification model showed the best performance using all features or attributes from the highest to the lowest weight namely; tipe_diagnosis, jenis_fasyankes, usia, kelurahan_kecamatan, riwayat_dm, riwayat_HIV, tahun, paduan_OAT, status_pekerjaan, jenis_kelamin, tipe_TBC, riwayat_TBC, bulan and sumber_obat on the original TB disease dataset in Semarang City. The recall and accuracy rate reached 75%. This result is better than the TB classification model in Semarang City that uses the oversampling dataset with SMOTE and only uses the top 10-12 attributes, with a recall and accuracy rate of 74%. This research shows that certain techniques in Machine Learning can help understand the factors influencing TB treatment outcomes.
Analisis Topic-Modelling Menggunakan Latent Dirichlet Allocation (LDA) Pada Ulasan Sosial Media Youtube Vika Alpiana; Abu Salam; Farrikh Alzami; Ifan Rizqa; Diana Aqmala
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 8, No 1 (2024): Januari 2024
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v8i1.7127

Abstract

This research explores the role of Micro, Small, and Medium Enterprises (MSMEs) in the Indonesian economy, focusing on sales and marketing challenges in the era of social media, especially YouTube. With millions of individuals using this platform to share product insights, reviews, and experiences, MSMEs need to receive relevant feedback. This study applies text mining, particularly the topic modeling analysis method with Latent Dirichlet Allocation (LDA), to analyze user comments on MSME videos, with an emphasis on Lumpia Gang Lombok Semarang on YouTube. Through the application of LDA, the identification of ten main topics is conducted, with the highest coherence value reaching 0.414027. The visualization of the intertopic distance map provides an understanding of the relationships between topics and dominant words. Comment analysis provides valuable insights into user preferences and perceptions of products, supporting MSMEs in understanding customer satisfaction and enhancing value for those enterprises. These findings also affirm the effectiveness of YouTube as a relevant data source for understanding public preferences for MSME products. This research details text processing methods, including extraction, cleaning, tokenization, normalization, removal of stopwords, and stemming. With this approach, the research not only provides insights into topic analysis in the context of social media but also makes a valuable contribution to the development and marketing of MSMEs through a better understanding of social media data, especially on the YouTube platform.
Evaluasi Performa Oversampling dan Augmentasi pada Klasifikasi Penyakit Kulit Menerapkan Convolutional Neural Network Deo Andrianto Iskandar; Abu Salam
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 8, No 1 (2024): Januari 2024
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v8i1.7119

Abstract

The skin is the largest outer part of the human body. Maintaining skin is very important. The appearance of unusual things on the skin will raise concerns because it is possible that the skin could be affected by fatal diseases. Limited specialist doctor examinations in Indonesia add to the difficulty in preventing skin diseases. Therefore, this research was conducted to facilitate the classification of skin diseases. Skin disease classification must have good accuracy or precision in classifying each type. This study classifies skin diseases accurately and precisely by evaluating the performance of Oversampling and Augmentation techniques. This research uses the Convolutional Neural Network (CNN) approach. Using the HAM10000 dataset which contains dermoscopic images with a total of 10015 images. This study applies Oversampling to overcome data imbalance and applies image augmentation to improve model training performance. The performance of the model is evaluated using accuracy, recall, precision, f1-score, specificity, sensitivity, gmean. Comparisons are obtained from testing the original dataset, the dataset with oversampling and various augmentation techniques. The evaluation results show that the third test, namely classification using the CNN approach with oversampling and augmentation rotation, zoom, width, height, vertical_flip, gets the best results, namely accuracy 0.98, recall 0.98, precision 0.98, f1-score 0.98, specificity 0.99, sensitivity 0.98, gmean 0.98.
Co-Authors Ardi Caesar Kurniawan Deo Andrianto Iskandar Diana Aqmala Farrikh Alzami Ifan Rizqa Vika Alpiana