Article Per Year (5 Year)
p-Index From 2021 - 2026
0.444
P-Index
This Author published in this journals
All Journal Register: Jurnal Ilmiah Teknologi Sistem Informasi JIPI (Jurnal Ilmiah Penelitian dan Pembelajaran Informatika)
Budiana, Mochamad Soebagja
Unknown Affiliation
Computer Science & IT Education

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

Found 2 Documents
Search

 1 
Advanced detection Denial of Service attack in the Internet of Things network based on MQTT protocol using fuzzy logic Budiana, Mochamad Soebagja; Negara, Ridha Muldina; Irawan, Arif Indra; Larasati, Harashta Tatimma
Register: Jurnal Ilmiah Teknologi Sistem Informasi Vol 7, No 2 (2021): July
Publisher : Information Systems - Universitas Pesantren Tinggi Darul Ulum

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26594/register.v7i2.2340

Abstract

Message Queuing Telemetry Transport (MQTT) is one of the popular protocols used on the Internet of Things (IoT) networks because of its lightweight nature. With the increasing number of devices connected to the internet, the number of cybercrimes on IoT networks will increase. One of the most popular attacks is the Denial of Service (DoS) attack. Standard security on MQTT uses SSL/TLS, but SSL/TLS is computationally wasteful for low-powered devices. The use of fuzzy logic algorithms with the Intrusion Detection System (IDS) scheme is suitable for detecting DoS because of its simple nature. This paper uses a fuzzy logic algorithm embedded in a node to detect DoS in the MQTT protocol with feature selection nodes. This paper's contribution is that the nodes feature selection used will monitor SUBSCRIBE and SUBACK traffic and provide this information to fuzzy input nodes to detect DoS attacks. Fuzzy performance evaluation is measured against changes in the number of nodes and attack intervals. The results obtained are that the more the number of nodes and the higher the traffic intensity, the fuzzy performance will decrease, and vice versa. However, the number of nodes and traffic intensity will affect fuzzy performance.
DEEP LEARNING-BASED ENVIRONMENTAL SOUND CLASSIFICATION USING TUNED MOBILEVIT WITH COMBINED AUGMENTATION TECHNIQUES Slameta, Slameta; Rahmatullah, Griffani Megiyanto; Karostiani, Novia; Budiana, Mochamad Soebagja; Hartono, R.W. Tri
JIPI (Jurnal Ilmiah Penelitian dan Pembelajaran Informatika) Vol 10, No 4 (2025)
Publisher : STKIP PGRI Tulungagung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29100/jipi.v10i4.9377

Abstract

Classifying environmental sounds poses significant challenges because of their naturally disorganized characteristics. This research introduces a deep learning method for categorizing urban audio using the MobileViT architecture, which serves as a versatile, lightweight solution for various deep learning applications. The study utilizes the UrbanSound8k dataset, enhanced through multiple augmentation strategies including noise injection, time stretching, pitch modulation, and mixup methods. These augmentation techniques are essential given the dataset's size constraints and help create a more robust model for practical applications. Following augmentation, the audio undergoes preprocessing to standardize length and is transformed into mel spectrograms, making it compatible with MobileViT's input requirements. The model undergoes training with both standard and optimized parameters, achieving peak performance exceeding 80% accuracy. The integration of augmented data and parameter optimization yields approximately 15% improvement over the baseline MobileViT configuration while preserving rapid inference speeds of roughly 7 milliseconds. The findings prove that MobileViT represents a promising solution for various environmental sound applications.
Co-Authors Arif Indra Irawan Griffani Megiyanto Rahmatullah Hartono, R.W. Tri Karostiani, Novia Larasati, Harashta Tatimma Ridha Muldina Negara Slameta, Slameta