Article Per Year (5 Year)
p-Index From 2021 - 2026
0.61
P-Index
This Author published in this journals
All Journal Jurnal Elektronika dan Telekomunikasi JIPI (Jurnal Ilmiah Penelitian dan Pembelajaran Informatika) Jurnal Pengabdian Masyarakat Sultan Indonesia
Karostiani, Novia
Unknown Affiliation
Religion Humanities Computer Science & IT Education Electrical & Electronics Engineering Engineering Languange, Linguistic, Communication & Media Social Sciences

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

Found 3 Documents
Search

 1 
Development of the Android Application for the Landslide Disaster Mitigation Real-time System based on Firebase Server and OneSignal Nawawi, Aif Umar; Pantjawati, Arjuni Budi; Saripudin, Aip; Hakim, Nurul Fahmi Arief; Nurhidayatulloh, Nurhidayatulloh; Karostiani, Novia; Anandayutya, Bagaskara; Darmawan, Alvin Dzaki Pratama
Jurnal Elektronika dan Telekomunikasi Vol 24, No 2 (2024)
Publisher : National Research and Innovation Agency

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55981/jet.674

Abstract

This article presents the development of SIDASIBELO (Landslide Information and Mitigation System), an Android-based application for real-time landslide monitoring and early warning. This system integrates data from several sensors that measure soil moisture, rainfall, slope angle, and ground vibrations at the monitored locations. The Firebase Real-time Database stores and transmits sensor data, while Firebase Cloud Messaging and OneSignal enable push notifications to alert users about potential landslide risks. There are four output status levels: SAFE, ALERT, CAUTION, and WARNING, which are determined based on a comprehensive analysis of the monitored parameters. Mitigation strategies include real-time parameter monitoring, early warnings, evacuation guidance, and user education on landslide preparedness. Testing on several Android devices demonstrated high compatibility, with an average successful server connection rate of 92.86%. Latency tests indicated an average response time of 894 ms from the input device to the database, 1.29 ms from the database to the Android device, and 2725 ms for push notifications. The system's total daily bandwidth usage for real-time data transmission is 27,648 MB, indicating high efficiency without overburdening the server's performance. While the app operates efficiently under ideal conditions, unstable network connections can lead to data retrieval failures or, in worst cases, app malfunctions. This remains a key challenge for our system. This system aims to raise awareness of landslide risks and enable timely evacuation, which could potentially reduce the negative impacts of landslides in vulnerable areas.
Meningkatkan Kualitas Kajian Dengan Pemasangan Media Audio Visual di Lingkungan Masjid Supriyadi, Tata; Hartono, Tri; Utomo, TB.; Soebagja Budiana, Mochamad; Karostiani, Novia; Rahayu, Maya
Jurnal Pengabdian Masyarakat Sultan Indonesia Vol. 2 No. 2 (2025): Abdisultan
Publisher : Sultan Publsiher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58291/abdisultan.v2i2.445

Abstract

Masjid memiliki peran strategis sebagai pusat kegiatan keagamaan dan pendidikan umat Islam. Salah satu kegiatan utama di masjid adalah kajian keislaman yang berfungsi memperdalam pemahaman jamaah terhadap ajaran agama. Namun, pelaksanaan kajian sering kali menghadapi kendala dalam penyampaian materi akibat keterbatasan media dan sarana pendukung, sehingga kualitas kegiatan belum optimal. Penelitian ini bertujuan untuk meningkatkan kualitas kajian melalui penerapan media audio visual di lingkungan masjid. Metode penelitian yang digunakan adalah metode deskriptif dengan pendekatan kualitatif, meliputi observasi, wawancara dengan pengurus masjid, dan evaluasi terhadap pelaksanaan kajian sebelum dan sesudah pemasangan media audio visual. Hasil penelitian menunjukkan bahwa penerapan media audio visual, seperti proyektor, layar, dan sistem pengeras suara yang memadai, secara signifikan meningkatkan efektivitas penyampaian materi, perhatian jamaah, serta partisipasi masyarakat dalam kegiatan kajian. Media tersebut juga menciptakan suasana kajian yang lebih interaktif, menarik, dan mudah dipahami oleh berbagai kalangan jamaah. Kesimpulannya, pemasangan media audio visual di lingkungan masjid terbukti efektif dalam meningkatkan kualitas kajian keagamaan dan memperkuat fungsi masjid sebagai pusat dakwah serta pembelajaran Islam yang adaptif terhadap kemajuan teknologi di era digital.
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 Aip Saripudin Anandayutya, Bagaskara Arjuni Budi Pantjawati Budiana, Mochamad Soebagja Darmawan, Alvin Dzaki Pratama Griffani Megiyanto Rahmatullah Hartono, R.W. Tri Hartono, Tri Maya Rahayu, Maya Nawawi, Aif Umar Nurhidayatulloh, Nurhidayatulloh Nurul Fahmi Arief Hakim Slameta, Slameta Soebagja Budiana, Mochamad Supriyadi, Tata Utomo, TB.