Article Per Year (5 Year)
p-Index From 2021 - 2026
0.751
P-Index
This Author published in this journals
All Journal TEKNOLOGI INFORMASI Informatics and Computer Engineering Journal Communautaire: Journal of Community Service Jurnal Informatika Polinema (JIP)
Vitri Tundjungsari
Universitas Esa Unggul
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Languange, Linguistic, Communication & Media Library & Information Science Public Health Social Sciences Other

Published : 4 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 4 Documents
Search

 1 
Klasifikasi Penyakit Ayam Berdasarkan Citra Kotoran Menggunakan CNN dengan Xception Shela Atya Mitasya; Ary Prabowo; Vitri Tundjungsari
Jurnal Informatika Polinema Vol. 12 No. 3 (2026): Vol. 12 No. 3 (2026)
Publisher : UPT P2M State Polytechnic of Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33795/jip.v12i3.9247

Abstract

Peternakan ayam di Indonesia menghadirkan potensi ekonomi yang substansial karena tingginya permintaan daging dan telur. Namun, peternakan ini juga menghadapi risiko signifikan dari penyakit yang dapat menginfeksi ayam secara tiba-tiba dan seringkali sulit dideteksi sejak dini. Penelitian ini bertujuan untuk membantu peternak mengidentifikasi penyakit ayam lebih cepat dan akurat dengan memanfaatkan teknologi pemrosesan citra digital. Sistem klasifikasi dibangun menggunakan metode Convolutional Neural Network (CNN) dengan arsitektur Xception, yang dikenal karena efisiensinya dalam mengekstraksi fitur visual. Model tersebut mengklasifikasikan citra menjadi empat kategori: Coccidiosis, Newcastle Disease, Salmonella, and healthy conditions. Proses pelatihan menggunakan dataset dari Kaggle dan sejumlah citra lapangan yang terbatas, dengan pembagian data 80:10:10 untuk pelatihan, validasi, dan pengujian. Model tersebut mencapai akurasi 94%, menunjukkan kinerja terbaik dalam mendeteksi Koksidiosis, sementara Penyakit Newcastle menimbulkan lebih banyak tantangan karena keterbatasan data. Pengujian lebih lanjut dengan 36 foto feses lapangan mengonfirmasi keandalan sistem, terutama dalam mengidentifikasi sampel yang sehat. Sistem ini terintegrasi ke dalam aplikasi seluler atau web yang dapat membantu peternak dalam mendeteksi penyakit ayam secara otomatis dari gambar tinja, yang pada akhirnya mengurangi kerugian dan mendukung praktik peternakan unggas yang lebih sehat.
Arduino Basic Training: Making a 12C LCD Running Text for Vocational High School Students Vitri Tundjungsari; Ai Selpia Andita; Alfina Poetri Abdillah; Ivan Febrian Pratama
Communautaire: Journal of Community Service Vol. 4 No. 1 (2025)
Publisher : Al-Qalam Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61987/communautaire.v4i1.1080

Abstract

The development of technology in the era of Industry 4.0 demands increased competencies in the fields of the Internet of Things (IoT) and microcontrollers, especially for students in Vocational High Schools (SMK). Limited hardware and laboratory facilities are major obstacles in practical learning processes. Therefore, utilizing simulation platforms such as Wokwi becomes an effective solution to support microcontroller-based learning. This training aims to provide basic knowledge of Arduino usage through a simulation project of creating a running text on an LCD I2C using Wokwi for SMK students. The method applied combines theory and practice with a participatory approach, involving 25 participants from the Computer and Network Engineering (TKJ) and Visual Communication Design (DKV) departments. The evaluation was conducted using pre-tests and post-tests consisting of 10 multiple-choice questions to measure participants' understanding before and after the training. The results show a significant improvement in post-test scores, particularly in understanding basic concepts of IoT, microcontrollers, and Arduino programming practices. These findings prove that Wokwi is an effective simulation tool for enhancing basic microcontroller programming skills among beginners. Thus, this training model can serve as an alternative solution to support practical learning in schools with limited physical equipment.
Analisis Perbandingan Sensitivitas dan Kinerja K-Means dan DBSCAN Terhadap Variasi Noise Rafael Austin; Ricky Dwi Putra; Ardi Ardi; Fuzail Fazle Rabbi; Lucky Pujiono WS; Vitri Tundjungsari
Teknologi Informasi : Teori, Konsep, dan Implementasi : Jurnal Ilmiah Vol 17 No 1 (2026): JURNAL TEKNOLOGI INFORMASI: Teori, Konsep dan Implementasi
Publisher : STMIK PPKIA Pradnya Paramita

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36382/qq0w1525

Abstract

Inaccurate or noisy data presents a significant challenge in machine learning, particularly in unsupervised clustering tasks. This study evaluates the robustness and performance of two popular clustering algorithms, K-Means and DBSCAN, against various levels of Gaussian noise (5%, 10%, 20%, and 30%) injected into a customer dataset. Evaluation was conducted using Silhouette Score and Davies-Bouldin Index (DBI). Initial results indicated that DBSCAN performed slightly better with a Silhouette Score of 0.4817 compared to K-Means at 0.4101. However, after noise injection, K-Means demonstrated superior stability by maintaining more consistent cluster memberships, whereas DBSCAN was more sensitive to distance variations, leading to significant fluctuations in cluster assignments. The study concludes that K-Means is more reliable for datasets where cluster integrity must be preserved despite minor data irregularities.
Perbandingan Metode K-Means dan Hierarchical Clustering pada Rekomendasi Musik Berbasis Audio Spotify Features Sistem Samuel Mahesa Sinulingga; Farrel Reyhan Putra; Andhika Dwi Rachmawanto; Michael Jeconiah Yonathan; Valentino Wijaya; Vitri Tundjungsari
Informatics and Computer Engineering Journal Vol 6 No 1 (2026): Periode Februari 2026
Publisher : Lembaga Penelitian dan Pengabdian Masyarakat (LPPM) Universitas Bina Sarana Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31294/icej.v6i1.11895

Abstract

Penelitian ini membandingkan metode K-Means dan Hierarchical Clustering dalam sistem rekomendasi musik berbasis audio features Spotify. Dataset yang digunakan berasal dari Spotify Tracks Dataset yang terdiri dari sekitar 114.000 lagu, kemudian melalui tahap pra-pemrosesan diperoleh sekitar 81.000 lagu valid. Untuk efisiensi komputasi, digunakan 5.000 lagu sebagai data eksperimen. Clustering dilakukan menggunakan 6 cluster dengan sembilan atribut audio. Evaluasi menggunakan Silhouette Score dan Davies–Bouldin Index menunjukkan bahwa K-Means memperoleh nilai Silhouette Score 0,1900 dan Davies–Bouldin Index 1,4445, sedangkan Hierarchical Clustering memperoleh nilai Silhouette Score 0,1782 dan Davies–Bouldin Index 1,4522. Hasil ini menunjukkan bahwa K-Means menghasilkan cluster yang lebih kompak. Sistem rekomendasi yang dibangun mampu memberikan rekomendasi lagu yang relevan berdasarkan kemiripan karakteristik audio.
Co-Authors Ai Selpia Andita Alfina Poetri Abdillah Andhika Dwi Rachmawanto Ardi Ardi Ary Prabowo Farrel Reyhan Putra Fuzail Fazle Rabbi Ivan Febrian Pratama Lucky Pujiono WS Michael Jeconiah Yonathan Rafael Austin Ricky Dwi Putra Samuel Mahesa Sinulingga Shela Atya Mitasya Valentino Wijaya