Article Per Year (5 Year)
p-Index From 2021 - 2026
0.947
P-Index
This Author published in this journals
All Journal Jurnal Sarjana Teknik Informatika JurTI (JURNAL TEKNOLOGI INFORMASI) METHODIKA: Jurnal Teknik Informatika dan Sistem Informasi Jurnal Mantik HOAQ (High Education of Organization Archive Quality) : Jurnal Teknologi Informasi
Erna Rosani Nubatonis
STIKOM Uyelindo Kupang
Computer Science & IT Economics, Econometrics & Finance Languange, Linguistic, Communication & Media

Published : 6 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 6 Documents
Search

 1 
System Monitoring Tingkat Kekeruhan Air dan Pemberian Pakan Ikan Pada Aquarium Berbasis IOT Yohanes Karmani; Yohanes Suban Belutowe; Erna Rosani Nubatonis
(JurTI) Jurnal Teknologi Informasi Vol 6, No 1 (2022): JUNI 2022
Publisher : Universitas Asahan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36294/jurti.v6i1.2598

Abstract

Internet of Things (IoT) adalah sebuah konsep dimana suatu objek yang memiliki kemampuan untuk mentransfer data melalui jaringan Internet tanpa memerlukan interaksi manusia ke manusia atau manusia ke komputer. Sistem Monitoring Tingkat Kekeruhan Air dan Pemberian Pakan Ikan pada aquarium berbasis Iot (Internet of Things) dalam pemberian pakan ikan berupa pelet, dan kejernihan air dalam aquarium karena ikan membutuhkan air yang jernih. pekerjaan yang rutin dilakukan pada aquarium adalah memberi pakan ikan dan mengganti air yang sudah keruh agar terlihat bersih dan menciptakan kondisi yang baik untuk ikan tersebut. Komponen yang digunakan meliputi ESP8266 nodeMCU, Sensor turbidity, Sensor suhu, Servo, Pompa air mini, dan Aplikasi sebagai Interface Untuk mengetahui tingkat kekeruhan air pada aquarium.
Implementation Of GLCM (Gray Level Co-Occurrence Matrix) & KNN( K-Nearest Neighbor ) For Classification Of Fiber Root Plant Types Based On Leaf Image Nubatonis, Erna Rosani
Jurnal Mantik Vol. 8 No. 2 (2024): August: Manajemen, Teknologi Informatika dan Komunikasi (Mantik)
Publisher : Institute of Computer Science (IOCS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35335/mantik.v8i2.5397

Abstract

This study aims to implement the GLCM (Gray Level Co-Occurrence Matrix) and KNN (K-Nearest Neighbor) methods in the classification of fiber root species based on leaf images. Fibrous roots are the most common root type in certain plants, and classifying plant species based on leaf image can provide useful information in contacting plants. The GLCM method is used to extract texture features from leaf images. The GLCM matrix describes the relative occurrence of pixel pairs with different gray intensities in the image. These features can provide information about leaf texture that can be used in classification. Furthermore, the KNN algorithm is used to classify plant types based on the extracted features. The dataset used in this study consists of a number of leaf images representing several different types of fiber root plants. Image processing includes pre-processing to obtain a clean image and ensure consistency of image size. After feature extraction using the GLCM method, these features are used as input for the KNN algorithm. KNN is used to classify unknown leaf images into one of the plant classes that have been previously trained. The experimental results show that the GLCM and KNN methods can provide good results in the classification of fiber root plant species based on leaf images. High classification accuracy indicates the effectiveness of this method in identifying plant species based on textural features of leaf images. Thus, this method can be a useful tool in the field of plant recognition and other applications that involve identifying plant species based on leaf images
ANALISA DAN PERANCANGAN PREDIKSI TINGKAT PRESENTASI MAHASISWA BARU MASUK SEBAGAI MAHASISWA AKTIF DI STIKOM UYELINDO KUPANG MENGGUNAKAN ROUGHT SET Nubatonis, Erna Rosani
HOAQ (High Education of Organization Archive Quality) : Jurnal Teknologi Informasi Vol. 10 No. 1 (2019): Jurnal HOAQ - Teknologi Informasi
Publisher : STIKOM Uyelindo Kupang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52972/hoaq.vol10no1.p23-29

Abstract

Acceptance of new students is the most important part of STIKOM UYELINDO Kupang as one of the benchmarks for the progress of the campus in the future. In the process of admitting new students (PMB), prospective new students must go through several stages of registration until the stage of filling out the KRS, so that the students concerned are legitimately declared as active students of STIKOM UYELINDO KUPANG. However, many cases occur that not all students arrive at the final stage of filling in the KRS to be declared as active students. Problems that occur result in the division responsible for new students difficult to predict that prospective students concerned in the process of admitting new students, will go through the process until the status of filling KRS or not, and also affect the prediction of the number of new student achievement. This study aims to find out and recognize the pattern of classification of new student registration status so that the level of presentation of new students entering the STIKOM UYELINDO KUPANG can be made by applying the rough set algorithm. In the process of applying Rough Set, it will produce a rule as a rule or pattern for classification of new student registration status data. The data used in this study is the data of new student registration in 2016-2018 with a total record of 579 records. The results of this study are expected to be an important input for the responsibility of new students and high school education institutions, in the strategy of screening new students to achieve the target of better new student admissions.
Klasifikasi Jenis Kopi Lokal Menggunakan Convolutional Neural Network Berbasis InceptionV3 Margaretha Maria Sina; Erna Rosani Nubatonis; Heni
Jurnal Sarjana Teknik Informatika Vol. 14 No. 2 (2026): Juni
Publisher : Program Studi Informatika, Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/jstie.v14i2.32193

Abstract

Kopi merupakan salah satu komoditas perkebunan unggulan yang memiliki nilai ekonomi tinggi dan menjadi sumber pendapatan masyarakat di berbagai daerah, termasuk Flores Sikka, Nusa Tenggara Timur. Identifikasi jenis kopi masih dilakukan secara manual berdasarkan pengamatan visual sehingga berpotensi menimbulkan kesalahan dan ketidakkonsistenan. Penelitian ini bertujuan mengembangkan model klasifikasi jenis kopi lokal menggunakan metode Convolutional Neural Network (CNN) berbasis arsitektur InceptionV3. Dataset yang digunakan terdiri atas 300 citra biji kopi yang terbagi ke dalam tiga kelas, yaitu Arabika, Robusta, dan Liberika. Tahapan penelitian meliputi akuisisi data, preprocessing, augmentasi data, pembagian data menggunakan 5-Fold Cross Validation, pelatihan model dengan transfer learning, serta evaluasi menggunakan confusion matrix. Model dilatih menggunakan ukuran citra 299×299 piksel, optimizer Adam, learning rate 0,00001, batch size 8, dan 40 epoch. Hasil pengujian menunjukkan bahwa model memperoleh rata-rata akurasi sebesar 96,6% dengan akurasi terbaik mencapai 98%. Nilai precision, recall, dan F1-score pada masing-masing kelas juga menunjukkan performa yang tinggi. Hasil penelitian membuktikan bahwa arsitektur InceptionV3 efektif dalam mengenali karakteristik visual biji kopi dan dapat digunakan sebagai solusi klasifikasi otomatis yang akurat dan konsisten. Hasil ini menunjukkan bahwa arsitektur InceptionV3 mampu mengenali fitur morfologi biji kopi lokal dengan baik meskipun menggunakan jumlah dataset yang relatif terbatas, sehingga berpotensi diterapkan sebagai sistem identifikasi kopi otomatis pada sektor pertanian dan industri pengolahan kopi.
IMPLEMENTASI TRANSFER LEARNING DENGAN FINE-TUNING PADA DETEKSI OBJEK MULTI-KELAS MENGGUNAKAN YOLO (STUDI KASUS CAR FREE DAY JALAN EL TARI KOTA KUPANG) Hendrikus Samuel Ola Sogen; Erna Rosani Nubatonis; Hasibun Asikin
METHODIKA: Jurnal Teknik Informatika dan Sistem Informasi Vol. 12 No. 2 (2026): Volume 12 Nomor 2 Tahun 2026
Publisher : Universitas Methodist Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46880/mtk.v12i2.5923

Abstract

Object detection is a computer vision technology used to recognize and determine the location of objects in images or videos. This study aims to implement the transfer learning method with fine-tuning on the YOLOv8m model to detect multi-class objects consisting of persons, vehicles, and umbrellas in the Car Free Day environment on El Tari Street, Kupang City, as well as to develop a web-based object detection system capable of automatically detecting objects in images and videos. The research dataset consisted of 315 images obtained through field documentation and annotated using Roboflow, which was then increased to 757 images through the augmentation process before being divided into training, validation, and testing datasets. The YOLOv8m pretrained model based on the COCO dataset was trained using Google Colab for 100 epochs with the transfer learning and fine-tuning approach. The results showed that the model achieved a precision of 0.903, a recall of 0.801, an mAP50 of 0.868, and an mAP50-95 of 0.625. In addition, the developed web-based system was able to automatically detect objects in images and videos and display bounding boxes, confidence scores, object counts, detection result graphs, and model evaluation metrics. The results of the study indicate that the application of fine-tuning to YOLOv8m is capable of improving the model's adaptability to the characteristics of the local Car Free Day environment, thereby potentially supporting more effective public activity monitoring.
SISTEM PELAPORAN PERBAIKAN DATA ALUMNI BERBASIS MOBILE WEB PADA UNIVERSITAS ARYASATYA DEO MURI Lepri Veronika Nino; Erna Rosani Nubatonis; Heni
METHODIKA: Jurnal Teknik Informatika dan Sistem Informasi Vol. 12 No. 2 (2026): Volume 12 Nomor 2 Tahun 2026
Publisher : Universitas Methodist Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46880/mtk.v12i2.6106

Abstract

Accurate and up-to-date alumni data is an important aspect in supporting academic reporting and information management in higher education. However, the alumni data improvement process at Aryasatya Deo Muri University is still done manually so it is less efficient, takes longer time, and makes it difficult for alumni to submit and monitor the status of data improvement. This study aims to design and build a mobile web-based Alumni Data Improvement Reporting System to facilitate alumni, academic departments, and PDDIKTI operators in the process of submitting, verifying, and monitoring data improvement. The system was developed using the Waterfall method which includes needs analysis, design, implementation, testing, and maintenance, by utilizing PHP, MySQL, and Bootstrap technology. System testing was carried out using the Black Box method and user evaluation through questionnaires to 57 alumni respondents selected using the Slovin formula. The results showed that all system functions ran according to needs, while the results of the user evaluation obtained a satisfaction level of 80.79% with the Strongly Agree category, which indicates that the system is easy to use and able to support the alumni data improvement process effectively. The main contribution of this research is the availability of a system that integrates supporting document upload features, verification and validation processes, and real-time monitoring of application status, thereby increasing the efficiency of alumni data management and supporting the provision of more accurate, up-to-date, and well-documented data.
Co-Authors Hasibun Asikin Hendrikus Samuel Ola Sogen Heni Lepri Veronika Nino Margaretha Maria Sina Yohanes Karmani Yohanes Suban Belutowe