Article Per Year (5 Year)
p-Index From 2021 - 2026
1.607
P-Index
This Author published in this journals
All Journal Majalah Ilmiah Teknologi Elektro Techno.Com: Jurnal Teknologi Informasi TELKOMNIKA (Telecommunication Computing Electronics and Control) Jurnal Media Elektro : Journal of Electrical Power, Informatics, Telecommunication, Electronics, Computer and Control System Indonesian Journal of Electrical Engineering and Computer Science Jurnal Lembaga Pengabdian Kepada Masyarakat Undana RENATA Jurnal Pengabdian Masyarakat Kita Semua Majalah Ilmiah Teknologi Elektro Jurnal SINTA: Sistem Informasi dan Teknologi Komputasi Journal of Applied Research In Computer Science and Information Systems
Silvester Tena
Teknik Elektro, Universitas Nusa Cendana, Indonesia
Humanities Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Earth & Planetary Sciences Economics, Econometrics & Finance Education Electrical & Electronics Engineering Energy Engineering Health Professions Industrial & Manufacturing Engineering Social Sciences Other

Published : 22 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 22 Documents
Search

 1   2   3 
APLIKASI ANDROID UNTUK MENDIAGNOSA PENYAKIT Silvester Tena; Beby H. A. Manafe; Welmy M. Ndoloe
Jurnal Media Elektro Vol 5 No 2 (2016): Oktober 2016
Publisher : Universitas Nusa Cendana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35508/jme.v0i0.6247

Abstract

Sistem pakar merupakan suatu sistem yang dirancang untuk dapat menirukan keahlian seorang pakar dalam memecahkanmasalah. Salah satu permasalahan dalam dunia kesehatan yakni mengenai penyakit mata. Mata merupakan organ tubuhyang wajib dijaga kesehatannya. Kemampuan masyarakat sangat minim dalam mengidentifikasi gejala awal penyakit yangdideritanya dan keterbatasan tenaga ahli sehingga diperlukan sistem pakar. Sistem pakar dapat membantu dokter untukmendiagnosa penyakit mata yang dialami secara dini dengan mengidentifikasi gejala awal yang dialami.Dalam mendiagnosa penyakit mata menggunakan sistem pakar diperlukan suatu metode untuk memberikan hasil diagnosayang dapat dipercaya keakuratannya. Metode Certainty Factor merupakan suatu metode yang dapat diterapkan pada sistempakar. Metode ini memberikan hasil diagnosa yang disertai dengan nilai tingkat kepastian dari tiap penyakit yang dideritaoleh pasien. Sistem pakar ini dikembangkan pada media smartphone berbasis android, sehingga memudahkan penggunadalam pemakaian secara portabel.Pengujian pada sistem pakar ini dilakukan dengan membandingkan hasil diagnosa yang diberikan oleh pakar dan hasildiagnosa dari sistem pakar pada 40 kasus penyakit mata yang diperoleh dari RSUD S.K Lerik Kota Kupang. Penyakit matayang didiagnosa yakni Katarak, Hordeolum, Corpus alienum kornea, Pterygium, Glaukoma dan Konjungtivitis karenapaling sering dialami oleh masyarakat. Hasil pengujiannya menunjukkan bahwa sistem pakar memberikan hasil yang akuratkarena disertai dengan nilai kepastian yang menggambarkan tingkat keyakinan dari pakar mengenai penyakit yangkemungkinan diderita pasien. Persentase keakuratan sistem pakar yang dibuat mencapai 92.5%.
Content-based image retrieval for fabric images: A survey Silvester Tena; Rudy Hartanto; Igi Ardiyanto
Indonesian Journal of Electrical Engineering and Computer Science Vol 23, No 3: September 2021
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v23.i3.pp1861-1872

Abstract

In recent years, a great deal of research has been conducted in the area of fabric image retrieval, especially the identification and classification of visual features. One of the challenges associated with the domain of content-based image retrieval (CBIR) is the semantic gap between low-level visual features and high-level human perceptions. Generally, CBIR includes two main components, namely feature extraction and similarity measurement. Therefore, this research aims to determine the content-based image retrieval for fabric using feature extraction techniques grouped into traditional methods and convolutional neural networks (CNN). Traditional descriptors deal with low-level features, while CNN addresses the high-level, called semantic features. Traditional descriptors have the advantage of shorter computation time and reduced system requirements. Meanwhile, CNN descriptors, which handle high-level features tailored to human perceptions, deal with large amounts of data and require a great deal of computation time. In general, the features of a CNN's fully connected layers are used for matching query and database images. In several studies, the extracted features of the CNN's convolutional layer were used for image retrieval. At the end of the CNN layer, hash codes are added to reduce  search time.
TRANSFORMING WOVEN IKAT FABRIC: ADVANCED CLASSIFICATION VIA TRANSFER LEARNING AND CONVOLUTIONAL NEURAL NETWORKS Tena, Silvester; Dwiandiyanta, Bernadectus Yudi
Jurnal Media Elektro Vol 12 No 2 (2023): Oktober 2023
Publisher : Universitas Nusa Cendana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35508/jme.v12i2.12579

Abstract

The woven ikat fabric from Nusa Tenggara Timur is a local wisdom that must be preserved. Due to its vast array of motifs, users often encounter challenges in its recognition. For this study, the TenunIkatNet dataset was employed. One prominent recognition method involves classification based on the motif type and geographical origin. The efficacy of the classification is heavily contingent upon the method of extraction employed. The Convolutional Neural Network (CNN) method is used for feature extraction and classification processes. This research compares the classification performance of the VGG16 baseline model and the proposed model. The proposed model modifies the baseline at the fully connected layer and the training process from the first convolution layer. Incorporating elements such as Global Average Pooling (GAP), Batch Bormalization (BN), and Dropout has proven instrumental in mitigating overfitting. The transfer learning strategy is used for feature extraction and classification because the model has been intelligently trained on a large dataset. The research findings unequivocally indicate that the performance of the modified model supersedes that of the baseline model. Based on the evaluation metrics, the proposed model is superior to the baseline model with precision, recall, accuracy, and F1-score, respectively 98.73%, 98.54%, 98.54%, and 98.53%
FAST IMAGE RETRIEVAL BERBASIS LOCALITY SENSITIVE HASHING DAN CONVOLUTIONAL NEURAL NETWORK Tena, Silvester; Dwiandiyanta, Bernadectus Yudi; Ina, Wenefrida Tulit
Jurnal Media Elektro Vol 13 No 1 (2024): April 2024
Publisher : Universitas Nusa Cendana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35508/jme.v13i1.15137

Abstract

Image retrieval systems with a fast search process are still challenging for researchers. Fast search methods are one of the most important parts of image retrieval. One of the techniques used is reducing feature dimensions using the Locality Sensitivity Hashing (LSH) method. Apart from that, feature types and image extraction methods are selected. Image feature extraction uses the Convolutional Neural Network (CNN) method in this research. Measuring similarity using the Hamming Distance (HD) and Euclidean Distance (ED) methods. The datasets used are TenunIkatNet and Batik300. The LSH method forms a hash table as a bucket to group similar images based on probability and in the form of binary code. The research results show that the LSH+HD+ED method provides faster search results than ED. The image retrieval time for the LSH+HD+ED and ED methods is 0.252 seconds and 4.5 seconds, respectively, for the TenunIkatNet dataset. Meanwhile, the Batik300 dataset is 0.03 seconds and 0.9 seconds. Using the LSH method is very effective for large datasets. Retrieval accuracy using the LSH+HD+ED method was 99.705% and 84% for the TenunIkatNet and Batik300 datasets, respectively. Meanwhile, the ED method produces 94.17% and 82% retrieval accuracy, respectively.
Aktivitas Sniffing pada Malware Pencuri Uang di Smartphone Android Zulfa, Mulki Indana; Tena, Silvester; Rizkiono, Sampurna Dadi
RENATA: Jurnal Pengabdian Masyarakat Kita Semua Vol. 1 No. 1 (2023): Renata - April 2023
Publisher : PT Berkah Tematik Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61124/1.renata.4

Abstract

Sniffing termasuk dalam cyber-crime yang dilakukan oleh program jahat atau berbahaya (malware) yang sangat merugikan korbannya dengan tujuan untuk mencuri data dan informasi penting lewat jaringan internet. Data yang dicuri umumnya adalah username atau akun login aplikasi ibanking, password m-banking, email, informasi kartu kredit, atau data penting digital lainnya. Tindak kejahatan ini biasanya dengan mengirimkan format berkas yang digunakan untuk memasang aplikasi android yang biasa dikenal dengan file .apk. File berekstensi .apk adalah aplikasi yang dapat dipasang pada perangkat android. Banyak yang menyalahgunakan file .apk ini, salah satunya berisi ransomware atau malware lainnya. Salah satu contoh malware terbaru adalah Sharkbot yang pertama kali ditemukan oleh Cleafy pada Oktober 2021. Keberadaannya di Play Store dideteksi oleh peneliti dari NCC Group yang baru saja membagikan analisis rinci tentang aksi malware tersebut. Salah satu fitur utama malware ini adalah Automatic Transfer System (ATS) yang memungkinkan hacker mentransfer uang korban tanpa sepengetahuan mereka. Ada beberapa cara pencegahan atau preventif untuk menghindari diri dari serangan malware. Jika memiliki server, dapat memasang firewall, Interusion Prevention System (IPS), Deep Packet Inspection (DPI), Unified Thread Management System, antivirus, hingga konten filtering.
IMAGE ENHANCEMENT MENGGGUNAKAN METODE LINEAR FILTERING DAN STATIONARY WAVELET TRANSFORM Silvester Tena
Jurnal Teknologi Elektro Vol 8 No 2 (2009): (July - December) Majalah Ilmiah Teknologi Elektro
Publisher : Program Studi Magister Teknik Elektro Universitas Udayana

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

The aim of the research is image enhancement using the linear filtering and the Stationary Wavelet Transform (SWT) method. The linear filtering method using in this research is median filter, low pass filter and wiener filter and the SWT method using wavelet haar/db1. The Noise as input for source image is salt&pepper and gaussian. The quality of image enhancement determined by qualitative and quantitative assesments. Quantitative performance of the method can be measured by MSE and PSNR. The research shows that ever greater of  the noise density cause the value of MSE uphill progressively but the value of PSNR decrease progressively. The qualitative assessment depend on the everyone perception to the image enhancement. The result obtained shows that the SWT method better than linear filtering method.
Pelatihan Sistem Pembukuan Berbasis Komputer Bagi Tim Pengelola Koperasi Sahabat Literasi Flobamorata Tena, Silvester; Galla, Wellem Fridz; Nursalim, Nursalim; Sampeallo, Agusthinus S
Jurnal Pengabdian Kepada Masyarakat Undana Vol 18 No 2 (2024): DESEMBER 2024
Publisher : Lembaga Penelitian dan Pengabdian Kepada Masyarakat Universitas Nusa Cendana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35508/jpkmlppm.v18i2.19398

Abstract

Empowering Cooperatives and Micro, Small, and Medium Enterprises (MSMEs) is strategic to boost the national economy. East Nusa Tenggara (ENT), as one of the cooperative provinces, is experiencing rapid growth in both quantity and quality. As pillars of regional and national economics, Cooperatives need to be developed, especially for small communities, in their various productive businesses. The development of cooperatives in NTT Province is quite significant until 2023, namely 4,301. Three thousand eight hundred sixty-six cooperatives are legal entities and active, while 435 cooperatives are not yet legal entities. The Koperasi Simpan Pinjam Sahabat Literasi Flobamorata (KSP Batera) is an institution founded by members who have the same destiny and share the same responsibility in the economic field. Its development is quite advanced regarding assets and the number of members. The main problem faced by KSP Batera is that financial management is still manual, and an Annual Member Meeting (AMM) has yet to be held. This happens because the educational background is inappropriate, and there needs to be more knowledge about the Cooperative Financial Accounting System (CFAS). Training activities for the management team on a computer-based financial accounting bookkeeping system is the best solution for the future development of this cooperative. The final result of the training activity is that the management team can complete a computer-based bookkeeping system and financial reports and prepare AMM reports to be accounted for after the close of the financial year. Maximum knowledge transfer occurs because the learning model in the form of theory and practice is 30% and 70%, respectively. Apart from that, assistance is also provided for managers both offline and online
KLASIFIKASI BENIH JAGUNG UNGGUL MENGGUNAKAN METODE MACHINE LEARNING K-NEAREST NEIGHBORS Seyk, Madeleine Nizara; Ina, Wenefrida Tulit; Djahi, Hendrik J.; Tena, Silvester
Jurnal Media Elektro Vol 13 No 2 (2024): Oktober 2024
Publisher : Universitas Nusa Cendana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35508/jme.v13i2.19054

Abstract

Classifying the quality of corn seeds by manual visual observation takes a long time. It also produces products with uneven quality due to visual limitations, fatigue, and differences in observer perception. This research aims to classify superior corn seeds using the machine learning method, namely K-Nearest Neighbors (K-NN). The research data uses 500 images of corn seeds consisting of 400 training images and 100 test images. Extraction of corn image features uses the Gray Level Co-occurrence Matrix (GLCM) method to obtain texture characteristics. The texture characteristic values ​​of metric natural corn images concist of contrast, energy, homogeneity and correlation. Based on the image texture characteristic values, classification is carried out using the K-Nearest Neighbor (K-NN) method. The classification results consist of classes of viable and non-viable corn seeds. The performance evaluation metric method calculates accuracy, sensitivity and specificity using a confusion matrix. This research shows that the value of k=5 is the most optimal, and the accuracy, sensitivity and sensitivity values, respectively, are 75%, 77% and 72% found in the ninth fold
SISTEM DETEKSI NOMINAL UANG KERTAS UNTUK PENYANDANG TUNANETRA BERBASIS KAMERA DENGAN OUTPUT SUARA Halla, Maria Arnoldia; Djahi, Hendrik J.; Tulit Ina, Wenefrida; Tena, Silvester
Jurnal SINTA: Sistem Informasi dan Teknologi Komputasi Vol. 2 No. 1 (2025): SINTA - JANUARI
Publisher : Berkah Tematik Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61124/sinta.v2i1.36

Abstract

Penyandang tunanetra mengalami kendala dalam mengenali nominal uang sehingga dibutuhkan alat bantu. Penelitian ini bertujuan untuk merancang sistem deteksi yang dapat mengenali nominal uang kertas. Bagi penyandang tunanetra dapat terbantu sehingga mengurangi ketergantungan pada orang lain dalam mengenali nominal uang. Algoritma Oriented FAST and Rotated BRIEF (ORB) digunakan untuk ekstraksi fitur yang dibutuhkan dalam mendeteksi serta mencocokkan fitur uang kertas. Sistem deteksi nominal uang kertas menggunakan Raspberry Pi 3B sebagai pengendali utama dan kamera OV5647 untuk menangkap gambar uang. Gambar yang ditangkap kamera akan diproses ekstraksi fitur dan dilakukan pencocokan gambar uji dan gambar dalam dataset. Keluaran berupa suara yang memberikan informasi nominal yang kertas sangat membantu penyandang tunanetra. Pengujian dilakukan pada jarak 5 cm hingga 30 cm untuk mengukur akurasi deteksi dan durasi waktu identifikasi. Hasil deteksi yang berhasil kemudian diubah menjadi suara dengan bantuan modul PAM8403. Hasil pengujian menunjukkan bahwa sistem mampu mendeteksi nominal uang dengan akurasi 100% pada jarak 5 cm hingga 10 cm, namun menurun menjadi 25% pada jarak 30 cm. Durasi waktu identifikasi dipengaruhi oleh jarak antara kamera dan uang kertas. Jarak semakin dekat durasi pengenalan lebih lama yaitu 10-15 detik, sedangkan pada jarak lebih jauh waktu identifikasi lebih singkat. Pada jarak dekat jumlah keypoints yang dihasilkan lebih banyak sehingga membutuhkan waktu lebih dalam dalam proses matching. Namun jarak semakin jauh akurasinya lebih rendah. Sistem deteksi nominal uang kertas cukup efektif meskipun performanya bergantung pada jarak antara kamera dan objek serta kualitas kamera. Kata kunci: Uang Kertas; kamera; ORB; Raspberry; Tunanetra.
Fruit and Vegetable Classification using Convolutional Neural Network with MobileNetV2 Khoiruddin, Muhammad; Tena, Silvester
Journal of Applied Research In Computer Science and Information Systems Vol. 2 No. 2 (2024): December 2024
Publisher : PT. BERBAGI TEKNOLOGI SEMESTA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61098/jarcis.v2i2.197

Abstract

Fruits are parts of plants that originate from the plant's pistils and usually contain seeds. Meanwhile, vegetables are leaves, legumes, or seeds that can be cooked. Fruits and vegetables have many variations that can be distinguished based on color, shape, and texture. However, the development of Artificial Intelligence (AI) technology has become pervasive in everyday life, one aspect of which is demonstrated through deep learning, a method of AI learning. Therefore, developing deep learning for tasks such as automatically detecting surrounding objects is necessary. This study aims to classify types of fruits and vegetables by applying a Convolutional Neural Network (CNN) with the MobileNetV2 architecture. In this study, fruits and vegetables encompassing 36 categories, including significant types in daily life, were considered. The results show that the classification system achieved an excellent accuracy rate of 97.31%, demonstrating the effectiveness of using deep learning techniques for this application
Co-Authors Beby H. A. Manafe Beby H.A. Manafe Brian J. Mooy Dominikus, Wara Sabon Dwiandiyanta, Bernadectus Yudi Galla, Wellem Fridz Gregorius Klau Halla, Maria Arnoldia Hendrik J. Djahi Hendro FJ Lami Herry Zadrak Kotta I Wayan Sukarjita Igi Ardiyanto Johanis F.M Bowakh Kalvein Rantelobo Lejap, Marianus Yakobus Lili Manafe, Beby H. A. Melzando L. F Tari Muhammad Khoiruddin Mulki Indana Zulfa, Mulki Indana Ndoloe, Welmy M Nursalim Nursalim Nursalim Nursalim Pratama, Bima Gerry Rizkiono, Sampurna Dadi Rudy Hartanto Sampeallo, Agusthinus S Samy Y. Doo Sarlince O. Manu Seyk, Madeleine Nizara Stephanie I. Pella Sudirman Syam Syahrul Syahrul Tari, Melzando L. F Tulit Ina, Wenefrida Varly M Ndolu Welmy M. Ndoloe Wenefrida T Ina Yoga Arya Setyadi