Article Per Year (5 Year)
p-Index From 2020 - 2025
4.494
P-Index
This Author published in this journals
All Journal Jurnal Simetris JUITA : Jurnal Informatika Jurnal CoreIT SELAPARANG: Jurnal Pengabdian Masyarakat Berkemajuan JURNAL TEKNIK INFORMATIKA DAN SISTEM INFORMASI Jurnal Teknologi Terpadu Jurnal Teknologi Komputer dan Sistem Informasi Jutisi: Jurnal Ilmiah Teknik Informatika dan Sistem Informasi Algoritme Jurnal Mahasiswa Teknik Informatika Informatics and Enginering Dedication Jurnal Ilmiah Teknologi dan Komputer (JITTER) MDP Student Conference JTKSI (Jurnal Teknologi Komputer dan Sistem Informasi) JuTISI (Jurnal Teknik Informatika dan Sistem Informasi)
Devella, Siska
UNIVERSITAS MULTI DATA PALEMBANG
Agriculture, Biological Sciences & Forestry Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Engineering Environmental Science Health Professions Languange, Linguistic, Communication & Media Law, Crime, Criminology & Criminal Justice Medicine & Pharmacology Nursing Public Health Social Sciences Other

Published : 29 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 29 Documents
Search

 1   2   3 
Klasifikasi Media Pembuangan Sampah Menggunakan Metode Resnet101-V2 Valentino Ruben Ho; Siska Devella; Derry Alamsyah
MDP Student Conference Vol 2 No 1 (2023): The 2nd MDP Student Conference 2023
Publisher : Universitas Multi Data Palembang

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (410.633 KB) | DOI: 10.35957/mdp-sc.v2i1.4338

Abstract

Sampah adalah benda/zat yang tidak digunakan lagi dan ditinggalkan oleh manusia. Plastik merupakan salah satu faktor yang membuat sampah sulit terurai. Penggunaan plastik dalam kehidupan manusia sudah menjadi hal yang lumrah dan rutin digunakan dalam aktivitas manusia. Media pembuangan limbah juga berkontribusi terhadap pencemaran lingkungan. Oleh karena itu, dalam penelitian ini peneliti meneliti media pengolahan limbah dengan menggunakan metode deep learning residual network (ResNet). ResNet adalah jenis arsitektur convolutional neural network (CNN) yang menggunakan model pra-terlatih. ResNet menghemat waktu karena tidak perlu melatih data dari awal. Data yang digunakan sebanyak 15.000 citra yang terbagi menjadi kantong sampah, kantong kertas, dan kantong plastik. Setelah pengujian, akurasi 98,65% dicapai dengan membandingkan 80% data pelatihan dan 20% pengujian. Dapat disimpulkan bahwa metode ResNet sangat baik dalam mengidentifikasi media pembuangan sampah.
KLASIFIKASI MONKEYPOX MENGGUNAKAN EKSTRAKSI FITUR LBP Gracivo Elsion Victory; Rusbandi Rusbandi; Siska Devella
MDP Student Conference Vol 2 No 1 (2023): The 2nd MDP Student Conference 2023
Publisher : Universitas Multi Data Palembang

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (810.12 KB) | DOI: 10.35957/mdp-sc.v2i1.4369

Abstract

Monkeypox merupakan penyakit yang secara klinis sangap mirip dengan cacar air dan campak oleh karena itu orang-orang sulit membedakan monkeypox dan non-monkeypox. Metode ekstraksi fitur teksur yang efektif adalah Local Binary Pattern (LBP). Public dataset monkeypox yang digunakan dalam penelitian ini gambarnya berjumlah 3.192 dan berukuran 224x224 pixels. LBP menghasilkan Output feature vector dengan ukuran 1 x 59 sebagai input untuk metode random forest dengan nilai n_estimator yaitu 100, 500 dan 1000. Hasil pengujian citra monkeypox dibagi menjadi 3 tahap pengujian yaitu dengan proporsi dataset 60:40, 70:30, dan 80:20. Pada pengujian dengan proporsi 60:40 mendapatkan hasil terbaik pada dengan n_estimator 100 mendapatkan accuracy 83% . Pengujian dengan proporsi 70:30 mendapatkan accuracy 83% pada setiap n_estimator dan proporsi dataset 80:20 mendapatkan n_estimator terbaik yaitu 500 karna mandapatkan accuracy tertinggi dari ketiga pengujian dengan nilai 85%. Oleh karena itu dapat dilakukan klasifikasi Monkeypox dengan menggunakan fitur ekstraksi LBP dan Random Forest.
Pengenalan Iris Dengan Normalisasi Menggunakan LBP dan RBF Al Rivan, Muhammad Ezar; Devella, Siska; Saputra, Jordi
Jurnal CoreIT: Jurnal Hasil Penelitian Ilmu Komputer dan Teknologi Informasi Vol 6, No 2 (2020): Desember 2020
Publisher : Fakultas Sains dan Teknologi, Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (515.475 KB) | DOI: 10.24014/coreit.v6i2.9685

Abstract

Biometrik merupakan sistem yang menggunakan bagian tubuh manusia untuk dijadikan identitas pribadi seseorang. Iris merupakan salah satu bagian tubuh yang dapat digunakan dalam biometri. Setiap iris memiliki tekstur yang sangat detail dan unik bahkan berbeda antara mata kanan dan kiri. Iris mata juga tidak berubah dan stabil dalam waktu yang lama sehingga dapat digunakan dalam sistem identifikasi. Pada penelitian ini proses yang dilakukan untuk melakukan identifikasi iris mata adalah akuisisi data, preprocessing, ekstraksi ciri dan klasifikasi. Prepocessing yang dilakukan berupa normalisasi iris dengan mengubah bentuk iris. Local Binary Pattern digunakan sebagai ektraksi ciri tekstur iris mata sedangkan untuk mengklasifikasikan ciri dari tekstur iris mata digunakan Jaringan Syaraf Tiruan Radial Basis Function (RBF). Dari hasil pengujian diperoleh hasil akurasi tertinggi sebesar 80% dengan menggunakan spread 225 untuk data training berupa 8 citra iris kiri dan data testing berupa 2 citra iris kiri.
Pemanfaatan Microsoft Office dan Prezi untuk Membuat Laporan dan Presentasi di Brimob Polda Sumatera Selatan Meiriyama, Meiriyama; Yohannes, Yohannes; Irsyad, Hafiz; Farisi, Ahmad; Devella, Siska; Al Rivan, Muhammad Ezar; Rachmat, Nur
FORDICATE Vol 3 No 1 (2023): November 2023
Publisher : Universitas Multi Data Palembang, Fakultas Ilmu Komputer dan Rekayasa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35957/fordicate.v3i1.6449

Abstract

Perkembangan ilmu pengetahuan dan teknologi suatu bangsa tergantung pada keberhasilan proses belajar mengajar di lembaga pendidikan. Penguasaan ilmu dan teknologi merupakan indikator pembangunan menuju kemajuan bangsa. Microsoft Office, termasuk Excel, Word, dan PowerPoint, adalah perangkat lunak aplikasi perkantoran yang dirancang untuk meningkatkan efisiensi kerja. Microsoft Word memfasilitasi pembuatan dokumen kantor, menghemat waktu, dan mengurangi penggunaan kertas. Microsoft Excel mempermudah pengolahan data numerik dengan fitur formula dan diagram. Microsoft PowerPoint mendukung pembuatan presentasi menarik dengan fitur sisipan teks, grafik, dan animasi. Selain itu, Prezi, alat presentasi berbasis internet, memungkinkan eksplorasi ide dengan konsep Zooming User Interface. Pelatihan ini ditujukan untuk staff dan anggota Brimob Polda Sumatera Selatan agar memiliki keterampilan dalam membuat dokumen, laporan, dan presentasi menggunakan Microsoft Office dan Prezi, sehingga dapat meningkatkan produktivitas dan kualitas pekerjaan.
Pengenalan Penggunaan Helm Proyek Berstandar Pada Citra Foto Berdasarkan SIFT Dengan SVM Devella, Siska; Wijaya, Albert Kusuma
JITTER : Jurnal Ilmiah Teknologi dan Komputer Vol 3 No 2 (2022): JITTER, Vol.3, No.2, August 2022
Publisher : Program Studi Teknologi Informasi, Fakultas Teknik, Universitas Udayana

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (412.203 KB) | DOI: 10.24843/JTRTI.2022.v03.i02.p09

Abstract

One of the causes of the high number of work accidents in Indonesia is not using personal protective equipment. The project helmet is a personal protective equipment that serves to protect he head. However, the level of awareness of workers using helmets in this project is still lacking. his study aims to determine the accuracy level of introduction to the use of standard project helmets. Scale Invariant Feature Transform (SIFT) and Support Vector Machine (SVM) are feature extraction and classification methods used in this study. The data used is in the form of 90 photos which are divided equally into 3 types of images. Research shows that there are 170 out of 180 upper bodies that have been successfully detected. The kernels used are linear, gaussian and polynomial. By sing 119 data as training data and 51 data as test data, the highest accuracy results are obtained the linear kernel with an overall accuracy rate of 68.63%.
Klasifikasi Motif Songket Palembang menggunakan Support Vector Machine berdasarkan Histogram of Oriented Gradients Yohannes, Yohannes; Al Rivan, Muhammad Ezar; Devella, Siska; Meiriyama, Meiriyama
Jurnal Teknologi Terpadu Vol 9 No 2 (2023): Desember, 2023
Publisher : LPPM STT Terpadu Nurul Fikri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54914/jtt.v9i2.1032

Abstract

Songket Palembang is one of the intangible cultural heritages with the domain of traditional craftsmanship and crafts. Songket Palembang has several motifs, including Chinese Flowers, Cantik Manis, and Pulir. Preservation efforts are carried out by providing an understanding of Palembang Songket patterns. This study classified Palembang Songket patterns based on shape features using the Histogram of Oriented Gradient (HOG) method. Based on the test results of 45 test data images, the HOG method can become a feature in the image classification of Palembang Songket patterns, namely Chinese Flowers, Cantik Manis, and Pulir. The Support Vector Machine (SVM) method is a classification method that can recognize Palembang Songket patterns with RBF, Linear, and Polynomial kernels. The results showed that the RBF kernel was the best kernel that produced an average accuracy value of 88.1%, a precision of 84.1%, a recall of 82.2%, and an f1-score of 82.6%, and the three Palembang Songket patterns tested, it was found that the Palembang Songket patterns that were easiest to classify well were the Cantik Manis patterns for all types of SVM kernels.
Ekstraksi Fitur Warna dengan Histogram HSV untuk Klasifikasi Motif Songket Palembang Yohannes, Yohannes; Al Rivan, Muhammad Ezar; Devella, Siska; Meiriyama, Meiriyama
JATISI (Jurnal Teknik Informatika dan Sistem Informasi) Vol 11 No 2 (2024): JATISI (Jurnal Teknik Informatika dan Sistem Informasi)
Publisher : Lembaga Penelitian dan Pengabdian pada Masyarakat (LPPM) STMIK Global Informatika MDP

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35957/jatisi.v11i2.8110

Abstract

Palembang Songket is a type of traditional woven cloth that has been registered as Indonesia's intangible cultural heritage since 2013. Palembang Songket has many motifs including Bunga Cina, Cantik Manis, and Pulir. The motifs on Palembang Songket have different meanings which can influence the selling price of the Songket. Recognition and classification of Palembang Songket types and motifs can be done by utilizing computer technology such as digital image processing and machine learning. In this research, the classification of Palembang Songket motifs was carried out using color features with histograms in Hue, Saturation, and Value (HSV) space and the Support Vector Machine (SVM) machine learning algorithm. Testing was carried out on a classification system using 45 test images. The histogram of HSV and SVM methods with the best kernel, namely RBF, were able to classify Palembang Songket motifs with an accuracy of 0.956; precision of 0.94; recall of 0.933; and f1-score of 0.931.
Pengenalan Motif Songket Palembang Menggunakan Convolutional Neural Network dengan Arsitektur ResNet-50 Cahyati, Imelia Dwinora; Devella, Siska; Yohannes, Yohannes
Jurnal Algoritme Vol 5 No 1 (2024): Oktober 2024 || Algoritme Jurnal Mahasiswa Teknik Informatika
Publisher : Program Studi Teknik Informatika Universitas Multi Data Palembang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35957/algoritme.v5i1.9404

Abstract

Songket fabric is a cultural heritage of Indonesia woven with gold or silver threads, creating textiles that are not only visually captivating but also rich in cultural significance. Each motif on Palembang Songket reflects the traditions and beliefs of the community, where the selection of motifs is often tailored to specific event contexts. However, the recognition of several motifs with similar patterns presents unique challenges in the identification process. This study aims to implement a Convolutional Neural Network (CNN) method for classifying Palembang Songket motifs. The dataset used consists of images of Songket motifs, including Bintang Berantai, Naga Besaung, Nampan Perak, and Pulir. The ResNet-50 architecture is utilized as the classification model. The results indicate that the implemented model achieves an accuracy of 96% in recognizing these motifs, thereby contributing to the preservation and enhancement of understanding regarding the cultural richness of Palembang Songket.
Pelatihan Moodle Sebagai Aplikasi Learning Management System untuk Administrator Sekolah di SMA Negeri 18 Palembang Rachmat, Nur; Devella, Siska; Meiriyama, Meiriyama
FORDICATE Vol 4 No 1 (2024): November 2024
Publisher : Universitas Multi Data Palembang, Fakultas Ilmu Komputer dan Rekayasa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35957/fordicate.v4i1.9597

Abstract

The Covid-19 pandemic requires every school to take innovative steps by utilizing technology in teaching and learning activities. Among various technological advancements in the world of education, Learning Management System (LMS) has emerged as a platform and Moodle is one of the most well-known and widely used LMS by educational institutions. Moodle has comprehensive features and is easy to understand for users. Through the Moodle LMS, educators can easily present comprehensive learning materials, create assessments, establish grading systems, track learning progress, view reports, and analyze learning outcomes. This technology is certainly desired to be adopted by State High School 18 Palembang to support a more effective learning process when conducted online. The schools action to support the smooth use of this LMS is to organize a training for school administrators. The training activities were attended by 5 staff members through direct practice methods, discussions and interactive question-and-answer sessions in the Computer Laboratory of Multi Data Palembang University.
Pengenalan Iris Menggunakan K – Nearest Neighbors dengan Ekstraksi Fitur Dicrete Cosine Transform Siska Devella
JTKSI (Jurnal Teknologi Komputer dan Sistem Informasi) Vol 2, No 1 (2019): JTKSI
Publisher : Institut Bakti Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56327/jtksi.v2i1.698

Abstract

Iris is a biometric based on physiological characteristics which are regarded as highly reliable in biometric recognition systems. The iris pattern between one person and another is very different, identical twins have different iris patterns, so the recognition system using iris has a very good level of security. In this research proposed iris recognition system using K-Nearest Neighbors as classifier and Discrete Cosine Transforms as feature extraction algorithm. The noisy regions should be distinguished before feature extraction in a pre-processing stage called segmentation (Localization and noise-removing) and normalization.  The normalization is a transform from Cartesian to polar coordinates. The iris image data used as a training image and test image are public datasets with a total data of 420 iris images. The experiment results show the level of recognition accuracy is 70%.
Co-Authors Ade Hendri Pandrean Cahyati, Imelia Dwinora Celvine Adi Putra Derry Alamsyah Farisi, Ahmad Firda Novia Rahmawati Gracivo Elsion Victory Hadisaputra, William Hafiz Irsyad Julian Rusli Tee Baldi Juliana Nasution Kelvin Arianto M Ezar Al Rivan Marcella, Dewi Meiriyama, Meiriyama Meiriyama, Meiriyama Ningrum Larasati Novan Wijaya Nur Rachmat Nur Rachmat Oktavius, Kevin Pandrean, Ade Hendri Prabowo, Adrianus Prasthio, Rial RR. Ella Evrita Hestiandari Rusbandi Rusbandi Sanders, Carmel Edra Sandra Mareza Adelfi Saputra, Jordi Valentino Ruben Ho Wijaya, Albert Kusuma William Hadisaputra Wiwik Handayani Yohannes Yohannes