Article Per Year (5 Year)
p-Index From 2021 - 2026
3.082
P-Index
This Author published in this journals
All Journal TEKNIK INFORMATIKA ARABIYAT Jurnal Edukasi dan Penelitian Informatika (JEPIN) JOIV : International Journal on Informatics Visualization Jurnal Ilmiah FIFO Jurnal Pilar Nusa Mandiri International Journal of Technology And Business Jurnal Pengabdian Masyarakat AbdiMas MATRIK : Jurnal Manajemen, Teknik Informatika, dan Rekayasa Komputer MULTINETICS JISKa (Jurnal Informatika Sunan Kalijaga) Cyber Security dan Forensik Digital (CSFD) Jurnal E-Komtek Journal of Applied Data Sciences Science, Technology, and Communication Journal
Siti Ummi Masruroh
Universitas Islam Negeri Syarif Hidayatullah Jakarta
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Education Electrical & Electronics Engineering Engineering Languange, Linguistic, Communication & Media Library & Information Science Materials Science & Nanotechnology Social Sciences

Published : 25 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 25 Documents
Search

 1   2   3 
Deep Convolutional Neural Networks Transfer Learning Comparison on Arabic Handwriting Recognition System Masruroh, Siti Ummi; Syahid, Muhammad Fikri; Munthaha, Firman; Muharram, Asep Taufik; Putri, Rizka Amalia
JOIV : International Journal on Informatics Visualization Vol 7, No 2 (2023)
Publisher : Society of Visual Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30630/joiv.7.2.1605

Abstract

Around 27 languages and more than 420 million people worldwide use Arabic letters. That makes the Arabic language one of the most used languages. However, the Arabic language has a challenge, namely the difference in letters based on their position. Arabic handwriting recognition is important for various applications, such as education and communication. One example is during a pandemic when most education has turned digital, making recognizing students' Arabic handwriting difficult. This paper aims to create a model that can recognize Arabic handwriting by comparing several CNN architectures using transfer learning to classify Arabic, Hijja, and AHCD handwriting datasets. Transfer learning is a model that has been trained by previous datasets to other datasets and is suitable for use in models with small datasets because it can improve model accuracy even with small datasets. The datasets were split into 60%, 20%, and 20% for training, validation, and testing. Each model uses data augmentation and 50% dropout on a fully connected layer to reduce overfitting. Some of the CNN architectures used in this study to create Arabic writing recognition models are ResNet, DenseNet, VGG16, VGG19, InceptionV3, and MobileNet. The models were compiled and trained with various parameters. The best model achieved to classify AHCD and Hijja dataset is VGG16 with Adam optimizer and 0.0001 learning rate. Based on this research, it is expected to know the performance of the best model for classifying Arabic handwriting.
WORKSHOP SERIAL PENULISAN KARYA ILMIAH DAN MANAJEMEN PUBLIKASI SEBAGAI UPAYA PROFESIONALISME PPPK DAN CPNS Muzaki, Muhamad Azka; Purnomo, Raihan Ade; Fatir, Luthfi Ikmal; Rohmatunisa, Nasya; Putri, Amanda; Rohman, Mazda Muhammad Fadlur; Masruroh, Siti Ummi
Jurnal Pengabdian Masyarakat AbdiMas Vol 12, No 2 (2025): Jurnal Pengabdian Masyarakat Abdimas
Publisher : Universitas Esa Unggul

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47007/abd.v12i2.10402

Abstract

AbstractDeveloping the professionalism of lecturers and academic staff, particularly Government Employees with Work Agreements (PPPK) and Civil Servant Candidates (CPNS), is crucial for university performance. Scientific publication serves as a key competence indicator, yet technical and substantive obstacles often hinder productivity. This article discusses the implementation of the "KKN In Campus" program through a workshop series organized by Puslitpen UIN Syarif Hidayatullah Jakarta. The methodology involved five intensive stages: research proposal strategy, proofreading, digital reference management, academic ethics, and journal indexation. The results indicate a significant improvement in participants' understanding of research roadmaps, proficiency in Mendeley and Zotero tools, and strategies for penetrating SINTA and Scopus-indexed journals. This program contributes strategically to building a productive and ethical academic culture.. Kata kunci : Scientific publication, reference management, journal indexation. AbstrakPengembangan profesionalisme dosen dan tenaga kependidikan, khususnya PPPK dan CPNS, merupakan elemen krusial bagi kinerja perguruan tinggi. Publikasi ilmiah menjadi indikator kompetensi utama, namun kendala teknis dan substantif sering menghambat produktivitas. Artikel ini membahas pelaksanaan program KKN In Campus melalui rangkaian workshop serial oleh Puslitpen UIN Syarif Hidayatullah Jakarta. Metode pelaksanaan mencakup lima tahap intensif: strategi proposal, proofreading, manajemen referensi digital, etika akademik, dan indeksasi jurnal. Hasil kegiatan menunjukkan peningkatan signifikan pada pemahaman peserta mengenai peta jalan riset, penguasaan tools Mendeley dan Zotero, serta strategi menembus jurnal terindeks SINTA dan Scopus. Program ini berkontribusi strategis dalam membangun budaya akademik yang produktif dan berintegritas. Kata kunci : Publikasi ilmiah, manajemen referensi, indeksasi jurnal.
User Interface and Exprience Gamification-Based E-Learning with Design Science Research Methodology Viva Arifin; Velia Handayani; Luh Kesuma Wardhani; Hendra Bayu Suseno; Siti Ummi Masruroh
MATRIK : Jurnal Manajemen, Teknik Informatika dan Rekayasa Komputer Vol. 22 No. 1 (2022)
Publisher : Universitas Bumigora

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30812/matrik.v22i1.2427

Abstract

In 2020, the Islamic Elementary Teacher Working Group (KKG MI) held an E-Learning Training for Islamic Elementary School Teachers in DKI Jakarta about one of the gamification applications, Quizizz. According to observation, many teachers are still perplexed when utilizing the Quizizz program. This is due to the application’s design and different functionalities, which still appear complicated to some teachers who aren’t used to using it. The existing gamification application is also considered not to meet the learning needs at Islamic elementary schools in Jakarta. This study intends to analyze and design User Interface (UI) and User Experience (UX) designs for gamification-based e-learning applications as solutions to the problems found. Data collection begins with an observation and also a literature study, questionnaires, and interviews. For the design, Design Science Research Methodology (DSRM) is used, which consists of six stages: Problem Identification & Motivation, Define the Objective for a Solution, Design & Development, Demonstration, Evaluation and Communication. The results of the evaluation of the gamification-based e-learning design designed with the User Experience Questionnaire (UEQ) and Task Success show that the e-learning design is considered attractive and users can interact with e-learning effectively and easily.
Convolutional Neural Network for Colorization of Black and White Photos Siti Ummi Masruroh; Andrew Fiade; Muhammad Ikhsan Tanggok; Rizka Amalia Putri; Luigi Ajeng Pratiwi
MATRIK : Jurnal Manajemen, Teknik Informatika dan Rekayasa Komputer Vol. 22 No. 2 (2023)
Publisher : Universitas Bumigora

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30812/matrik.v22i2.2652

Abstract

People today are very fond of capturing moments by taking pictures. Various photo functions are used to document all forms of information that you want to store. In photos with digital images that have black and white, the information obtained is less than optimal, so an image processing process is needed to get color photos. Based on this, the author wants to change photos from black and white to color photos. The method used in this research is Convolutional Neural Network (CNN). This study uses Atlas 200 DK hardware and Ascend 310 processor. The data used in this study are 32 black and white photos in .jpg format as training data and perform 6 experimental scenarios with different numbers of black and white photos in each experiment. The total black and white photos used to experiment were 81 photos. The results obtained are models that successfully perform processing in the form of color photos with the appropriate color results in predicting the possible color of the object in each pixel in the photo. Based on this research, the trend of artificial intelligence can be implemented in changing the color of photos according to color predictions.
Accuracy of K-Nearest Neighbors Algorithm Classification For Archiving Research Publications Muhamad Nur Gunawan; Titi Farhanah; Siti Ummi Masruroh; Ahmad Mukhlis Jundulloh; Nafdik Zaydan Raushanfikar; Rona Nisa Sofia Amriza
MATRIK : Jurnal Manajemen, Teknik Informatika dan Rekayasa Komputer Vol. 23 No. 3 (2024)
Publisher : Universitas Bumigora

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30812/matrik.v23i3.3915

Abstract

The Archives and Research Publication Information System plays an important role in managing academic research and scientific publications efficiently. With the increasing volume of research and publications carried out each year by university researchers, the Research Archives and Publications Information System is essential for organizing and processing these materials. However, managing large amounts of data poses challenges, including the need to accurately classify a researcher's field of study. To overcome these challenges, this research focuses on implementing the K-Nearest Neighbors classification algorithm in the Archives and Research Publications Information System application. This research aims to improve the accuracy of classification systems and facilitate better decision-making in the management of academic research. This research method is systematic involving data acquisition, pre-processing, algorithm implementation, and evaluation. The results of this research show that integrating Chi-Square feature selection significantly improves K-Nearest Neighbors performance, achieving 86% precision, 84.3% recall, 89.2% F1 Score, and 93.3% accuracy. This research contributes to increasing the efficiency of the Archives and Research Publication Information System in managing research and academic publications.
Co-Authors Aditya Mirza Bahari Ahmad Akmaluddin Ahmad Arya Swaraja Ahmad Mukhlis Jundulloh Amrullah, Faiq Fawwaz Amyn, Ilham Maulana Andrew Fiade Arini Arini Arini Arini Arini Arini Ariq Cahya Wardhana Armenia, Ivan Gustra Manca Asep Taufik Muharram Azhar Azhar Fatir, Luthfi Ikmal Fitri Mintarsih Galang Ardian Sugianto Hapsari Tiaraningtias Hendra Bayu Suseno Hendra Bayu Susueno Herlino Nanang Husni Teja Sukmana Ilham Maulana Amyn Imam Tri Wibowo Iska, Zikri Neni I’im Umamil Khoiri Kamarusdiana Kamarusdiana Karimi, Husain Faiz Kaula Fahmi Khairani, Dewi Luh Kesuma Wardhani Luhur Bayuaji, Luhur Luigi Ajeng Pratiwi Miftakhul Nuuril Azizah Muhamad Nur Gunawan Muhammad Ammaridho Romdhan Siregar Muhammad Ikhsan Tanggok Muhammad Yusuf Nurpariz Munthaha, Firman Muzaki, Muhamad Azka Nadia Azza Nafdik Zaydan Raushanfikar Nanda Alivia Rizqy Vitalaya Nenny Anggraini Nenny Anggraini Nenny Anggraini, Nenny Nurbojatmiko Nurbojatmiko, Nurbojatmiko Nurhayati NURUL FAIZAH Okfalisa Okfalisa Purnomo, Raihan Ade putri, amanda Putri, Rizka Amalia Rahman, Abdul Wahab Abdul Rizka Amalia Putri Rizka Amalia Putri Rohman, Mazda Muhammad Fadlur Rohmatunisa, Nasya Rona Nisa Sofia Amriza Shofi, Imam Marzuki Siti Hanna Syahid, Muhammad Fikri Titi Farhanah Velia Handayani Victor Amrizal Viva Arifin Viva Arifin Wisnu Ari Mukti Zainal Arifin Hasibuan