Claim Missing Document
Check
Articles

Found 40 Documents
Search

Analisis Fungsi Aktivasi pada Algoritma Backpropagation dalam Pengenalan Aksara Batak Toba Esrayanti Simanjuntak; Nurul Khairina; Zulfikar Sembirirng; Rizki Muliono; Muhathir Muhathir
JUSTINDO (Jurnal Sistem dan Teknologi Informasi Indonesia) Vol. 8 No. 2 (2023): JUSTINDO
Publisher : Universitas Muhammadiyah Jember

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32528/justindo.v8i2.331

Abstract

Indonesia merupakan salah satu Negara Asia yang memiliki suku dan budaya yang beragam. Suku Batak merupakan suku yang ada di daerah Sumatera Utara. Suku ini terbagi menjadi beberapa jenis berdasarkan wilayahnya. Suku Batak Toba memiliki bahasa daerah yang sangat unik dan sistem tulisan yang berbeda. Aksara Batak Toba sering digunakan dalam upacara keagamaan dan peristiwa penting. Dalam penelitian ini, peneliti akan melakukan studi tentang aksara Batak Toba. Peneliti akan menganalisis Algoritma Backpropagation dalam pengenalan aksara Batak Toba dengan variasi fungsi aktivasi. Data input berupa file citra yang akan melalui tahap preprocessing, diikuti dengan ekstraksi fitur, normalisasi, pelatihan, dan pengujian pola aksara Batak Toba. Pada proses pelatihan dan pengujian pola, peneliti akan menggunakan data latih yang terdiri dari beberapa jenis aksara dan melakukan beberapa kali pengujian dengan jumlah epoch yang bervariasi, yaitu 150, 300, 450, 600, 750, 900, 1050, dan 1200 epoch. Dari hasil pengujian yang dilakukan, diperoleh hasil akurasi tertinggi pada dua jenis fungsi aktivasi, khususnya pada epoch ke-1050. Akurasi pada fungsi aktivasi Sigmoid Bipolar mencapai 80,53% dan pada fungsi aktivasi Sigmoid Biner mencapai 78,95%.
Copyright Protection of Scientific Works using Digital Watermarking by Embedding DOI QR Code Harahap, Muhammad Khoiruddin; Khairina, Nurul
Journal of Computer Networks, Architecture and High Performance Computing Vol. 3 No. 2 (2021): Journal of Computer Networks, Architecture and High Performance Computing, July
Publisher : Information Technology and Science (ITScience)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/cnahpc.v3i2.1064

Abstract

Digital identifier is a technology used to prove ownership of a work. At this time, the Digital Object Identifier is a form of implementation of the digital identifier used in every scientific work. Not infrequently there are several cases of theft of ownership or copyright of a work, both scientific works, and certain other works. Watermarking is a technique created to protect the ownership of works. Watermarking techniques can be applied to several media such as audio, video, and also documents, one of which is the Portable Document Format document file. In this study, researchers want to build copyright protection for scientific works. Researchers offer research concepts using a Digital Object Identifier which is always installed on scientific papers to be published. The Digital Object Identifier will later become the basic data in building the Quick Response Code. The Digital Object Identifier of each scientific work will not be the same as each other, this will certainly make the Quick Response Code more unique. The results show that the watermarking process in building copyright protection of scientific works can be very successful Quick Response Code can be read and detected properly without experiencing lag time. Quick Response Code readings from several variations of motion are also not very influential, so it can be concluded that distance does not limit the detection of Quick Response Codes. From this research, researchers can deduce that the watermark is performed on the scientific work not only serves as the copyright protection of that scientific paper but can also be an alternative for other researchers to access the scientific work.
The Integration of HSV and GLCM Features with LDA for Classification of Breadfruit Maturity Levels Hamdan Pratama; Nurul Khairina; Nanda Novita; Muhammad Huda Firdaus; Yolanda Y.P. Rumapea
Journal of Information Systems and Technology Research Vol. 5 No. 1 (2026): January 2026
Publisher : Ali Institute or Research and Publication

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55537/jistr.v5i1.1377

Abstract

Breadfruit is a perennial plant that has historically been distributed throughout Southeast Asia as a food source. Breadfruit that has entered the harvest period or has fallen on its own has several levels of maturity, namely raw, unripe, ripe, and rotten. Breadfruit that has been separated from the tree will have the same characteristics, namely green and slightly yellowish or brownish in colour. The research problem centres on the trouble buyers and sellers have when determining the maturity level of breadfruit. Based on this problem, the purpose of this study is to classify the maturity level of breadfruit using the LDA method. With image classification, it is hoped that the maturity level of breadfruit can be identified more accurately. The research gap in this study lies in the limited number of feature extraction methods used simultaneously, as well as the infrequent use of LDA methods for classification. In this study, Linear Discriminant Analysis is applied together with GLCM and HSV-based feature extraction. The LDA is a statistical method used for classification. LDA focuses on finding lines that separate two or more classes in a dataset by maximizing the distance between class averages and minimizing variance within classes. GLCM feature extraction is an image-processing technique used to evaluate texture. The contribution of this research lies in its improved classification performance and greater accuracy compared to previous studies. It offers a statistical description of how pairs of gray levels are distributed within an image, helping to reveal texture patterns and characteristics. The results of this study show that the classification of maturity levels in breadfruit images is good. This is measured by an accuracy of 89.9333%, precision of 90.1732%, recall of 89.3333%, and an F1-score of 89.7513%.
Penerapan Mobilenetv3 untuk Klasifikasi Jenis Bahan Pakaian Doni Poulus Sinaga; Nurul Khairina
INCODING: Journal of Informatics and Computer Science Engineering Vol 5, No 2 (2025): INCODING OKTOBER
Publisher : Mahesa Research Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34007/incoding.v5i2.829

Abstract

This study aims to develop an efficient and accurate model for classifying clothing material types using the MobileNetV3 architecture. Clothing material images were collected from open sources and processed through resizing, normalization, and data augmentation. The model was trained using transfer learning and evaluated using accuracy, precision, recall, and F1-score metrics. The evaluation results showed an accuracy of 92%, with the best performance in the silk and polyester categories. However, misclassifications still occurred for materials with similar textures, such as linen and cotton. Compared to previous studies, this approach offers advantages in computational efficiency for mobile and edge computing applications. This research contributes to the development of an automated clothing material classification system to support the textile and fashion industries. Further improvements are needed by enhancing dataset quality and fine-tuning the model to better distinguish materials with visually similar characteristics.
KLASIFIKASI KESEHATAN JANIN PADA IBU HAMIL MENGGUNAKAN METODE SUPPORT VECTOR MACHINE M. Farhan Darkani; Nurul Khairina
INCODING: Journal of Informatics and Computer Science Engineering Vol 5, No 2 (2025): INCODING OKTOBER
Publisher : Mahesa Research Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34007/incoding.v5i2.830

Abstract

Monitoring fetal health is a crucial aspect of pregnancy, requiring accurate and efficient methods for early detection of potential complications. This study aims to develop a fetal health classification system using the Support Vector Machine (SVM) algorithm. The data analyzed includes various fetal physiological parameters obtained through routine examinations, such as heart rate, fetal movements, and other relevant indicators. SVM was chosen due to its capability to handle non-linear data and its high classification accuracy. The classification process involves data preprocessing, feature selection, model training, and performance evaluation using metrics such as accuracy, precision, recall, and F1-score. The results indicate that SVM can effectively classify fetal health conditions with high accuracy, making it a promising diagnostic support tool for medical professionals. This study contributes to maternal and fetal healthcare by offering a machine learning-based approach that enhances the effectiveness of fetal health monitoring systems.  
Analysis of Public Sentiment about Sea Games eSport on Twitter using the Adaboost Algorithm Muhammad Syifa; Nurul Khairina; Dian Noviandri; Yuan Anisa; Nanda Novita
Jurnal Teknoinfo Vol. 20 No. 2 (2026): Period July 2026
Publisher : Universitas Teknokrat Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33365/teknoinfo.v20i2.1706

Abstract

This research aims to analyze public sentiment towards the Sea Games eSports as reflected in conversations on the Twitter platform. The two main issues in focus are how the public sentiment towards the Sea Games eSports event and whether their responses tend to be positive or negative towards the event. The research method used is the Adaboost Algorithm, a technique in data mining that aims to improve classification accuracy. Adaboost was used to analyze sentiment from Twitter conversation data by using feature selection to select weak classification functions, then combining them into a new classification function. The results showed that the highest evaluation was achieved in the 2nd test with the use of training data by 90% and testing by 10%, which resulted in an accuracy of 98%. Sentiment analysis of the Sea Games eSports showed that the majority of Twitter users expressed 111 (95.7%) positive sentiments, while only 5 (4.3%) negative sentiments. This indicates that people tend to give positive responses to the Sea Games eSports event. This research illustrates that sentiment analysis using the Adaboost Algorithm is able to provide accurate results in mapping public responses to the Sea Games eSports event on Twitter. The implication is that the strong support from the community towards this event can be an important basis for further development and promotion of Sea Games eSports.
Pelatihan Peningkatan Kemampuan Penterjemahan Artikel Ilmiah dengan Grammarly, Google Translate dan Paraphrasing Nurul Khairina; Wahyuddin Albra
Jurnal Solusi Masyarakat Dikara Vol 1, No 1 (2021): Desember 2021
Publisher : Yayasan Lembaga Riset dan Inovasi Dikara

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

Abstract

Konsep webinar mulai marak diminati sejak masa pandemic Covid-19, namun sampai tahun ini pun para akademisi masing sering melakukan webinar dengan berbagai tema acara. Pelatihan dengan konsep webinar tidak mengurangi tingkat pemahaman peserta webinar, bahkan dengan adanya webinar, narasumber dan peserta yang berbeda kota dan berbeda negara pun dapat lebih leluasa berbagi ilmu. Kegiatan secara daring bukan hanya dilakukan untuk webinar saja, namun juga dapat digunakan untuk aktifitas akademi dosen seperti mengajar, penelitian, pengabdian dan juga penunjang. Salah satu kegiatan pengabdian dalam bentuk webinar juga sering dilakukan oleh para akademisi. Pelatihan yang dilakukan oleh penulis berikut ini merupakan pelatihan yang dilakukan melalui webinar yang dilaksanakan oleh ITScience, dimana penulis merupakan salah satu narasumber pada webinar tersebut. Pelatihan yang dibawakan oleh penulis merupakan pelatihan peningkatan kemampuan menterjemahkan artikel ilmiah dengan tools Grammarly, Google Translate dan Paraphrasing. Dalam menterjemahkan kalimat, peserta diarahkan untuk menterjemahkan lebih dari satu kali tahapan, sebainya peserta menterjemahkan sebanyak tiga kali tahapan. Dalam menggunakan Google Translate, peserta juga diajarkan menterjemahkan kalimat dengan fitur Google Transalate yang diiringi dengan tools Grammarly untuk memperbaiki tenses, kata benda, kata sifat dan kata keterangan. Tahapan terjemahan yang terakhir adalah memperbaiki kesesuaian parafrase yang dapat dilakukan dengan menggunakan tools Paraphrasing. Kegiatan pengabdian yang dilakukan melalui webinar ini berjalan dengan baik dan antusias peserta dapat dilihat dari kehadiran peserta yang mencapai ± 90 orang.
Sistem Informasi Manajemen Data Surat Dengan Algoritma Blowfish Essay Puspita Sitopu; Nurul Khairina; Rizki Muliono; Muhathir Muhathir
Sisfo: Jurnal Ilmiah Sistem Informasi Vol. 6 No. 1 (2022): Sisfo: Jurnal Ilmiah Sistem Informasi, Mei 2022
Publisher : Universitas Malikussaleh

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29103/sisfo.v6i1.7964

Abstract

Perkembangan teknologi informasi yang semakin pesat saat ini menuntut kita untuk mampu mengikuti perkembangannya. Komunikasi secara digital di era modern dapat menjadi salah satu ancaman akan adanya penyadapan, penyalahgunaan informasi, dan pencurian data penting yang tidak diinginkan oleh pihak yang tidak berwenang. Apalagi jika informasi tersebut bersifat rahasia dan memliki ruang lingkup yang luas dalam kenegaraan. Oleh karena itu, keamanan penyimpanan data menjadi sangat penting. Data yang terdapat pada surat masuk ataupun surat keluar dalam satu sekolah juga memliki kerahasiaan yang harus dijaga, kemana surat dikirimkan dan dari mana surat berasal juga menjadi salah satu hal yang perlu dijaga kerahasiannya. Atas dasar inilah peneliti ingin membangun sistem informasi manajemen surat yang berfokus pada penyimpanan data surat atau database surat. Dari berbagai metode penyandian yang ada hingga saat ini, salah satunya adalah metode Kriptografi Blowfish yang menggunakan blok cipher 64-bit dengan panjang kunci variabel. Proses enkripsi pada penelitian ini merupakan proses memberikan kunci rahasia pada surat tersebut agar surat tersebut berubah menjadi tulisan sandi yang tidak dapat dipahami oleh pihak yang tidak berwenang. Proses deskripsi merupakan proses menterjemahkan kembali surat yang telah terahasia agar pihak sekolah dapat membaca surat yang dimaksud. Dari hasil pengujian sistem informasi, sistem informasi manajemen surat dapat menerapkan Algoritma Blowfish dengan baik, hal ini ditandai dengan adanya perubahan nomor surat, tanggal pengiriman surat serta tujuan pengiriman surat pada saat proses enkripsi maupun pada saat proses dekripsi.
Integrasi Literasi Keuangan dan Digital Marketing untuk Pemberdayaan UMKM Kuliner Minasari Nasution; Abdul Gani; Andry Roy PS; Zahri Fadli; Mahyudin Mahyudin; Nurul Khairina
Jurnal IPTEK Bagi Masyarakat Vol 5 No 3 (2026)
Publisher : Ali Institute of Research and Publication

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55537/j-ibm.v5i3.1505

Abstract

This community service program aims to improve the competitiveness of culinary MSMEs in Siboruon Village through financial literacy and digital marketing education. This activity was attended by 35 participants and was carried out using participatory training and practical mentoring methods. Evaluation was conducted through pre-test and post-test questionnaires that were analyzed statistically. The results showed a significant increase in financial literacy scores, from an average of 2.48 to 4.21 (p < 0.001), as well as digital marketing competencies, from an average of 2.10 to 4.03 (p < 0.001). A total of 71.4% of participants successfully created or optimized business social media accounts. The novelty of this program lies in the integration of simple bookkeeping and platform-based digital marketing tailored to the characteristics of rural MSMEs. This program has proven to be effective in strengthening managerial capacity and increasing the competitiveness of MSMEs.
Sistem Informasi Rekapitulasi Data Penjualan Pada Toko Obat Sinar Raya Berbasis Web Nurul Khairina; Josua Prayuda Pakpahan
JPPkM: Jurnal Pengabdian dan Pemberdayaan kepada Masyarakat Vol. 2 No. 2 (2026): JPPkM:Juli
Publisher : Yayasan Pemimpin Inovasi Science

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

Abstract

Sinar Raya Drugstore is a pharmaceutical business that still manages sales transactions and drug inventory records manually. This process creates several challenges in data management, including recording inaccuracies, slower report preparation, and limitations in monitoring drug stock effectively. As transaction activities continue to increase, manual data processing becomes less efficient and may affect the accuracy of operational information. To address these issues, this community service program developed a web-based application to support sales and inventory data management through a more organized digital process. The program focuses on developing a Web-Based Sales Data Recapitulation Information System for Sinar Raya Drugstore. The application was implemented using PHP as the programming language and MySQL as the database management system. The development process applied the waterfall method, which consists of requirement analysis, system modeling, application development, evaluation, and maintenance. The implementation results indicate that the developed system is capable of automating transaction recording, generating periodic sales reports, and providing real-time inventory information. In addition, the application helps improve operational efficiency, minimize recording errors, and simplify the process of managing sales data at Sinar Raya Drugstore.