Claim Missing Document
Check
Articles

Found 30 Documents
Search

Penerapan User-Based Collaborative Filtering Algorithm Arfiani Nur Khusna; Krisvan Patra Delasano; Dimas Chaerul Ekty Saputra
MATRIK : Jurnal Manajemen, Teknik Informatika dan Rekayasa Komputer Vol 20 No 2 (2021)
Publisher : LPPM Universitas Bumigora

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (535.972 KB) | DOI: 10.30812/matrik.v20i2.1124

Abstract

Sistem online memanfaatkan website sebagai media pemasaran. Namun dengan perkembangan teknologi, pemasaran dilakukan dengan online terdapat kendala yaitu banyaknya produk yang tersedia dalam pemilihan produk. Sistem rekomendasi adalah sistem yang menyarankan informasi berguna atau menduga yang akan dilakukan user untuk mencapai tujuannya, seperti mencari teknik yang terbaik dalam memberikan rekomendasi bagi user. Menurut hasil survey yang telah dilakukan terhadap 17 orang pemakai website pemasaran produk Gadget Shield didapatkan 88,20% mengharapkan adanya penilaian user terhadap produk. Penelitian ini akan melakukan pengembangan sistem rekomendasi produk Gadget Shield pada toko Jackskins menggunakan metode User-Based Collaborative Filtering serta menggunakan Euclidean Distance untuk mengukur jarak kemiripan antar User dan Weighted Sum digunakan untuk mencari rekomendasi produk. Diharapkan dengan adanya sistem dapat memudahkan User dalam pencarian produk Gadget Shield terbaik. Guna menghasilkan produk rekomendasi,hasil nilai kemiripaan dilakukan perhitungan dengan algoritma Weighted Sum. Sistem rekomendasi Collaborative Filtering telah diuji menggunakan metode pengujian akurasi Root Mean Square Error (RMSE) dan pengujian User Acceptance Test (UAT). Hasil uji RMSE menunjukkan nilai 0,496 atau akurasinya 90,08%. Hasil pengujian UAT didapatkan 86,86% diterima. Informasi dari proses tersebutlah yang nantinya diharapkan akan bermanfaat sebagai dasar sumber rekomendasi yang akurat.
PERANCANGAN APLIKASI QUESTION ANSWERING SYSTEM PADA TERJEMAHAN ALQURAN Arfiani Nur Khusna; Murein Miksa Mardhia
Journal of Information System Management (JOISM) Vol. 1 No. 1 (2019): Juli
Publisher : Universitas Amikom Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (340.496 KB) | DOI: 10.24076/joism.2019v1i1.19

Abstract

Al quran merupakan tuntunan bagi umat Islam. Suatu permasalahan tidak hanya mengacu pada satu ayat ataupun satu surat sehingga dibutuhkan waktu yang lama dalam proses pencarian secara manual, mengingat banyaknya jumlah ayat dan surat yang terkandung dalam Al quran. Berdasarkan hasil kuisioner yang dibagikan kepada 50 responden, terdapat 75% responden tidak dapat atau kesulitan dalam mencari jawaban terhadap makna atau masalah yang didasarkan pada terjemahan Al quran. Question answering system adalah sistem yang mengijinkan user menyatakan kebutuhan informasinya dalam bentuk natural language question (pertanyaan dalam bahasa alami), dan mengembalikan kutipan teks singkat atau bahkan frase sebagai jawaban. Penelitian ini merancang aplikasi question answering system pada terjemahan al quran untuk membantu pengguna menemukan jawaban terjemahan Al quran dengan menggunakan pertanyaan yaitu dimana, apa, siapa, berapa, kapan dan mengapa. Berdasarkan hasil pengujian rancangan aplikasi diperoleh nilai usability 28 dari 35 yang menunjukkan bahwa rancangan aplikasi layak dikembangkan sebagai alat bantu dalam mencari jawaban terjemahan Al quran dan sesuai kebutuhan pengguna.
Health Counseling to Enhance Maternal Knowledge about Nutrition in Toddlers Liena - Sofiana; Arfiani Nur Khusna
International Journal of Healthcare Research Vol. 1 No. 2 (2018)
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (151.914 KB)

Abstract

Background: The level of maternal knowledge about high nutrition can affect the diet of baby and will certainly affect nutritional status of toddlers. The knowledge can be generated from several ways, one of them is counseling. Counseling is one method can be used easily to provide the knowledge about the nutrition of toddlers to mothers.Objective: The purpose of this study is to determine the effect of health counseling about nutrition of toddlers on mothers in the posyandu Kauman Yogyakarta.Methodology: This study used quasy experimental with pretest and posttest. The populations in this study include all mothers of children who came to the posyandu Kauman Yogyakarta with the sampling technique with total sample are 26 respondents. The processing data used the Wilcoxon test because the data is not normally distributed.Results: The results shows that there is an effect of health counseling in increasing maternal knowledge about nutrition of baby in Kauman Yogyakarta posyandu (p = 0.000).Conclusion: there is an effect of health counseling in increasing maternal knowledge about nutrition of children in posyandu Kauman Yogyakarta.
Implementation of Named Entity Recognition with a Developing Question Answering System: A Case Study in the Merapi Volcano Museum Khusna, Arfiani Nur; Putri, Okhy Kharisma; Saputra, Dimas Chaerul Ekty
Journal of Intelligent Computing & Health Informatics Vol 3, No 1 (2022): March
Publisher : Universitas Muhammadiyah Semarang Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26714/jichi.v3i1.9205

Abstract

Merapi volcano museum is a place to get some information about active mountain activities, the general public can access the website page at mgm.slemankab.go.id. Indeed, visitors are given easy access, but the information provided by the website is not fully complete, causing visitors to feel dissatisfied. Based on the results of a questionnaire from 40 respondents, it was found that 50.55% of website visitors did not get the information they wanted. Therefore, in this research, we built a Question Answering System (QAS) using the Named Entity Recognition (NER) method that has been implemented into Telegram. To improve the performance of the QAS system, testing and analysis has been carried out with a "white box" approach. The results show that the QAS system has 3 regions and 3 independent paths, with path 1 being 1-2-3-4-11, path 2 being 1-2-3-4-5-6-7-8-11, and path 3 being 1-2-3-4-5-6-7-9-10-11. Based on the results of this study, all three paths can produce the correct answer.
Data Augmentation Using Test-Time Augmentation on Convolutional Neural Network-Based Brand Logo Trademark Detection Suyahman, Suyahman; Sunardi, Sunardi; Murinto, Murinto; Khusna, Arfiani Nur
Indonesian Journal of Artificial Intelligence and Data Mining Vol 7, No 2 (2024): September 2024
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/ijaidm.v7i2.28804

Abstract

The detection and acknowledgment of logos holds significant importance in the corporate sphere, facilitating the detection of unauthorized logo usage and ensuring trademark uniqueness within specific industry sectors. Presently, convolutional neural networks powered by deep learning are widely utilized for image recognition. However, their effectiveness is dependent on a substantial volume of training images which may not always be readily available. This study suggests employing Test Time Augmentation to address dataset constraints by expanding the original dataset, thereby enhancing classification accuracy and preventing overfitting. Test-Time Augmentation is a method used to improve the accuracy of convolutional neural networks by creating numerous augmented variations of the test images and then merging their predictions. The research findings indicate that the application of TTA has the highest performance on the VGG16 model with 98% precision, 99% recall, and 98% F1-score, and 98.87% accuracy
Effect of Learning Rate on VGG19 Model Architecture for Human Skin Disease Classification Habie, Khairul Fathan; Murinto, Murinto; Sunardi, Sunardi; Khusna, Arfiani Nur
Decode: Jurnal Pendidikan Teknologi Informasi Vol. 4 No. 3: NOVEMBER 2024
Publisher : Program Studi Pendidikan Teknologi Infromasi UMK

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51454/decode.v4i3.576

Abstract

The skin is the largest external organ that serves to protect human internal organs and is very sensitive to various diseases, so early detection is very important to reduce the risk and increase the chance of recovery. This study aims to classify skin disease types using CNN algorithm with VGG19 architecture and learning rate adjustment to get a more optimal model, using a dataset from Kaggle consisting of 3,295 images with six classes, including several types of skin diseases and one healthy skin class. The preprocessing process includes dividing the data into training and testing sets, resizing the images to fit the VGG19 architecture, and normalization to scale the pixel values from 0-255 to a range of 0-1. The results show that using a learning rate of 0.00003 produces the best performance with 97.29% accuracy, 97.36% precision, 97.29% recall, and 97.30% F1-score. These findings confirm that the CNN algorithm with VGG19 architecture can classify skin disease types well.
Optimalisasi pengelolaan keuangan digital keluarga di PRA Kauman Yogyakarta Khusna, Arfiani Nur; Putra, Ulinnuha Yudiansa; Rahmawati, Fitri Maulidah
KACANEGARA Jurnal Pengabdian pada Masyarakat Vol 8, No 3 (2025): Agustus
Publisher : Institut Teknologi Dirgantara Adisutjipto

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.28989/kacanegara.v8i3.2668

Abstract

Program ini dilaksanakan karena dari wawancara awal menunjukkan rendahnya tingkat pengetahuan ibu-ibu Pimpinan Ranting ‘Aisyiyah (PRA) Kauman tentang pengelolaan keuangan keluarga, termasuk perencanaan, penentuan kebutuhan dan keinginan serta pencatatan keuangan. Program pengabdian bertujuan untuk meningkatkan keterampilan dalam pengelolaan keuangan keluarga dan dapat menggunakan platform digital keuangan secara benar. Metode pelatihan dilakukan melalui penjelasan materi dan menggunakan simulasi dompet terkait perencanaan keuangan keluarga dan penentuan prioritas pengeluaran. Selain itu, terdapat juga materi dan kartu simulasi literasi keuangan digital. Hasilnya, menunjukkan bertambahnya wawasan dan pengetahuan terkait pengelolaan keuangan keluarga dan literasi keuangan digital serta peserta dapat menggunakan platform keuangan digital sesuai kebutuhan keluarga. Evaluasi pelaksanaan pelatihan menunjukkan peserta yang mengikuti pelatihan setuju dan puas dalam mengikuti pelatihan dengan skor 42,43 dari 50. Peserta menjadi lebih paham dalam membuat perencanaan keuangan keluarga dan pentingnya mengetahui platform literasi keuangan digital yang sudah marak digunakan masyarakat pada umumnya.
Enhancing Customer Satisfaction: Exploring the Earliest Due Date Method for Production Scheduling at PT. X Khusna, Arfiani Nur; Prabowo, Ferry Agung
Jurnal Nasional Pendidikan Teknik Informatika: JANAPATI Vol. 14 No. 2 (2025)
Publisher : Prodi Pendidikan Teknik Informatika Universitas Pendidikan Ganesha

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23887/janapati.v14i2.84476

Abstract

Efficient production scheduling is essential for meeting customer demands on time and enhancing a company's operational efficiency. PT. X faces challenges in optimizing production schedules and meeting order deadlines efficiently. This study aims to evaluate the effectiveness of the earliest due date (EDD) method in production scheduling at PT. X. A quantitative approach was used, involving 100 production data samples from PT. X. The EDD method was applied to set the production order based on the earliest deadline of each order. Factors considered included order specifications, machine capabilities, and set deadlines. The EDD method improved the accuracy of production schedules, efficient use of resources, and customer satisfaction with on-time delivery. The results showed a 100% success rate for the EDD method in prioritizing orders based on the earliest deadlines, thereby improving production schedules and on-time delivery to customers. The study confirms the importance of the EDD method in enhancing production scheduling practices and achieving operational efficiency at PT. X. Future research should explore additional scheduling methods to further improve production processes and customer satisfaction.
Sistem Informasi Terintegrasi Pengelolaan Catatan Kasus Konseling Siswa menggunakan User-Centered Design Prakasa, Anabela Aji; Mardhia, Murein Miksa; Aretama, Lucky Barga; Khusna, Arfiani Nur; Perwira, Luqman Tifa
Journal Global Technology Computer Vol 4 No 3 (2025): Agustus 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/jogtc.v4i3.8259

Abstract

Deviant behavior in adolescents is a significant issue in education, particularly in the field of Guidance and Counseling (BK). The paper-based manual recording system makes it difficult for BK teachers to manage data such as case histories, counseling reports, and attendance. This study aims to develop a website-based BK information system using the User-Centered Design (UCD) approach and the Waterfall method. Data was collected through interviews and observations of BK teachers, followed by designing a user-friendly interface, system development, and testing. This system enables BK teachers to manage student data efficiently and allows principals to monitor reports in real time. The results of the System Usability Scale test showed an average score of 80.75 (category B, Good), and the Blackbox test showed appropriate functionality. The system proved effective, efficient, and met user needs in managing BK services in schools thus enabling BK teachers to focus more on quality counseling with data-based decision making.
Peningkatan Kompetensi Guru di SMA Negeri 2 Playen, Gunungkidul, Daerah Istimewa Yogyakarta melalui Pelatihan Membuat Komik Digital sebagai Media Pembelajaran Berbasis Kecerdasan Artifisial Yulianto, Dinan; Khusna, Arfiani Nur; Evitasari, Rachma Tia
Jurnal Pengabdian Masyarakat Terapan Vol 2 No 2 (2025): JUPITER Agustus 2025
Publisher : Informatika, Universitas Jenderal Soedirman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20884/1.jupiter.2.2.59

Abstract

Sekolah Menengah Atas Negeri 2 Playen memiliki program reguler untuk meningkatkan kompetensi pihak kepala sekolah dan guru yang memuat nilai-nilai lifelong learning. Hasil diskusi kepada pihak guru mengidentifikasi media pembelajaran yang telah diterapkan oleh guru meliputi buku paket, modul pembelajaran, lembar kerja siswa, poster, media power-point, dan media audio-visual. Namun, guru memiliki kesadaran terkait kendala dalam pengembangan media pembelajaran digital yang lebih inovatif. Faktor keterbatasan pengalaman guru dalam menggunakan teknologi dapat memperlambat pengembangan media pembelajaran digital yang kreatif dan inovatif. Faktor keterbatasan waktu dan beban kerja yang tinggi juga menyebabkan guru kesulitan dalam pengembangan media pembelajaran digital secara komprehensif. Upaya mengatasi masalah pengembangan media pembelajaran digital yang kreatif dan inovatif secara komprehensif dilakukan pelatihan berbasis kecerdasan artifisial. Program pelatihan dilakukan secara terstruktur melalui metode pre-test, presentasi, praktik, diskusi, serta post-test. Program edukasi kepada guru meliputi materi terminologi dan peran media pembelajaran, klasifikasi media pembelajaran kovensional dan digital, metode produksi media pembelajaran digital Multimedia Development Life Cycle, serta sistem lisensi digital dari aset digital. Program pelatihan teknis kepada guru meliputi praktik akses sumber daya aset digital serta praktik membuat komik digital secara semi-autonomus dan autonomus. Hasil pre-test dan post-test kepada 40 guru mengidentifikasi peningkatan rerata nilai guru dari 62% menjadi 87% sebagai representasi nilai ketercapaian pemahaman dan penguasaan materi pelatihan yang meningkat secara signifikan. Implikasi positif dari program pelatihan ini meliputi peningkatan nilai pemahaman dan keterampilan teknis guru dalam menciptakan media pembelajaran berupa komik digital berbasis teknologi kecerdasan artifisial.