Article Per Year (5 Year)
p-Index From 2021 - 2026
0.444
P-Index
This Author published in this journals
All Journal METIK JURNAL Jurnal Informasi Teknologi dan Sistem (INTEKSIS)
Susana Susana
Sistem Informasi, Fakultas Teknologi Informasi, Universitas Widya Dharma Pontianak
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Earth & Planetary Sciences Electrical & Electronics Engineering Other

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

 1 
Perancangan E-Katalog Produk Berbasis Android pada PT Samudera Jaya Benelli Menggunakan Metode User Centered Design (UCD) Susana Lin
METIK JURNAL Vol 4 No 2 (2020): METIK Jurnal
Publisher : LP3M Universitas Mulia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47002/metik.v4i2.182

Abstract

Technological developments encourage business actors to be more creative in their competition to provide the best services to their consumers. In the field of motor vehicle sales today, however, brochures are still widely used in introducing their products. In light of this, PT Samudera Jaya Benelli wants to have an android-based e-catalog that contains information on their motorbike products so that it will facilitate the process of delivering information to potential customers who visit the showroom. Additionally, the use of e-catalogs can help the company save on the cost of printing brochures and catalogs, which has been the common practice so far. Furthermore, the development of this e-catalog information system uses the User-Centered Designing (UCD) method. The purpose of using UCD is to produce applications that have high use value, which includes the convenience in the usage, management, and effectiveness of the application, as well as the compatibility of the application to users' needs. Therefore, it is expected that this Android-based (mobile) e-catalog application will be able to increase efficiency and provide convenience in displaying products in the form of a digital catalog that has a modern, complete, and simple appearance
Aplikasi Mobile Money Management Dengan Fitur Optical Character Recognition Menggunakan Framework React Native Susana Lin; Genrawan Hoendarto
METIK JURNAL Vol 5 No 2 (2021): METIK Jurnal
Publisher : LP3M Universitas Mulia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47002/metik.v5i2.291

Abstract

Financial management is one of the important things in the process of achieving the financial goals of a person or an organization. Everyone has their own way to manages finances, this is dependent on the character and they goals. Financial management can be done conventionally, for example by manual method which is commonly done by write the expenses, income, and savings in a notebook. However, if the note must contain details of the transactions carried out, it can be considered less efficient. The use of Optical Character Recognition will be able to answer this problem, by taking a picture of the transaction, all transaction details will be recorded on the smartphone, and the user can validate the results obtained and save the record on the smartphone user. Users can also immediately see the total transactions made according to the selected time range without having to calculate each transaction made manually. The application will be designed using the react native framework which allows it to run on various platforms.
KLASIFIKASI KEPRIBADIAN MELALUI GAMBAR TULISAN TANGAN MENGGUNAKAN METODE CONVOLUTIONAL NEURAL NETWORK Thomas Aldo; Sandi Tendean; Susana Susana
INTEKSIS Vol 13 No 1: Mei 2026
Publisher : LPPM Universitas Widya Dharma Pontianak

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.66003/inteksis.v13i1.10619

Abstract

Salah satu alasan mengapa teknologi berkembang pesat adalah karena efektivitas dan efisiensi waktu. Masalah yang ditemukan oleh penulis yaitu tentang ilmu psikologis yang tidak banyak dikuasai orang khususnya ilmu pembacaan tulisan tangan sehingga membutuhkan pelatihan dan pembelajaran khusus. Peneliti bertujuan membangun dan mencari nilai parameter paling optimal untuk pengenalan tulisan tangan dengan sebuah gambar berbasis deep learning. Peneliti menggunakan mengumpulkan gambar dengan teknik Simple Random Sampling untuk dijadikan dataset dan metode CNN (Convolutional Neural Network) berbasis AlexNet sebagai metode untuk melakukan pengujian dan percobaan pengenalan gambar tulisan tangan. Penelitian ini menghasilkan nilai-nilai parameter paling optimal berdasarkan pengujian dari beberapa parameter yang ada. Tujuan dari penelitian ini adalah untuk mempermudah para peneliti lain yang ingin membuat aplikasi deep learning pengenalan gambar. Sumber dataset yang dipakai pada penelitian ini didapatkan dari gambar scan atau foto tulisan tangan orang-orang sekitar sebanyak 418 gambar. Pengujian dilakukan dengan aplikasi MatLab dan beberapa parameter yang dilakukan ujicoba yaitu input size, epoch, mini batch size dan learning rate. Pada akhir pengujian peneliti mendapatkan hasil akurasi pengenalan sebesar 94.17 persen dan telah memberikan hasil yang sangat baik dan sesuai harapan. Peneliti menyimpulkan bahwa pembangunan aplikasi deep learning pengenalan tulisan tangan ini berjalan dengan baik. Peneliti menyimpulkan bahwa aplikasi deep learning pengenalan tulisan tangan ini berjalan dengan baik. Peneliti lain dapat menjadikan penelitian ini sebagai acuan untuk mengembangkan menjadi lebih baik lagi.
Co-Authors Genrawan Hoendarto Tendean, Sandi Thomas Aldo