Article Per Year (5 Year)
p-Index From 2020 - 2025
1.36
P-Index
This Author published in this journals
All Journal Sinkron : Jurnal dan Penelitian Teknik Informatika TEKNOKOM : Jurnal Teknologi dan Rekayasa Sistem Komputer Journal of Computer System and Informatics (JoSYC) Jurasik (Jurnal Riset Sistem Informasi dan Teknik Informatika) Digital Transformation Technology (Digitech) Scientica: Jurnal Ilmiah Sains dan Teknologi
Wijaya, Yunan Fauzi
Unknown Affiliation
Religion Agriculture, Biological Sciences & Forestry Humanities Civil Engineering, Building, Construction & Architecture Computer Science & IT Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Industrial & Manufacturing Engineering Library & Information Science Social Sciences Other

Published : 7 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 7 Documents
Search

 1 
Advancing Fruit Image Classification with State-of-the-Art Deep Learning Techniques Wijaya, Yunan Fauzi; Hindarto, Djarot
Sinkron : jurnal dan penelitian teknik informatika Vol. 8 No. 2 (2024): Article Research Volume 8 Issue 2, April 2024
Publisher : Politeknik Ganesha Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33395/sinkron.v8i2.13604

Abstract

Fruit image classification technology using deep learning is making significant contributions in the agriculture and food retail sectors, promising to increase efficiency and productivity. However, there is an identified knowledge gap in dealing with the considerable variation in fruit appearance caused by factors such as type, size, color, and lighting conditions, as well as the precise identification of damage or disease. This research focuses on applying the developed Convolutional Neural Network architecture to fill this gap by using it in an extensive and diverse dataset, covering 67,692 image files categorized into 131 fruit classes. The training process showed substantial accuracy improvement, with training accuracy reaching 98.39% and validation accuracy at 90%, while training loss decreased to 0.0430 and validation loss to 0.2991. In the advanced stage of training, the training accuracy peaked at 99.43% in the 59th epoch with a shallow loss of 0.0251. However, the validation loss showed variation, indicating room for improvement in model generalization. The findings provide insight into the potential and challenges of applying Convolutional Neural Network models and fruit image classification with improved fruit sorting accuracy. Contribution to the literature in the field of information technology and agriculture by showing deep learning models can be improved to address the issue of fruit image variability.
Penerapan Algoritma Bubble Sort Dalam Aplikasi Mobile Penentuan Nilai Prestasi Siswa Resiana, Cindy Dinda; Wijaya, Yunan Fauzi; Darusalam, Ucuk
Jurasik (Jurnal Riset Sistem Informasi dan Teknik Informatika) Vol 9, No 1 (2024): Edisi Februari
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/jurasik.v9i1.753

Abstract

In high school, the aim is to improve the effectiveness and time efficiency of the student performance assessment process. The solution obtained is to use the bubble sort algorithm, which will be optimized to increase the performance of the bubble sort algorithm and generate more efficient results. In the implementation of the bubble sort algorithm for this research, the sorting is done in descending order, starting from the smallest value. Consequently, the first position with the highest value is obtained as "94" for Nurlita Hasibuan, and the lowest value is "56" for Hendro Mahardika. In this study, the optimization of the algorithm resulted in a time complexity of ???? (???? ????og (????)), which performed efficiently. The system testing in this research utilized the SUS method, and the final result obtained a SUS score of "83.95", which corresponds to a grade A with an Excellent rating.
Aplikasi Mobile Pendaftaran Pasien Klinik Berbasis Algoritma Multilevel Queue Dan FIFO Untuk Meningkatkan Layanan Antrian Priambudi, Abiyoga; Wijaya, Yunan Fauzi; Darusalam, Ucuk
Jurasik (Jurnal Riset Sistem Informasi dan Teknik Informatika) Vol 9, No 1 (2024): Edisi Februari
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/jurasik.v9i1.754

Abstract

In this continuously evolving era of technology, the use of smartphone has become commonplace, including in the healthcare sector. However, there are still several issues such as long queues, uncertain appointment scheduling, and unexpected waiting times in the case of health care service such as in a hospital. Therefor, the aim of this research is to address these problems by developing a mobile application that utilizes multilevel queue and FIFO algorithms. The methods used in this research include data collection through questionnaires and documentation. A specific clinic is the subject of this study, involving both patients and clinic staff. The expected outcome is to enhance patient satisfaction through more efficient and expedited registration and queue processes. The result can enhance patient satisfaction because the registration and queueing process becomes faster and more efficient.
ANALISIS SENTIMEN TERHADAP PENUTUPAN TIKTOK SHOP MENGGUNAKAN ALGORITMA NAÏVE BAYES CLASSIFIER PADA MEDIA SOSIAL X Faradian, Havadz; Rubhasy , Albar; Wijaya, Yunan Fauzi
Scientica: Jurnal Ilmiah Sains dan Teknologi Vol. 2 No. 4 (2024): Scientica: Jurnal Ilmiah Sains dan Teknologi
Publisher : Komunitas Menulis dan Meneliti (Kolibi)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.572349/scientica.v2i4.1207

Abstract

Pemanfaatan teknologi informasi telah berkembang pesat, terutama dengan kemunculan media sosial yang memungkinkan masyarakat untuk menyampaikan pendapat secara tak terbatas. Salah satu platform microblogging yang memfasilitasi pengguna dalam berbagi pendapat, emosi, pengalaman, dan topik menarik lainnya adalah X. Di X, beragam topik dibahas oleh pengguna, termasuk tentang penutupan TikTok Shop, sebuah fitur baru dalam dunia belanja yang mencakup berbagai proses mulai dari proses pembelian hingga pengiriman dapat dilakukan tanpa harus menggunakan platform lain. Penelitian pun dilakukan untuk menguji dampak kegunaan yang dirasakan, kemudahan penggunaan yang dirasakan, dan kesesuaian dengan gaya hidup terhadap keinginan membeli melalui perdagangan sosial. Terdapat berbagai sentimen di masyarakat terkait program ini, sehingga klasifikasi pendapat berdasarkan sentimennya diperlukan untuk mengetahui kecenderungan opini terhadap penutupan TikTok Shop, apakah positif atau negatif. Dalam analisisnya, data diperoleh melalui proses scraping menggunakan bahasa pemrograman Python. Sebanyak 253 data berhasil dikumpulkan dari proses scraping, yang kemudian melalui tahap preprocessing seperti cleansing, case folding, tokenizing, normalisasi, filtering, dan stemming.
Kombinasi Algoritma Priority Scheduling dan Earliest Due Date untuk Sistem Penjadwalan Slitting Produk Berbasis Web Afrianto, Muhammad Iqbal; Fauziah, Fauziah; Wijaya, Yunan Fauzi
TEKNOKOM Vol. 7 No. 1 (2024): TEKNOKOM
Publisher : Department of Computer Engineering, Universitas Wiralodra

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31943/teknokom.v7i1.176

Abstract

Production scheduling is one of the most critical components of production management that can impact efficiency and resource utilization. This research focuses on the development of a web-based production scheduling system that integrates two algorithms, Earliest Due Date (EDD) and Priority Scheduling. This research includes the analysis, design, implementation and testing of a those two algorithms in a web-based application for production management. The result of this research will be analyzed through the results of how both algorithms affects lateness and tardiness. The research findings indicate that the application can effectively manage Work Orders. The application can generate an optimal schedule when conditions arise where some tasks have higher priority than others by combining both algorithms. The system can identify potentially late tasks by calculating the tardiness of the given jobs. And from the analysis results, the application can generate an efficient production schedule with an on-time accuracy rate of 74%, and the average delay for each job is 0.95 hours.
Implementasi Data Mining Untuk Penerima Bantuan PKH Pemerintah dengan Menerapkan Algoritma Klastering K-Medoids Wijaya, Yunan Fauzi
Journal of Computer System and Informatics (JoSYC) Vol 5 No 3 (2024): May 2024
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josyc.v5i3.5197

Abstract

In 2019, a very heartbreaking event occurred for the entire world population. Where the consequences of the outbreak caused total paralysis of all activities in the world. The impact of non-performance of economic activities has caused the paralysis of the economy throughout the world, not only affecting small companies but also large companies. Especially in Indonesia itself, during the Covid-19 pandemic, there were many large-scale employee layoffs. The impact of this is increasing the number of family poverty cases in Indonesia. The Family Hope Program (PKH) is a program run by the government through the Ministry of Social Affairs. Even though the PKH program is based on the implementation of the Ministry of Social Affairs, the determination process is carried out by each social service in each region. There are still many families who are poor families who actually do not receive PKH assistance. This problem is caused by the large number of families in an area which requires quite a long process. The determination of poor families determined by the relevant agencies should be able to be seen based on data on previous PKH aid recipients. Data mining is a data mining process, data mining is carried out with the aim of obtaining new information that is valuable and important. Clustering or Clustering is part of data mining which aims to group data. Clustering is the formation of a new cluster from previously existing data. The K-Medoids algorithm is an algorithm for clustering data mining. In the K-Medoids algorithm, a process is carried out based on calculating the closest distance. From the process that has been carried out, it is estimated that there are 2 (two) clusters formed where in cluster 1 there are 7 families included in it. Meanwhile, in cluster 2 there are 8 families included.
Analisis Kompleksitas Password Dengan Metode KNN, Naïve Bayes, Decision Tree, Ensemble Methods Dan Linear Regression Mardiani, Eri; Rahmansyah, Nur; Wijaya, Yunan Fauzi; Fitri, Annisa Amalia; Mustafa, Rayhan; Rizki, Muhammad Romadhoni; Pramesti, Komang Mustika
Digital Transformation Technology Vol. 3 No. 2 (2023): Artikel Periode September 2023
Publisher : Information Technology and Science(ITScience)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/digitech.v3i2.3513

Abstract

Dalam era digital yang semakin kompleks dan penuh tantangan, keamanan kata sandi menjadi krusial untuk melindungi informasi sensitif dan mencegah potensi ancaman keamanan siber. Kata sandi merupakan lapisan pertama pertahanan dalam banyak sistem keamanan digital, oleh karena itu, pemahaman mendalam tentang metode yang efisien dalam menilai dan memprediksi kompleksitas password sangatlah penting. Ketika dihadapkan dengan data yang sangat kompleks, diperlukan analisis dan representasi visual data agar informasi dapat lebih mudah dipahami. Untuk mengilustrasikan data dengan cara yang interaktif dan dapat dimengerti oleh berbagai kalangan, salah satu software atau alat bantu yang dapat digunakan adalah Orange. Dalam pengolahan data ini menggunakan aplikasi orange, kami menganalisis bagaimana prediksi hubungan antara password dan tingkat kompleksitasnya menggunakan fitur-fitur yang telah dikonstruksi. melakukan analisis data mining melalui penerapan teknik klasifikasi dengan memanfaatkan lima metode algoritma yang berbeda. Dataset yang akan dijadikan dasar proyek berasal dari publikasi data pada situs Kaggle.com.
Co-Authors Afrianto, Muhammad Iqbal Faradian, Havadz Fauziah Fauziah Fitri, Annisa Amalia Hindarto, Djarot Mardiani, Eri Mustafa, Rayhan Pramesti, Komang Mustika Priambudi, Abiyoga Rahmansyah, Nur Resiana, Cindy Dinda Rizki, Muhammad Romadhoni Rubhasy , Albar Ucuk Darusalam