Claim Missing Document
Check
Articles

Found 28 Documents
Search

YOLOv5 and U-Net-based Character Detection for Nusantara Script Agi Prasetiadi; Julian Saputra; Iqsyahiro Kresna; Imada Ramadhanti
JOIN (Jurnal Online Informatika) Vol 8 No 2 (2023)
Publisher : Department of Informatics, UIN Sunan Gunung Djati Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15575/join.v8i2.1180

Abstract

Indonesia boasts a diverse range of indigenous scripts, called Nusantara scripts, which encompass Bali, Batak, Bugis, Javanese, Kawi, Kerinci, Lampung, Pallava, Rejang, and Sundanese scripts. However, prevailing character detection techniques predominantly cater to Latin or Chinese scripts. In an extension of our prior work, which concentrated on the classification of script types and character recognition within Nusantara script systems, this study advances our research by integrating object detection techniques, employing the YOLOv5 model, and enhancing performance through the incorporation of the U-Net model to facilitate the pinpointing of fundamental Nusantara script's character locations within input document images. Subsequently, our investigation delves into rearranging these character positions in alignment with the distinctive styles of Nusantara scripts. Experimental results reveal YOLOv5's performance, yielding a loss rate of approximately 0.05 in character location detection. Concurrently, the U-Net model exhibits an accuracy ranging from 75% to 90% for predicting character regions. While YOLOv5 may not achieve flawless detection of all Nusantara scripts, integrating the U-Net model significantly enhances the detection rate by 1.2%.
Fragmented-cuneiform-based convolutional neural network for cuneiform character recognition Prasetiadi, Agi; Saputra, Julian
IAES International Journal of Artificial Intelligence (IJ-AI) Vol 13, No 1: March 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijai.v13.i1.pp554-562

Abstract

Cuneiform has been a widely used writing system in one of the human history phases. Although there are millions of tablets, have been excavated today, only around 100,000 tablets have been read. The difficulty in translating also increased if the tablet has damaged areas resulting in some of its characters become fragmented and hard to read. This paper investigates the possibility of reading fragmented cuneiform characters from Noto Sans Cuneiform font based on convolutional neural network (CNN). The dataset is built on extracted 921 characters from the font. These characters are then intentionally being damaged with specific patterns, resulting set of fragmented characters ready to be trained. The model produced by this training phase then being used to read the unseen fragmented pattern of cuneiform sets. The model also being tested for reading normal characters set. From the simulation, 83.86% accuracy of reading fragmented characters are obtained. Interestingly, 96.42% accuracy is obtained while the model is being tested for reading normal characters.
Acapella-based music generation with sequential models utilizing discrete cosine transform Saputra, Julian; Prasetiadi, Agi; Kresna, Iqsyahiro
IAES International Journal of Artificial Intelligence (IJ-AI) Vol 13, No 3: September 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijai.v13.i3.pp3371-3380

Abstract

Making musical instruments that accompany vocals in a song depends on the mood quality and the music composer’s creativity. The model created by other researchers has restrictions that include being limited to musical instrument digital interface files and relying on recurrent neural networks (RNN) or Transformers for the recursive generation of musical notes. This research offers the world’s first model capable of automatically generating musical instruments accompanying human vocal sounds. The model we created is divided into three types of sound input: short input, combed input, and frequency sound based on the discrete cosine transform (DCT). By combining the sequential models such as Autoencoder and gated recurrent unit (GRU) models, we will evaluate the performance of the resulting model in terms of loss and creativity. The best model has a performance evaluation that resulted in an average loss of 0.02993620155. The hearing test results from the sound output produced in the frequency range 0-1,600 Hertz can be heard clearly, and the tones are quite harmonious. The model has the potential to be further developed in future research in the field of sound processing.
Dental caries detection using faster region-based convolutional neural network with residual network Lanyak, Andre Citro Febriliyan; Prasetiadi, Agi; Widodo, Haris Budi; Ghani, Muhammad Hisyam; Athallah, Abiyan
IAES International Journal of Artificial Intelligence (IJ-AI) Vol 13, No 2: June 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijai.v13.i2.pp2027-2035

Abstract

Dental caries is the highest prevalent dental disease in the world by 2022. Caries can be stopped by early detection of patients through efficient screening. Previously, there have been several methods used to detect caries such as single shot multibox detector (SSD), faster region-based convolutional neural network (Faster R-CNN) and you only look once (YOLO). This research aims to develop accurate dental caries detection using Faster R-CNN. Using a dataset collected from scraping on the internet, this research is started by creating an original dataset consisting of 81 base images which are then augmented to a total of 486 images and annotated by dental health experts from Jenderal Soedirman University. Transfer learning using pre-trained Faster R-CNN residual network (ResNet)-50 and ResNet-101 model is utilized to detect and localise dental caries. The Faster R-CNN ResNet-50 model trained using the Adam optimizer produces a mean average precision (mAP) of 0.213, and those using the momentum optimizer produce a mAP of 0.177. While the Faster R-CNN ResNet-101 model trained using the Adam optimizer produces a mAP of 0.192, and those using the momentum optimizer produce a mAP of 0.004. The model trained on the dataset showed satisfactory results in detecting dental caries, especially ResNet-50 with Adam optimizer.
Implementasi Sistem Konfigurasi Router Berbasis Natural Language Processing dengan Pendekatan Low Rank Adaptation Finetuning dan 8-Bit Quantization Utomo, Hanung Addi Chandra; Saputra, Yuris Mulya; Prasetiadi, Agi
Journal of Internet and Software Engineering Vol 4 No 2 (2023): Journal of Internet and Software Engineering
Publisher : Department of Electrical Engineering and Informatics, Vocational College, Universitas Gadjah Mada

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22146/jise.v4i2.9093

Abstract

Konfigurasi Router merupakan salah satu hal penting dalam jaringan komputer. Proses ini memerlukan pemahaman tentang bahasa dan sintaks khusus yang dapat memakan waktu lama bagi seseorang yang tidak terbiasa. Penerapan Natural language processing bisa membantu mengatasi masalah ini. Untuk mencapai tujuan dari penerapan ini, Finetuning perlu dilakukan pada model yang ada seperti model GPT-J-6B yang telah dilatih menggunakan 6 milyar parameter. Dengan menggunakan dataset yang terdiri dari konfigurasi router, diharapkan proses finetuning bisa meningkatkan performa model untuk mendeteksi maksud dari input text dalam Bahasa natural yang kemudian bisa memberikan command-command yang sesuai dengan perintah yang diberikan. Selain itu penggunaan teknik lain seperti Low Rank Adaptation (LoRA) yang dapat digunakan untuk mengoptimalkan proses Finetuning agar lebih efisien tanpa mengurangi performa model, dan penggunaan teknik 8-bit quantization untuk memperkecil penggunaan resource saat menjalankan model. Dengan beberapa teknik ini, proses finetuning dapat dilakukan dengan stabil dalam Google Colaboratory. Oleh karena itu, dengan implementasi NLP pada konfigurasi router ini dan teknik-teknik diatas, dapat meningkatkan efektivitas pengelolaan jaringan dengan menggunakan waktu dan sumber daya yang efisien. Melalui penelitian ini berhasil didapatkan model konfigurasi router berbasis NLP dengan akurasi sebesar 98%.
Automatic Vocal Completion for Indonesian Language Based on Recurrent Neural Network Prasetiadi, Agi; Dwi Sripamuji, Asti; Riski Amalia, Risa; Saputra, Julian; Ramadhanti, Imada
IT Journal Research and Development Vol. 9 No. 1 (2024)
Publisher : UIR PRESS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25299/itjrd.2024.14171

Abstract

Most Indonesian social media users under the age of 25 use various words, which are now often referred to as slang, including abbreviations in communicating. Not only causes, but this variation also poses challenges for the natural language processing of Indonesian. The previous researchers tried to improve the Recurrent Neural Network to correct errors at the character level with an accuracy of 83.76%. This study aims to normalize abbreviated words in Indonesian into complete words using a Recurrent Neural Network in the form of Bidirected Long Short-Term Memory and Gated Recurrent Unit. The dataset is built with several weight confgurations from 3-Gram to 6-Gram consisting of words without vowels and complete words with vowels. Our model is the frst model in the world that tries to fnd incomplete Indonesian words, which eventually become fully lettered sentences with an accuracy of 97.44%.
Monitoring Kualitas Air Tambak Udang Menggunakan NodeMCU, Firebase, dan Flutter Harry Pratama Ramadhan; Condro Kartiko; Agi Prasetiadi
Jurnal Teknik Informatika dan Sistem Informasi Vol 6 No 1 (2020): JuTISI
Publisher : Maranatha University Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.28932/jutisi.v6i1.2365

Abstract

Abstract — Based on the prior study, some shrimp ponds went bankrupt due to pond water quality monitoring is still not good. Many shrimps get sick and die for water quality monitoring still relies on laboratory checks and is rarely done because of financial problems. The purpose of this study is to develop a monitoring system of shrimp pond water quality especially for vannamei shrimp using an Internet of Things (IoT)-based device with a data logging method. The system role is to monitor the water condition, record sensor data, and provide water quality status of shrimp ponds based on water movement, turbidity of water, and water temperature. The data logger device uses a microcontroller named NodeMCU ESP8266 and two sensors namely the LDR sensor and the water temperature sensor dallas 18b20. The devices are connected to the internet and send all water quality monitoring data to Google's database service called Firebase. The results of the water quality monitoring can be accessed through an Android-based monitoring application that is built using Flutter framework which contains information. Keywords— Flutter Android; Internet of Things; Monitoring System; Water Quality
Penerapan Estimasi Posisi dan Tracking Wajah Pada Sistem Presensi Mahasiswa Afrillebar Putra Pratama; Agi Prasetiadi; Elisa Usada
Jurnal Teknik Informatika dan Sistem Informasi Vol 6 No 2 (2020): JuTISI
Publisher : Maranatha University Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.28932/jutisi.v6i2.2730

Abstract

The current presence system can be done with a computerized system, one of which is the face biometric system. This study focuses on the application of position estimation and tracking based on clustering on people's faces to determine the position in three dimensions. Position estimation can be obtained by making a kernel that is ready to be used to predict three-dimensional coordinates of faces based on two-dimensional coordinates of two images. Position estimation can be done by utilizing the Machine Learning algorithm family. In this study, Least Absolute Shrinkage and Selection Operators (LASSO) is used to perform the position estimation. Meanwhile, clustering in this study uses the K-Means algorithm. Based on the test results, the kernel error obtained in estimating the face location is 9.23 cm. The tracking accuracy of an object based on clustering is 100%.