Article Per Year (5 Year)
p-Index From 2020 - 2025
5.995
P-Index
This Author published in this journals
All Journal IAES International Journal of Artificial Intelligence (IJ-AI) IJCCS (Indonesian Journal of Computing and Cybernetics Systems) JOIN (Jurnal Online Informatika) JOIV : International Journal on Informatics Visualization Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) IT JOURNAL RESEARCH AND DEVELOPMENT IJIS - Indonesian Journal On Information System JURNAL TEKNIK INFORMATIKA DAN SISTEM INFORMASI Jurnal Tekno Insentif Journal of Informatics, Information System, Software Engineering and Applications (INISTA) Jurnal Teknik Informatika (JUTIF) Journal of Dinda : Data Science, Information Technology, and Data Analytics Journal of Internet and Software Engineering Jurnal INFOTEL SmartComp Jurnal Informatika: Jurnal Pengembangan IT JuTISI (Jurnal Teknik Informatika dan Sistem Informasi)
Agi Prasetiadi
Institut Teknologi Telkom Purwokerto
Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering Engineering

Published : 28 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 28 Documents
Search

 1   2   3 
Automatic Birdsong Splitting and Syllabic Analysis of Jalak Suren Agi Prasetiadi; Julian Saputra
Journal of INISTA Vol 5 No 2 (2023): May 2023
Publisher : LPPM INSTITUT TEKNOLOGI TELKOM PURWOKERTO

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20895/inista.v5i2.1091

Abstract

The study of birdsong has received relatively limited attention in the field of artificial intelligence, despite its long-standing intrigue and the question of whether birds possess a form of language. Previous research has provided evidence suggesting the presence of structurally organized words recognized by birds, such as the strong reactions observed in Japanese tits and Pied babblers when exposed to specific sequences of artificially played calls. Altering the speed of a sequence also influences the birds' responses, further supporting the existence of organized linguistic units in avian vocalizations. In this study, we propose a novel approach for analyzing birdsong by employing automatic syllable segmentation and syllabic similarity analysis. Our focus is on the Jalak Suren species (Sturnus contra), renowned for its melodious song. Through the identification and categorization of distinct syllabic units in birdsong recordings, we investigate the statistical occurrence of these syllables within the sequence of birdsong. Our findings reveal remarkable similarities between the statistical occurrence of syllables in birdsong and those found in human language passages
Minimalist DCT-based Depthwise Separable Convolutional Neural Network Approach for Tangut Script Agi Prasetiadi; Julian Saputra; Imada Ramadhanti; Asti Dwi Sripamuji; Risa Riski Amalia
Indonesian Journal of Data Science, IoT, Machine Learning and Informatics Vol 3 No 2 (2023): August
Publisher : Research Group of Data Engineering, Faculty of Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20895/dinda.v3i2.1106

Abstract

The Tangut script, a lesser-explored dead script comprising numerous characters, has received limited attention in deep learning research, particularly in the field of optical character recognition (OCR). Existing OCR studies primarily focus on widely-used characters like Chinese characters and employ deep convolutional neural networks (CNNs) or combinations with recurrent neural networks (RNNs) to enhance accuracy in character recognition. In contrast, this study takes a counterintuitive approach to develop an OCR model specifically for the Tangut script. We utilize shorter layers with slimmer filters using a depthwise separable convolutional neural network (DSCNN) architecture. Furthermore, we preprocess the dataset using a frequency-based transformation, namely the Discrete Cosine Transform (DCT). The results demonstrate successful training of the model, showcasing faster convergence and higher accuracy compared to traditional deep neural networks commonly used in OCR applications.
Deep Learning Approaches for Nusantara Scripts Optical Character Recognition Agi Prasetiadi; Julian Saputra; Iqsyahiro Kresna; Imada Ramadhanti
IJCCS (Indonesian Journal of Computing and Cybernetics Systems) Vol 17, No 3 (2023): July
Publisher : IndoCEISS in colaboration with Universitas Gadjah Mada, Indonesia.

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22146/ijccs.86302

Abstract

The number of speakers of regional languages who are able to read and to write traditional scripts in Indonesia is decreasing. If left unaddressed, this will lead to the extinction of Nusantara scripts and it is not impossible that their reading methods will be forgotten in the future. To anticipate this, this study aims to preserve the knowledge of reading ancient scripts by developing a Deep Learning model that can read document images written using one of the 10 Nusantara scripts we have collected: Bali, Batak, Bugis, Javanese, Kawi, Kerinci, Lampung, Pallava, Rejang, and Sundanese. While previous studies have made efforts to read traditional Nusantara scripts using various Machine Learning and Convolutional Neural Network algorithms, they have primarily focused on specific scripts and lacked an integrated approach from script type recognition to character recognition. This study is the first to comprehensively address the entire range of Nusantara scripts, encompassing script type detection and character recognition. Convolutional Neural Network, ConvMixer, and Visual Transformer models were utilized and their respective performances were compared. The results demonstrate that our models achieved 96% accuracy in classifying Nusantara script types, with character recognition accuracy ranging from 93% to approximately 100% across the ten scripts.
Navigating Bitcoin Panic-Selling using Linear Approach Agi Prasetiadi
JURNAL INFOTEL Vol 12 No 4 (2020): November 2020
Publisher : LPPM INSTITUT TEKNOLOGI TELKOM PURWOKERTO

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20895/infotel.v12i4.543

Abstract

COVID-19 affects significant human activity around the globe, including Bitcoin prices. The Bitcoin price is well known for its volatility, so it is not a big shocker when the panic-selling occurs during the pandemic. However, the mechanism to cope with these breakouts, especially the bearish one, is contentious. The experts give numerous pieces of advice with different conclusions in the end. It is also the same with Machine Learning. Various kernels show different results regarding how the price will move. It depends on the window size, how the data is being preprocessed, and the algorithm used. This paper inspects the best combination that various machine learning can offer with a linear approach to navigate the price prediction based on its depth interval, window size until the algorithms themselves. This paper also proposed a new approach to seeing the prediction range called s-steps ahead prediction using a linear model. The result shows that simple machine learning can herd 99.715% profit even during the bearish breakout.
Classification Based on Configuration Objects by Using Procrustes Analysis Ridho Ananda; Agi Prasetiadi
JURNAL INFOTEL Vol 13 No 2 (2021): May 2021
Publisher : LPPM INSTITUT TEKNOLOGI TELKOM PURWOKERTO

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20895/infotel.v13i2.637

Abstract

Classification is one of the data mining topics that will predict an object to go into a certain group. The prediction process can be performed by using similarity measures, classification trees, or regression. On the other hand, Procrustes refers to a technique of matching two configurations that have been implemented for outlier detection. Based on the result, Procrustes has a potential to tackle the misclassification problem when the outliers are assumed as the misclassified object. Therefore, the Procrustes classification algorithm (PrCA) and Procrustes nearest neighbor classification algorithm (PNNCA) were proposed in this paper. The results of those algorithms had been compared to the classical classification algorithms, namely k-Nearest Neighbor (k-NN), Support Vector Machine (SVM), AdaBoost (AB), Random Forest (RF), Logistic Regression (LR), and Ridge Regression (RR). The data used were iris, cancer, liver, seeds, and wine dataset. The minimum and maximum accuracy values obtained by the PrCA algorithm were 0.610 and 0.925, while the PNNCA were 0.610 and 0.963. PrCA was generally better than k-NN, SVM, and AB. Meanwhile, PNNCA was generally better than k-NN, SVM, AB, and RF. Based on the results, PrCA and PNNCA certainly deserve to be proposed as a new approach in the classification process.
Klasifikasi Penyakit Daun Kentang dengan Metode CNN dan RNN Jihan Rihadatul Aisya; Agi Prasetiadi
Jurnal Tekno Insentif Vol 17 No 1 (2023): Jurnal Tekno Insentif
Publisher : Lembaga Layanan Pendidikan Tinggi Wilayah IV

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36787/jti.v17i1.888

Abstract

Abstrak Banyak jenis penyakit dan hama yang menyerang tanaman ketang masih dijumpai oleh para petani di Indonesia. Padahal kentang merupakan jenis sayuran yang tergolong familiar dan termasuk makanan pokok utama. Diperlukan metode klasifikasi untuk menggambarkan dan membandingkan hasil akurasi penyakit kentang. Dalam penelitian ini akan melakukan image processing dengan teknik transfer learning dan dilakukan augmentasi data, menggunakan metode klasifikasi Convolitonal Neural Network (CNN) dengan jenis VGG16 dan ResNet50 dan Recurrent Neural Network (RNN) jenis LSTM untuk mengklasifikasi dan membandingkan hasil akurasi penyakit daun kentang seperti, Late blight (Busuk Daun), Early blight (Bercak Daun), Daun Berlubang, Daun Menggulung dan Daun sehat. Pada penelitian ini mencari model terbaik dengan arsitektur VGG16 dense layer 75 memperoleh nilai tertinggi dengan nilai precision 0.87, recall 0.86, accuracy 0.86 dan f1-score 0.86, sedangkan untuk model dengan arsitektur VGG16 dan LSTM dense layer 100 memperoleh hasil terendah dengan nilai precision 0.21, recall 0.24, accuracy 0.24 dan f1-score 0.21. Abstract Many types of diseases that attack potato plants are still found by farmers in Indonesia. Whereas potato is a type of vegetable that is quite familiar and includes the main staple food. A classification method is needed to describe and compare the results of potato disease accuracy. In this study, image processing with transfer learning techniques and data augmentation will be carried out, using the CNN classification method with VGG16 and ResNet50 types and RNN LSTM types to classify and compare the results of potato leaf disease accuracy in five category In this study, looking for the best model with VGG16 dense layer architecture 75 obtained the highest value with a precision value of 0.87, recall 0.86, Accuracy 0.86, and f1-score 0.86, while the model with VGG16 architecture and LSTM dense layer 100 obtained the lowest result with a precision value of 0.21, recall 0.24, Accuracy 0.24 and f1-score 0.21.
Personalisasi Otomatis Aplikasi Caca (Cari Cafe) Berbasis Artificial Intelligence Salma Pusriwijayanti; Agi Prasetiadi; Diandra Chika Fransisca
Smart Comp :Jurnalnya Orang Pintar Komputer Vol 12, No 4 (2023): Smart Comp: Jurnalnya Orang Pintar Komputer
Publisher : Politeknik Harapan Bersama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30591/smartcomp.v12i4.5570

Abstract

Peningkatan produksi kopi menciptakan peluang bisnis olahan kopi, memunculkan banyak cafe. Dalam mengikuti perkembangan zaman, pengusaha perlu menggunakan teknologi terkini dengan menyediakan aplikasi reservasi cafe untuk meningkatkan kepuasan pelanggan dan bersaing di pasar yang semakin kompetitif. Penelitian sebelumnya mengenai aplikasi berbasis mobile dengan Extreme Programming yang fokus pada kepuasan pelanggan, memungkinkan pemesanan makanan lebih awal, dan memantau pesanan pelanggan melalui website. Penelitian ini membuat aplikasi CACA (Cari Cafe) yang dirancang untuk melakukan reservasi cafe dan menyediakan informasi tentang cafe-cafe pada satu aplikasi berbasis website. Dalam mencapai personalisasi otomatis, teknologi artificial intelligence seperti Optical Character Recognition (OCR), Convolutional Neural Network (CNN), dan Siamese Neural Network (SNN) digunakan. Personalisasi otomatis aplikasi CACA melibatkan pembacaan e-KTP sebagai data registrasi, pengenalan gambar wajah pengguna untuk memberikan rekomendasi cafe berdasarkan kesukaan atau kebiasaan, dan pencocokan wajah pengguna untuk verifikasi akun member. Penelitian ini berhasil mengimplementasikan OCR pada gambar e-KTP dengan bounding box di mana nilai box_loss sebesar 0.05211 dan nilai cls_loss sebesar 0.01598. Penggunaan transfer learning model VGG16 dengan fungsi aktivasi sigmoid untuk menebak 11 komponen kesukaan atau kebiasaan pengguna juga mencapai tingkat keberhasilan yang optimal. Selain itu, metode verifikasi menggunakan SNN juga memberikan hasil yang baik, dengan mencocokan foto pada gambar e-KTP dengan foto selfie dan mencapai akurasi sebesar 0.9285 dengan nilai loss 0.0170.
Monitoring Kualitas Air Tambak Udang Dengan Metode Data Logging dan Algoritma KNN Berbasis Internet Of Things Harry Pratama Ramadhan; Condro Kartiko; Agi Prasetiadi
Jurnal Informatika: Jurnal Pengembangan IT Vol 6, No 1 (2021): JPIT, Januari 2021
Publisher : Politeknik Harapan Bersama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30591/jpit.v6i1.2136

Abstract

Berdasarkan pengalaman peneliti, banyak pengusaha budi daya tambak udang di Indonesia mengalami bangkrut, hal tersebut disebabkan karena biaya yang besar untuk satu kali cek laboratorium sehingga budi daya tambak udang mengalami gagal panen dikarenakan banyak udang yang terserang penyakit dan mati. Pada penelitian ini dibuat sebuah alat pemantauan kualitas air dari tambak udang vannamei menggunakan metode data logging berdasarkan nilai suhu air dan algoritma ­k-nearest neighbors untuk memprediksi kesehatan udang dan kondisi air tambak udang dari pergerakan air. Perangkat data logger menggunakan mikrokontroler NodeMCU ESP8266, sensor LDR, dan sensor suhu air Dallas DS18B20, kemudian data logger terhubung ke layanan basis data milik Google yaitu Firebase realtime database untuk menyimpan data pemantauan kualitas air. Terdapat layanan web services yang di hosting pada layanan website milik Heroku untuk menjalankan algoritma k-nearest neighbors menggunakan perintah httprequest dari aplikasi Android yang dibangun menggunakan framework Flutter. Aplikasi Flutter Android berisi widget monitoring, detail monitoring dan prediksi dengan  tingkat akurasi yang diberikan sebesar 99.9 % untuk kesehatan udang serta 97.5 % untuk kondisi air.
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%.
CLOTHING RECOMMENDATION AND FACE SWAP MODEL BASED ON VGG16, AUTOENCODER, AND FACIAL LANDMARK POINTS Imada Ramadhanti; Agi Prasetiadi; Iqsyahiro Kresna A
Jurnal Teknik Informatika (Jutif) Vol. 5 No. 1 (2024): JUTIF Volume 5, Number 1, February 2024
Publisher : Informatika, Universitas Jenderal Soedirman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jutif.2024.5.1.1016

Abstract

The selection of clothes in e-commerce sometimes contains doubts about the clothes that consumers choose because the clothes are not yet known to suit the consumer's body. So this research provides a solution through a clothing recommendation model according to the size and concept of clothing. Furthermore, there is a face exchange model whose job is to exchange faces between the consumer's face and the face on the recommended clothing. The dataset used in the classification model is clothing that is put into 8 classes with variations in size, clothing concept, and veiled or without headscarves, while making the autoencoder model requires source and target face datasets of 3,000 faces each. The method used to make clothing model recommendations is VGG16 and the face exchange model uses the autoencoder and facial landmark points methods. The results of the classification model with 2 different architectures obtain an accuracy of 97.01% and 94.49% respectively. Then the results of the autoencoder models for the 12 models produced the lowest loss values ​​with autoencoder I of 0.00012951 and in autoencoder II of 8.01e-05. The face landmark point method is used if the autoencoder method does not produce a good face swap.
Co-Authors Afrillebar Putra Pratama Amalia Beladinna Arifa Annisa Nugraheni Arum, Refiani Pintan Asti Dwi Sripamuji Athallah, Abiyan Condro Kartiko Diandra Chika Fransisca Dwi Sripamuji, Asti Eko Sanjaya Elfrida Ratnawati Elisa Usada Elisa Usada Fadhilah Gusti Safinatunnajah Ghani, Muhammad Hisyam habiba, adinda miftahul ilmi Haris Budi Widodo Harry Pratama Ramadhan Harry Pratama Ramadhan Ibnu Kasyful Haq Imada Ramadhanti Imada Ramadhanti Imada Ramadhanti Iqsyahiro Kresna A Jihan Rihadatul Aisya Julian Saputra Julian Saputra Lanyak, Andre Citro Febriliyan Lela Sari Kristina Merlinda Wibowo Merlinda Wibowo Olvy Diaz Annesa Pratama, Afrillebar Putra Ramadhan, Harry Pratama Ramadhani, Rima Dias Ramadhanti, Imada Ridho Ananda Risa Riski Amalia Riski Amalia, Risa Salma Pusriwijayanti Saputra, Yuris Mulya Utomo, Hanung Addi Chandra Wahyu Andi Saputra Yustika Rahma