Article Per Year (5 Year)
p-Index From 2021 - 2026
0.991
P-Index
This Author published in this journals
All Journal Indonesian Journal of Electronics and Instrumentation Systems TELKOMNIKA (Telecommunication Computing Electronics and Control) Jurnal Informatika: Jurnal Pengembangan IT
Diyah Utami Kusumaning Putri
Universitas Gadjah Mada
Computer Science & IT Electrical & Electronics Engineering

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

Found 3 Documents
Search

 1 
Penggunaan Pre-trained Model untuk Klasifikasi Kualitas Sekrup Muhammad Rafif; Diyah Utami Kusumaning Putri; Lukman Awaludin
IJEIS (Indonesian Journal of Electronics and Instrumentation Systems) Vol 12, No 2 (2022): Oktober
Publisher : IndoCEISS in colaboration with Universitas Gadjah Mada, Indonesia.

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22146/ijeis.78112

Abstract

Inspeksi kualitas produk berbasis citra merupakan hal yang penting bagi industri manufaktur. Tugas tersebut sebagian besar masih dilakukan oleh manusia yang memiliki unit per hour rendah. Metode konvensional untuk inspeksi citra masih mengandalkan metode berbasis fitur, yang memiliki masalah sulitnya generalisasi dan ekstraksi fitur. Masalah tersebut diatasi dengan metode CNN, tetapi CNN membutuhkan data yang besar dan waktu training yang lama. Penggunaan pre-trained model dan augmentasi citra dapat menyelesaikan permasalahan pada metode-metode sebelumnya. Namun, belum ada penelitian yang secara lengkap meneliti dan membandingkan performa berbagai pre-trained model dan variasi augmentasi citra untuk tugas inspeksi citra kualitas produk manufaktur.Proses penelitian menggunakan dataset sekrup berjenis multi class dan binary class pada 33 jenis pre-trained model dan 8 jenis augmentasi citra. Pengujian pre-trained model menggunakan dataset gabungan seluruh jenis augmentasi citra. Model dengan akurasi tertinggi adalah EfficientNetV2-L untuk dataset multi class (97.8%) dan VGG-19 untuk dataset binary class (96.5%). Augmentasi citra dengan signifikansi tertinggi terhadap performa model adalah blur, dengan akurasi 81.1% pada multi class dan 92% pada binary class. Keseluruhan proses pengujian pre-trained model dan augmentasi citra berjalan dengan baik. Kata kunci—Inspeksi kualitas produk, Pre-trained model, Augmentasi citra
Expert System for Identification of Skin Disease in Humans using Naive Bayes Classifier Method on Web Dinar Nugroho Pratomo; Diyah Utami Kusumaning Putri
Jurnal Informatika: Jurnal Pengembangan IT Vol 7, No 1 (2022): JPIT, Januari 2022
Publisher : Politeknik Harapan Bersama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30591/jpit.v7i1.3098

Abstract

Expert System Identification of Skin Disease in Human is an application that adopts expert knowledge, in this case, a dermatologist, to identify skin diseases in humans found in Indonesia. This expert system is constructed using a naive bayes classifier. To make the system interface more dynamic and easy to access by anyone, this system is made based on the web. Through this web application, users can consult with a system like an expert to know the skin disease that occurs to the human and find the correct treatment to solve the problems.
Hybrid convolutional neural networks-support vector machine classifier with dropout for Javanese character recognition Diyah Utami Kusumaning Putri; Dinar Nugroho Pratomo; Azhari Azhari
TELKOMNIKA (Telecommunication Computing Electronics and Control) Vol 21, No 2: April 2023
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/telkomnika.v21i2.24266

Abstract

This research paper explores the hybrid models for Javanese character recognition using 15600 characters gathered from digital and handwritten sources. The hybrid model combines the merit of deep learning using convolutional neural networks (CNN) to involve feature extraction and a machine learning classifier using support vector machine (SVM). The dropout layer also manages overfitting problems and enhances training accuracy. For evaluation purposes, we also compared CNN models with three different architectures with multilayer perceptron (MLP) models with one and two hidden layer(s). In this research, we evaluated three variants of CNN architectures and the hybrid CNN-SVM models on both the accuracy of classification and training time. The experimental outcomes showed that the classification performances of all CNN models outperform the classification performances of both MLP models. The highest testing accuracy for basic CNN is 94.2% when using model 3 CNN. The increment of hidden layers to the MLP model just slightly enhances the accuracy. Furthermore, the hybrid model gained the highest accuracy result of 98.35% for classifying the testing data when combining model 3 CNN with the SVM classifier. We get that the hybrid CNN-SVM model can enhance the accuracy results in the Javanese characters recognition.
Co-Authors Azhari Azhari Dinar Nugroho Pratomo Lukman Awaludin Muhammad Rafif