Article Per Year (5 Year)
p-Index From 2021 - 2026
1.879
P-Index
This Author published in this journals
All Journal TEKNIK INFORMATIKA JOIV : International Journal on Informatics Visualization Applied Information System and Management LUGAS Jurnal Komunikasi Data Science: Journal of Computing and Applied Informatics Jurnal Teknologi Terpadu Abdimas Galuh: Jurnal Pengabdian Kepada Masyarakat Jurnal Teknologi Informatika dan Komputer Jurnal Teknik Informatika
Asep Taufik Muharram
Politeknik Negeri Jakarta
Agriculture, Biological Sciences & Forestry Computer Science & IT Economics, Econometrics & Finance Electrical & Electronics Engineering Engineering Languange, Linguistic, Communication & Media Law, Crime, Criminology & Criminal Justice Nursing

Published : 12 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 12 Documents
Search

 1   2 
Design of Livestream Video System and Classification of Rice Disease Agustin, Maria; Hermawan, Indra; Arnaldy, Defiana; Muharram, Asep Taufik; Warsuta, Bambang
JOIV : International Journal on Informatics Visualization Vol 7, No 1 (2023)
Publisher : Society of Visual Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30630/joiv.7.1.1336

Abstract

One of the agricultural products which is an important aspect of the life of Indonesian people is rice. Rice disease has a devastating effect on rice production, while detecting rice diseases in real-time is still difficult. Therefore, this study designed a Livestream video system that is equipped with a rice disease Classification system. The Livestream system utilizes 4G network communication and is assisted by the WebSocket protocol to communicate in real-time and for the rice disease Classification system using YOLO algorithm. In addition, Livestream uses the raspberry pi camera V2 to take video stream data. In analyzing the performance of the Livestream system, four tests were carried out, namely: functionality test, connectivity test, classification performance test, and implementation performance test. The test was carried out using the wireshark and conky tools, while the classification training used 5447 images from the Huy Minh do dataset that he provided on the Kaggle website. The results show that all programs run well and get a good QoS value according to the index of the parameter results, it is also found that sending non-base64 can reduce the size of the data to approximately 200,000 bytes/s and the performance of the classification system is good because it has an average accuracy of 80% even though it is quite burdening the raspberry pi. This system can still be optimized and developed further to support research in the field of data transmission and the performance of machine learning in a microcontroller.
Deep Convolutional Neural Networks Transfer Learning Comparison on Arabic Handwriting Recognition System Masruroh, Siti Ummi; Syahid, Muhammad Fikri; Munthaha, Firman; Muharram, Asep Taufik; Putri, Rizka Amalia
JOIV : International Journal on Informatics Visualization Vol 7, No 2 (2023)
Publisher : Society of Visual Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30630/joiv.7.2.1605

Abstract

Around 27 languages and more than 420 million people worldwide use Arabic letters. That makes the Arabic language one of the most used languages. However, the Arabic language has a challenge, namely the difference in letters based on their position. Arabic handwriting recognition is important for various applications, such as education and communication. One example is during a pandemic when most education has turned digital, making recognizing students' Arabic handwriting difficult. This paper aims to create a model that can recognize Arabic handwriting by comparing several CNN architectures using transfer learning to classify Arabic, Hijja, and AHCD handwriting datasets. Transfer learning is a model that has been trained by previous datasets to other datasets and is suitable for use in models with small datasets because it can improve model accuracy even with small datasets. The datasets were split into 60%, 20%, and 20% for training, validation, and testing. Each model uses data augmentation and 50% dropout on a fully connected layer to reduce overfitting. Some of the CNN architectures used in this study to create Arabic writing recognition models are ResNet, DenseNet, VGG16, VGG19, InceptionV3, and MobileNet. The models were compiled and trained with various parameters. The best model achieved to classify AHCD and Hijja dataset is VGG16 with Adam optimizer and 0.0001 learning rate. Based on this research, it is expected to know the performance of the best model for classifying Arabic handwriting.
Co-Authors Abdurojak Abdurojak Abdurojak, Abdurojak Airlangga Yudiatama Alyassar, Nibras Anita Hidayati Ariawan Andi Suhandana Asep Erlan Maulana Davi Rama Fadillah Defiana Arnaldy Fadillah, Davi Rama Fawziyyah, Haniifah Firman Syah I Gusti Agung Komang Diafari Djuni Hartawan Iga Yusdisti Imam Syafganti INDRA HERMAWAN Jasmine, Syahda Afallia Maria Agustin Mauldy Laya Munthaha, Firman Noorlela Marcheta Pradiptyas, Ayres Putri, Rizka Amalia Rasyid, Muhammad Haikal Al Siti Ummi Masruroh Syahda Afallia Jasmine Syahid, Muhammad Fikri Thoyyibah T Warsuta, Bambang Yudiatama, Airlangga Yusdisti, Iga