Candra Nur Ihsan

Candra Nur Ihsan

Auto-generated profile, based on publicly available information

Candra Nur Ihsan

Research Center for Artificial Intelligence and Cyber Security, National Research and Innovation Agency, Bandung, Indonesia

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
13 January 2024 in Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi)
Verified
Journal Article
Open access
PDF file
CICandra Nur Ihsan
Candra Nur Ihsan
NANova Agustina
Nova Agustina
MNMuchammad Naseer
Muchammad Naseer
HGHarya Gusdevi
Harya Gusdevi
JRJack Febrian Rusdi
Jack Febrian Rusdi
FAFahmi Abdullah
Fahmi Abdullah
Tea is one of the top ten export products sent from Indonesia to foreign countries. However, in recent years, the amount of tea leaf exports from Indonesia has decreased, although the value of the export impacts the country’s economic structure. In addition to market competition, Indonesia must maintain tea leaf production so that the increase in export decline is not significant or even increases tea leaf export production. To improve production quality and reduce production costs, early detection of tea leaf diseases is necessary. This study aims to classify tea leaf images for early detection of tea leaf disease so that appropriate treatment can be carried out early. This study compares machine learning algorithms to determine the best algorithm for detecting tea leaf diseases. The algorithms tested as performance comparisons in classifying tea leaf diseases are random forest (RF), support vector classifier (SVC), extra tree classifier (ETC), decision tree (DT), XGBoost classifier (XGB), and convolutional neural algorithms. Network (CNN). As a result, the average accuracy performance generated by ETC produces a higher value than other algorithms, i.e., getting an average accuracy performance of 77.47%. Another algorithm, SVC, has an average accuracy of 76.57%, RF of 76.12%, DT of 65.31%, XGB of 71.62%, and the lowest is CNN of 59.08%. ETC has been proven to be the most superior machine learning algorithm for detecting tea leaf diseases in this study.

14 July 2024 in Kuwait Journal of Science
Verified
Journal Article
Open access
ISIis Sofiati
Iis Sofiati
ANAmalia Nurlatifah
Amalia Nurlatifah
Erma YulihastinErma Yulihastin
Erma Yulihastin
CICandra Nur Ihsan
Candra Nur Ihsan
SWSigit Kurniawan Jati Wicaksana
Sigit Kurniawan Jati Wicaksana
HSHaries Satyawardhana
Haries Satyawardhana

10 September 2025 in Journal of King Saud University – Engineering Sciences
Verified
Journal Article
Open access
PDF file
ARAde Ramdan
Ade Ramdan
VZVicky Zilvan
Vicky Zilvan
AYAsri Rizki Yuliani
Asri Rizki Yuliani
HPHilman Pardede
Hilman Pardede
AHAna Hadiana
Ana Hadiana
BSBambang Sugiarto
Bambang Sugiarto
A Green World Campaign using batteries focuses on powering environmentally friendly initiatives and promoting sustainable practices. As a result, demand for lithium-ion batteries (LIB) has continued to increase over the last decade. The battery is used ubiquitously in daily life, including consumer electronics, portable devices, and electric vehicles. However, they have safety and performance concerns related to their end-of-life (EOL). Once the battery has reached its EOL, its capacity is prone to leaking, causing the battery cells to lose their capacity more rapidly. As a consequence, they need to be charged more often. Moreover, the leaks could cause short circuits, leading to serious accidents, such as fires and even explosions. This condition can be prevented by forecasting the remaining useful life of the battery. An accurate battery life prediction system monitors the remaining life of LIBs and provides an early warning when the battery is nearing its EOL. In this paper, we propose a system that utilizes a Gated Convolutional Neural Network (GCNN) with a Convolutional Block Attention Module (CBAM) to predict the remaining useful life of LIBs. We evaluated the method on two datasets: NASA and CALCE. The experimental results show that our proposed method enhances prediction accuracy by reducing the prediction error by 30.51% for RMSE and 37.38% for MAPE on the NASE dataset. Conversely, the reduction in prediction error on the CALCE datasets was 30.31% for RMSE and 38.43% for MAPE.

22 November 2022
Verified
Conference Paper
Open access
RYRaden Sandra Yuwana
Raden Sandra Yuwana
RARuth Andini
Ruth Andini
HPHilman Pardede
Hilman Pardede
WSWinita Sulandari
Winita Sulandari
ESEndang Suryawati
Endang Suryawati
ASAhmad Afif Supianto
Ahmad Afif Supianto
The number of medical abbreviations in the world is due to the increasing number of diseases, technological advances in the medical field, research in the medical field, and the emergence of various drugs. A large number of medical abbreviations often have the same abbreviation but it has a different meaning. The similarity of these medical abbreviations often results in ambiguous abbreviations. The ambiguity of this abbreviation can be reduced by creating a system based on Artificial Intelligent (AI). In this paper, we have compared various models using Naive Bayes, LSTM, Logistic Regression, and SVM to get the best model for medical abbreviations disambiguation. The experimental results indicate that the highest model accuracy is obtained by LSTM model, which is at 97.21%.