cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Dayat Kurniawan
Contact Email
Dayat Kurniawan
Phone
-
Journal Mail Official
redaksi@jurnalet.com
Editorial Address
-
Location
Kota adm. jakarta selatan,
Dki jakarta
INDONESIA
Jurnal Elektronika dan Telekomunikasi
Published by Lembaga Ilmu Pengetahuan Indonesia
ISSN : 14118289     EISSN : 25279955     DOI : -
Core Subject : Engineering,
Electrical & Electronics Engineering Engineering
Jurnal Elektronika dan Telekomunikasi (JET) is an open access, a peer-reviewed journal published by Research Center for Electronics and Telecommunication - Indonesian Institute of Sciences. We publish original research papers, review articles and case studies on the latest research and developments in the field of electronics, telecommunications, and microelectronics engineering. JET is published twice a year and uses double-blind peer review. It was first published in 2001.
Arjuna Subject : -
Articles 403 Documents
 37   38   39   40   41 
Bacterial Classification Using Deep Structured Convolutional Neural Network for Low Resource Data M Faizal Amri; Asri Rizki Yuliani; Dwi Esti Kusumandari; Artha Ivonita Simbolon; M. Ilham Rizqyawan; Ulfah Nadiya
Jurnal Elektronika dan Telekomunikasi Vol 23, No 1 (2023)
Publisher : National Research and Innovation Agency

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55981/jet.533

Abstract

Bacterial identification is an essential task in medical disciplines and food hygiene. The characteristics of bacteria can be examined under a microscope using culture techniques. However, traditional clinical laboratory culture methods require considerable work, primarily physical and manual effort. An automated process using deep learning technology has been widely used for increasing accuracy and decreasing working costs. In this paper, our research evaluates different types of existing deep CNN models for bacterial contamination classification when low-resource data are used. They are baseline CNN, GCNN, ResNet, and VGGNet. The performance of CNN models was also compared with the traditional machine learning method, including SIFT+SVM. The performance of the DIBaS dataset and our own collected dataset have been evaluated. The results show that VGGNet achieves the highest accuracy. In addition, data augmentation was performed to inflate the dataset. After fitting the model with augmented data, the results show that the accuracy increases significantly. This improvement is consistent in all models and both datasets.
Appendix Vol. 23 No. 1 Salita Ulitia Prini
Jurnal Elektronika dan Telekomunikasi Vol 23, No 1 (2023)
Publisher : National Research and Innovation Agency

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Oxygen Level System Development in WSN and IoT-Based Factory Rifki Muhendra; Aisyah Amin
Jurnal Elektronika dan Telekomunikasi Vol 23, No 1 (2023)
Publisher : National Research and Innovation Agency

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55981/jet.512

Abstract

The health of workers is essential to factory productivity. The lack of oxygen experienced by factory workers for a prolonged duration can disrupt the brain system. One solution to this problem is to build manufacturing facilities with well-maintained airflow, especially oxygen. The system can flow air from outside the factory into the factory based on the measurement of the oxygen level. In this research, an airflow system using the internet of things (IoT) and wireless sensor network (WSN) technology was developed to ensure no oxygen shortage in the factory space. The system comprises three main parts: an oxygen level sensor, a fan controller circuit, and a cloud-based communication system. The oxygen level sensor can measure the volume of oxygen in the factory room and is also connected to the fan controller to control the airflow to the radio-frequency (RF) communication factory room. Oxygen level monitoring data are also sent to the cloud server so that the condition of the factory space can be monitored remotely using internet computers and mobile devices. Performance tests that have been carried out show that the system can increase the oxygen level by 82% from its pre-installed condition. The system built is easy-to-install, low-power, and reliable, with a data loss value of only 1.67%. WSN implementation at the factory does not require a lot of wiring, thus making the system cheaper.

Page 41 of 41 | Total Record : 403

 37   38   39   40   41 

Filter by Year

2013 2023


Reset
Filter By Issues
All Issue Vol 23, No 1 (2023) Vol 22, No 2 (2022) Vol 22, No 1 (2022) Vol 21, No 2 (2021) Vol 21, No 1 (2021) Vol 20, No 2 (2020) Vol 20, No 1 (2020) Vol 19, No 2 (2019) Vol 19, No 1 (2019) Vol 18, No 2 (2018) Vol 18, No 2 (2018) Vol 18, No 1 (2018) Vol 18, No 1 (2018) Vol 17, No 2 (2017) Vol 17, No 2 (2017) Vol 17, No 1 (2017) Vol 17, No 1 (2017) Vol 16, No 2 (2016) Vol 16, No 2 (2016) Vol 16, No 1 (2016) Vol 16, No 1 (2016) Vol 15, No 2 (2015) Vol 15, No 2 (2015) Vol 15, No 1 (2015) Vol 15, No 1 (2015) Vol 14, No 2 (2014) Vol 14, No 2 (2014) Vol 14, No 1 (2014) Vol 14, No 1 (2014) Vol 13, No 2 (2013) Vol 13, No 2 (2013) Vol 13, No 1 (2013) Vol 13, No 1 (2013) Vol 01-12 (Printed Issues) More Issue