Article Per Year (5 Year)
p-Index From 2019 - 2024
0.408
P-Index
This Author published in this journals
All Journal Jurnal Elektronika dan Telekomunikasi
Miftahushudur, Tajul
Unknown Affiliation
Electrical & Electronics Engineering Engineering

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
Infinite Latent Feature Selection Technique for Hyperspectral Image Classification Miftahushudur, Tajul; Ali Wael, Chaeriah Bin; Praludi, Teguh
Jurnal Elektronika dan Telekomunikasi Vol 19, No 1 (2019)
Publisher : Indonesian Institute of Sciences

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14203/jet.v19.32-37

Abstract

The classification process is one of the most crucial processes in hyperspectral imaging. One of the limitations in classification process using machine learning technique is its complexities, where hyperspectral image format has a thousand band that can be used as a feature for learning purpose. This paper presents a comparison between two feature selection technique based on probability approach that not only can tackle the problem, but also improve accuracy. Infinite Latent Feature Selection (ILFS) and Relief Techniques are implemented in a hyperspectral image to select the most important feature or band before applied in Support Vector Machine (SVM). The result showed ILFS technique can improve classification accuracy better than Relief (92.21% vs. 88.10%). However, Relief can extract less feature to reach its best accuracy with only 6 features compared with ILFS with 9.
COMPARISON STUDY OF TIME SYNCHRONIZATION IN NC-OFDM SYSTEMS BASED ON SYMMETRIC CORRELATOR Miftahushudur, Tajul; Suyoto, Suyoto
Jurnal Elektronika dan Telekomunikasi Vol 19, No 2 (2019)
Publisher : Indonesian Institute of Sciences

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14203/jet.v19.57-63

Abstract

NC-OFDM as one of the candidates for the Cognitive Radio (CR) system has many challenges in the synchronizing time. This is due to the frequency sharing which can cause Narrowband Interference (NBI), which causes a very significant time synchronization error. Large errors in time synchronization can reduce overall NCOFDM system performance. In this study, we evaluate the time synchronization performance of NC-OFDM systems on the multipath channel in the present of NBI. We provide an evaluation of the time synchronization performance by comparing the time synchronization algorithm that has a timing metric such as an impulse-like (Symmetric correlator). Here, we present three algorithms that use the symbol training to calculate the arrival time of the NC-OFDM symbol. The simulation conducted by considering the effects of multipath channel, Signal to Noise Ratio (SNR), Carrier Frequency Offset (CFO), and SIR (Signal to Interference Ratio). SIR is modeled with NBI. Algorithm performance is measured by MAE (Mean Absolute Error) and MSE (Mean Squared Error). Simulation results show that the autocorrelation-based method has very poor performance in MAE and MSE tests, so it is not suitable for NC-OFDMbased Cognitive Radio systems. The GLRT (Generalized Likelihood Ratio Test) method and Iterative Normalization method perform well in case the NC-OFDM Cognitive Radio systems.
Co-Authors Chaeriah Bin Ali Wael, Chaeriah Bin Suyoto Suyoto Teguh Praludi