Article Per Year (5 Year)
p-Index From 2021 - 2026
0.408
P-Index
This Author published in this journals
All Journal Journal of Computer Science, Information Technology and Telecommunication Engineering (JCoSITTE) sudo Jurnal Teknik Informatika
Hane Yorda Dinata
Universitas Pendidikan Indonesia
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Electrical & Electronics Engineering Engineering

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

Found 2 Documents
Search

 1 
Optimized Hybrid CLDNN Architecture with Enhanced Temporal-Spatial Feature Extraction for Robust Automatic Modulation Classification in Cognitive Radio Networks Daryan Pratama Alifi; Hane Yorda Dinata; Galura Muhammad Suranegara; Ichwan Nul Ichsan
Journal of Computer Science, Information Technology and Telecommunication Engineering Vol 7, No 1 (2026)
Publisher : Universitas Muhammadiyah Sumatera Utara, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30596/jcositte.v7i1.28935

Abstract

Automatic Modulation Classification (AMC) is a pivotal technology for efficient spectrum management in future cognitive radio networks. While Deep Learning has advanced the field, standard Convolutional Neural Networks (CNN) often struggle to capture long-term temporal dependencies in signals affected by fading. This study proposes an Optimized Hybrid CLDNN architecture that integrates a "Wide-Kernel" CNN (k=7) for enhanced spatial feature extraction and a "High-Capacity" LSTM (100 units) for robust temporal modeling. Experimental validation using the RadioML 2016.10a dataset demonstrates that the proposed optimizations yield significant performance gains. Specifically, the model achieves a classification accuracy of 84.5% at 0 dB SNR, outperforming standard baselines in the critical transition regime. Furthermore, it reaches a peak accuracy of 92.4% at high SNR (+18 dB). A notable finding is the reduction of inter-class confusion between 16-QAM and 64-QAM, where the misclassification rate is suppressed to approximately 15%, confirming the architecture's effectiveness in resolving hierarchical modulation ambiguities in dynamic wireless environments.
Psychoacoustically-Weighted Adaptive Digital Filtering for Enhanced Speech Quality and Audio Size Efficiency Hane Yorda Dinata; Eldyana Citra Laksita
sudo Jurnal Teknik Informatika Vol. 5 No. 1 (2026): Edisi Maret
Publisher : Ilmu Bersama Center

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56211/sudo.v5i1.1373

Abstract

Balancing perceptual quality with computational efficiency remains challenging in speech enhancement systems. This research presents an adaptive filtering framework integrating psychoacoustic modeling with multi-stage noise reduction. The architecture combines spectral subtraction and Wiener filtering, modulated by Bark-scale perceptual weighting derived from critical band theory. Unlike conventional approaches, the system exploits frequency-dependent auditory sensitivity to concentrate processing on perceptually salient regions while reducing representation of masked components. Experimental validation across diverse acoustic conditions yielded an average SNR improvement of 4.2 dB over baseline techniques, with simultaneous 31.7% file size reduction through psychoacoustically-guided quantization. PESQ assessment produced a mean opinion score of 4.23, confirming excellent quality preservation. Convergence analysis revealed 23% faster adaptation attributed to perceptually-weighted cost functions. Robustness testing across white noise, babble, and environmental sounds demonstrated consistent performance with minimal variance, indicating strong generalization capability. These findings show that incorporating human auditory principles simultaneously improves perceptual quality, computational efficiency, and system adaptability—critical for bandwidth-constrained applications in mobile communications, streaming platforms, and assistive devices
Co-Authors Daryan Pratama Alifi Eldyana Citra Laksita Galura Muhammad Suranegara Ichwan Nul Ichsan