arXiv subjects

Huy-Dung Han

Publications and source records attributed to Huy-Dung Han.

5 recordsLinked to original sources

arXiv2026

DeepTokenEEG Enhancing Mild Cognitive Impairment and Alzheimers Classification via Tokenized EEG Features

The detection of Alzheimers disease (AD) is considered crucial, as timely intervention can improve patient outcomes. Electroencephalogram (EEG)-based diagnosis has been recognized as a non-invasive, accessible, and cost-effective approach for AD detection; however, it faces challenges related to data availability, accuracy of modern deep learning methods, and the time-consuming nature of expert-based interpretation. In this study, a novel lightweight and high-performance model, DeepTokenEEG, was designed for the diagnosis of AD and the classification of EEG signals from AD patients, individuals with other neurological conditions, and healthy subjects. Unlike traditional heavy-weight models, DeepTokenEEG ultilizes spatial and temporal tokenizer that effectively captures AD-related biomarkers in both temporal and frequency domain with only 0.29 million paramaters. Trained in a combined dataset of 274 subjects, including 180 AD cases, and 94 healthy controls, the proposed method achieves a maximum recorded accuracy of 100% on specific frequency bands, representing an improvement of 1.41-15.35% over state-of-the-art methods on the same dataset. These results indicate the potential of DeepTokenEEG for early detection and screening of AD, with promising applicability for deployment due to its compact size.

cs.LG↗

arXiv2025

Enhancing Alzheimer's Detection through Late Fusion of Multi-Modal EEG Features

Alzheimer s disease (AD) is a progressive neurodegenerative disorder characterized by cognitive decline, where early detection is essential for timely intervention and improved patient outcomes. Traditional diagnostic methods are time-consuming and require expert interpretation, thus, automated approaches are highly desirable. This study presents a novel deep learning framework for AD diagnosis using Electroencephalograph (EEG) signals, integrating multiple feature extraction techniques including alpha-wave analysis, Discrete Wavelet Transform (DWT), and Markov Transition Fields (MTF). A late-fusion strategy is employed to combine predictions from separate neural networks trained on these diverse representations, capturing both temporal and frequency-domain patterns in the EEG data. The proposed model attains a classification accuracy of 87.23%, with a precision of 87.95%, a recall of 86.91%, and an F1 score of 87.42% when evaluated on a publicly available dataset, demonstrating its potential for reliable, scalable, and early AD screening. Rigorous preprocessing and targeted frequency band selection, particularly in the alpha range due to its cognitive relevance, further enhance performance. This work highlights the promise of deep learning in supporting physicians with efficient and accessible tools for early AD diagnosis.

eess.SP↗

arXiv2025

Investigation of Using Non-Contact Electrodes for Fetal ECG Monitoring

Regular physiological monitoring of maternal and fetal parameters is indispensable for ensuring safe outcomes during pregnancy and parturition. Fetal electrocardiogram (fECG) assessment is crucial to detect fetal distress and developmental anomalies. Given challenges of prenatal care due to the lack of medical professionals and the limit of accessibility, especially in remote and resource-poor areas, we develop a fECG monitoring system using novel non-contact electrodes (NCE) to record the fetal/maternal ECG (f/mECG) signals through clothes, thereby improving the comfort during measurement. The system is designed to be incorporated inside a maternity belt with data acquisition, data transmission module as well as novel NCEs. Thorough characterizations were carried out to evaluate the novel NCE against traditional wet electrodes (i.e., Ag/AgCl electrodes), showing comparable performance. A successful {preliminary pilot feasibility study} conducted with pregnant women (n = 10) between 25 and 32 weeks of gestation demonstrates the system's performance, usability and safety.

eess.SP↗

arXiv2016

A Convex Relaxation Approach to Higher-Order Statistical Approaches to Signal Recovery

In this work, we investigate an efficient numerical approach for solving higher order statistical methods for blind and semi-blind signal recovery from non-ideal channels. We develop numerical algorithms based on convex optimization relaxation for minimization of higher order statistical cost functions. The new formulation through convex relaxation overcomes the local convergence problem of existing gradient descent based algorithms and applies to several well-known cost functions for effective blind signal recovery including blind equalization and blind source separation in both single-input-single-output (SISO) and multi-input-multi-output (MIMO) systems. We also propose a fourth order pilot based cost function that benefits from this approach. The simulation results demonstrate that our approach is suitable for short-length packet data transmission using only a few pilot symbols.

cs.IT↗

arXiv2015

Cross-layer Chase Combining with Selective Retransmission, Analysis and Throughput Optimization for OFDM Systems

In this paper, we present bandwidth efficient retransmission method employong selective retransmission approach at modulation layer under orthogonal frequency division multiplexing (OFDM) signaling. Our proposed cross-layer design embeds a selective retransmission sublayer in physical layer (PHY) that targets retransmission of information symbols transmitted over poor quality OFDM sub-carriers. Most of the times, few errors in decoded bit stream result in packet failure at medium access control (MAC) layer. The unnecessary retransmission of good quality information symbols of a failed packet has detrimental effect on overall throughput of transceiver. We propose a cross-layer Chase combining with selective retransmission (CCSR) method by blending Chase combining at MAC layer and selective retransmission in PHY. The selective retransmission in PHY targets the poor quality information symbols prior to decoding, which results into lower hybrid automatic repeat reQuest (HARQ) retransmissions at MAC layer. We also present tight bit-error rate (BER) upper bound and tight throughput lower bound for CCSR method. In order to maximize throughput of the proposed method, we formulate optimization problem with respect to the amount of information to be retransmitted in selective retransmission. The simulation results demonstrate significant throughput gain of the proposed CCSR method as compared to conventional Chase combining method.

cs.IT↗