Hieu T. Nguyen

Dr. Hieu T. Nguyen


Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

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

Representative Publications

View All Publications
3 September 2020 in IEEE Access
Verified
Journal Article
Open access
YYYasin Yari
Yasin Yari
TNThuy V. Nguyen
Thuy V. Nguyen
HNHieu T. Nguyen
Hieu T. Nguyen
Deep learning, as one of the currently most popular computer science research trends, improves neural networks, which has more and deeper layers allowing higher abstraction levels and more accurate data-based. Although deep convolutional neural networks, as a deep learning algorithm, has recently achieved promising results in data analysis, the requirement for a large amount of data prevents its use in medical data analysis since it is challenging to obtain data from the medical field. Breast cancer is a common cancer in women. To diagnose this kind of cancer, breast cell shapes in histopathology images should be examined by senior pathologists. The number of pathologists per population in the world is not enough, especially in Africa, and human mistake may occur in diagnosis procedure. After the evaluation of deep learning methods and algorithms in breast histological data processing, we tried to improve the current systems’ accuracy. As a result, this study proposes two effective deep transfer learning-based models, which rely on pre-trained DCNN using a large collection of ImageNet dataset images that improve current state-of-the-art systems in both binary and multiclass classification. We transfer pre-trained weights of the ResNet50 and DesneNet121 on the Imagenet as initial weights and fine-tune these models with a deep classifier with data augmentation to detect various malignant and benign samples tissues in the two categories of binary classification and multiclass classification. The proposed models have been examined with optimized hyperparameters in magnification-dependent and magnification-independent classification modes. In the multiclass classification, the proposed system achieved up to 98% accuracy. As for binary classification, the proposed system provides up to 100% accuracy. The results outperform previous studies accuracies in all defined performance metrics in breast cancer CAD systems from histological images.

15 July 2021 in IEEE Access
Verified
Journal Article
Open access
HDHung N. Dang
Hung N. Dang
HNHieu T. Nguyen
Hieu T. Nguyen
TNThuy V. Nguyen
Thuy V. Nguyen
Nowadays, large-scale multiple-input multiple-output (LS-MIMO) with low-resolution analog-to-digital converters (ADCs) is a favorable transmission scheme for 5G and beyond wireless networks to reduce the power consumption of the radio frequency chains and to increase the network capacity. This paper derives the joint message-passing detection and decoding algorithm based on the double-layer graph for LS-MIMO communication systems with mixed-ADCs. The new protograph extrinsic information chart (PEXIT) algorithm is developed to analytically evaluate the performance of protograph low-density parity-check code under various mixed-ADC combinations and LS-MIMO configuration scenarios. The simulation results validate the accuracy of the proposed algorithm. Furthermore, our experiments show that the mixed-ADC system can achieve a significant power gain even when only one received antenna is equipped with high-resolution ADCs. It is observed that 4-bit or 5-bit resolution is an optimal choice for the high-resolution receive antennas. Interestingly, mixed-ADC systems with Ternay-ADCs generally provide significant gains at the cost of the increase in the average resolution by a fraction of a bit. There are specific scenarios where the Ternary-ADC-based system outperforms the 1-bit-ADC based system at the same or lower average resolution. In the particular case of 16 ×16 MIMO configuration where the number of low-resolution antennas is N L = 12 and the number of high-resolution antennas is N H = 4, the Ternary-ADC based system can obtain a power gain of about 2 dB at the frame error rate (FER) or bit error rate (BER) level of 10 -5 .

6 March 2020 in IEEE Access
Verified
Journal Article
Open access
HVHieu D. Vu
Hieu D. Vu
TNThuy V. Nguyen
Thuy V. Nguyen
DNDiep Nguyen
Diep Nguyen
HNHieu T. Nguyen
Hieu T. Nguyen
Protograph low-density parity-check (LDPC) codes and large-scale multi-input multi-output (LS-MIMO) systems have achieved great interest with various practical applications. However, how to effectively evaluate and design protograph LDPC codes for LS-MIMO systems remains a challenging yet critical problem, especially for low-latency applications. To solve that design challenge, the protograph extrinsic information transfer chart (PEXIT) algorithm for LS-MIMO systems, so-called LS-MIMO-PEXIT algorithm, is first derived based on the mutual information functions of messages that are passed on the joint MIMO detection and LDPC decoding graph. The proposed LS-MIMO-PEXIT algorithm plays a vital role in the optimization process of designing new protograph LDPC codes, tailored for LS-MIMO communications systems. Experiment results demonstrate that the analytical results based on the LS-MIMO-PEXIT algorithm are in good agreement with the simulation results under various input constraints, including the coding rate, the number of decoding iterations, and the LS-MIMO configuration. On top of that, the new protograph LDPC codes designed using our LS-MIMO-PEXIT algorithm achieve a coding gain from 0.2 dB at a low coding rate to 0.4 dB at a high coding rate in comparison with the state-of-the-art protograph codes in the literature. Additionally, we incorporate the practical design experience and the theoretical analysis of mutual functions into a two-step procedure to search for protograph LDPC codes that do not have error-floor behavior at frame error rate (FER) or bit error rate (BER) as low as 10-5 or 10-7, respectively. Together with the coding gain, the error-floor-free feature of the proposed protograph LDPC codes is vitally important for future wireless networks where the ultra-reliability is one of the critical requirements

20 June 2025 in IEEE Access
Verified
Journal Article
Open access
DHDuc Anh Hoang
Duc Anh Hoang
HNHieu T. Nguyen
Hieu T. Nguyen
TLThang N. Le
Thang N. Le
Low-resolution analog-to-digital converters (ADCs) offer a compelling approach to reducing power consumption and hardware complexity in large-scale multiple-input multiple-output (LS-MIMO) systems for next-generation wireless networks. However, aggressive quantization significantly increases detection complexity—particularly for high-order modulation schemes—due to elevated noise and interference. In this paper, we propose a novel framework that jointly detects and decodes signals in LS-MIMO systems employing superposition modulation and low-resolution ADCs. Our approach leverages a message-passing (MP) algorithm that decomposes each high-order symbol into multiple BPSK layers, enabling more tractable soft-interference cancellation and extrinsic information updates. To theoretically assess system performance, we further develop a modified Protograph Extrinsic Information Transfer (PEXIT) algorithm, which integrates the effects of MIMO fading, ADC quantization noise, and protograph LDPC decoding into a single analytical tool. This modified PEXIT accurately predicts the iterative decoding thresholds under varying antenna dimensions, ADC resolutions, and superposition weighting schemes, thus facilitating a systematic code and modulation design process. Extensive numerical results corroborate the analysis, demonstrating that equal-weight superposition modulation provides consistent performance gains over conventional equal-distance constellations, especially in low-to-moderate quantization scenarios. These findings highlight the importance of power allocation strategies for superposition modulation in practical LS-MIMO receivers with coarse quantizers. Overall, this work offers a unified perspective on superposition modulation, low-resolution ADCs, and advanced LDPC decoding, opening new avenues for designing energy-efficient and spectrally efficient communication systems suitable for 5G-and-beyond networks.

19 October 2023
Verified
Conference Paper
Closed access
DHDuc A. Hoang
Duc A. Hoang
TNThang Le Nhat
Thang Le Nhat
HDHung Dang
Hung Dang
HNHieu T. Nguyen
Hieu T. Nguyen
This paper presents Bussgang-based belief propagation (BP) detection for a large-scale multiple-input multiple-out (MIMO) communication system with one-bit analog-to-digital converters (ADCs). A closed-form presentation of the proposed receiver is derived using the Bussgang decomposition to model the non-linear effect of the one-bit ADC. The computer simulation results show that the Bussgang-based belief propagation detector outperforms the previous one, which was based on the additive noise model (AQNM).

1 May 2026
Verified
Book Chapter
Closed access
VBVan Kien Bui
Van Kien Bui
HNHieu T. Nguyen
Hieu T. Nguyen
TNTuan Anh Nguyen
Tuan Anh Nguyen
THTrong-Minh Hoang
Trong-Minh Hoang
APAnh Thu Pham
Anh Thu Pham