Quang Nhat Le
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Quang Nhat Le has a total of 36 co-authors. Here are the top co-authors by number of shared publications:
- Trung Quang Duong
Memorial University
11 shared publications - Octavia A. Dobre
Memorial University of Newfoundland
9 shared publications - Shanza Shakoor
Memorial University
5 shared publications - Berk Canberk
School of Computing, Engineering and Built Environment, Edinburgh Napier University, Edinburgh, U.K.
3 shared publications - Hyundong Shin
Kyung Hee University
3 shared publications - Van-Dinh Nguyen
School of Computer Science and Statistics, Trinity College Dublin, Dublin 2, Ireland
3 shared publications
Latest Publications
- 4 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (14) , 32185-32199
Secure Near-Field Location Division Multiple Access via Quantum-Classical Learning Workflow
This study realizes secure near-field location division multiple access through employing both a variational quantum circuit and a nature-inspired algorithm. With the escalating demands of the sixth generation (6G) and beyond, there is growing interest in using large numbers of antenna elements, making near-field communications more practical Seizing this opportunity, we leverage near-field communications for a distinct multiple access technique, termed location division multiple access (LDMA), which capitalizes on spatial orthogonality to distinguish users by both angle and distance. Nevertheless, relying on beamforming to direct signals to distinct users poses a clear physical-layer security risk: adversaries might eavesdrop on messages intended for legitimate users, prompting the need to optimize beamforming to enhance security while adhering to wireless systems’ constraints. To make matters worse, conventional approaches typically entail multiple matrix inversions, and the optimization problem is far from trivial to solve due to its non-convexity and NP-hardness. To this end, our solution leverages variational quantum circuits (VQC), motivated by the potential benefits offered by quantum computing. On top of that, we improve upon the existing VQC workflows by integrating a classical algorithm, particularly, the differential evolution algorithm, thereby reducing quantum computational resource demands while maintaining high exploration efficiency. We further investigate how different quantum circuit depths influence the balance between expressibility and convergence. Simulation results reveal that our proposed scheme consistently outperforms conventional benchmarks in terms of secrecy rates, while simultaneously satisfying quality-of-service (QoS) constraints and power allocation requirements.
- 4 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (14) , 32185-32199
Secure Near-Field Location Division Multiple Access via Quantum-Classical Learning Workflow
This study realizes secure near-field location division multiple access through employing both a variational quantum circuit and a nature-inspired algorithm. With the escalating demands of the sixth generation (6G) and beyond, there is growing interest in using large numbers of antenna elements, making near-field communications more practical Seizing this opportunity, we leverage near-field communications for a distinct multiple access technique, termed location division multiple access (LDMA), which capitalizes on spatial orthogonality to distinguish users by both angle and distance. Nevertheless, relying on beamforming to direct signals to distinct users poses a clear physical-layer security risk: adversaries might eavesdrop on messages intended for legitimate users, prompting the need to optimize beamforming to enhance security while adhering to wireless systems’ constraints. To make matters worse, conventional approaches typically entail multiple matrix inversions, and the optimization problem is far from trivial to solve due to its non-convexity and NP-hardness. To this end, our solution leverages variational quantum circuits (VQC), motivated by the potential benefits offered by quantum computing. On top of that, we improve upon the existing VQC workflows by integrating a classical algorithm, particularly, the differential evolution algorithm, thereby reducing quantum computational resource demands while maintaining high exploration efficiency. We further investigate how different quantum circuit depths influence the balance between expressibility and convergence. Simulation results reveal that our proposed scheme consistently outperforms conventional benchmarks in terms of secrecy rates, while simultaneously satisfying quality-of-service (QoS) constraints and power allocation requirements.
- 1 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Signal Processing
- Vol. 20 (4) , 607-621
Safeguarding Low-Altitude Integrated Sensing and Communications Networks via UAV-Mounted RIS
In this paper, we investigate secure transmission in an integrated sensing and communication-cell-free network with the help of a low-altitude uncrewed aerial vehicle-mounted reconfigurable intelligent surface (URIS). The dual-functional access points (APs) simultaneously transmit communication signals to serve legitimate users and emit sensing signal to sense the target, who also acts as a potential eavesdropper (Eve) to intercept the communication signals. To enhance security, the artificial noise (AN) is employed by APs to degrade the Eve's reception. We formulate a sum secrecy rate maximization problem that jointly optimizes the APs' transmit beamformings, AN covariance, RIS's phase shifts, and URIS trajectory. Due to the non-convex nature of the formulated problem, it is divided into three tractable subproblems and solved by an iterative alternating optimization algorithm that incorporates the majorization–minimization framework, semidefinite relaxation, and successive convex approximation techniques. Numerical results confirm that the proposed scheme significantly improves secrecy performance compared with baseline schemes without using AN, fixed RIS, and without deploying URIS.
- 1 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Signal Processing
- Vol. 20 (4) , 607-621
Safeguarding Low-Altitude Integrated Sensing and Communications Networks via UAV-Mounted RIS
In this paper, we investigate secure transmission in an integrated sensing and communication-cell-free network with the help of a low-altitude uncrewed aerial vehicle-mounted reconfigurable intelligent surface (URIS). The dual-functional access points (APs) simultaneously transmit communication signals to serve legitimate users and emit sensing signal to sense the target, who also acts as a potential eavesdropper (Eve) to intercept the communication signals. To enhance security, the artificial noise (AN) is employed by APs to degrade the Eve's reception. We formulate a sum secrecy rate maximization problem that jointly optimizes the APs' transmit beamformings, AN covariance, RIS's phase shifts, and URIS trajectory. Due to the non-convex nature of the formulated problem, it is divided into three tractable subproblems and solved by an iterative alternating optimization algorithm that incorporates the majorization–minimization framework, semidefinite relaxation, and successive convex approximation techniques. Numerical results confirm that the proposed scheme significantly improves secrecy performance compared with baseline schemes without using AN, fixed RIS, and without deploying URIS.
- 28 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Communications
- Vol. 74 (00906778) , 4278-4290
Weighted Sum Rate Maximization for RIS-Mounted UAV-Aided Cell-Free ISAC Systems
This paper considers the cell-free integrated sensing and communication (CF-ISAC) networks utilizing reconfigurable intelligent surface (RIS)-mounted uncrewed aerial vehicles (UAVs). We aim to maximize the sum of weighted sum rate within the whole ISAC period by jointly optimizing access points (APs)’ transmit beamformings, RISs’ phase shifts, user-RIS association, and UAVs’ locations. To deal with a highly complex non-convex optimization problem, we propose an alternating optimization solutions by decomposing the original problem into three subproblems. In particular, for optimizing APs’ transmit beamformings, RISs’ phase shifts, and user-RIS association, we convert the log-sum problem into a quadratically constrained quadratic programming problem using the Lagrangian dual principle and multi-ratio fractional programming. For optimizing UAVs’ locations, the successive convex approximation technique is used to transform it into a convex problem. Simulation results highlight the considerable performance advantage of the proposed network compared to benchmark schemes employing fixed RISs, without RIS-mounted UAVs (URISs), and collocated network with URISs.
- 28 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Communications
- Vol. 74 (00906778) , 4278-4290
Weighted Sum Rate Maximization for RIS-Mounted UAV-Aided Cell-Free ISAC Systems
This paper considers the cell-free integrated sensing and communication (CF-ISAC) networks utilizing reconfigurable intelligent surface (RIS)-mounted uncrewed aerial vehicles (UAVs). We aim to maximize the sum of weighted sum rate within the whole ISAC period by jointly optimizing access points (APs)’ transmit beamformings, RISs’ phase shifts, user-RIS association, and UAVs’ locations. To deal with a highly complex non-convex optimization problem, we propose an alternating optimization solutions by decomposing the original problem into three subproblems. In particular, for optimizing APs’ transmit beamformings, RISs’ phase shifts, and user-RIS association, we convert the log-sum problem into a quadratically constrained quadratic programming problem using the Lagrangian dual principle and multi-ratio fractional programming. For optimizing UAVs’ locations, the successive convex approximation technique is used to transform it into a convex problem. Simulation results highlight the considerable performance advantage of the proposed network compared to benchmark schemes employing fixed RISs, without RIS-mounted UAVs (URISs), and collocated network with URISs.
- Open Access
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of the Communications Society
- Vol. 7, 13071-13084
Self-Adaptive Differential Evolution-Based Inductance Optimization for Resonant Acoustic RIS in Underwater Communications
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of the Communications Society
- Vol. 7, 13071-13084
Open AccessSelf-Adaptive Differential Evolution-Based Inductance Optimization for Resonant Acoustic RIS in Underwater Communications
- Open Access
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of the Communications Society
- Vol. 7, 9816-9830
Channel Estimation and Relay Selection for Space–Air–Ground–Sea Integrated Networks
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of the Communications Society
- Vol. 7, 9816-9830
Open AccessChannel Estimation and Relay Selection for Space–Air–Ground–Sea Integrated Networks
- Open Access
- 11 November 2025
- Published by European Alliance for Innovation n.o. in EAI Endorsed Transactions on Industrial Networks and Intelligent Systems
- Vol. 13 (1)
Artificial Intelligence-Driven Early Prediction of Student Dropout and Academic Outcomes in Higher Education: A Comparative Study of Advanced Machine Learning Approaches
Student dropout in higher education remains a critical challenge with significant academic, social, and economic implications. Early identification of students at risk of dropout enables institutions to design timely and targeted interventions that support academic success and improve retention rates. This study proposes a machine learning (ML)–driven framework for the early prediction of student dropout and academic outcomes in higher education using a comprehensive, real-world dataset collected from a higher education institution. The prediction task is formulated as a multiclass classification problem with three outcomes: dropout, enrolled, and graduate. To evaluate the effectiveness of different modeling approaches, we conduct a comparative analysis of widely used ML algorithms, including Logistic Regression, Naïve Bayes, k-Nearest Neighbors, Support Vector Machine, Decision Trees, Random Forest (RF), AdaBoost, XGBoost, LightGBM, and CatBoost. Results indicate that ensemble models achieve the best performance. RF attains the highest test accuracy (0.7797) and ROC-AUC (OvR) (0.8919), while LightGBM yields the best Macro-F1 (0.7082). Feature importance analysis shows that early academic progress indicators (approved units and semester grades) are the strongest predictors, followed by selected administrative/contextual factors such as tuition-fee status and course. Overall, this study provides empirical evidence supporting the use of ML techniques as effective decision-support tools for higher education institutions. The proposed framework offers actionable insights for administrators and policymakers seeking to develop data-driven strategies aimed at reducing dropout rates, improving academic success, and promoting equitable access to educational opportunities.
- 11 November 2025
- Published by European Alliance for Innovation n.o. in EAI Endorsed Transactions on Industrial Networks and Intelligent Systems
- Vol. 13 (1)
Open AccessArtificial Intelligence-Driven Early Prediction of Student Dropout and Academic Outcomes in Higher Education: A Comparative Study of Advanced Machine Learning Approaches
Student dropout in higher education remains a critical challenge with significant academic, social, and economic implications. Early identification of students at risk of dropout enables institutions to design timely and targeted interventions that support academic success and improve retention rates. This study proposes a machine learning (ML)–driven framework for the early prediction of student dropout and academic outcomes in higher education using a comprehensive, real-world dataset collected from a higher education institution. The prediction task is formulated as a multiclass classification problem with three outcomes: dropout, enrolled, and graduate. To evaluate the effectiveness of different modeling approaches, we conduct a comparative analysis of widely used ML algorithms, including Logistic Regression, Naïve Bayes, k-Nearest Neighbors, Support Vector Machine, Decision Trees, Random Forest (RF), AdaBoost, XGBoost, LightGBM, and CatBoost. Results indicate that ensemble models achieve the best performance. RF attains the highest test accuracy (0.7797) and ROC-AUC (OvR) (0.8919), while LightGBM yields the best Macro-F1 (0.7082). Feature importance analysis shows that early academic progress indicators (approved units and semester grades) are the strongest predictors, followed by selected administrative/contextual factors such as tuition-fee status and course. Overall, this study provides empirical evidence supporting the use of ML techniques as effective decision-support tools for higher education institutions. The proposed framework offers actionable insights for administrators and policymakers seeking to develop data-driven strategies aimed at reducing dropout rates, improving academic success, and promoting equitable access to educational opportunities.