Gia Hy Nguyen

Mr. Gia Hy Nguyen

orcid

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
27 April 2023 in Algorithms
Verified
Journal Article
Open access
PDF file
GNGia Hy Nguyen
Gia Hy Nguyen
STSrikanth Thudumu
Srikanth Thudumu
HDHung Du
Hung Du
KMKon Mouzakis
Kon Mouzakis
RVRajesh Vasa
Rajesh Vasa
Several approaches have applied Deep Reinforcement Learning (DRL) to Unmanned Aerial Vehicles (UAVs) to do autonomous object tracking. These methods, however, are resource intensive and require prior knowledge of the environment, making them difficult to use in real-world applications. In this paper, we propose a Lightweight Deep Vision Reinforcement Learning (LDVRL) framework for dynamic object tracking that uses the camera as the only input source. Our framework employs several techniques such as stacks of frames, segmentation maps from the simulation, and depth images to reduce the overall computational cost. We conducted the experiment with a non-sparse Deep Q-Network (DQN) (value-based) and a Deep Deterministic Policy Gradient (DDPG) (actor-critic) to test the adaptability of our framework with different methods and identify which DRL method is the most suitable for this task. In the end, a DQN is chosen for several reasons. Firstly, a DQN has fewer networks than a DDPG, hence reducing the computational resources on physical UAVs. Secondly, it is surprising that although a DQN is smaller in model size than a DDPG, it still performs better in this specific task. Finally, a DQN is very practical for this task due to the ability to operate in continuous state space. Using a high-fidelity simulation environment, our proposed approach is verified to be effective.

11 October 2025 in Machine Learning with Applications
Verified
Journal Article
Open access
GNGia Hy Nguyen
Gia Hy Nguyen
STSrikanth Thudumu
Srikanth Thudumu
HDHung Du
Hung Du
RVRajesh Vasa
Rajesh Vasa
KMKon Mouzakis
Kon Mouzakis

25 May 2025
Verified
Conference Paper
Open access
QNQuoc-Toan Nguyen
Quoc-Toan Nguyen
GNGia Hy Nguyen
Gia Hy Nguyen
QTQuang-Hieu Tang
Quang-Hieu Tang
TTTien Truong
Tien Truong
VPVan-Tuan Pham
Van-Tuan Pham
DWDavid Williams-King
David Williams-King

23 January 2025 in arXiv
Verified
Preprint
Open access
PDF file
GNGia Hy Nguyen
Gia Hy Nguyen
BPBao Pham
Bao Pham
HDHung Du
Hung Du
STSrikanth Thudumu
Srikanth Thudumu
RVRajesh Vasa
Rajesh Vasa
KMKon Mouzakis
Kon Mouzakis
Object Tracking is essential for many computer vision applications, such as autonomous navigation, surveillance, and robotics. Unlike Passive Object Tracking (POT), which relies on static camera viewpoints to detect and track objects across consecutive frames, Active Object Tracking (AOT) requires a controller agent to actively adjust its viewpoint to maintain visual contact with a moving target in complex environments. Existing AOT solutions are predominantly single-agent-based, which struggle in dynamic and complex scenarios due to limited information gathering and processing capabilities, often resulting in suboptimal decision-making. Alleviating these limitations necessitates the development of a multi-agent system where different agents perform distinct roles and collaborate to enhance learning and robustness in dynamic and complex environments. Although some multi-agent approaches exist for AOT, they typically rely on external auxiliary agents, which require additional devices, making them costly. In contrast, we introduce the Collaborative System for Active Object Tracking (CSAOT), a method that leverages multi-agent deep reinforcement learning (MADRL) and a Mixture of Experts (MoE) framework to enable multiple agents to operate on a single device, thereby improving tracking performance and reducing costs. Our approach enhances robustness against occlusions and rapid motion while optimizing camera movements to extend tracking duration. We validated the effectiveness of CSAOT on various interactive maps with dynamic and stationary obstacles.

18 October 2023
Verified
Conference Paper
Closed access
GNGia Hy Nguyen
Gia Hy Nguyen
PTPhuoc Trinh
Phuoc Trinh
LNLe-Minh Nguyen
Le-Minh Nguyen
DCDuc Thanh Chau
Duc Thanh Chau
Analysis of sales meetings is vital in many businesses to obtain insights about clients' needs and evaluate sales representatives' performance. This paper introduces a sales meeting analysis prototype, Cinnalyst, which helps sales managers observe how their employees perform in client meetings. By conducting statistics from meetings in the past, it can reveal many important factors to improve sales efficiency. To automatically analyze the sales meeting content, the proposed system includes three modules: speaking party detection, conversational topic classification, and dialogue act classification. We demonstrate the performance of Cinnalyst in practical cases where users can experience the analyses of conversational topics and dialogue acts in sales meetings. A demonstration video is attached with this paper at https://youtu.be/d7toaexlB0E.

15 November 2025 in arXiv
Verified
Preprint
Open access
PDF file
HDHung Du
Hung Du
GNGia Hy Nguyen
Gia Hy Nguyen
STSrikanth Thudumu
Srikanth Thudumu
RVRajesh Vasa
Rajesh Vasa
KMKon Mouzakis
Kon Mouzakis
Connected and autonomous vehicles across land, water, and air must often operate in dynamic, unpredictable environments with limited communication, no centralized control, and partial observability. These real-world constraints pose significant challenges for coordination, particularly when vehicles pursue individual objectives. To address this, we propose a decentralized Multi-Agent Reinforcement Learning (MARL) framework that enables vehicles, acting as agents, to communicate selectively based on local goals and observations. This goal-aware communication strategy allows agents to share only relevant information, enhancing collaboration while respecting visibility limitations. We validate our approach in complex multi-agent navigation tasks featuring obstacles and dynamic agent populations. Results show that our method significantly improves task success rates and reduces time-to-goal compared to non-cooperative baselines. Moreover, task performance remains stable as the number of agents increases, demonstrating scalability. These findings highlight the potential of decentralized, goal-driven MARL to support effective coordination in realistic multi-vehicle systems operating across diverse domains.