Truong Son Nguyen

Mr. Truong Son Nguyen

orcid

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

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

Representative Publications

View All Publications
6 November 2025 in IEEE Sensors Journal
Verified
Journal Article
Closed access
TNTruong Son Nguyen
Truong Son Nguyen
JPJiwon Park
Jiwon Park
JSJae Kyu Suhr
Jae Kyu Suhr
This article proposes a lightweight 3-D object detection method that fuses light detection and ranging (LiDAR) and camera data for traffic monitoring. The proposed method is designed to run in real time on low-end edge devices, which is essential for surveillance scenarios involving large-scale edge deployments. This method transforms LiDAR and camera data into spatially aligned 2-D bird's-eye view (BEV) images and processes them using a two-stream 2-D convolutional neural network (CNN). This network separately extracts features from heterogeneous data using two backbones, fuses them based on cross-modal interaction with multiscale integration, and predicts 3-D bounding boxes by an extended Euler-region proposal network (E-RPN). In experiments, the proposed method was quantitatively evaluated on a public dataset and outperformed the previous method, CoopDet3D, achieving an mAP of 93.37%. Furthermore, its practicality was demonstrated on a low-end processor, the Qualcomm QCS610 system on chip (SoC), by inferring over 10 frames per second with only a 3.52 percentage point drop in mAP after simplification through pruning and quantization.

9 June 2025 in ETRI Journal
Verified
Journal Article
Closed access
TNTruong Son Nguyen
Truong Son Nguyen
HCHuy Nhat Cao
Huy Nhat Cao
MPMinh Trien Pham
Minh Trien Pham

6 October 2026 in Agriculture
Verified
Journal Article
Open access
PDF file
HHHung Quang Ha
Hung Quang Ha
HCHa Duc Chu
Ha Duc Chu
NCNguyễn Nguyên Chương
Nguyễn Nguyên Chương
TPTruong Trinh Phung
Truong Trinh Phung
TATouhidur Rahman Anik
Touhidur Rahman Anik
Lam-Son Phan TranLam-Son Phan Tran
Lam-Son Phan Tran
Fruit maturity and ripeness determine harvest timing, postharvest management, market quality, and consumer acceptance. Conventional assessments commonly depend on destructive physicochemical analyses or subjective visual inspection, which limits rapid and repeated evaluation across production and supply chains. This review synthesizes recent advances in non-destructive fruit maturity and ripeness assessment using machine vision, visible and near-infrared spectroscopy, hyperspectral and multispectral imaging, acoustic and mechanical techniques, electronic noses, and dielectric measurements. Particular attention is given to data preprocessing, feature extraction, chemometric modeling, conventional machine learning, and deep learning approaches used to associate sensor responses with firmness, soluble solids content, acidity, pigment composition, internal defects, and physiological stage. The reviewed evidence indicates that spectroscopy and imaging provide strong predictive performance, while multimodal sensing can improve reliability by combining complementary external and internal attributes. However, differences in cultivar, orchard conditions, instruments, sampling protocols, reference measurements, and validation strategies restrict model transferability and cross-study comparison. The review further identifies the gaps that most constrain deployment, which include the absence of standardized maturity definitions, the scarcity of multisite datasets with external validation, the limited reporting of explainable models and uncertainty estimates, and the few sensor-fusion systems tested under edge-deployment conditions.

13 November 2025
Verified
Book Chapter
Closed access
PDF file
HCHuy Nhat Cao
Huy Nhat Cao
TNTruong Son Nguyen
Truong Son Nguyen
MPMinh Trien Pham
Minh Trien Pham
DPDuy Hung Pham
Duy Hung Pham

27 February 2026 in IEEE Transactions on Automation Science and Engineering
Verified
Journal Article
Closed access
TNTruong Son Nguyen
Truong Son Nguyen
HCHuy-Nhat Cao
Huy-Nhat Cao
NTNguyen Huu Thai
Nguyen Huu Thai
MPMinh Trien Pham
Minh Trien Pham
Ensuring resilient operation in networked multi-robot systems is critical when both physical safety and wireless communication are challenged by environmental uncertainty or adversarial interference. This paper presents Communication-Aware Control Barrier Function (C-CBF), a scalable control framework that integrates probabilistic communication constraints into safety-critical control synthesis using Control Barrier Functions (CBFs). By modeling wireless degradation via Rician fading, we formulate a reception-aware constraint that is optimized jointly with inter-agent collision avoidance through local Quadratic Programs (QPs). Each robot computes its control input using only neighbor state information. A decoupled approximation of globally coupled constraints ensures real-time feasibility. Adaptive slack variables enable the system to remain feasible even under conflicting demands, enhancing robustness in complex environments. Simulation results demonstrate that C-CBF ensures safe and connected operation across large-scale, cluttered environments under severe fading conditions. A confidence-tightened variant guarantees forward invariance in probability under channel-model mismatch. This leads to graceful degradation of safety without additional runtime cost. This framework provides a scalable foundation for resilient multi-robot autonomy and can be integrated with distributed optimal control solvers in future work.

15 November 2026 in Smart Agricultural Technology
Verified
Journal Article
Open access
MVMinh-Trung Vu
Minh-Trung Vu
TNTruong Son Nguyen
Truong Son Nguyen
HTHoang-Thang Tran
Hoang-Thang Tran
HCHuy Nhat Cao
Huy Nhat Cao
MPMinh Trien Pham
Minh Trien Pham