Ngoc Thanh Pham
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Ngoc Thanh Pham has a total of 48 co-authors. Here are the top co-authors by number of shared publications:
- Hai Xuan Le
International School, Vietnam National University, Hanoi, Vietnam
6 shared publications - Hieu Trinh
School of Engineering, Deakin University, Waurn Ponds, Geelong, VIC 3216, Australia
5 shared publications - Thai Dinh Kim
Vietnam National University, Hanoi
4 shared publications - Doan Dong Nguyen
Vietnam National University
3 shared publications - Manh Hung Do
Hanoi University of Science and Technology, Hanoi, Vietnam
3 shared publications - Amanullah Maung Than Oo
School of Engineering, Macquarie University, Sydney, NSW 2109, Australia
2 shared publications
Latest Publications
- Open Access
- 13 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 74030-74047
EfficientEndoSeg: A Lightweight YOLOv5-Based Framework for Endoscopic Surgical Instrument Segmentation and Skill-Related Motion Analysis
This study addresses the challenge of achieving accurate and real-time surgical instrument instance segmentation under strict computational constraints in minimally invasive surgery by proposing EfficientEndoSeg, a compact and high-throughput segmentation framework coupled with tool-tip analysis. Building on the You Only Look Once (YOLO) version 5 instance segmentation baseline, EfficientEndoSeg incorporates four targeted architectural refinements: the C3SG2 module combining GhostNetV2 and Swin Transformer components to enhance local–global representation, Ghost Convolution for parameter-efficient feature extraction, a Double-Attention (A2) block for contextual refinement, and Complete Intersection-over-Union–guided Soft Non-Maximum Suppression to improve robustness in crowded surgical scenes. The framework is systematically evaluated on an internally annotated extension of the m2cai16-tool dataset, comprising 5,249 endoscopic frames and 8,785 polygon-level annotations across seven instrument categories, which serves as a controlled benchmark for experimental validation. These architectural modifications reduce model parameters by 25% and increase inference throughput by 52.7%, while consistently improving recall and mean Average Precision across multiple Intersection-over-Union thresholds. The proposed model matches or surpasses recent YOLO version 7 to version 12 variants and remains competitive with transformer-based and two-stage frameworks, including SegFormer, ISINet, LETNet, Detectron2, and Mask R-CNN. In addition, a training-free tool-tip tracking module based on modified K3M skeletonization enables trajectory, heatmap, and usage analyses, facilitating qualitative skill-related motion assessment without additional learning overhead. Overall, EfficientEndoSeg delivers a reproducible, lightweight, and deployment-ready solution for segmentation-driven surgical scene understanding and instrument motion analysis.
- 13 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 74030-74047
Open AccessEfficientEndoSeg: A Lightweight YOLOv5-Based Framework for Endoscopic Surgical Instrument Segmentation and Skill-Related Motion Analysis
This study addresses the challenge of achieving accurate and real-time surgical instrument instance segmentation under strict computational constraints in minimally invasive surgery by proposing EfficientEndoSeg, a compact and high-throughput segmentation framework coupled with tool-tip analysis. Building on the You Only Look Once (YOLO) version 5 instance segmentation baseline, EfficientEndoSeg incorporates four targeted architectural refinements: the C3SG2 module combining GhostNetV2 and Swin Transformer components to enhance local–global representation, Ghost Convolution for parameter-efficient feature extraction, a Double-Attention (A2) block for contextual refinement, and Complete Intersection-over-Union–guided Soft Non-Maximum Suppression to improve robustness in crowded surgical scenes. The framework is systematically evaluated on an internally annotated extension of the m2cai16-tool dataset, comprising 5,249 endoscopic frames and 8,785 polygon-level annotations across seven instrument categories, which serves as a controlled benchmark for experimental validation. These architectural modifications reduce model parameters by 25% and increase inference throughput by 52.7%, while consistently improving recall and mean Average Precision across multiple Intersection-over-Union thresholds. The proposed model matches or surpasses recent YOLO version 7 to version 12 variants and remains competitive with transformer-based and two-stage frameworks, including SegFormer, ISINet, LETNet, Detectron2, and Mask R-CNN. In addition, a training-free tool-tip tracking module based on modified K3M skeletonization enables trajectory, heatmap, and usage analyses, facilitating qualitative skill-related motion assessment without additional learning overhead. Overall, EfficientEndoSeg delivers a reproducible, lightweight, and deployment-ready solution for segmentation-driven surgical scene understanding and instrument motion analysis.
- 8 January 2026
- Published by Springer Nature in The International Journal of Advanced Manufacturing Technology
- Vol. 142 (7-8) , 4229-4243
A fuzzy logic decoupling control approach for quality improvement in caustic soda systems using RTDS and 800xA SCADA with IEC 104 integration
- 8 January 2026
- Published by Springer Nature in The International Journal of Advanced Manufacturing Technology
- Vol. 142 (7-8) , 4229-4243
A fuzzy logic decoupling control approach for quality improvement in caustic soda systems using RTDS and 800xA SCADA with IEC 104 integration
- 26 October 2025
- Published by Springer Nature
- p. 272-283
Fuzzy Logic Controller Based Decoupler for Quality-Enhancing Thermal Mixing Tanks
- 26 October 2025
- Published by Springer Nature
- p. 272-283
Fuzzy Logic Controller Based Decoupler for Quality-Enhancing Thermal Mixing Tanks
- 27 August 2025
- Published by Springer Nature
- p. 145-155
Leveraging Large Language Models for Student Performance Predictions
- 27 August 2025
- Published by Springer Nature
- p. 145-155
Leveraging Large Language Models for Student Performance Predictions
- 5 June 2025
- Published by Springer Nature
- p. 356-369
Design Smart Factory Using RTDS and 800xA SCADA Based on IEC 60870-5-104
- 5 June 2025
- Published by Springer Nature
- p. 356-369
Design Smart Factory Using RTDS and 800xA SCADA Based on IEC 60870-5-104
- 5 June 2025
- Published by Springer Nature
- p. 324-335
Novel of Frequency Stabilizing Strategy for Delayed Smart Grids Incorporated Wind Turbines via Memorable Estimator
- 5 June 2025
- Published by Springer Nature
- p. 324-335
Novel of Frequency Stabilizing Strategy for Delayed Smart Grids Incorporated Wind Turbines via Memorable Estimator
- 20 March 2025
- Published by Wiley in International Journal of Robust and Nonlinear Control
- Vol. 35 (11) , 4497-4522
An Adaptive State Observer for the Autonomous Underwater Vehicles With Uncertainties by Utilising Neural Network
The article proposes a novel adaptive observer utilising a two‐hidden‐layer neural network to estimate the states, including positions, rotations and velocities in the North‐East‐Down (NED) reference frame, of Autonomous Underwater Vehicles (AUVs). The studied AUVs are characterised by uncertain and nonlinear mathematical models, as well as the effects of unknown environmental disturbances. In addition to the novelty of the observer's structure, a salient feature of the proposed observer lies in its ability to estimate accurately unmeasured states irrespective of the strong nonlinear output‐to‐state mapping of the AUVs and inaccurate output measurement. In terms of designing output‐feedback controllers, instead of proposing a particular controller, the class of output‐feedback controllers for the AUV system has been systematically investigated such that the stability of the closed‐loop AUV system is ensured when combined with the proposed observer. The efficacy of the proposed observer has been verified rigorously through theoretical analysis and simulation results.
- 20 March 2025
- Published by Wiley in International Journal of Robust and Nonlinear Control
- Vol. 35 (11) , 4497-4522
An Adaptive State Observer for the Autonomous Underwater Vehicles With Uncertainties by Utilising Neural Network
The article proposes a novel adaptive observer utilising a two‐hidden‐layer neural network to estimate the states, including positions, rotations and velocities in the North‐East‐Down (NED) reference frame, of Autonomous Underwater Vehicles (AUVs). The studied AUVs are characterised by uncertain and nonlinear mathematical models, as well as the effects of unknown environmental disturbances. In addition to the novelty of the observer's structure, a salient feature of the proposed observer lies in its ability to estimate accurately unmeasured states irrespective of the strong nonlinear output‐to‐state mapping of the AUVs and inaccurate output measurement. In terms of designing output‐feedback controllers, instead of proposing a particular controller, the class of output‐feedback controllers for the AUV system has been systematically investigated such that the stability of the closed‐loop AUV system is ensured when combined with the proposed observer. The efficacy of the proposed observer has been verified rigorously through theoretical analysis and simulation results.
- 11 March 2025
- Published by Springer Nature
- p. 556-565
A Study on Fuzzy Logic-Based Adaptive Controller for 3-Wheeled Mobile Robot
- 11 March 2025
- Published by Springer Nature
- p. 556-565
A Study on Fuzzy Logic-Based Adaptive Controller for 3-Wheeled Mobile Robot
- 17 December 2024
- Published by Springer Nature
- p. 227-237
Short-Term Electricity Demand Forecast Leveraging Google Trends Data Toward Smart Green Energy Supply
- 17 December 2024
- Published by Springer Nature
- p. 227-237
Short-Term Electricity Demand Forecast Leveraging Google Trends Data Toward Smart Green Energy Supply
- Open Access
- 1 June 2024
- Published by Institute of Advanced Engineering and Science in Indonesian Journal of Electrical Engineering and Computer Science
- Vol. 34 (3) , 1582-1592
Plant pathology identification using local-global feature level based on transformer
Deep learning plays a crucial role in addressing the challenge of plant disease identification in the field of agriculture. Detecting diseases in plants requires extensive effort, along with a comprehensive understanding of various plant diseases and increased processing time. Balancing both speed and accuracy in predicting leaf diseases in plants can significantly improve crop production and reduce environmental damage. In this paper, we examined deseases on popular plants in agriculture. We proposed a novel model to predict crop pathology on a feature space of global-local based on transformer aggregation. Paticular, we use refined feature of different layer to correlate semantics from high-level feature and low-level feature. Besides, to capture the extended temporal scale across the entire image, we employ a transformer to discern long-range dependencies among frames. Subsequently, the enhanced features incorporating these dependencies are inputted into a classifier for preliminary crop pathology prediction. The plant village dataset and VietNam strawberry disease (VNStr) dataset were utilized for training and disease classification in the experiments. Extensive experiments show that the proposed method outperforms by 99.18% and 94.05% accuracy in plant village and VNStr, respectivly. The model after being judged was applied on Android devices and therefore is easy to use.
- 1 June 2024
- Published by Institute of Advanced Engineering and Science in Indonesian Journal of Electrical Engineering and Computer Science
- Vol. 34 (3) , 1582-1592
Open AccessPlant pathology identification using local-global feature level based on transformer
Deep learning plays a crucial role in addressing the challenge of plant disease identification in the field of agriculture. Detecting diseases in plants requires extensive effort, along with a comprehensive understanding of various plant diseases and increased processing time. Balancing both speed and accuracy in predicting leaf diseases in plants can significantly improve crop production and reduce environmental damage. In this paper, we examined deseases on popular plants in agriculture. We proposed a novel model to predict crop pathology on a feature space of global-local based on transformer aggregation. Paticular, we use refined feature of different layer to correlate semantics from high-level feature and low-level feature. Besides, to capture the extended temporal scale across the entire image, we employ a transformer to discern long-range dependencies among frames. Subsequently, the enhanced features incorporating these dependencies are inputted into a classifier for preliminary crop pathology prediction. The plant village dataset and VietNam strawberry disease (VNStr) dataset were utilized for training and disease classification in the experiments. Extensive experiments show that the proposed method outperforms by 99.18% and 94.05% accuracy in plant village and VNStr, respectivly. The model after being judged was applied on Android devices and therefore is easy to use.