Kien Trung Luong
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Kien Trung Luong has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Anh Tuan Tran
SAP Innovation Lab, FPT University, Vietnam
1 shared publication - Ban Quy Tran
Department of Computing Fundamentals, FPT University, Hanoi, Vietnam
1 shared publication - Hung Viet Nguyen
FPT University, Hanoi, Vietnam
1 shared publication - Minh Quang Dang
FPT University, Hanoi, Vietnam
1 shared publication Ngoc Le
FPT University, Hanoi, Vietnam
1 shared publicationPhuong Anh Nguyen
FPT University, Hanoi, Vietnam
1 shared publication
Latest Publications
- Open Access
- 10 April 2026
- Published by International Association of Online Engineering (IAOE) in International Journal of Online and Biomedical Engineering (iJOE)
- Vol. 22 (04) , 43–61
Smart Medical Robots: Dynamic LLM Routing for Question-Answering Systems
Inefficient non-clinical information delivery in medical centers burdens patients and staff, despite the potential of LLM-enhanced humanoid robots. Practical deployment faces critical hurdles: high cloud-LLM latencies, on-robot computational limits, and lacking secure, distributed knowledge sharing under strict privacy regulations. This paper introduces Dynamic LLM Routing for Smart Medical Robots, a framework designed for clinical question-answering systems. Our hybrid edge-cloud architecture integrates three core innovations: a dynamic LLM selection mechanism routing queries based on context (complexity, domain, and urgency), an optimized edge computing layer for privacy-preserving local processing, and an intelligent, privacy-preserving caching system enabling secure knowledge sharing and continuous learning. Evaluated on 7,500 authentic hospital queries, our system achieved a 50% reduction in average response latency (0.62s vs. 1.23s), an 89.7% completion rate, and a 62% reduction in external data transmission (73% cache hit rate). These results demonstrate our framework’s efficacy in enabling scalable, efficient, and privacy-compliant AI-powered humanoid robots for critical healthcare information delivery.
- 10 April 2026
- Published by International Association of Online Engineering (IAOE) in International Journal of Online and Biomedical Engineering (iJOE)
- Vol. 22 (04) , 43–61
Open AccessSmart Medical Robots: Dynamic LLM Routing for Question-Answering Systems
Inefficient non-clinical information delivery in medical centers burdens patients and staff, despite the potential of LLM-enhanced humanoid robots. Practical deployment faces critical hurdles: high cloud-LLM latencies, on-robot computational limits, and lacking secure, distributed knowledge sharing under strict privacy regulations. This paper introduces Dynamic LLM Routing for Smart Medical Robots, a framework designed for clinical question-answering systems. Our hybrid edge-cloud architecture integrates three core innovations: a dynamic LLM selection mechanism routing queries based on context (complexity, domain, and urgency), an optimized edge computing layer for privacy-preserving local processing, and an intelligent, privacy-preserving caching system enabling secure knowledge sharing and continuous learning. Evaluated on 7,500 authentic hospital queries, our system achieved a 50% reduction in average response latency (0.62s vs. 1.23s), an 89.7% completion rate, and a 62% reduction in external data transmission (73% cache hit rate). These results demonstrate our framework’s efficacy in enabling scalable, efficient, and privacy-compliant AI-powered humanoid robots for critical healthcare information delivery.
- Open Access
- 4 March 2025
- Published by Association for Computing Machinery (ACM)
- p. 25-40
Neural Radiance Field Reconstruction in Complex Scenes Without Camera Parameter Dependency
- 4 March 2025
- Published by Association for Computing Machinery (ACM)
- p. 25-40
Open AccessNeural Radiance Field Reconstruction in Complex Scenes Without Camera Parameter Dependency
- Open Access
- 23 February 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-7
Improvement for Large-Scale Image Data using Fuzzy Rough C-Mean Based Unsupervised CNN Clustering: An Empirical Study on designbyhumans.com
Clustering analysis, specifically for extensive image data, is increasingly being applied in various fields such as finance, risk management, prediction, etc., and has been a fascinating subject in many scientific discussions. Deep learning, a widely used approach, and classical methods address complex classification problems stemming from real-world cases. In this study, we took various approaches to classification problems and measured their effectiveness by combining different techniques using the results of different scenarios. Many approaches have been proposed to solve the clustering problem; complex clustering methods such as hierarchical, density-based, centroid-based, and graph theoretical have been submitted. However, when it comes to real-world applications, they exposed significant drawbacks when the dataset introduced immeasurable vagueness, uncertainty, or overlapping samples that made it impossible to predict and classify. Several attempts have been made to improve the clustering method's performance, including joint CNN clustering models. Still, many of them carry the cons of the complicated clustering method, which limits the capability of CNN. The combined CNN clustering method is designed to address the problem with those deterministic CNN clustering models and was evaluated on a dataset we collected from the website designbyhumans.com, with enough features to represent a non-synthetic dataset. This research aims to improve upon the established model by using estimation techniques in determining model parameters and graphing plots to justify those choices and give insights into how the model performs on a non-synthetic dataset like ours. We concluded that the model significantly improved compared with a popular complex clustering method, which has been evaluated by computational time, using different metrics to represent how better separated each cluster was. Based on conducted experiments and the future development of the method, we discussed and addressed some of the drawbacks of this approach.
- 23 February 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-7
Open AccessImprovement for Large-Scale Image Data using Fuzzy Rough C-Mean Based Unsupervised CNN Clustering: An Empirical Study on designbyhumans.com
Clustering analysis, specifically for extensive image data, is increasingly being applied in various fields such as finance, risk management, prediction, etc., and has been a fascinating subject in many scientific discussions. Deep learning, a widely used approach, and classical methods address complex classification problems stemming from real-world cases. In this study, we took various approaches to classification problems and measured their effectiveness by combining different techniques using the results of different scenarios. Many approaches have been proposed to solve the clustering problem; complex clustering methods such as hierarchical, density-based, centroid-based, and graph theoretical have been submitted. However, when it comes to real-world applications, they exposed significant drawbacks when the dataset introduced immeasurable vagueness, uncertainty, or overlapping samples that made it impossible to predict and classify. Several attempts have been made to improve the clustering method's performance, including joint CNN clustering models. Still, many of them carry the cons of the complicated clustering method, which limits the capability of CNN. The combined CNN clustering method is designed to address the problem with those deterministic CNN clustering models and was evaluated on a dataset we collected from the website designbyhumans.com, with enough features to represent a non-synthetic dataset. This research aims to improve upon the established model by using estimation techniques in determining model parameters and graphing plots to justify those choices and give insights into how the model performs on a non-synthetic dataset like ours. We concluded that the model significantly improved compared with a popular complex clustering method, which has been evaluated by computational time, using different metrics to represent how better separated each cluster was. Based on conducted experiments and the future development of the method, we discussed and addressed some of the drawbacks of this approach.