Author name cluster

Tuan Nguyen

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

10 papers

2 author rows

JBHI Journal 2025 Journal Article

Deep Learning-Based Integrated System for Intraoperative Blood Loss Quantification in Surgical Sponges

Dang Nguyen
Minh Huu Nhat Le
Trung Q. Le
Chinyere Charles-Okezie
Michael J. Diaz
Cameron Sabet
Hung The Dang
Tuan Nguyen

Accurate quantification of intraoperative blood loss is crucial for enhancing patient safety and the success rate of surgeries. Traditional estimation techniques, mainly reliant on visual assessments, are prone to significant inaccuracies due to their subjective nature. This study introduces MDCare, an innovative deep learning-integrated system designed to substantially improve the precision of blood loss quantification using surgical sponges. By integrating advanced hardware components, including a mass sensor and webcam, with sophisticated algorithms like ResNet-18 and YOLOv4, MDCare achieves classification accuracy up to 96. 2% and sponge detection accuracies above 91% for both synthetic and real blood scenarios. The system processes images at 7. 4 frames per second, aligning with the exigent pace of surgical environments, thereby supporting surgeons with real-time, accurate blood loss data essential for timely and informed decision-making. The contributions of the paper are: (1) Demonstrating the application of advanced machine learning models in a critical clinical setting, achieving significantly higher accuracy in blood loss estimation compared to traditional methods; (2) Validating the system's efficacy in real-time surgical environments, thereby enhancing the decision-making process and potentially reducing postoperative complications; (3) Setting a new standard in surgical care by integrating a complex system into real-world clinical workflows, showcasing its adaptability and potential for widespread adoption. Future work will focus on expanding the dataset and refining the algorithms to ensure the MDCare system's robustness and adaptability across surgical settings. The findings underscore the potential of MDCare to automate and refine critical aspects of surgery, marking a significant advancement in surgical care.

Details DOI

IJCAI Conference 2025 Conference Paper

TRIKOP: Exploring Visual Prompting Paradigms for Multi-Grade Knee Osteoarthritis Classification on MRI Images

Hieu Phan
Hung Pham
Dat Nguyen
Khoa Le
Tuan Nguyen
Triet Tran
Tho Quan

Knee osteoarthritis (KOA) is a degenerative joint disease that significantly impacts quality of life. While transfer learning shows promise in medical imaging, its application to KOA diagnosis remains challenging due to medical data's unique characteristics. To address this, we propose TRIKOP, a framework leveraging Visual Prompting for KOA diagnosis on MRI. Our approach explores three prompt-generating strategies that extract clinically relevant information from input images. Each prompt type is encoded using a tailored method to integrate effectively into the Vision Transformer for optimal representation. Among them, the contrastive embedding prompting strategy achieves 63. 04% accuracy on the OAI dataset, surpassing prior studies. Moreover, TRIKOP produces attention maps highlighting diagnostically significant regions, improving model interpretability. This work highlights TRIKOP’s potential to improve AI-driven KOA diagnosis and clinical support.

PDF Details DOI

EAAI Journal 2024 Journal Article

Backdoor attacks and defenses in federated learning: Survey, challenges and future research directions

Thuy Dung Nguyen
Tuan Nguyen
Phi Le Nguyen
Hieu H. Pham
Khoa D. Doan
Kok-Seng Wong

Federated learning (FL) is an approach within the realm of machine learning (ML) that allows the use of distributed data without compromising personal privacy. In FL, it becomes evident that the training data among participants frequently exhibit heterogeneous distribution characteristics. This inherent heterogeneity poses a substantial challenge for the orchestration server as it strives to assess the reliability of each local model update. Due to this challenge, FL becomes susceptible to various potential risks, with the ominous backdoor attack standing out as one of the most menacing threats. Backdoor attacks involve the insertion of malicious functionality into a targeted model through poisoned updates from malicious clients. These attacks can cause the global model to misbehave on specific inputs while appearing normal in other instances. Although the backdoor attacks received significant attention for their potential impact on practical deep learning applications, their exploration within the realm of FL remains limited. This survey seeks to address this gap by offering an all-encompassing examination of prevailing backdoor attack tactics and defenses in the context of FL. We include an exhaustive analysis of diverse approaches to provide a comprehensive understanding of this intricate landscape. Furthermore, we also discuss the challenges and potential future directions for attacks and defenses in the context of FL.

Details DOI

NMR Workshop 2024 Conference Paper

Linear Algebraic Partial Evaluation of Logic Programs

Tuan Nguyen
Katsumi Inoue
Chiaki Sakama

In logic programming, partial evaluation performs unfolding rules of a program in advance to reduce the cost of inferencing steps. Recently, partial evaluation of logic programs has been implemented in vector spaces by computing the powers of matrix representations. It has been reported that linear algebraic partial evaluation substantially enhances the practical performance of linear algebraic methods for logic programming. However, most recent research has focused exclusively on 𝐴𝑛𝑑-rules, assuming that their dependency graph is acyclic. In this paper, we introduce cycle-resolving techniques to ensure that linear algebraic partial evaluation works effectively even with cycles in the program. Additionally, we demonstrate that linear algebraic partial evaluation can also be extended to accommodate 𝑂𝑟-rules. Moreover, we propose using eigendecomposition and Jordan normal form to conduct the partial evaluation in vector spaces. We compare the proposed techniques on a set of acyclic and cyclic logic programs to evaluate their effectiveness. It is shown that the iteration method for partial evaluation, especially with sparse format, is the most efficient one in general cases. However, the decomposition method has the potential for future research to leverage eigenvalues and eigenvectors of program matrices for reasoning with logic programming.

Details

IJCAI Conference 2021 Conference Paper

TIDOT: A Teacher Imitation Learning Approach for Domain Adaptation with Optimal Transport

Tuan Nguyen
Trung Le
Nhan Dam
Quan Hung Tran
Truyen Nguyen
Dinh Phung

Using the principle of imitation learning and the theory of optimal transport we propose in this paper a novel model for unsupervised domain adaptation named Teacher Imitation Domain Adaptation with Optimal Transport (TIDOT). Our model includes two cooperative agents: a teacher and a student. The former agent is trained to be an expert on labeled data in the source domain, whilst the latter one aims to work with unlabeled data in the target domain. More specifically, optimal transport is applied to quantify the total of the distance between embedded distributions of the source and target data in the joint space, and the distance between predictive distributions of both agents, thus by minimizing this quantity TIDOT could mitigate not only the data shift but also the label shift. Comprehensive empirical studies show that TIDOT outperforms existing state-of-the-art performance on benchmark datasets.

PDF Details DOI

AIJ Journal 2017 Journal Article

Robust planning with incomplete domain models

Tuan Nguyen
Sarath Sreedharan
Subbarao Kambhampati

Most current planners assume complete domain models and focus on generating correct plans. Unfortunately, domain modeling is a laborious and error-prone task, thus real world agents have to plan with incomplete domain models. While domain experts cannot guarantee completeness, often they are able to circumscribe the incompleteness of the model by providing annotations as to which parts of the domain model may be incomplete. In this paper, we study planning problems with incomplete domain models where the annotations specify possible preconditions and effects of actions. We show that the problem of assessing the quality of a plan, or its plan robustness, is #P-complete, establishing its equivalence with the weighted model counting problems. We present two approaches to synthesizing robust plans. While the method based on the compilation to conformant probabilistic planning is much intuitive, its performance appears to be limited to only small problem instances. Our second approach based on stochastic heuristic search works well for much larger problems. It aims to use the robustness measure directly for estimating heuristic distance, which is then used to guide the search. Our planning system, PISA, outperforms a state-of-the-art planner handling incomplete domain models in most of the tested domains, both in terms of plan quality and planning time. Finally, we also present an extension of PISA called C PISA that is able to exploit the available of past successful plan traces to both improve the robustness of the synthesized plans and reduce the domain modeling burden.

Details DOI

AAAI Conference 2013 Conference Paper

Model-Lite Case-Based Planning

Hankz Hankui Zhuo
Tuan Nguyen
Subbarao Kambhampati

There is increasing awareness in the planning community that depending on complete models impedes the applicability of planning technology in many real world domains where the burden of specifying complete domain models is too high. In this paper, we consider a novel solution for this challenge that combines generative planning on incomplete domain models with a library of plan cases that are known to be correct. While this was arguably the original motivation for case-based planning, most existing case-based planners assume (and depend on) from-scratch planners that work on complete domain models. In contrast, our approach views the plan generated with respect to the incomplete model as a “skeletal plan” and augments it with directed mining of plan fragments from library cases. We will present the details of our approach and present an empirical evaluation of our method in comparison to a state-of-the-art case-based planner that depends on complete domain models.

PDF Details

IJCAI Conference 2013 Conference Paper

Refining Incomplete Planning Domain Models through Plan Traces

Hankz Hankui Zhuo
Tuan Nguyen
Subbarao Kambhampati

Most existing work on learning planning models assumes that the entire model needs to be learned from scratch. A more realistic situation is that the planning agent has an incomplete model which it needs to reﬁne through learning. In this paper we propose and evaluate a method for doing this. Our method takes as input an incomplete model (with missing preconditions and effects in the actions), as well as a set of plan traces that are known to be correct. It outputs a “reﬁned” model that not only captures additional precondition/effect knowledge about the given actions, but also “macro actions”. We use a MAX-SAT framework for learning, where the constraints are derived from the executability of the given plan traces, as well as the preconditions/effects of the given incomplete model. Unlike traditional macro-action learners which use macros to increase the efﬁciency of planning (in the context of a complete model), our motivation for learning macros is to increase the accuracy (robustness) of the plans generated with the reﬁned model. We demonstrate the effectiveness of our approach through a systematic empirical evaluation.

PDF Details DOI

NeurIPS Conference 2013 Conference Paper

Synthesizing Robust Plans under Incomplete Domain Models

Tuan Nguyen
Subbarao Kambhampati
Minh Do

PDF Details

ICRA Conference 1997 Conference Paper

The BUGS "Basic UXO Gathering System" project for UXO clearance & mine countermeasures

Christopher K. DeBolt
Chris O'Donnell
Craig Freed
Tuan Nguyen

The objective of the Basic UXO Gathering System (BUGS) is to test, evaluate and demonstrate the use of distributed robotics in clearing unexploded submunitions and minefield neutralization. A team consisting of industry, universities, and the government is working together on the BUGS programme. We are concentrating on control methodologies required for multiple, autonomous robots working together to perform a practical and useful mission. The choice of architecture is important in selecting a system that is flexible enough to operate reliably and robustly in an unknown environment. This paper also addresses the current team efforts on the BUGS project.

Details