arXiv subjects

Hung Cao

Publications and source records attributed to Hung Cao.

At least 37 records · Page 2Linked to original sources

arXiv2026

Towards Precision Cardiovascular Analysis in Zebrafish: The ZACAF Paradigm

Quantifying cardiovascular parameters like ejection fraction in zebrafish as a host of biological investigations has been extensively studied. Since current manual monitoring techniques are time-consuming and fallible, several image processing frameworks have been proposed to automate the process. Most of these works rely on supervised deep-learning architectures. However, supervised methods tend to be overfitted on their training dataset. This means that applying the same framework to new data with different imaging setups and mutant types can severely decrease performance. We have developed a Zebrafish Automatic Cardiovascular Assessment Framework (ZACAF) to quantify the cardiac function in zebrafish. In this work, we further applied data augmentation, Transfer Learning (TL), and Test Time Augmentation (TTA) to ZACAF to improve the performance for the quantification of cardiovascular function quantification in zebrafish. This strategy can be integrated with the available frameworks to aid other researchers. We demonstrate that using TL, even with a constrained dataset, the model can be refined to accommodate a novel microscope setup, encompassing diverse mutant types and accommodating various video recording protocols. Additionally, as users engage in successive rounds of TL, the model is anticipated to undergo substantial enhancements in both generalizability and accuracy. Finally, we applied this approach to assess the cardiovascular function in nrap mutant zebrafish, a model of cardiomyopathy.

eess.IV↗

arXiv2026

Adaptive Collaboration of Arena-Based Argumentative LLMs for Explainable and Contestable Legal Reasoning

Legal reasoning requires not only high accuracy but also the ability to justify decisions through verifiable and contestable arguments. However, existing Large Language Model (LLM) approaches, such as Chain-of-Thought (CoT) and Retrieval-Augmented Generation (RAG), often produce unstructured explanations that lack a formal mechanism for verification or user intervention. To address this limitation, we propose Adaptive Collaboration of Argumentative LLMs (ACAL), a neuro-symbolic framework that integrates adaptive multi-agent collaboration with an Arena-based Quantitative Bipolar Argumentation Framework (A-QBAF). ACAL dynamically deploys expert agent teams to construct arguments, employs a clash resolution mechanism to adjudicate conflicting claims, and utilizes uncertainty-aware escalation for borderline cases. Crucially, our framework supports a Human-in-the-Loop (HITL) contestability workflow, enabling users to directly audit and modify the underlying reasoning graph to influence the final judgment. Empirical evaluations on the LegalBench benchmark demonstrate that ACAL outperforms strong baselines across Gemini-2.5-Flash-Lite and Gemini-2.5-Flash architectures, effectively balancing efficient predictive performance with structured transparency and contestability. Our implementation is available at: https://github.com/loc110504/ACAL.

cs.MA↗

arXiv2026

SEval-NAS: A Search-Agnostic Evaluation for Neural Architecture Search

Neural architecture search (NAS) automates the discovery of neural networks that meet specified criteria, yet its evaluation procedures are often hardcoded, limiting the ability to introduce new metrics. This issue is especially pronounced in hardware-aware NAS, where objectives depend on target devices such as edge hardware. To address this limitation, we propose SEval-NAS, a metric-evaluation mechanism that converts architectures to strings, embeds them as vectors, and predicts performance metrics. Using NATS-Bench and HW-NAS-Bench, we evaluated accuracy, latency, and memory. Kendall's $τ$ correlations showed stronger latency and memory predictions than accuracy, indicating the suitability of SEval-NAS as a hardware cost predictor. We further integrated SEval-NAS into FreeREA to evaluate metrics not originally included. The method successfully ranked FreeREA-generated architectures, maintained search time, and required minimal algorithmic changes. Our implementation is available at: https://github.com/Analytics-Everywhere-Lab/neural-architecture-search

cs.LG↗

arXiv2025

Enhancing Alzheimer's Detection through Late Fusion of Multi-Modal EEG Features

Alzheimer s disease (AD) is a progressive neurodegenerative disorder characterized by cognitive decline, where early detection is essential for timely intervention and improved patient outcomes. Traditional diagnostic methods are time-consuming and require expert interpretation, thus, automated approaches are highly desirable. This study presents a novel deep learning framework for AD diagnosis using Electroencephalograph (EEG) signals, integrating multiple feature extraction techniques including alpha-wave analysis, Discrete Wavelet Transform (DWT), and Markov Transition Fields (MTF). A late-fusion strategy is employed to combine predictions from separate neural networks trained on these diverse representations, capturing both temporal and frequency-domain patterns in the EEG data. The proposed model attains a classification accuracy of 87.23%, with a precision of 87.95%, a recall of 86.91%, and an F1 score of 87.42% when evaluated on a publicly available dataset, demonstrating its potential for reliable, scalable, and early AD screening. Rigorous preprocessing and targeted frequency band selection, particularly in the alpha range due to its cognitive relevance, further enhance performance. This work highlights the promise of deep learning in supporting physicians with efficient and accessible tools for early AD diagnosis.

eess.SP↗

arXiv2025

Variational Quantum Rainbow Deep Q-Network for Optimizing Resource Allocation Problem

Resource allocation remains NP-hard due to combinatorial complexity. While deep reinforcement learning (DRL) methods, such as the Rainbow Deep Q-Network (DQN), improve scalability through prioritized replay and distributional heads, classical function approximators limit their representational power. We introduce Variational Quantum Rainbow DQN (VQR-DQN), which integrates ring-topology variational quantum circuits with Rainbow DQN to leverage quantum superposition and entanglement. We frame the human resource allocation problem (HRAP) as a Markov decision process (MDP) with combinatorial action spaces based on officer capabilities, event schedules, and transition times. On four HRAP benchmarks, VQR-DQN achieves 26.8% normalized makespan reduction versus random baselines and outperforms Double DQN and classical Rainbow DQN by 4.9-13.4%. These gains align with theoretical connections between circuit expressibility, entanglement, and policy quality, demonstrating the potential of quantum-enhanced DRL for large-scale resource allocation. Our implementation is available at: https://github.com/Analytics-Everywhere-Lab/qtrl/.

cs.AI↗

arXiv2025

Motion2Meaning: A Clinician-Centered Framework for Contestable LLM in Parkinson's Disease Gait Interpretation

AI-assisted gait analysis holds promise for improving Parkinson's Disease (PD) care, but current clinical dashboards lack transparency and offer no meaningful way for clinicians to interrogate or contest AI decisions. To address this issue, we present Motion2Meaning, a clinician-centered framework that advances Contestable AI through a tightly integrated interface designed for interpretability, oversight, and procedural recourse. Our approach leverages vertical Ground Reaction Force (vGRF) time-series data from wearable sensors as an objective biomarker of PD motor states. The system comprises three key components: a Gait Data Visualization Interface (GDVI), a one-dimensional Convolutional Neural Network (1D-CNN) that predicts Hoehn & Yahr severity stages, and a Contestable Interpretation Interface (CII) that combines our novel Cross-Modal Explanation Discrepancy (XMED) safeguard with a contestable Large Language Model (LLM). Our 1D-CNN achieves 89.0% F1-score on the public PhysioNet gait dataset. XMED successfully identifies model unreliability by detecting a five-fold increase in explanation discrepancies in incorrect predictions (7.45%) compared to correct ones (1.56%), while our LLM-powered interface enables clinicians to validate correct predictions and successfully contest a portion of the model's errors. A human-centered evaluation of this contestable interface reveals a crucial trade-off between the LLM's factual grounding and its readability and responsiveness to clinical feedback. This work demonstrates the feasibility of combining wearable sensor analysis with Explainable AI (XAI) and contestable LLMs to create a transparent, auditable system for PD gait interpretation that maintains clinical oversight while leveraging advanced AI capabilities. Our implementation is publicly available at: https://github.com/hungdothanh/motion2meaning.

cs.HC↗

arXiv2025

Investigation of Using Non-Contact Electrodes for Fetal ECG Monitoring

Regular physiological monitoring of maternal and fetal parameters is indispensable for ensuring safe outcomes during pregnancy and parturition. Fetal electrocardiogram (fECG) assessment is crucial to detect fetal distress and developmental anomalies. Given challenges of prenatal care due to the lack of medical professionals and the limit of accessibility, especially in remote and resource-poor areas, we develop a fECG monitoring system using novel non-contact electrodes (NCE) to record the fetal/maternal ECG (f/mECG) signals through clothes, thereby improving the comfort during measurement. The system is designed to be incorporated inside a maternity belt with data acquisition, data transmission module as well as novel NCEs. Thorough characterizations were carried out to evaluate the novel NCE against traditional wet electrodes (i.e., Ag/AgCl electrodes), showing comparable performance. A successful {preliminary pilot feasibility study} conducted with pregnant women (n = 10) between 25 and 32 weeks of gestation demonstrates the system's performance, usability and safety.

eess.SP↗

arXiv2025

SimInterview: Transforming Business Education through Large Language Model-Based Simulated Multilingual Interview Training System

Business interview preparation demands both solid theoretical grounding and refined soft skills, yet conventional classroom methods rarely deliver the individualized, culturally aware practice employers currently expect. This paper introduces SimInterview, a large language model (LLM)-based simulated multilingual interview training system designed for business professionals entering the AI-transformed labor market. Our system leverages an LLM agent and synthetic AI technologies to create realistic virtual recruiters capable of conducting personalized, real-time conversational interviews. The framework dynamically adapts interview scenarios using retrieval-augmented generation (RAG) to match individual resumes with specific job requirements across multiple languages. Built on LLMs (OpenAI o3, Llama 4 Maverick, Gemma 3), integrated with Whisper speech recognition, GPT-SoVITS voice synthesis, Ditto diffusion-based talking head generation model, and ChromaDB vector databases, our system significantly improves interview readiness across English and Japanese markets. Experiments with university-level candidates show that the system consistently aligns its assessments with job requirements, faithfully preserves resume content, and earns high satisfaction ratings, with the lightweight Gemma 3 model producing the most engaging conversations. Qualitative findings revealed that the standardized Japanese resume format improved document retrieval while diverse English resumes introduced additional variability, and they highlighted how cultural norms shape follow-up questioning strategies. Finally, we also outlined a contestable AI design that can explain, detect bias, and preserve human-in-the-loop to meet emerging regulatory expectations.

cs.CY↗

arXiv2025

Privacy-Preserving Multi-Stage Fall Detection Framework with Semi-supervised Federated Learning and Robotic Vision Confirmation

The aging population is growing rapidly, and so is the danger of falls in older adults. A major cause of injury is falling, and detection in time can greatly save medical expenses and recovery time. However, to provide timely intervention and avoid unnecessary alarms, detection systems must be effective and reliable while addressing privacy concerns regarding the user. In this work, we propose a framework for detecting falls using several complementary systems: a semi-supervised federated learning-based fall detection system (SF2D), an indoor localization and navigation system, and a vision-based human fall recognition system. A wearable device and an edge device identify a fall scenario in the first system. On top of that, the second system uses an indoor localization technique first to localize the fall location and then navigate a robot to inspect the scenario. A vision-based detection system running on an edge device with a mounted camera on a robot is used to recognize fallen people. Each of the systems of this proposed framework achieves different accuracy rates. Specifically, the SF2D has a 0.81% failure rate equivalent to 99.19% accuracy, while the vision-based fallen people detection achieves 96.3% accuracy. However, when we combine the accuracy of these two systems with the accuracy of the navigation system (95% success rate), our proposed framework creates a highly reliable performance for fall detection, with an overall accuracy of 99.99%. Not only is the proposed framework safe for older adults, but it is also a privacy-preserving solution for detecting falls.

cs.CV↗

arXiv2025

Multimedia Verification Through Multi-Agent Deep Research Multimodal Large Language Models

This paper presents our submission to the ACMMM25 - Grand Challenge on Multimedia Verification. We developed a multi-agent verification system that combines Multimodal Large Language Models (MLLMs) with specialized verification tools to detect multimedia misinformation. Our system operates through six stages: raw data processing, planning, information extraction, deep research, evidence collection, and report generation. The core Deep Researcher Agent employs four tools: reverse image search, metadata analysis, fact-checking databases, and verified news processing that extracts spatial, temporal, attribution, and motivational context. We demonstrate our approach on a challenge dataset sample involving complex multimedia content. Our system successfully verified content authenticity, extracted precise geolocation and timing information, and traced source attribution across multiple platforms, effectively addressing real-world multimedia verification scenarios.

cs.CV↗

arXiv2025

Heart2Mind: Human-Centered Contestable Psychiatric Disorder Diagnosis System using Wearable ECG Monitors

Psychiatric disorders affect millions globally, yet their diagnosis faces significant challenges in clinical practice due to subjective assessments and accessibility concerns, leading to potential delays in treatment. To help address this issue, we present Heart2Mind, a human-centered contestable psychiatric disorder diagnosis system using wearable electrocardiogram (ECG) monitors. Our approach leverages cardiac biomarkers, particularly heart rate variability (HRV) and R-R intervals (RRI) time series, as objective indicators of autonomic dysfunction in psychiatric conditions. The system comprises three key components: (1) a Cardiac Monitoring Interface (CMI) for real-time data acquisition from Polar H9/H10 devices; (2) a Multi-Scale Temporal-Frequency Transformer (MSTFT) that processes RRI time series through integrated time-frequency domain analysis; (3) a Contestable Diagnosis Interface (CDI) combining Self-Adversarial Explanations (SAEs) with contestable Large Language Models (LLMs). Our MSTFT achieves 91.7% accuracy on the HRV-ACC dataset using leave-one-out cross-validation, outperforming state-of-the-art methods. SAEs successfully detect inconsistencies in model predictions by comparing attention-based and gradient-based explanations, while LLMs enable clinicians to validate correct predictions and contest erroneous ones. This work demonstrates the feasibility of combining wearable technology with Explainable Artificial Intelligence (XAI) and contestable LLMs to create a transparent, contestable system for psychiatric diagnosis that maintains clinical oversight while leveraging advanced AI capabilities. Our implementation is publicly available at: https://github.com/Analytics-Everywhere-Lab/heart2mind.

cs.AI↗

arXiv2025

ODExAI: A Comprehensive Object Detection Explainable AI Evaluation

Explainable Artificial Intelligence (XAI) techniques for interpreting object detection models remain in an early stage, with no established standards for systematic evaluation. This absence of consensus hinders both the comparative analysis of methods and the informed selection of suitable approaches. To address this gap, we introduce the Object Detection Explainable AI Evaluation (ODExAI), a comprehensive framework designed to assess XAI methods in object detection based on three core dimensions: localization accuracy, faithfulness to model behavior, and computational complexity. We benchmark a set of XAI methods across two widely used object detectors (YOLOX and Faster R-CNN) and standard datasets (MS-COCO and PASCAL VOC). Empirical results demonstrate that region-based methods (e.g., D-CLOSE) achieve strong localization (PG = 88.49%) and high model faithfulness (OA = 0.863), though with substantial computational overhead (Time = 71.42s). On the other hand, CAM-based methods (e.g., G-CAME) achieve superior localization (PG = 96.13%) and significantly lower runtime (Time = 0.54s), but at the expense of reduced faithfulness (OA = 0.549). These findings demonstrate critical trade-offs among existing XAI approaches and reinforce the need for task-specific evaluation when deploying them in object detection pipelines. Our implementation and evaluation benchmarks are publicly available at: https://github.com/Analytics-Everywhere-Lab/odexai.

cs.CV↗

arXiv2025

One-transmitter Multiple-receiver Wireless Power Transfer System Using an Exceptional Point of Degeneracy

Robust transfer efficiency against the various operating conditions in a wireless power transfer system remains a fundamentally important challenge. This challenge becomes even more critical when transferring power to groups of inductively coupled receivers. We propose a method for efficient wireless power transfer to multiple receivers exploiting the concept of exceptional points of degeneracy (EPD) in a self-oscillating system. In previous studies based on PT symmetry, a receiver's operation has been divided into two strong and weak coupling regimes, and the power transfer efficiency is constant in the strong coupling regime when varying the coupling factor. Here, the concept of strong and weak coupling and constant power efficiency is extended to a system of multiple receivers that do not follow PT symmetry. The transmitter has saturable nonlinear gain and the EPD is analyzed when the system oscillates after reaching saturation. We show that the important feature to have a roughly constant power efficiency, independently of the positions of the receivers, is the existence of an EPD that separates the weak and strong regimes. Our proposed method demonstrates a system with less sensitivity to the coupling change than a conventional system without EPD when the receivers and their couplings to the transmitter are not necessarily identical.

physics.app-ph↗

arXiv2025

Encoded Spatial Attribute in Multi-Tier Federated Learning

This research presents an Encoded Spatial Multi-Tier Federated Learning approach for a comprehensive evaluation of aggregated models for geospatial data. In the client tier, encoding spatial information is introduced to better predict the target outcome. The research aims to assess the performance of these models across diverse datasets and spatial attributes, highlighting variations in predictive accuracy. Using evaluation metrics such as accuracy, our research reveals insights into the complexities of spatial granularity and the challenges of capturing underlying patterns in the data. We extended the scope of federated learning (FL) by having multi-tier along with the functionality of encoding spatial attributes. Our N-tier FL approach used encoded spatial data to aggregate in different tiers. We obtained multiple models that predicted the different granularities of spatial data. Our findings underscore the need for further research to improve predictive accuracy and model generalization, with potential avenues including incorporating additional features, refining model architectures, and exploring alternative modeling approaches. Our experiments have several tiers representing different levels of spatial aspects. We obtained accuracy of 75.62% and 89.52% for the global model without having to train the model using the data constituted with the designated tier. The research also highlights the importance of the proposed approach in real-time applications.

cs.LG↗

arXiv2024

XEdgeAI: A Human-centered Industrial Inspection Framework with Data-centric Explainable Edge AI Approach

Recent advancements in deep learning have significantly improved visual quality inspection and predictive maintenance within industrial settings. However, deploying these technologies on low-resource edge devices poses substantial challenges due to their high computational demands and the inherent complexity of Explainable AI (XAI) methods. This paper addresses these challenges by introducing a novel XAI-integrated Visual Quality Inspection framework that optimizes the deployment of semantic segmentation models on low-resource edge devices. Our framework incorporates XAI and the Large Vision Language Model to deliver human-centered interpretability through visual and textual explanations to end-users. This is crucial for end-user trust and model interpretability. We outline a comprehensive methodology consisting of six fundamental modules: base model fine-tuning, XAI-based explanation generation, evaluation of XAI approaches, XAI-guided data augmentation, development of an edge-compatible model, and the generation of understandable visual and textual explanations. Through XAI-guided data augmentation, the enhanced model incorporating domain expert knowledge with visual and textual explanations is successfully deployed on mobile devices to support end-users in real-world scenarios. Experimental results showcase the effectiveness of the proposed framework, with the mobile model achieving competitive accuracy while significantly reducing model size. This approach paves the way for the broader adoption of reliable and interpretable AI tools in critical industrial applications, where decisions must be both rapid and justifiable. Our code for this work can be found at https://github.com/Analytics-Everywhere-Lab/vqixai.

cs.CV↗

arXiv2024

High-Precision UWB-Based Real-Time Locating System for Rodent Behavioral Studies

Rodents have long been established as the premier model for behavioral studies, traditionally raised and maintained in conventional cage environments. However, these settings often limit rodents' ability to exhibit their full range of intrinsic behaviors and natural interactions. Precise tracking of animal movement is a critical component in behavioral research, but traditional methods, such as video tracking, present challenges, particularly with nocturnal species like rodents. This study introduces the application of ultra-wideband (UWB) sensor technology to develop a novel tracking system. The UWB DWM1001C sensor was integrated into a custom-made device worn by a single rat. A simplified habitat, measuring four-by-two feet, was used to evaluate system performance. The results show positioning accuracy errors of less than five millimeters for line-of-sight (LoS) and less than 50 millimeters for non-line-of-sight (NLoS) scenarios. This research provides a more accurate and reliable approach for animal localization, showcasing the potential of UWB sensor technology in enhancing precision in behavioral studies.

eess.IV↗

arXiv2024

MACeIP: A Multimodal Ambient Context-enriched Intelligence Platform in Smart Cities

This paper presents a Multimodal Ambient Context-enriched Intelligence Platform (MACeIP) for Smart Cities, a comprehensive system designed to enhance urban management and citizen engagement. Our platform integrates advanced technologies, including Internet of Things (IoT) sensors, edge and cloud computing, and Multimodal AI, to create a responsive and intelligent urban ecosystem. Key components include Interactive Hubs for citizen interaction, an extensive IoT sensor network, intelligent public asset management, a pedestrian monitoring system, a City Planning Portal, and a Cloud Computing System. We demonstrate the prototype of MACeIP in several cities, focusing on Fredericton, New Brunswick. This work contributes to innovative city development by offering a scalable, efficient, and user-centric approach to urban intelligence and management.

cs.AI↗

arXiv2024

An Adaptive Indoor Localization Approach Using WiFi RSSI Fingerprinting with SLAM-Enabled Robotic Platform and Deep Neural Networks

Indoor localization plays a vital role in the era of the IoT and robotics, with WiFi technology being a prominent choice due to its ubiquity. We present a method for creating WiFi fingerprinting datasets to enhance indoor localization systems and address the gap in WiFi fingerprinting dataset creation. We used the Simultaneous Localization And Mapping (SLAM) algorithm and employed a robotic platform to construct precise maps and localize robots in indoor environments. We developed software applications to facilitate data acquisition, fingerprinting dataset collection, and accurate ground truth map building. Subsequently, we aligned the spatial information generated via the SLAM with the WiFi scans to create a comprehensive WiFi fingerprinting dataset. The created dataset was used to train a deep neural network (DNN) for indoor localization, which can prove the usefulness of grid density. We conducted experimental validation within our office environment to demonstrate the proposed method's effectiveness, including a heatmap from the dataset showcasing the spatial distribution of WiFi signal strengths for the testing access points placed within the environment. Notably, our method offers distinct advantages over existing approaches as it eliminates the need for a predefined map of the environment, requires no preparatory steps, lessens human intervention, creates a denser fingerprinting dataset, and reduces the WiFi fingerprinting dataset creation time. Our method achieves 26% more accurate localization than the other methods and can create a six times denser fingerprinting dataset in one-third of the time compared to the traditional method. In summary, using WiFi RSSI Fingerprinting data surveyed by the SLAM-Enabled Robotic Platform, we can adapt our trained DNN model to indoor localization in any dynamic environment and enhance its scalability and applicability in real-world scenarios.

cs.RO↗