arXiv subjects

Xiaojun Wang

Publications and source records attributed to Xiaojun Wang.

At least 19 recordsLinked to original sources

arXiv2026

Towards Precision Therapy in Hepatocellular Carcinoma: A Clinical-Reasoning LLM for Risk Stratification and Treatment Guidance

Hepatocellular carcinoma (HCC) is a common malignancy and a leading cause of cancer-related mortality. Current guidelines and staging systems provide coarse categories, but often miss within-stage heterogeneity and the clinical context in electronic medical records (EMRs). We present HCC-STAR (Hepatocellular Carcinoma Staging, Treatment And pRognosis), a clinically aligned large language model that reads routine EMR narratives and jointly outputs risk score-based staging, ranked guideline-consistent treatments with evidence-based rationales, and individualized survival estimates. We curated about 30,000 HCC cases from SEER and expanded them into EMR-style narrative training data using a clinician-validated, prompt-based augmentation workflow. On this corpus, we developed a knowledge-aligned reasoning framework optimized with a step-verifiable composite reward, moving beyond text-level memorization of clinical guidelines. In a multi-center cohort of 6,668 patients from 12 hospitals in China, HCC-STAR achieved state-of-the-art performance in treatment recommendation and risk stratification compared with clinical guidelines and competitive models, including GPT-5 and Gemini-2.5 Pro. Hypothetical overall-survival analysis showed a median survival of 51 months under adherence to HCC-STAR recommendations, compared with 29 and 32 months under BCLC and CNLC. In clinician-centric evaluations, blinded hepatobiliary specialists rated HCC-STAR's reasoning and evidence-based justifications as trustworthy. The model surpassed resident and attending physicians in treatment accuracy and helped physicians make more accurate decisions faster when used as an assistant. These findings support HCC-STAR as a reliable and verifiable decision-support system for risk stratification and precision therapy in HCC.

cs.AI↗

arXiv2025

Supervisory Control of Discrete Event Systems for Small Language Under Cyber Attacks

Cyber attacks are unavoidable in networked discrete event systems where the plant and the supervisor communicate with each other via networks. Because of the nondeterminism in observation and control caused by cyber attacks, the language generated by the supervised system becomes nondeterministic. The small language is defined as the lower bound on all possible languages that can be generated by the supervised system, which is needed for a supervised system to perform some required tasks under cyber attacks. In this paper, we investigate supervisory control for the small language. After introducing CA-S-controllability and CA-S-observability, we prove that the supervisory control problem of achieving a required small language is solvable if and only if the given language is CA-Scontrollable and CA-S-observable. If the given language is not CA-S controllable and/or CA-S-observable, we derive conditions under which the infimal CA-S-controllable and CA-S-observable superlanguage exists and can be used to design a supervisor satisfying the given requirement.

eess.SY↗

arXiv2025

Fish-Vista: A Multi-Purpose Dataset for Understanding & Identification of Traits from Images

We introduce Fish-Visual Trait Analysis (Fish-Vista), the first organismal image dataset designed for the analysis of visual traits of aquatic species directly from images using problem formulations in computer vision. Fish-Vista contains 69,126 annotated images spanning 4,154 fish species, curated and organized to serve three downstream tasks of species classification, trait identification, and trait segmentation. Our work makes two key contributions. First, we perform a fully reproducible data processing pipeline to process images sourced from various museum collections. We annotate these images with carefully curated labels from biological databases and manual annotations to create an AI-ready dataset of visual traits, contributing to the advancement of AI in biodiversity science. Second, our proposed downstream tasks offer fertile grounds for novel computer vision research in addressing a variety of challenges such as long-tailed distributions, out-of-distribution generalization, learning with weak labels, explainable AI, and segmenting small objects. We benchmark the performance of several existing methods for our proposed tasks to expose future research opportunities in AI for biodiversity science problems involving visual traits.

cs.CV↗

arXiv2025

Robust Indoor Localization in Dynamic Environments: A Multi-source Unsupervised Domain Adaptation Framework

Fingerprint localization has gained significant attention due to its cost-effective deployment, low complexity, and high efficacy. However, traditional methods, while effective for static data, often struggle in dynamic environments where data distributions and feature spaces evolve-a common occurrence in real-world scenarios. To address the challenges of robustness and adaptability in fingerprint localization for dynamic indoor environments, this paper proposes DF-Loc, an end-to-end dynamic fingerprint localization system based on multi-source unsupervised domain adaptation (MUDA). DF-Loc leverages historical data from multiple time scales to facilitate knowledge transfer in specific feature spaces, thereby enhancing generalization capabilities in the target domain and reducing reliance on labeled data. Specifically, the system incorporates a Quality Control (QC) module for CSI data preprocessing and employs image processing techniques for CSI fingerprint feature reconstruction. Additionally, a multi-scale attention-based feature fusion backbone network is designed to extract multi-level transferable fingerprint features. Finally, a dual-stage alignment model aligns the distributions of multiple source-target domain pairs, improving regression characteristics in the target domain. Extensive experiments conducted in office and classroom environments demonstrate that DF-Loc outperforms comparative methods in terms of both localization accuracy and robustness. With 60% of reference points used for training, DF-Loc achieves average localization errors of 0.79m and 3.72m in "same-test" scenarios, and 0.94m and 4.39m in "different-test" scenarios, respectively. This work pioneers an end-to-end multi-source transfer learning approach for fingerprint localization, providing valuable insights for future research in dynamic environments.

cs.CV↗

arXiv2024

Comparative Analysis of Machine Learning-Based Imputation Techniques for Air Quality Datasets with High Missing Data Rates

Urban pollution poses serious health risks, particularly in relation to traffic-related air pollution, which remains a major concern in many cities. Vehicle emissions contribute to respiratory and cardiovascular issues, especially for vulnerable and exposed road users like pedestrians and cyclists. Therefore, accurate air quality monitoring with high spatial resolution is vital for good urban environmental management. This study aims to provide insights for processing spatiotemporal datasets with high missing data rates. In this study, the challenge of high missing data rates is a result of the limited data available and the fine granularity required for precise classification of PM2.5 levels. The data used for analysis and imputation were collected from both mobile sensors and fixed stations by Dynamic Parcel Distribution, the Environmental Protection Agency, and Google in Dublin, Ireland, where the missing data rate was approximately 82.42%, making accurate Particulate Matter 2.5 level predictions particularly difficult. Various imputation and prediction approaches were evaluated and compared, including ensemble methods, deep learning models, and diffusion models. External features such as traffic flow, weather conditions, and data from the nearest stations were incorporated to enhance model performance. The results indicate that diffusion methods with external features achieved the highest F1 score, reaching 0.9486 (Accuracy: 94.26%, Precision: 94.42%, Recall: 94.82%), with ensemble models achieving the highest accuracy of 94.82%, illustrating that good performance can be obtained despite a high missing data rate.

cs.LG↗

arXiv2024

High-Throughput Information Storage in An Intelligent Response Phosphor

Persistent phosphor has emerged as a promising candidate for information storage due to the rapid accessibility and low-energy requirements. However, the low storage capacity has limited its practical application. Herein, we skillfully designed and developed NaGdGeO4:Pb2+,Tb3+ stimulated phosphor by trace doped Sm3+. As expected, this phosphor demonstrates the larger carrier capacity than traditional commercial SrAl2O4:Eu2+,Dy3+ phosphors and super-strong thermo-stimulated luminescence (TSL) that is three times greater than its photoluminescence (PL) intensity (PL efficiency: 17.3%). A mechanism of the enhanced and controllable TSL is proposed based on electron-hole defect pair structure. We further present a high-throughput optical data recording in five dimensions in a single fluorescent film recording layer. The findings described here provides not only a universal approach for construction TSL materials, but also a new paradigm for future generation optical storage technology.

physics.optics↗

arXiv2024

Dynamic Indoor Fingerprinting Localization based on Few-Shot Meta-Learning with CSI Images

While fingerprinting localization is favored for its effectiveness, it is hindered by high data acquisition costs and the inaccuracy of static database-based estimates. Addressing these issues, this letter presents an innovative indoor localization method using a data-efficient meta-learning algorithm. This approach, grounded in the ``Learning to Learn'' paradigm of meta-learning, utilizes historical localization tasks to improve adaptability and learning efficiency in dynamic indoor environments. We introduce a task-weighted loss to enhance knowledge transfer within this framework. Our comprehensive experiments confirm the method's robustness and superiority over current benchmarks, achieving a notable 23.13\% average gain in Mean Euclidean Distance, particularly effective in scenarios with limited CSI data.

cs.LG↗

arXiv2023

Enhancing Feature Extraction for Indoor Fingerprint Localization Using Diversified Data

Given the rapid advancements in wireless communication and terminal devices, high-speed and convenient WiFi has permeated various aspects of people's lives, and attention has been drawn to the location services that WiFi can provide. Fingerprint-based methods, as an excellent approach for localization, have gradually become a hot research topic. However, in practical localization, fingerprint features of traditional methods suffer from low reliability and lacking robustness in complex indoor environments. To overcome these limitations, this paper proposes a innovative feature extraction-enhanced intelligent localization scheme named Secci, based on diversified channel state information (CSI). By modifying the device driver, diversified CSI data are extracted and transformed into RGB CSI images, which serve as input to a deep convolutional neural network (DCNN) with SE attention mechanism-assisted training in the offline stage. Employing a greedy probabilistic approach, rapid prediction of the estimated location is performed in the online stage using test RGB CSI images. The Secci system is implemented using off-the-shelf WiFi devices, and comprehensive experiments are carried out in two representative indoor environments to showcase the superior performance of Secci compared to four existing algorithms.

eess.SP↗

arXiv2023

Mass-selected Ion-molecule Cluster Beam Apparatus for Ultrafast Photofragmentation Studies

We describe an apparatus to study the fragmentation of ion-molecule clusters triggered by laser excitation and transfer of an electron from the iodide to the neutral molecule. The apparatus comprises a source to generate ion-molecule clusters, a time-of-flight (TOF) spectrometer and a mass filter to select the desired anions, and a linear-plus-quadratic reflectron mass spectrometer to discriminate the fragment anions after the femtosecond laser excites the clusters. The fragment neutrals and anions are then captured by two channeltron detectors. The apparatus performance is tested by measuring the photofragments: I$^-$, CF$_3$I$^-$ and neutrals from photoexcitation of the ion-molecule cluster CF$_3$I$\cdot$I$^-$ using femtosecond UV laser pulses with a wavelength of 266 nm. The experimental results are compared with our ground state and excited state electronic structure calculations and the existed results and calculations, with particular attention to the dynamics of the photoexcitation and photodissociation.

physics.chem-ph↗

arXiv2022

Toward a Flexible Metadata Pipeline for Fish Specimen Images

Flexible metadata pipelines are crucial for supporting the FAIR data principles. Despite this need, researchers seldom report their approaches for identifying metadata standards and protocols that support optimal flexibility. This paper reports on an initiative targeting the development of a flexible metadata pipeline for a collection containing over 300,000 digital fish specimen images, harvested from multiple data repositories and fish collections. The images and their associated metadata are being used for AI-related scientific research involving automated species identification, segmentation and trait extraction. The paper provides contextual background, followed by the presentation of a four-phased approach involving: 1. Assessment of the Problem, 2. Investigation of Solutions, 3. Implementation, and 4. Refinement. The work is part of the NSF Harnessing the Data Revolution, Biology Guided Neural Networks (NSF/HDR-BGNN) project and the HDR Imageomics Institute. An RDF graph prototype pipeline is presented, followed by a discussion of research implications and conclusion summarizing the results.

cs.CV↗

arXiv2022

Thou Shalt Not Reject the P-value

Since its debut in the 18th century, the P-value has been an important part of hypothesis testing-based scientific discoveries. As the statistical engine accelerates, questions are beginning to be raised, asking to what extent scientific discoveries based on P-values are reliable and reproducible, and the voice calling for adjusting the significance level or banning the P-value has been increasingly heard. Inspired by these questions and discussions, here we enquire into the useful roles and misuses of the P-value in scientific studies. For common misuses and misinterpretations, we provide modest recommendations for practitioners. Additionally, we compare statistical significance with clinical relevance. In parallel, we review the Bayesian alternatives for seeking evidence. Finally, we discuss the promises and risks of using meta-analysis to pool P-values from multiple studies to aggregate evidence. Taken together, the P-value underpins a useful probabilistic decision-making system and provides evidence at a continuous scale. But its interpretation must be contextual, considering the scientific question, experimental design (including the model specification, sample size, and significance level), statistical power, effect size, and reproducibility.

stat.ME↗

arXiv2021

Highly-robust reentrant superconductivity in CsV3Sb5 under pressure

Here we present the superconducting property and structural stability of kagome CsV3Sb5 under in-situ high pressures. For the initial SC-I phase, its Tc is quickly enhanced from 3.5 K to 7.6 K and then totally suppressed at P~10 GPa. Further increasing the applied pressures, an SC-II phase emerges at P~15 GPa and persists up to 100 GPa. The Tc rapidly increases to the maximal value of 5.2 K at P=53.6 GPa and rather slowly decreases to 4.7 K at P=100 GPa. A two-dome-like variation of Tc in CsV3Sb5 is concluded here. The Raman measurements demonstrate that weakening of E2g model and strengthening of A1g model occur without phase transition as entering the SC-II phase, which is supported by the results of phonon spectra calculations. Electronic structure calculations reveal that exertion of pressure may bridge the gap of topological surface nontrivial states near EF, i. e. Z2 invariant. Meanwhile, it enlarges Fermi surface significantly, consistent with the increased carrier density. The findings here point out the change of electronic structure and strengthened electron-phonon coupling should be responsible for the pressure-induced reentrant SC.

cond-mat.supr-con↗

arXiv2020

On the Radiality Constraints for Distribution System Restoration and Reconfiguration Problems

Radiality constraints are involved in both distribution system restoration and reconfiguration problems. However, a set of widely used radiality constraints, i.e., the spanning tree (ST) constraints, has its limitations which have not been well recognized. In this letter, the limitation of the ST constraints is analyzed and an effective set of constraints, referred to as the single-commodity flow constraints, is presented. Furthermore, a combined set of constraints is proposed and case studies indicate that the combined constraints can gain computational efficiency in the reconfiguration problem. Recommendations on the use of radiality constraints are also provided.

eess.SY↗

arXiv2019

Secrecy Outage and Diversity Analysis of Multiple Cooperative Source-Destination Pairs

We study the physical-layer security of a multiple source-destination (SD) pairs coexisting wireless network in the face of an eavesdropper, where an eavesdropper intends to wiretap the signal transmitted by the SD pairs. In order to protect the wireless transmission against eavesdropping, we propose a cooperation framework relying on two stages. Specifically, an SD pair is selected to access the total allocated spectrum using an appropriately designed scheme at the beginning of the first stage. The other source nodes (SNs) simultaneously transmit their data to the SN of the above-mentioned SD pair relying on an orthogonal way during the first stage. Then, the SN of the chosen SD pair transmits the data packets containing its own messages and the other SNs' messages to its dedicated destination node (DN) in the second stage, which in turn will forward all the other DNs' data to the application center via the core network. We conceive a specific SD pair selection scheme, termed as the transmit antenna selection aided source-destination pair selection (TAS-SDPS). We derive the secrecy outage probability (SOP) expressions for the TAS-SDPS, as well as for the conventional round-robin source-destination pair selection (RSDPS) and non-cooperative (Non-coop) schemes for comparison purposes. Furthermore, we carry out the secrecy diversity gain analysis in the high main-to-eavesdropper ratio (MER) region, showing that the TAS-SDPS scheme is capable of achieving the maximum attainable secrecy diversity order.

cs.IT↗

arXiv2017

Unified quantum no-go theorems and transforming of quantum states in a restricted set

The linear superposition principle in quantum mechanics is essential for several no-go theorems such as the no-cloning theorem, the no-deleting theorem and the no-superposing theorem. It remains an open problem of finding general forbidden principles to unify these results. In this paper, we investigate general quantum transformations forbidden or permitted by the superposition principle for various goals. First, we prove a no-encoding theorem that forbids linearly superposing of an unknown pure state and a fixed state in Hilbert space of finite dimension. Two general forms include the no-cloning theorem, the no-deleting theorem, and the no-superposing theorem as special cases. Second, we provide a unified scheme for presenting perfect and imperfect quantum tasks (cloning and deleting) in a one-shot manner. This scheme may yield to fruitful results that are completely characterized with the linear independence of the input pure states. The generalized upper bounds for the success probability will be proved. Third, we generalize a recent superposing of unknown states with fixed overlaps when multiple copies of the input states are available.

quant-ph↗

arXiv2016

High efficiency near diffraction-limited mid-infrared flat lenses based on metasurface reflectarrays

A limiting factor in the development of mid-infrared optics is the lack of abundant materials that are transparent, low cost, lightweight, and easy to machine. In this paper, we demonstrate a metasurface device that circumvents these limitations. A flat lens based on antenna reflectarrays was designed to achieve near diffraction-limited focusing with a high efficiency (experiment: 80%, simulation: 83%) at 45(o) incidence angle at λ = 4.6 μm. This geometry considerably simplifies the experimental arrangement compared to the common geometry of normal incidence which requires beam splitters. Simulations show that the effect of comatic aberrations is small compared to parabolic mirrors. The use of single-step photolithography allows large scale fabrication.

physics.optics↗

arXiv2015

Moore-Gibson-Thompson equation with memory, part II: general decay of energy

We study a temporally third order (Moore-Gibson-Thompson) equation with a memory term. Previously it is known that, in non-critical regime, the global solutions exist and the energy functionals decay to zero. More precisely, it is known that the energy has exponential decay if the memory kernel decays exponentially. The current work is a generalization of the previous one (Part I) in that it allows the memory kernel to be more general and shows that the energy decays the same way as the memory kernel does, exponentially or not.

math.AP↗

arXiv2015

Moore-Gibson-Thompson equation with memory, part I: exponential decay of energy

We are interested in the Moore-Gibson-Thompson(MGT) equation with memory \begin{equation}\nonumber τu_{ttt}+ αu_{tt}+c^2\A u+b\A u_t -\int_0^tg(t-s)\A w(s)ds=0. \end{equation} We first classify the memory into three types. Then we study how a memory term creates damping mechanism and how the memory causes energy decay.

math.AP↗