arXiv subjects

Yang An

Publications and source records attributed to Yang An.

At least 19 recordsLinked to original sources

arXiv2026

GenFAR: A generalized representation of brain structure, derived from 49,246 multi-cohort MRIs via deep learning

Deep learning models for neuroimaging have largely been developed for individual tasks, limiting knowledge transfer across applications. Here we introduce GenFAR, a modular deep learning framework that learns general, clinically informed features from brain MRIs. We trained this modular architecture on 49,246 individuals across 11 cohorts, using 17 diverse classification and regression tasks spanning cognition, clinical, diagnosis, demographics, and biomarkers. This yields aggregated, focused feature sets that capture rich, clinically- and biologically-relevant brain representations. We developed a sequential learning approach where tasks progressively build on previously learned representations. Through an analysis of 5,000 task sequences, we identified an optimal sequence length of six tasks and introduced a Donor Score metric to quantify each task's contribution to downstream performance. This analysis revealed five consistently strong donor tasks (Age, AD/MCI, MMSE, Hypertension, Hyperlipidemia) that formed the base of our sequential model. We demonstrated the utility of our learned representation, in various tasks beyond those included in the training set, to serve as the foundation for specialized secondary predictors. We further showed that using the learned feature representation can substantially increase the sample efficiency of secondary deep learning training tasks and models, as well as improve their accuracy.

cs.CV↗

arXiv2026

Probabilistic results for monoids of order-preserving transformations

Let $\mathcal{PO}_n$ be the monoid of all order-preserving partial transformations on $X_n=\{1,\dots, n\}$ with the natural order, and let $\mathcal{O}_n$ and $\mathcal{POI}_n$ denote its submonoids of order-preserving full and injective partial transformations, respectively. For each transformation $\alpha\in\mathcal{PO}_n$, write the random variables $Y(\alpha)=|{\im}\alpha|$ and $Y_r(\alpha)=|{\im}\alpha|$ given that $|{\dom}\alpha|=r$ for $0 \leqslant r \leqslant n$. We determine the probability distribution, expectation and variance of $Y_r$ and $Y$ for $\mathcal{PO}_n$ and $\mathcal{POI}_n$. In particular, $Y_r(\alpha)$ follows a hypergeometric distribution $H(n+r-1,n,r)$ for $\alpha \in \mathcal{PO}_n$, while $Y_r(\alpha)$ is degenerate and $Y(\alpha)$ follows a hypergeometric distribution $H(2n,n,n)$ for $\alpha \in \mathcal{POI}_n$.

math.GR↗

arXiv2026

Fixed points of orientation-preserving full transformation

Let $\mathcal{OP}_n$ be the monoid of all orientation-preserving full transformations on $X_n=\{1,\dots, n\}$ with the natural order. For $\alpha \in \mathcal{OP}_n$, let $F(\alpha)=\{y\in X_n: y\alpha=y\}$ and $F(n,m)=|\{\alpha:|F(\alpha)|=m\}|$. Umar posed the question about the number $F(n,m)$ of elements of $\mathcal{OP}_n$ with $m$ fixed points. In this paper, we show that the number $F(n,m)$ of $\mathcal{OP}_n$ is $\binom{2n}{n-m}$ for $2\leqslant m\leqslant n$ and get the expectation and probability distribution of the cardinality of fixed-point set $F(\alpha)$ for $\alpha\in\mathcal{OP}_n$.

math.GR↗

arXiv2026

Coverage Path Planning for Autonomous Sailboats in Inhomogeneous and Time-Varying Oceans: A Spatiotemporal Optimization Approach

Autonomous sailboats are well suited for long-duration ocean observation due to their wind-driven endurance. However, their performance is highly anisotropic and strongly influenced by inhomogeneous and time-varying wind and current fields, limiting the effectiveness of existing coverage methods such as boustrophedon sweeping. Planning under these environmental and maneuvering constraints remains underexplored. This paper presents a spatiotemporal coverage path planning framework tailored to autonomous sailboats, combining (1) topology-based morphological constraints in the spatial domain to promote compact and continuous coverage, and (2) forecast-aware look-ahead planning in the temporal domain to anticipate environmental evolution and enable foresighted decision-making. Simulations conducted under stochastic inhomogeneous and time-varying ocean environments, including scenarios with partial directional accessibility, demonstrate that the proposed method generates efficient and feasible coverage paths where traditional strategies often fail. To the best of our knowledge, this study provides the first dedicated solution to the coverage path planning problem for autonomous sailboats operating in inhomogeneous and time-varying ocean environments, establishing a foundation for future cooperative multi-sailboat coverage.

cs.RO↗

arXiv2026

Dynamic Modeling, Parameter Identification and Numerical Analysis of Flexible Cables in Flexibly Connected Dual-AUV Systems

This research presents a dynamic modeling framework and parameter identification methods for describing the highly nonlinear behaviors of flexibly connected dual-AUV systems. The modeling framework is established based on the lumped mass method, integrating axial elasticity, bending stiffness, added mass and hydrodynamic forces, thereby accurately capturing the time-varying response of the forces and cable configurations. To address the difficulty of directly measuring material-related and hydrodynamic coefficients, this research proposes a parameter identification method that combines the physical model with experimental data. High-precision inversion of the equivalent Youngs modulus and hydrodynamic coefficients is performed through tension experiments under multiple configurations, effectively demonstrating that the identified model maintains predictive consistency in various operational conditions. Further numerical analysis indicates that the dynamic properties of flexible cable exhibit significant nonlinear characteristics, which are highly dependent on material property variations and AUV motion conditions. This nonlinear dynamic behavior results in two typical response states, slack and taut, which are jointly determined by boundary conditions and hydrodynamic effects, significantly affecting the cable configuration and endpoint loads. In this research, the dynamics of flexible cables under complex boundary conditions is revealed, providing a theoretical foundation for the design, optimization and further control research of similar systems.

cs.RO↗

arXiv2025

Holographic Ordering and Negative entropy in Non-equilibrium Euclidean Black Hole Path Integralsl

The Gibbons-Hawking-York (GHY) approach was developed for a Euclidean path integral derivation of equilibrial black hole entropy. To extend it to a near-equilibrium Euclidean path integral, we study a static Euclidean shell model. We calculate the Euclidean action shift for the static simple model thin shell held just outside the horizon, and find agreement with Casini's version of Bekenstein bound. We find a negative entropy deficit associated to the gravitational attraction towards the shell. For a holographic interpretation, the deficit corresponds precisely to the apparent horizon area deviation from the extremal surfaces Therefore, we develop a Euclidean path integral framework in which gravitational force emerges from negative entropy gradients due to Hawking temperature gradients. This setup allows us to introduce Onsager reciprocity and a linear-response relation to build a dissipating system, and treat the configuration as a near-equilibrium steady state (NESS). This clarify that the gravitational potential is a phenomenon informational and ordering, rather than entropic and disordering.

hep-th↗

arXiv2024

Enhancing EEG Signal Generation through a Hybrid Approach Integrating Reinforcement Learning and Diffusion Models

The present study introduces an innovative approach to the synthesis of Electroencephalogram (EEG) signals by integrating diffusion models with reinforcement learning. This integration addresses key challenges associated with traditional EEG data acquisition, including participant burden, privacy concerns, and the financial costs of obtaining high-fidelity clinical data. Our methodology enhances the generation of EEG signals with detailed temporal and spectral features, enriching the authenticity and diversity of synthetic datasets. The uniqueness of our approach lies in its capacity to concurrently model time-domain characteristics, such as waveform morphology, and frequency-domain features, including rhythmic brainwave patterns, within a cohesive generative framework. This is executed through the reinforcement learning model's autonomous selection of parameter update strategies, which steers the diffusion process to accurately reflect the complex dynamics inherent in EEG signals. We validate the efficacy of our approach using both the BCI Competition IV 2a dataset and a proprietary dataset, each collected under stringent experimental conditions. Our results indicate that the method preserves participant privacy by generating synthetic data that lacks biometric identifiers and concurrently improves the efficiency of model training by minimizing reliance on large annotated datasets. This research offers dual contributions: firstly, it advances EEG research by providing a novel tool for data augmentation and the advancement of machine learning algorithms; secondly, it enhances brain-computer interface technologies by offering a robust solution for training models on diverse and representative EEG datasets. Collectively, this study establishes a foundation for future investigations in neurological care and the development of tailored treatment protocols in neurorehabilitation.

eess.SP↗

arXiv2024

Human-Machine Co-Adaptation for Robot-Assisted Rehabilitation via Dual-Agent Multiple Model Reinforcement Learning (DAMMRL)

This study introduces a novel approach to robot-assisted ankle rehabilitation by proposing a Dual-Agent Multiple Model Reinforcement Learning (DAMMRL) framework, leveraging multiple model adaptive control (MMAC) and co-adaptive control strategies. In robot-assisted rehabilitation, one of the key challenges is modelling human behaviour due to the complexity of human cognition and physiological systems. Traditional single-model approaches often fail to capture the dynamics of human-machine interactions. Our research employs a multiple model strategy, using simple sub-models to approximate complex human responses during rehabilitation tasks, tailored to varying levels of patient incapacity. The proposed system's versatility is demonstrated in real experiments and simulated environments. Feasibility and potential were evaluated with 13 healthy young subjects, yielding promising results that affirm the anticipated benefits of the approach. This study not only introduces a new paradigm for robot-assisted ankle rehabilitation but also opens the way for future research in adaptive, patient-centred therapeutic interventions.

cs.RO↗

arXiv2024

Refining Corpora from a Model Calibration Perspective for Chinese Spelling Correction

Chinese Spelling Correction (CSC) commonly lacks large-scale high-quality corpora, due to the labor-intensive labeling of spelling errors in real-life human writing or typing scenarios. Two data augmentation methods are widely adopted: (1) \textit{Random Replacement} with the guidance of confusion sets and (2) \textit{OCR/ASR-based Generation} that simulates character misusing. However, both methods inevitably introduce noisy data (e.g., false spelling errors), potentially leading to over-correction. By carefully analyzing the two types of corpora, we find that though the latter achieves more robust generalization performance, the former yields better-calibrated CSC models. We then provide a theoretical analysis of this empirical observation, based on which a corpus refining strategy is proposed. Specifically, OCR/ASR-based data samples are fed into a well-calibrated CSC model trained on random replacement-based corpora and then filtered based on prediction confidence. By learning a simple BERT-based model on the refined OCR/ASR-based corpus, we set up impressive state-of-the-art performance on three widely-used benchmarks, while significantly alleviating over-correction (e.g., lowering false positive predictions).

cs.CL↗

arXiv2024

EEG_RL-Net: Enhancing EEG MI Classification through Reinforcement Learning-Optimised Graph Neural Networks

Brain-Computer Interfaces (BCIs) rely on accurately decoding electroencephalography (EEG) motor imagery (MI) signals for effective device control. Graph Neural Networks (GNNs) outperform Convolutional Neural Networks (CNNs) in this regard, by leveraging the spatial relationships between EEG electrodes through adjacency matrices. The EEG_GLT-Net framework, featuring the state-of-the-art EEG_GLT adjacency matrix method, has notably enhanced EEG MI signal classification, evidenced by an average accuracy of 83.95% across 20 subjects on the PhysioNet dataset. This significantly exceeds the 76.10% accuracy rate achieved using the Pearson Correlation Coefficient (PCC) method within the same framework. In this research, we advance the field by applying a Reinforcement Learning (RL) approach to the classification of EEG MI signals. Our innovative method empowers the RL agent, enabling not only the classification of EEG MI data points with higher accuracy, but effective identification of EEG MI data points that are less distinct. We present the EEG_RL-Net, an enhancement of the EEG_GLT-Net framework, which incorporates the trained EEG GCN Block from EEG_GLT-Net at an adjacency matrix density of 13.39% alongside the RL-centric Dueling Deep Q Network (Dueling DQN) block. The EEG_RL-Net model showcases exceptional classification performance, achieving an unprecedented average accuracy of 96.40% across 20 subjects within 25 milliseconds. This model illustrates the transformative effect of the RL in EEG MI time point classification.

eess.SP↗

arXiv2024

EEG_GLT-Net: Optimising EEG Graphs for Real-time Motor Imagery Signals Classification

Brain-Computer Interfaces connect the brain to external control devices, necessitating the accurate translation of brain signals such as from electroencephalography (EEG) into executable commands. Graph Neural Networks (GCN) have been increasingly applied for classifying EEG Motor Imagery signals, primarily because they incorporates the spatial relationships among EEG channels, resulting in improved accuracy over traditional convolutional methods. Recent advances by GCNs-Net in real-time EEG MI signal classification utilised Pearson Coefficient Correlation (PCC) for constructing adjacency matrices, yielding significant results on the PhysioNet dataset. Our paper introduces the EEG Graph Lottery Ticket (EEG_GLT) algorithm, an innovative technique for constructing adjacency matrices for EEG channels. It does not require pre-existing knowledge of inter-channel relationships, and it can be tailored to suit both individual subjects and GCN model architectures. Our findings demonstrated that the PCC method outperformed the Geodesic approach by 9.65% in mean accuracy, while our EEG_GLT matrix consistently exceeded the performance of the PCC method by a mean accuracy of 13.39%. Also, we found that the construction of the adjacency matrix significantly influenced accuracy, to a greater extent than GCN model configurations. A basic GCN configuration utilising our EEG_GLT matrix exceeded the performance of even the most complex GCN setup with a PCC matrix in average accuracy. Our EEG_GLT method also reduced MACs by up to 97% compared to the PCC method, while maintaining or enhancing accuracy. In conclusion, the EEG_GLT algorithm marks a breakthrough in the development of optimal adjacency matrices, effectively boosting both computational accuracy and efficiency, making it well-suited for real-time classification of EEG MI signals that demand intensive computational resources.

cs.LG↗

arXiv2023

Replica wormhole as a vacuum-to-vacuum transition

The recent developments related to the black hole information paradox have brought us a confusing object: the replica wormhole. We are trying to better understand the object from the viewpoint of the thermo-mixed double and spontaneous symmetry breaking. It was shown that the replica wormhole can be regarded as a transition between different degenerate vacua, and the corresponding gravitational partition function should be controlled by the manifold of the degenerate vacua. We also check the wormhole partition function in 2-dimensional Jackiw-Teitelboim gravity and show that the wormhole saddle is indeed controlled by the dimension of the degenerate vacua. Moreover, it is suggested that the replica wormhole geometries connecting different vacua can be related to the measurement process of soft hair that compares different vacuum configurations.

hep-th↗

arXiv2023

Maxwell's Demon for Emergent Page Curve and Split Property

Seeking for the proper situation of Emergent Gravity, we recent reveal that the entropic mechanism only happens when extremal surfaces are varied, which is similar to the non-gravitational-bath-coupled setup of the island development. In this paper, we consider perturbing thin shell state outside horizon during equilibrating, to find the evolution of these Euclidean states requires an external force to be $ F_{ex}\propto T_{H}\delta A(\mu_a)$, proportional to area variation of the apparent horizon which could transform into the actual event horizon as extremal surface. We analogize the falling tendency to the 2nd law tendency, and then explore the potential tendency violation of Hawking radiation. This analogy recalls the role of Maxwell's Demon to interpret the mechanism of the bath for the Page curve to emerge in a close universe. It could reconcile the Split Problem concerning quantum gravity raised by Raju.

hep-th↗

arXiv2022

Understanding quantum black holes from quantum reduced loop gravity

We systematically study the top-down model of loop quantum black holes (LQBHs), recently derived by Alesci, Bahrami and Pranzetti (ABP). To understand the structure of the model, we first derive several well-known LQBH solutions by taking proper limits. These include the B\"ohmer-Vandersloot and Ashtekar-Olmedo-Singh models, which were all obtained by the so-called bottom-up polymerizations within the framework of the minisuperspace quantizations. Then, we study the ABP model, and find that the inverse volume corrections become important only when the radius of the two-sphere is of the Planck size. For macroscopic black holes, the minimal radius obtained at the transition surface is always much larger than the Planck scale, and hence these corrections are always sub-leading. The transition surface divides the whole spacetime into two regions, and in one of them the spacetime is asymptotically Schwarzschild-like, while in the other region, the asymptotical behavior sensitively depends on the ratio of two spin numbers involved in the model, and can be divided into three different classes. In one class, the spacetime in the 2-planes orthogonal to the two spheres is asymptotically flat, and in the second one it is not even conformally flat, while in the third one it can be asymptotically conformally flat by properly choosing the free parameters of the model. In the latter, it is asymptotically de Sitter. However, in any of these three classes, sharply in contrast to the models obtained by the bottom-up approach, the spacetime is already geodesically complete, and no additional extensions are needed in both sides of the transition surface. In particular, identical multiple black hole and white hole structures do not exist.

gr-qc↗

arXiv2022

KnowAugNet: Multi-Source Medical Knowledge Augmented Medication Prediction Network with Multi-Level Graph Contrastive Learning

Predicting medications is a crucial task in many intelligent healthcare systems. It can assist doctors in making informed medication decisions for patients according to electronic medical records (EMRs). However, medication prediction is a challenging data mining task due to the complex relations between medical codes. Most existing studies focus on utilizing inherent relations between homogeneous codes of medical ontology graph to enhance their representations using supervised methods, and few studies pay attention to the valuable relations between heterogeneous or homogeneous medical codes from history EMRs, which further limits the prediction performance and application scenarios. Therefore, to address these limitations, this paper proposes KnowAugNet, a multi-sourced medical knowledge augmented medication prediction network which can fully capture the diverse relations between medical codes via multi-level graph contrastive learning framework. Specifically, KnowAugNet first leverages the graph contrastive learning using graph attention network as the encoder to capture the implicit relations between homogeneous medical codes from the medical ontology graph and obtains the knowledge augmented medical codes embedding vectors. Then, it utilizes the graph contrastive learning using a weighted graph convolutional network as the encoder to capture the correlative relations between homogeneous or heterogeneous medical codes from the constructed medical prior relation graph and obtains the relation augmented medical codes embedding vectors. Finally, the augmented medical codes embedding vectors and the supervised medical codes embedding vectors are retrieved and input to the sequential learning network to capture the temporal relations of medical codes and predict medications for patients.

cs.AI↗

arXiv2021

MeSIN: Multilevel Selective and Interactive Network for Medication Recommendation

Recommending medications for patients using electronic health records (EHRs) is a crucial data mining task for an intelligent healthcare system. It can assist doctors in making clinical decisions more efficiently. However, the inherent complexity of the EHR data renders it as a challenging task: (1) Multilevel structures: the EHR data typically contains multilevel structures which are closely related with the decision-making pathways, e.g., laboratory results lead to disease diagnoses, and then contribute to the prescribed medications; (2) Multiple sequences interactions: multiple sequences in EHR data are usually closely correlated with each other; (3) Abundant noise: lots of task-unrelated features or noise information within EHR data generally result in suboptimal performance. To tackle the above challenges, we propose a multilevel selective and interactive network (MeSIN) for medication recommendation. Specifically, MeSIN is designed with three components. First, an attentional selective module (ASM) is applied to assign flexible attention scores to different medical codes embeddings by their relevance to the recommended medications in every admission. Second, we incorporate a novel interactive long-short term memory network (InLSTM) to reinforce the interactions of multilevel medical sequences in EHR data with the help of the calibrated memory-augmented cell and an enhanced input gate. Finally, we employ a global selective fusion module (GSFM) to infuse the multi-sourced information embeddings into final patient representations for medications recommendation. To validate our method, extensive experiments have been conducted on a real-world clinical dataset. The results demonstrate a consistent superiority of our framework over several baselines and testify the effectiveness of our proposed approach.

cs.AI↗

arXiv2020

Soft black hole information paradox: Page curve from Maxwell soft hair of a black hole

Treating Maxwell soft hair as a transition function that relates U(1) gauge fields living in the asymptotic region and near-horizon region, the U(1) gauge parameter $\phi$ naturally becomes a good label of those Maxwell soft hair degrees of freedom. This interpretation also builds the connection between Maxwell soft hair and U(1) edge modes living in the intermediate region, which admits a well-defined effective action description. We study the statistical properties by Euclidean path integral, which concludes that the soft hair density of state increases with black hole temperature. Hawking radiations increase black hole entropy by creating entanglements, while the measurements of soft modes project the black hole onto lower entropy states. The competition between phase spaces of Hawking radiations and soft hair measurements gives rise to one version of the Page curve consistent with the unitary evolution of the black hole.

hep-th↗

arXiv2020

From Goals, Waypoints & Paths To Long Term Human Trajectory Forecasting

Human trajectory forecasting is an inherently multi-modal problem. Uncertainty in future trajectories stems from two sources: (a) sources that are known to the agent but unknown to the model, such as long term goals and (b)sources that are unknown to both the agent & the model, such as intent of other agents & irreducible randomness indecisions. We propose to factorize this uncertainty into its epistemic & aleatoric sources. We model the epistemic un-certainty through multimodality in long term goals and the aleatoric uncertainty through multimodality in waypoints& paths. To exemplify this dichotomy, we also propose a novel long term trajectory forecasting setting, with prediction horizons upto a minute, an order of magnitude longer than prior works. Finally, we presentY-net, a scene com-pliant trajectory forecasting network that exploits the pro-posed epistemic & aleatoric structure for diverse trajectory predictions across long prediction horizons.Y-net significantly improves previous state-of-the-art performance on both (a) The well studied short prediction horizon settings on the Stanford Drone & ETH/UCY datasets and (b) The proposed long prediction horizon setting on the re-purposed Stanford Drone & Intersection Drone datasets.

cs.CV↗