arXiv subjects

Jun Ni

Publications and source records attributed to Jun Ni.

At least 19 recordsLinked to original sources

arXiv2026

Physics-Aware Complex-Valued State Space Model with Scattering-Prior Feature Modulation for PolSAR Image Classification

Polarimetric synthetic aperture radar (PolSAR) image classification is a representative task for physics-aware GeoAI, where land-cover semantics are closely coupled with electromagnetic scattering mechanisms. Many existing complex-valued networks can preserve amplitude-phase information, but they are often limited in long-range spatial dependency modeling and usually incorporate polarimetric priors only as input-level or shallow auxiliary features. As a result, physical knowledge is insufficiently used to guide deep feature evolution. To address this issue, this paper proposes CV-SSMNet, a physics-aware complex-valued state-space network with scattering-aware feature modulation for PolSAR image classification. The proposed method builds a complex-valued state-space model (CV-SSM) in the original complex domain to capture long-range spatial dependencies while preserving polarimetric amplitude-phase coupling. Meanwhile, seven physically meaningful scattering priors, are encoded as FiLM-style modulation signals to adaptively recalibrate complex-valued representations during feature evolution. CV-SSMNet further integrates multi-scale complex convolutions, branch-wise CV-SSM encoding, prior-guided recalibration, and lightweight global context aggregation, enabling physically guided representation learning from local scattering structures to global spatial context. Experiments on three L-band benchmark datasets and an additional P-band BIOMASS evaluation demonstrate that CV-SSMNet achieves competitive accuracy, improved regional consistency, and better boundary preservation, supporting the effectiveness of embedding polarimetric scattering mechanisms into complex-valued long-range GeoAI representation learning.

cs.CV↗

arXiv2026

Foundation Models to Unlock Real-World Evidence from Nationwide Medical Claims

Evidence derived from large-scale real-world data (RWD) is increasingly informing regulatory evaluation and healthcare decision-making. Administrative claims provide population-scale, longitudinal records of healthcare utilization, expenditure, and detailed coding of diagnoses, procedures, and medications, yet their potential as a substrate for healthcare foundation models remains largely unexplored. Here we present ReClaim, a generative transformer trained from scratch on 43.8 billion medical events from more than 200 million enrollees in the MarketScan claims data spanning 2008-2022. ReClaim models longitudinal trajectories across diagnoses, procedures, medications, and expenditure, and was scaled to 140 million, 700 million, and 1.7 billion parameters. Across over 1,000 disease-onset prediction tasks, ReClaim achieved a mean AUC of 75.6%, substantially outperforming disease-specific LightGBM (66.3%) and the transformer-based Delphi model (69.4%), with the largest gains for rare diseases. These advantages held across retrospective and prospective evaluations and in external validation on two independent datasets. Performance improved monotonically with scale, and post-training added 13.8 percentage points over pre-training alone. Beyond disease prediction, ReClaim captured financial outcomes and improved real-world evidence (RWE) analyses: for healthcare expenditure forecasting it increased explained variance from 0.28 to 0.37 relative to LightGBM, and in a target trial emulation it reduced systematic bias by 72% on average relative to Delphi. Together, these results establish administrative claims as a scalable substrate for healthcare foundation models and show that learned representations generalize across time periods and data sources, supporting disease surveillance, expenditure forecasting, and RWE generation.

cs.AI↗

arXiv2026

SFFNet: Synergistic Feature Fusion Network With Dual-Domain Edge Enhancement for UAV Image Object Detection

Object detection in unmanned aerial vehicle (UAV) images remains a highly challenging task, primarily caused by the complexity of background noise and the imbalance of target scales. Traditional methods easily struggle to effectively separate objects from intricate backgrounds and fail to fully leverage the rich multi-scale information contained within images. To address these issues, we have developed a synergistic feature fusion network (SFFNet) with dual-domain edge enhancement specifically tailored for object detection in UAV images. Firstly, the multi-scale dynamic dual-domain coupling (MDDC) module is designed. This component introduces a dual-driven edge extraction architecture that operates in both the frequency and spatial domains, enabling effective decoupling of multi-scale object edges from background noise. Secondly, to further enhance the representation capability of the model's neck in terms of both geometric and semantic information, a synergistic feature pyramid network (SFPN) is proposed. SFPN leverages linear deformable convolutions to adaptively capture irregular object shapes and establishes long-range contextual associations around targets through the designed wide-area perception module (WPM). Moreover, to adapt to the various applications or resource-constrained scenarios, six detectors of different scales (N/S/M/B/L/X) are designed. Experiments on two challenging aerial datasets (VisDrone and UAVDT) demonstrate the outstanding performance of SFFNet-X, achieving 36.8 AP and 20.6 AP, respectively. The lightweight models (N/S) also maintain a balance between detection accuracy and parameter efficiency. The code will be available at https://github.com/CQNU-ZhangLab/SFFNet.

cs.CV↗

arXiv2025

Modeling and Control of AWOISV: A Filtered Tube-Based MPC Approach for Simultaneous Tracking of Lateral Position and Heading Angle

An all-wheel omni-directional independent steering vehicle (AWOISV) is a specialized all-wheel independent steering vehicle with each wheel capable of steering up to 90{\deg}, enabling unique maneuvers like yaw and diagonal movement. This paper introduces a theoretical steering radius angle and sideslip angle ($ \theta_R $-$\beta_R $) representation, based on the position of the instantaneous center of rotation relative to the wheel rotation center, defining the motion modes and switching criteria for AWOISVs. A generalized $ v$-$\beta$-$r $ dynamic model is developed with forward velocity $v$, sideslip angle $\beta$, and yaw rate $r$ as states, and $\theta_R$ and $\beta_R$ as control inputs. This model decouples longitudinal and lateral motions into forward and rotational motions, allowing seamless transitions across all motion modes under specific conditions. A filtered tube-based linear time-varying MPC (FT-LTVMPC) strategy is proposed, achieving simultaneous tracking of lateral position and arbitrary heading angles, with robustness to model inaccuracies and parameter uncertainties. Co-simulation and hardware-in-loop (HIL) experiments confirm that FT-LTVMPC enables high-precision control of both position and heading while ensuring excellent real-time performance.

cs.RO↗

arXiv2025

SCAWaveNet: A Spatial-Channel Attention-Based Network for Global Significant Wave Height Retrieval

Recent advancements in spaceborne GNSS missions have produced extensive global datasets, providing a robust basis for deep learning-based significant wave height (SWH) retrieval. While existing deep learning models predominantly utilize CYGNSS data with four-channel information, they often adopt single-channel inputs or simple channel concatenation without leveraging the benefits of cross-channel information interaction during training. To address this limitation, a novel spatial-channel attention-based network, namely SCAWaveNet, is proposed for SWH retrieval. Specifically, features from each channel of the DDMs are modeled as independent attention heads, enabling the fusion of spatial and channel-wise information. For auxiliary parameters, a lightweight attention mechanism is designed to assign weights along the spatial and channel dimensions. The final feature integrates both spatial and channel-level characteristics. Model performance is evaluated using four-channel CYGNSS data. When ERA5 is used as a reference, SCAWaveNet achieves an average RMSE of 0.438 m. When using buoy data from NDBC, the average RMSE reaches 0.432 m. Compared to state-of-the-art models, SCAWaveNet reduces the average RMSE by at least 3.52% on the ERA5 dataset and by 5.68% on the NDBC buoy observations. The code is available at https://github.com/Clifx9908/SCAWaveNet.

cs.LG↗

arXiv2024

Deep Koopman-based Control of Quality Variation in Multistage Manufacturing Systems

This paper presents a modeling-control synthesis to address the quality control challenges in multistage manufacturing systems (MMSs). A new feedforward control scheme is developed to minimize the quality variations caused by process disturbances in MMSs. Notably, the control framework leverages a stochastic deep Koopman (SDK) model to capture the quality propagation mechanism in the MMSs, highlighted by its ability to transform the nonlinear propagation dynamics into a linear one. Two roll-to-roll case studies are presented to validate the proposed method and demonstrate its effectiveness. The overall method is suitable for nonlinear MMSs and does not require extensive expert knowledge.

eess.SY↗

arXiv2023

Stochastic Deep Koopman Model for Quality Propagation Analysis in Multistage Manufacturing Systems

The modeling of multistage manufacturing systems (MMSs) has attracted increased attention from both academia and industry. Recent advancements in deep learning methods provide an opportunity to accomplish this task with reduced cost and expertise. This study introduces a stochastic deep Koopman (SDK) framework to model the complex behavior of MMSs. Specifically, we present a novel application of Koopman operators to propagate critical quality information extracted by variational autoencoders. Through this framework, we can effectively capture the general nonlinear evolution of product quality using a transferred linear representation, thus enhancing the interpretability of the data-driven model. To evaluate the performance of the SDK framework, we carried out a comparative study on an open-source dataset. The main findings of this paper are as follows. Our results indicate that SDK surpasses other popular data-driven models in accuracy when predicting stagewise product quality within the MMS. Furthermore, the unique linear propagation property in the stochastic latent space of SDK enables traceability for quality evolution throughout the process, thereby facilitating the design of root cause analysis schemes. Notably, the proposed framework requires minimal knowledge of the underlying physics of production lines. It serves as a virtual metrology tool that can be applied to various MMSs, contributing to the ultimate goal of Zero Defect Manufacturing.

cs.LG↗

arXiv2023

Shapley-based Explainable AI for Clustering Applications in Fault Diagnosis and Prognosis

Data-driven artificial intelligence models require explainability in intelligent manufacturing to streamline adoption and trust in modern industry. However, recently developed explainable artificial intelligence (XAI) techniques that estimate feature contributions on a model-agnostic level such as SHapley Additive exPlanations (SHAP) have not yet been evaluated for semi-supervised fault diagnosis and prognosis problems characterized by class imbalance and weakly labeled datasets. This paper explores the potential of utilizing Shapley values for a new clustering framework compatible with semi-supervised learning problems, loosening the strict supervision requirement of current XAI techniques. This broad methodology is validated on two case studies: a heatmap image dataset obtained from a semiconductor manufacturing process featuring class imbalance, and a benchmark dataset utilized in the 2021 Prognostics and Health Management (PHM) Data Challenge. Semi-supervised clustering based on Shapley values significantly improves upon clustering quality compared to the fully unsupervised case, deriving information-dense and meaningful clusters that relate to underlying fault diagnosis model predictions. These clusters can also be characterized by high-precision decision rules in terms of original feature values, as demonstrated in the second case study. The rules, limited to 1-2 terms utilizing original feature scales, describe 12 out of the 16 derived equipment failure clusters with precision exceeding 0.85, showcasing the promising utility of the explainable clustering framework for intelligent manufacturing applications.

cs.LG↗

arXiv2023

Fault Prognosis of Turbofan Engines: Eventual Failure Prediction and Remaining Useful Life Estimation

In the era of industrial big data, prognostics and health management is essential to improve the prediction of future failures to minimize inventory, maintenance, and human costs. Used for the 2021 PHM Data Challenge, the new Commercial Modular Aero-Propulsion System Simulation dataset from NASA is an open-source benchmark containing simulated turbofan engine units flown under realistic flight conditions. Deep learning approaches implemented previously for this application attempt to predict the remaining useful life of the engine units, but have not utilized labeled failure mode information, impeding practical usage and explainability. To address these limitations, a new prognostics approach is formulated with a customized loss function to simultaneously predict the current health state, the eventual failing component(s), and the remaining useful life. The proposed method incorporates principal component analysis to orthogonalize statistical time-domain features, which are inputs into supervised regressors such as random forests, extreme random forests, XGBoost, and artificial neural networks. The highest performing algorithm, ANN-Flux, achieves AUROC and AUPR scores exceeding 0.95 for each classification. In addition, ANN-Flux reduces the remaining useful life RMSE by 38% for the same test split of the dataset compared to past work, with significantly less computational cost.

cs.LG↗

arXiv2023

Collective excitations of the Chern-insulator states in commensurate double moir\'{e} superlattices of twisted bilayer graphene on hexagonal boron nitride

We study the collective excitation modes of the Chern insulator states in magic-angle twisted bilayer graphene aligned with hexagonal boron nitride (TBG/BN) at odd integer fillings ($\nu$) of the flat bands. For the $1 \times 1$ commensurate double moir\'{e} superlattices in TBG/BN at three twist angles ($\theta'$) between BN and graphene, self-consistent Hartree-Fock calculations show that the electron-electron interaction and the broken $C_{2z}$ symmetry lead to the Chern-insulator ground states with valley-spin flavor polarized HF bands at odd $\nu$. In the active-band approximation, the HF bands in the same flavor of TBG/BN are much more separated than those of the pristine TBG with TBG/BN having a larger intra-flavor band gap so that the energies of the lowest intra-flavor exciton modes of TBG/BN computed within the time-dependent HF method are much higher than those of TBG and reach about 20 meV, and the exciton wavefunctions of TBG/BN become less localized than those of TBG. The inter-flavor valley-wave modes in TBG/BN have excitation energies higher than 2.5 meV which is also much larger than that of TBG, while the spin-wave modes all have zero excitation gap. In contrast to TBG with particle-hole symmetric excitation modes for positive and negative $\nu$, the excitation spectrums and gaps of TBG/BN at positive $\nu$ are rather different from those at negative $\nu$. The quantitative behavior of the excitation spectrum of TBG/BN also varies with $\theta'$. Full HF calculations demonstrate that more HF bands besides the two central bands can have rather large contributions from the single-particle flat-band states, then the lowest exciton modes that determine the optical properties of the Chern insulator states in TBG/BN are generally the ones between the remote and flat-like bands, while the valley-wave modes have similar energies as those in the active-band approximation.

cond-mat.mes-hall↗

arXiv2022

Energetic stability and spatial inhomogeneity in the local electronic structure of relaxed twisted trilayer graphene

We study the energetic stability and the local electronic structure of the general twisted trilayer graphene (TTG) with the top and bottom layers rotated with respect to the middle layer respectively by $\theta$ and $\theta'$. Approximate supercells of the moir\'{e}-of-moir\'{e} superlattices with $\theta$ and $\theta^{\prime}$ within $1^{\circ}\sim 2^{\circ}$ are established to describe the structural and electronic properties of relaxed TTG with the periodic boundary condition. Full relaxation demonstrates that the commensurate TTG with $\theta=\theta^{\prime}$ has the local minimum total energy ($E_{tol}$) at a fixed $\theta$, while $E_{tol}$ first reaches a local maximum and begins to drop with decreasing $\theta^{\prime}$ for $\theta^{\prime} < \theta$. Some regions exhibit enhanced in-plane relaxation in the top and bottom layers but suppressed relaxation in the middle layer and form a hexagonal network with the moir\'{e}-of-moir\'{e} length scale. The stacking configurations with the atoms in the three layers vertically aligned at the origin of the relaxed TTG supercells at $\theta$ around $1.6^{\circ}$ and $\theta^{\prime}$ around $1.4^{\circ}$ have a high density of states (DOS) near the Fermi level ($E_F$), which can reach that of the mirror symmetric TTG with equal twist angles of about $1.7^{\circ}$. In contrast, some other stackings can have rather low DOS around $E_F$. The significant stacking dependence of DOS for some TTG supercells demonstrates that the local electronic structure of TTG can exhibit strong spatial inhomogeneity when the twist angles are slightly away from those of the small supercells with large variations of DOS among different stackings. Moreover, the structural relaxation of TTG plays a crucial role in the high DOS and its strong stacking dependence.

cond-mat.mes-hall↗

arXiv2021

Emergence of intrinsically isolated flat bands and their topology in fully relaxed twisted multi-layer graphene

We study the electronic structure and band topology of fully relaxed twisted multi-layer graphene (TMLG). Isolated flat bands emerge in TMLG with the number of layers [$M+N$ with $M$ the layer number of the bottom few-layer graphene (FLG)] up to 10 and with various stacking orders, and most of them are on the hole side. The touched bands of FLGs around the Fermi level are split by the moir\'{e} coupling through the electron-hole asymmetry in low-energy bands of FLGs and by the vertical hopping between next-nearest layers. The full structural relaxation leads to global gaps that completely isolate a flat band. For TMLG with given $M$ and $N$, the highest magnitude of Chern numbers ($|C|$) of the separable flat bands reaches $M+N-1$ and can be hosted by certain isolated bands. The $|C|=9$ occurs in the isolated flat valence band of several configurations with 10 layers. Such high $|C|$ originates from the lifting of the band-state degeneracy in the weak regime of moir\'{e} coupling or from the topological phase transitions induced by the strong moir\'{e} coupling. Moreover, large orbital magnetic moments arise in isolated flat bands with high $|C|$ and depend on the structural configurations of TMLG.

cond-mat.mes-hall↗

arXiv2020

Misalignment instability in magic-angle twisted bilayer graphene on hexagonal boron nitride

We study the stability and electronic structure of magic-angle twisted bilayer graphene on the hexagonal boron nitride (TBG/BN). Full relaxation has been performed for commensurate supercells of the heterostructures with different twist angles ($\theta'$) and stackings between TBG and BN. We find that the slightly misaligned configuration with $\theta' = 0.54^\circ$ and the AA/AA stacking has the globally lowest total energy due to the constructive interference of the moir\'{e} interlayer potentials and thus the greatly enhanced relaxation in its $1 \times 1$ commensurate supercell. Gaps are opened at the Fermi level ($E_F$) for small supercells with the stackings that enable strong breaking of the $C_2$ symmetry in the atomic structure of TBG. For large supercells with $\theta'$ close to those of the $1 \times 1$ supercells, the broadened flat bands can still be resolved from the spectral functions. The $\theta' = 0.54^\circ$ is also identified as a critical angle for the evolution of the electronic structure with $\theta'$, at which the energy range of the mini-bands around $E_F$ begins to become narrower with increasing $\theta'$ and their gaps from the dispersive bands become wider. The discovered stablest TBG/BN with a finite $\theta'$ of about $0.54^\circ$ and its gapped flat bands agree with recent experimental observations.

cond-mat.mes-hall↗

arXiv2020

Autonomous Formula Racecar: Overall System Design and Experimental Validation

This paper develops and summarizes the work of building the autonomous integrated system including perception system and vehicle dynamic controller for a formula student autonomous racecar. We propose a system framework combining X-by-wired modification, perception & motion planning and vehicle dynamic control as a template of FSAC racecar which can be easily replicated. A LIDAR-vision cooperating method of detecting traffic cone which is used as track mark is proposed. Detection algorithm of the racecar also implements a precise and high rate localization method which combines the GPS-INS data and LIDAR odometry. Besides, a track map including the location and color information of the cones is built simultaneously. Finally, the system and vehicle performance on a closed loop track is tested. This paper also briefly introduces the Formula Student Autonomous Competition (FSAC).

cs.RO↗

arXiv2020

Symmetry breaking in the double moir\'{e} superlattices of relaxed twisted bilayer graphene on hexagonal boron nitride

We study the atomic and electronic structures of the commensurate double moir\'{e} superlattices in fully relaxed twisted bilayer graphene (TBG) nearly aligned with the hexagonal boron nitride (BN). The single-particle effective Hamiltonian ($\hat{H}^0$) taking into account the relaxation effect and the full moir\'{e} Hamiltonian introduced by BN has been built for TBG/BN. The mean-field (MF) band structures of the self-consistent Hartree-Fock (SCHF) ground states at different number ($\nu$) of filled flat bands relative to the charge neutrality point (CNP) are obtained based on $\hat{H}^0$ in the plane-wave-like basis. The single-particle flat bands in TBG/BN become separated by the opened gap at CNP due to the symmetry breaking in $\hat{H}^0$. We find that the broken $C_2$ symmetry in $\hat{H}^0$ mainly originates from the intralayer inversion-asymmetric structural deformation in the graphene layer adjacent to BN, which introduces spatially non-uniform modifications of the intralayer Hamiltonian. The gapped flat bands have finite Chern numbers. For TBG/BN with the magic twist angle, the SCHF ground states with $|\nu|$ = 1-3 are all insulating with narrow MF gaps. When the flat conduction bands are filled, the gap at $\nu$ = 1 is smaller than that at $\nu$ = 3, suggesting that the nontrivial topological properties associated with the flat Chern bands are more likely to be observed at $\nu = 3$. This is similar for negative $\nu$ with empty valence bands. The dependence of the electronic structure of TBG/BN on positive $\nu$ is roughly consistent with recent experimental observations.

cond-mat.mes-hall↗

arXiv2020

Learning based Predictive Error Estimation and Compensator Design for Autonomous Vehicle Path Tracking

Model predictive control (MPC) is widely used for path tracking of autonomous vehicles due to its ability to handle various types of constraints. However, a considerable predictive error exists because of the error of mathematics model or the model linearization. In this paper, we propose a framework combining the MPC with a learning-based error estimator and a feedforward compensator to improve the path tracking accuracy. An extreme learning machine is implemented to estimate the model based predictive error from vehicle state feedback information. Offline training data is collected from a vehicle controlled by a model-defective regular MPC for path tracking in several working conditions, respectively. The data include vehicle state and the spatial error between the current actual position and the corresponding predictive position. According to the estimated predictive error, we then design a PID-based feedforward compensator. Simulation results via Carsim show the estimation accuracy of the predictive error and the effectiveness of the proposed framework for path tracking of an autonomous vehicle.

cs.RO↗

arXiv2020

Pressure induced gap modulation and topological transitions in twisted bilayer and double bilayer graphene

We study the electronic and topological properties of fully relaxed twisted bilayer (TBG) and double bilayer (TDBG) graphene under perpendicular pressure. An approach has been proposed to obtain the equilibrium in-plane structural deformation and out-of-plane corrugation in moir\'{e} superlattices under pressure. We find that the in-plane relaxation becomes much stronger under higher pressure, while the corrugation height in each layer is maintained. The comparison between band structures of relaxed and rigid structures demonstrates that not only the gaps on the electron and hole sides ($\Delta_e$ and $\Delta_h$) are significantly underestimated without relaxation but also the detailed dispersions of the middle bands of rigid structures are rather different from those of relaxed systems. $\Delta_e$ and $\Delta_h$ in TBG reach maximum values around critical pressures with narrowest middle bands. Topological transitions occur in TDBG under pressure with the middle valence and conduction bands in one valley touching and their Chern numbers transferred to each other. The pressure can also tune the gap at the neutrality point of TDBG, which becomes closed for a pressure range and reopened under higher pressure. The behavior of electronic structure of supertlattices under pressure is sensitive to the twist angle $\theta$ with the critical pressures generally increase with $\theta$.

cond-mat.mes-hall↗

arXiv2020

Integrating global spatial features in CNN based Hyperspectral/SAR imagery classification

The land cover classification has played an important role in remote sensing because it can intelligently identify things in one huge remote sensing image to reduce the work of humans. However, a lot of classification methods are designed based on the pixel feature or limited spatial feature of the remote sensing image, which limits the classification accuracy and universality of their methods. This paper proposed a novel method to take into the information of remote sensing image, i.e., geographic latitude-longitude information. In addition, a dual-branch convolutional neural network (CNN) classification method is designed in combination with the global information to mine the pixel features of the image. Then, the features of the two neural networks are fused with another fully neural network to realize the classification of remote sensing images. Finally, two remote sensing images are used to verify the effectiveness of our method, including hyperspectral imaging (HSI) and polarimetric synthetic aperture radar (PolSAR) imagery. The result of the proposed method is superior to the traditional single-channel convolutional neural network.

cs.LG↗