arXiv subjects

Wang Hui

Publications and source records attributed to Wang Hui.

7 recordsLinked to original sources

arXiv2026

JW-FD: A Long Horizon Multimodal Solar Flare Forecasting Dataset

Solar flares drive severe space weather hazards, and forecasting their occurrence remains a central challenge for both heliophysics and operational space weather services. Data driven methods require long horizon datasets in which images, magnetic features, and flare labels are coregistered in space and time. We present JW-FD (JW-Flare Dataset), a 15 year multimodal release spanning 1 January 2011 through 31 December 2025, constructed from SDO/HMI line of sight magnetograms, NOAA Solar Region Summary reports, and NOAA X-ray flare event lists. The dataset comprises 3,064 independent active regions and 1,991,247 coregistered magnetogram crops, together with FITS, PNG, CSV, and MP4 modalities. Each sample provides 29 magnetic features linked to configurable flare labels under a strict pre-eruption window spanning seven forecast horizons and four GOES intensity thresholds. An 8:1:1 split at the active region level is adopted to prevent temporal leakage between partitions. PNG branches are released at six magnetic saturation thresholds, and internal Transformer experiments on >=C1.0 forecasting suggest Bth=1000 G as a preliminary default, although the optimal saturation is model and task dependent. The open source construction pipeline is available at https://github.com/Xiaoxuan-1/JW-FD.

astro-ph.SR↗

arXiv2026

Scientific-Intention Driven Embodied Intelligent Solar Telescope: Conceptual Design

Artificial Intelligence (AI) is profoundly transforming the paradigms of scientific research. Cutting-edge technologies such as Large Language Models (LLMs) and embodied intelligence are continuously pushing the boundaries of scientific instrumentation. Against this backdrop, this paper proposes a novel conceptual system: the Scientific-Intention Driven Embodied Intelligent Solar Telescope (SIDEST). The system is designed with three core layers to achieve three types of intelligent scientific research closed loops. First, the Scientific Intent Research and Demonstration Layer parses the research objectives and intents of scientists (e.g., solar physicists) through natural language interaction, achieving a closed loop for the generation and optimization of executable observation plans aligned with scientific intent via in-depth research. Subsequently, the Observation Realization Layer schedules embodied intelligent solar telescopes to implement a closed loop for the execution of scientific observation plans. Finally, the Evaluation and Evolution Layer coordinates intelligent agents for data processing and scientific analysis to analyze observation data, generate research reports, and iteratively optimize observation strategies and model methods based on results, thereby realizing a self-evolving closed loop for the entire system. During the research process, we constructed a minimal prototype system based on a precision temperature control device for solar telescope birefringent filters to validate the core principles of SIDEST. This prototype successfully implemented all key steps of intention-driven automated research, demonstrating the feasibility of the technical pathways for the three types of intelligent research closed loops. SIDEST redefines telescopes through cutting-edge AI methods.

astro-ph.IM↗

arXiv2025

A Vision-Language Model for Focal Liver Lesion Classification

Accurate classification of focal liver lesions is crucial for diagnosis and treatment in hepatology. However, traditional supervised deep learning models depend on large-scale annotated datasets, which are often limited in medical imaging. Recently, Vision-Language models (VLMs) such as Contrastive Language-Image Pre-training model (CLIP) has been applied to image classifications. Compared to the conventional convolutional neural network (CNN), which classifiers image based on visual information only, VLM leverages multimodal learning with text and images, allowing it to learn effectively even with a limited amount of labeled data. Inspired by CLIP, we pro-pose a Liver-VLM, a model specifically designed for focal liver lesions (FLLs) classification. First, Liver-VLM incorporates class information into the text encoder without introducing additional inference overhead. Second, by calculating the pairwise cosine similarities between image and text embeddings and optimizing the model with a cross-entropy loss, Liver-VLM ef-fectively aligns image features with class-level text features. Experimental results on MPCT-FLLs dataset demonstrate that the Liver-VLM model out-performs both the standard CLIP and MedCLIP models in terms of accuracy and Area Under the Curve (AUC). Further analysis shows that using a lightweight ResNet18 backbone enhances classification performance, particularly under data-constrained conditions.

cs.CV↗

arXiv2019

Some Experimental Results of Relieving Discomfort in Virtual Reality by Disturbing Feedback Loop in Human Brain

Recently, great progress has been made in virtual reality(VR) research and application. However, virtual reality faces a big problem since its appearance, i.e. discomfort (nausea, stomach awareness, etc). Discomfort can be relieved by increasing hardware (sensor, cpu and display) speed. But this will increase cost. This paper gives another low cost solution. The phenomenon of cybersickness is explained with the control theory: discomfort arises if feedback scene differs from expectation, so it can be relieved by disturbing feedback loop in human brain. A hardware platform is build to test this explanation. The VR display on a Samsung S6 is blurred while head movement is detected. The effect is evaluated by comparing responses to the Simulated Sickness Questionnaire (SSQ) between a control and experimental condition. Experimental results show that the new method can ease discomfort remarkably with little extra cost. As a result, VR may be used more widely in teaching (like foreign language, medicine). It's also reasonable to expect likewise merits in other VR applications.

cs.HC↗

arXiv1999

Inclusive and Direct Photons in S + Au Central Collisions at 200A GeV/c

A hadron and string cascade model, JPCIAE, which is based on LUND string model, PYTHIA event generator especially, is used to study both inclusive photon production and direct photon production in 200A GeV S + Au central collisions. The model takes into account the photon production from the partonic QCD scattering process, the hadronic final-state interaction, and the hadronic decay and deals with them consistently. The results of JPCIAE model reproduce successfully both the WA93 data of low p_T inclusive photon distribution and the WA80 data of transverse momentum dependent upper limit of direct photon. The photon production from different decay channels is investigated for both direct and inclusive photons. We have discussed the effects of the partonic QCD scattering and the hadronic final-state interaction on direct photon production as well.

nucl-th↗

arXiv1999

$J/ψ$ normal and anomalous suppressions in a hadron and string cascade model

A mechanism for the effective dissociation of a $c\bar{c}$ pair in the colour electric field of strings is introduced into a hadron and string cascade model, i.e. JPCIAE, which is based on the LUND model, simulating ultra-relativistic nucleus - nucleus collisions. This new mechanism together with the known mechanism of nuclear absorption (both baryons and mesons) could reproduce fairly the data of the normal and anomalous $J/ψ$ suppressions in minimum bias pA, AB (with light projectile), and Pb + Pb collisions at 200 A GeV/c. However the impact parameter (E_T) dependence of the $J/ψ$ suppression factor, both, in S + U and Pb + Pb reactions at 200 A GeV/c and 158 A GeV/c, respectively, is not well reproduced. We also tested the additional mechanism of the energy degradation of leading particles, with which both, the normal and anomalous $J/ψ$ suppressions in minimum bias pA, AB, and Pb + Pb collisions and the E_T dependence of the $J/ψ$ suppression factor are better reproduced.

nucl-th↗

arXiv1998

Formation time effect on J/ψdynamical nuclear suppression

The proposed hadronic and string cascade model, JPCIAE, for ultrarelativistic nucleus - nucleus collisions based on the LUND model and the PYTHIA event generator especially, is used to investigate the $J/ψ$ suppression due to the nuclear absorption of a $J/ψ$ in minimum bias pA and BA collisions at 200 A GeV energy. With the different sets of reasonable formation time for hadron and $J/ψ$ the results of $J/ψ$ suppression factor from both the usual scenario and the Glauber - like simulations are comparable with all the NA38 pA and BA data, except the NA50 data of Pb + Pb collisions. However, the difference between the usual scenario and the Glauber - like simulation, hence the difference between the dynamical simulation and Glauber theory, can not be ignored. The sensitive effect of the hadron formation time on the $J/ψ$ suppression is studied in detail. The results seem to denote that for the $J/ψ$ suppression the meson absorption plays role in pA as well as in BA collisions.

nucl-th↗