arXiv subjects

Yingzhe Wang

Publications and source records attributed to Yingzhe Wang.

5 recordsLinked to original sources

arXiv2026

Controlled McKean--Vlasov Contagion with State-Dependent Killing

We study controlled McKean--Vlasov contagion with state-dependent killing, common noise, loss feedback, and interacting populations. The main result is a comparison principle for the two-population killed-particle HJB on a decomposed state space of alive sub-probability measures and cemetery masses. The proof combines a Wasserstein smooth-gauge comparison argument with a killing-jump absorption estimate for mass transfer into the cemetery state. We also establish a multi-population mean-field limit, an explicit first-order particle convergence rate, conditional propagation of chaos, controlled well-posedness, and a steep-killing bridge to absorbing-boundary default. Finite-particle convergence tests and a two-population HJB feedback experiment illustrate the theory.

math.OC↗

arXiv2026

Robust Cross-Domain WiFi Fall Detection via Physics-Driven Attention-Enhanced Transformers

Device-free fall detection utilizing WiFi Channel State Information (CSI) has emerged as a promising, privacy-preserving solution for elderly health monitoring in the Internet of Things (IoT) era. However, existing deep learning approaches suffer from severe performance degradation when deployed in unseen environments due to static background overfitting and Non-Line-of-Sight (NLoS) signal attenuation. To address these critical bottlenecks, we propose a robust, domain-generalizable framework featuring a novel Attention-Enhanced CNN-Transformer hybrid architecture. First, we design a physics-driven \textbf{Dynamic Variance Gate (DVG)} to dynamically calculate local temporal variance, acting as a soft-attention mask that eliminates static environmental DC components while amplifying dynamic human motion. Second, we introduce a Physics-Aware Data Augmentation strategy to force the network to learn invariant morphological signatures rather than environment-specific noise. Furthermore, a Convolutional Block Attention Module (CBAM) is integrated to refine spatiotemporal features prior to Transformer-based sequence modeling. Extensive cross-domain evaluations across four distinct indoor environments demonstrate that our method achieves 97.6\% accuracy in NLoS scenarios and 98.8\% in completely unseen environments without target-domain fine-tuning. Finally, we deploy the proposed framework on an edge computing system equipped with commercial WiFi NICs. Real-world live inference field tests confirm the system's robustness against unseen environmental layouts and its capability for continuous, low-latency whole-home safety monitoring.

eess.SP↗

arXiv2024

A Hybrid Neural Network Model For Predicting The Nitrate Concentration In The Recirculating Aquaculture System

This study was groundbreaking in its application of neural network models for nitrate management in the Recirculating Aquaculture System (RAS). A hybrid neural network model was proposed, which accurately predicted daily nitrate concentration and its trends using six water quality parameters. We conducted a 105-day aquaculture experiment, during which we collected 450 samples from five sets of RAS to train our model (C-L-A model) which incorporates Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), and self-Attention. Furthermore, we obtained 90 samples from a standalone RAS as the testing data to evaluate the performance of the model in practical applications. The experimental results proved that the C-L-A model accurately predicted nitrate concentration in RAS and maintained good performance even with a reduced proportion of training data. We recommend using water quality parameters from the past 7 days to forecast future nitrate concentration, as this timeframe allows the model to achieve maximum generalization capability. Additionally, we compared the performance of the C-L-A model with three basic neural network models (CNN, LSTM, self-Attention) as well as three hybrid neural network models (CNN-LSTM, CNN-Attention, LSTM-Attention). The results demonstrated that the C-L-A model (R2=0.956) significantly outperformed the other neural network models (R2=0.901-0.927). Our study suggests that the utilization of neural network models, specifically the C-L-A model, could potentially assist the RAS industry in conserving resources for daily nitrate monitoring.

cs.CE↗

arXiv2023

Enhance the Field Strength by Adding Soft Iron in the Hybrid Permanent magnet

Permanent magnet has a small and compact structure, is especially suitable for a narrow space. With the aid of soft iron, the magnetic field can be increased much more and the field uniformity can be well controlled. Most Permanent magnets have a symmetry structure; the soft iron can be selected as the float magnet pole to keep its constant scalar potential, and take roles as media to collect the direct flux from the permanent blocks, then release indirect flux in magnet aperture and to the nearby return yoke. This paper presents the magnetic flux method to design and fabricate a hybrid permanent dipole by using axially and radially magnetized permanent blocks. A variable gradient permanent quadrupole and a variable gradient sextupole are designed as the extend design examples . They all consist of two nested hybrid permanent rings, where the iron poles are used to control the field quality, collect the magnetic flux from the outer ring, block the skew quadrupole and high order harmonics.

physics.acc-ph↗

arXiv2021

Development of a novel transposed cable with in-plane bending of HTS tapes (X-cable)

A compact HTS cable that is able to carry large current density is crucial for developing high field accelerator magnets. We are reporting a novel HTS cable (named X-cable) that could achieve a high current density as the Roebel cable, but is implemented by in-plane bending stacked HTS tapes directly to realize the transposition. The cable is jointly developed with an industrial company on a production line: ready for large scale production from the beginning. Recently, a prototype cable with REBCO coated conductor has been successfully fabricated. Test results show no significant degradation, demonstrated the feasibility of such cable concept. In this paper, the cable's design concept, in-plane bending performance of the REBCO tapes, fabrication procedure and test results of this first prototype cable will be presented.

physics.acc-ph↗