Searcharxiv⌕ Search

arXiv subjects

Yanru Li

Publications and source records attributed to Yanru Li.

6 recordsLinked to original sources

Clinician Assessment of Laryngeal Disease with Auditory AI before Laryngoscopy: A Paired Reader Study

Background: Before laryngoscopy, clinicians assess the likely cause of hoarseness and whether to suspect a precancerous or malignant lesion. Whether voice-based artificial intelligence (AI) supports pre-laryngoscopic categorization is unknown. Methods: We developed an auditory large language model that generates a patient-level assessment card (provisional category, voice-quality ratings, and rationale) and a prespecified malignancy alert from voice recordings, patient information, and acoustic measures obtained before laryngoscopy at one center. We evaluated both in a held-out test set and a later cohort. In a sequential reader study, 32 otolaryngology clinicians categorized held-out cases without AI and, 1 to 2 weeks later, reviewed their initial categories with the card (without the alert). Results: Across 800 paired assessments, reader accuracy was 49.8% before and 56.8% after review (difference, 7.0 percentage points; 95% CI, 1.7 to 13.5; P < 0.001); 99 categories changed from incorrect to correct and 43 from correct to incorrect (ratio, 2.30; 95% CI, 1.22 to 5.31). Accuracy rose 14.7 points when the model was correct and fell 8.7 when incorrect. Provisional-category accuracy was 72% in held-out testing and 67% in temporal validation. The malignancy alert flagged 85.7% and 86.8% of precancerous or malignant lesions. Sensitivity for precancerous or malignant lesions increased from 53.9% to 75.0% after AI-assisted review (difference, 21.1 percentage points; 95% CI, 4.3 to 42.0). Conclusions: In this single-center study, clinicians' pre-laryngoscopic categorization accuracy was higher after reviewing the AI assessment card, although the sequential design cannot fully separate AI assistance from reassessment; gains depended on model correctness without clearly selective adoption. Randomized and external evaluations, including of the malignancy alert, are needed.

eess.AS↗

Action-Guided Reachability for Deterministic World Models of Vision-Based Systems

End-to-end vision-based controllers map raw camera images directly to control actions, yet verifying their closed-loop behavior remains challenging: no analytical model maps a physical state to a camera image, and propagating a set of states through high-dimensional images yields loose reachable sets. We address both challenges with two techniques. First, we propose a Deterministic World Model (DWM), a latent-free decoder that generates camera images only from the physical state, trained with a saliency-weighted reconstruction loss and a control-consistency loss. The DWM replaces the camera in the closed loop, so a sound and tight reachable tube of the surrogate closed loop can be computed without bounding any latent variables. Second, we propose an action-guided partition-and-verify scheme that certifies as many initial sets as possible within a fixed computation budget. A Gaussian process learned from cheap simulations orders the cells and splits those that lie across the property boundary, while every other unknown cell is split along the state dimension that most changes the controller's actions along the simulated closed loop, i.e., the one that most reduces the pixel uncertainty reaching the controller. On a CARLA braking system and three Gym benchmarks, the DWM is more accurate to the real camera than a cGAN surrogate and yields 1.9x to 69x narrower robustness intervals. The vision part causes most of the remaining overapproximation, and our splitting reduces the unknown fraction of the four-dimensional CartPole initial set from 21.88% to 8.18% within the budget.

cs.CV↗

A Network for structural dense displacement based on 3D deformable mesh model and optical flow

This study proposes a Network to recognize displacement of a RC frame structure from a video by a monocular camera. The proposed Network consists of two modules which is FlowNet2 and POFRN-Net. FlowNet2 is used to generate dense optical flow as well as POFRN-Net is to extract pose parameter H. FlowNet2 convert two video frames into dense optical flow. POFRN-Net is inputted dense optical flow from FlowNet2 to output the pose parameter H. The displacement of any points of structure can be calculated from parameter H. The Fast Fourier Transform (FFT) is applied to obtain frequency domain signal from corresponding displacement signal. Furthermore, the comparison of the truth displacement on the First floor of the First video is shown in this study. Finally, the predicted displacements on four floors of RC frame structure of given three videos are exhibited in the last of this study.

cs.CV↗

Nearest-Neighboring Pairing of Monolayer NbSe2 Facilitates the Emergence of Topological Superconducting States

NbSe2, which simultaneously exhibits superconductivity and spin-orbit coupling, is anticipated to pave the way for topological superconductivity and unconventional electron pairing. In this paper, we systematically study topological superconducting (TSC) phases in monolayer NbSe2 through mixing on-site s-wave pairing (ps) with nearest-neighbor pairing (psA1) based on a tight-binding model. We observe rich phases with both fixed and sensitive Chern numbers (CNs) depending on the chemical potential (μ) and out-of-plane magnetic field (Vz). As the psA1 increases, the TSC phase manifests matching and mismatching features according to whether there is a bulk-boundary correspondence (BBC). Strikingly, the introduction of mixed wave pairing significantly reduces the critical Vz to form TSC phases compared with the pure s-wave paring. Moreover, the TSC phase can be modulated even at Vz=0 under appropriate μ and psA1, which is identified by the robust topological edge states (TESs) of ribbons. Additionally, the mixed pairing influences the hybridization of bulk and edge states, resulting in a matching/mismatching BBC with localized/oscillating TESs on the ribbon. Our finding is helpful for the realization of TSC states in experiment, as well as designing and regulating TSC materials.

cond-mat.supr-con↗

Current controlled non-hysteresis magnetic switching in the ansence of magnetic field

By means of local ion implantation, we investigated the influence of lateral interface on current-induced magnetic switching by spin-orbit torque in a perpendicularly magnetized Pt/Co/Ta multilayer. The experimental results show that, in this system, the domain wall motion under electrical current can be affected by two mechanisms: symmetry breaking and current-driven Néel wall motion at the lateral interface. The dominant mechanism is symmetry breaking (current-driven Néel wall motion) at the large (small) current. Due to the competitive relationship of these two mechanisms, the non-hysteresis effect magnetic switching without an external magnetic field is obtained. Based on the non-hysteresis effect magnetic switching, we can realize AND and OR logic gates without resetting.

physics.app-ph↗

All-Linear Multistate Magnetic Switching Induced by Electrical Current

We present an alternative mechanism to control the domain wall motion, whose directions are manipulated by the amplitude of electrical currents when modulating the ratio of D/A (constants of Dzyaloshinskii-Moriya interaction over exchange interaction). To confirm this mechanism, we observe this type of domain wall motion and demonstrate linear magnetic switching without hysteresis effect via adjusting the D/A of Ta/Pt/Co/Ta multilayer device with ion implantations. We further find field-free biased and chirally controllable multistate switching at the lateral interface of ion exposed and unexposed area, which is due to the current induced Neel wall motion and a strong exchange coupling at this interface.

physics.app-ph↗