Show newer

Domination in Graph Theory: A Bibliometric Analysis of Research Trends, Collaboration and Citation Networks arxiv.org/abs/2503.08690 .SI .DL

Out-of-Distribution Segmentation in Autonomous Driving: Problems and State of the Art arxiv.org/abs/2503.08695 .IV .CV .RO

Blockchain As a Platform For Artificial Intelligence (AI) Transparency arxiv.org/abs/2503.08699 .CR .AI .CY

Real-Time Semantic Segmentation of Aerial Images Using an Embedded U-Net: A Comparison of CPU, GPU, and FPGA Workflows arxiv.org/abs/2503.08700 .CV .AI .AR .LG

SDTrack: A Baseline for Event-based Tracking via Spiking Neural Networks arxiv.org/abs/2503.08703 .NE .CV

A Secure Blockchain-Assisted Framework for Real-Time Maritime Environmental Compliance Monitoring arxiv.org/abs/2503.08707 .CR .ET

TH-Bench: Evaluating Evading Attacks via Humanizing AI Text on Machine-Generated Text Detectors arxiv.org/abs/2503.08708 .CR .AI

An Improved Adaptive Orthogonal Basis Deflation Method for Multiple Solutions with Applications to Nonlinear Elliptic Equations in Varying Domains arxiv.org/abs/2503.07624 .NA .OC .NA

An Improved Adaptive Orthogonal Basis Deflation Method for Multiple Solutions with Applications to Nonlinear Elliptic Equations in Varying Domains

Multiple solutions are common in various non-convex problems arising from industrial and scientific computing. Nonetheless, understanding the nontrivial solutions' qualitative properties seems limited, partially due to the lack of efficient and reliable numerical methods. In this paper, we design a dedicated numerical method to explore these nontrivial solutions further. We first design an improved adaptive orthogonal basis deflation method by combining the adaptive orthogonal basis method with a bisection-deflation algorithm. We then apply the proposed new method to study the impact of domain changes on multiple solutions of certain nonlinear elliptic equations. When the domain varies from a circular disk to an elliptical disk, the corresponding functional value changes dramatically for some particular solutions, which indicates that these nontrivial solutions in the circular domain may become unstable in the elliptical domain. Moreover, several theoretical results on multiple solutions in existing literature are verified. For the nonlinear Sine-Gordon equation with parameter $λ$, nontrivial solutions are found for $λ> λ_2$, here $λ_2$ is the second eigenvalue of the corresponding linear eigenvalue problem. For the singularly perturbed Ginzburg-Landau equation, highly concentrated solutions are numerically found which suggests that their convergent limit is a delta function when the perturbation parameter goes to zero

arXiv.org

Psychological Counseling Ability of Large Language Models arxiv.org/abs/2503.07627 .LG .AI .CL .CY

Psychological Counseling Ability of Large Language Models

With the development of science and the continuous progress of artificial intelligence technology, Large Language Models (LLMs) have begun to be widely utilized across various fields. However, in the field of psychological counseling, the ability of LLMs have not been systematically assessed. In this study, we assessed the psychological counseling ability of mainstream LLMs using 1096 psychological counseling skill questions which were selected from the Chinese National Counselor Level 3 Examination, including Knowledge-based, Analytical-based, and Application-based question types. The analysis showed that the correctness rates of the LLMs for Chinese questions, in descending order, were GLM-3 (46.5%), GPT-4 (46.1%), Gemini (45.0%), ERNIE-3.5 (45.7%) and GPT-3.5 (32.9%). The correctness rates of the LLMs for English questions, in descending order, were ERNIE-3.5 (43.9%), GPT-4 (40.6%), Gemini (36.6%), GLM-3 (29.9%) and GPT-3.5 (29.5%). A chi-square test indicated significant differences in the LLMs' performance on Chinese and English questions. Furthermore, we subsequently utilized the Counselor's Guidebook (Level 3) as a reference for ERNIE-3.5, resulting in a new correctness rate of 59.6%, a 13.8% improvement over its initial rate of 45.8%. In conclusion, the study assessed the psychological counseling ability of LLMs for the first time, which may provide insights for future enhancement and improvement of psychological counseling ability of LLMs.

arXiv.org

A finite element model to analyze crack-tip fields in a transversely isotropic strain-limiting elastic solid arxiv.org/abs/2503.07628 .NA .NA

A finite element model to analyze crack-tip fields in a transversely isotropic strain-limiting elastic solid

This paper presents a finite element model for the analysis of crack-tip fields in a transversely isotropic strain-limiting elastic body. A nonlinear constitutive relationship between stress and linearized strain characterizes the material response. This algebraically nonlinear relationship is critical as it mitigates the physically inconsistent strain singularities that arise at crack tips. These strain-limiting relationships ensure that strains remain bounded near the crack tip, representing a significant advancement in the formulation of boundary value problems (BVPs) within the context of first-order approximate constitutive models. For a transversely isotropic elastic material containing a crack, the equilibrium equation, derived from the balance of linear momentum under a specified nonlinear constitutive relation, is shown to reduce to a second-order, vector-valued, quasilinear elliptic BVP. A robust numerical method is introduced, integrating Picard-type linearization with a continuous Galerkin-type finite element procedure for spatial discretization. Numerical results, obtained for tensile loading conditions and two distinct material fiber orientations, illustrate that the evolution of crack-tip strains occurs significantly slower than that of the normalized stresses. However, the strain-energy density is most pronounced near the crack tip, consistent with observations from linearized elasticity theory. It is demonstrated that the framework investigated herein can serve as a basis for formulating physically meaningful and mathematically well-defined BVPs, which are essential for exploring crack evolution, damage, nucleation, and failure in anisotropic strain-limiting elastic materials.

arXiv.org

FourierNAT: A Fourier-Mixing-Based Non-Autoregressive Transformer for Parallel Sequence Generation arxiv.org/abs/2503.07630 .LG .CL

FourierNAT: A Fourier-Mixing-Based Non-Autoregressive Transformer for Parallel Sequence Generation

We present FourierNAT, a novel non-autoregressive Transformer (NAT) architecture that employs Fourier-based mixing in the decoder to generate output sequences in parallel. While traditional NAT approaches often face challenges with capturing global dependencies, our method leverages a discrete Fourier transform to mix token embeddings across the entire sequence dimension, coupled with learned frequency-domain gating. This allows the model to efficiently propagate context without explicit autoregressive steps. Empirically, FourierNAT achieves competitive results against leading NAT baselines on standard benchmarks like WMT machine translation and CNN/DailyMail summarization, providing significant speed advantages over autoregressive Transformers. We further demonstrate that learned frequency-domain parameters allow the model to adaptively focus on long-range or short-range dependencies, partially mitigating the well-known coherence gaps in one-pass NAT generation. Overall, FourierNAT highlights the potential of integrating spectral-domain operations to accelerate and improve parallel text generation. This approach can potentially provide great computational and time savings in inference tasks LLMs.

arXiv.org

A Quantum Neural Network Transfer-Learning Model for Forecasting Problems with Continuous and Discrete Variables arxiv.org/abs/2503.07633 -ph .SY .LG .SY

A Quantum Neural Network Transfer-Learning Model for Forecasting Problems with Continuous and Discrete Variables

This study introduces a continuous-variable quantum neural network (CV-QNN) model designed as a transfer-learning approach for forecasting problems. The proposed quantum technique features a simple structure with only eight trainable parameters, a single quantum layer with two wires to create entanglement, and ten quantum gates, hence the name QNNet10, effectively mimicking the functionality of classical neural networks. A notable aspect is that the quantum network achieves high accuracy with random initialization after a single iteration. This pretrained model is innovative as it requires no training or parameter tuning when applied to new datasets, allowing for parameter freezing while enabling the addition of a final layer for fine-tuning. Additionally, an equivalent discrete-variable quantum neural network (DV-QNN) is presented, structured similarly to the CV model. However, analysis shows that the two-wire DV model does not significantly enhance performance. As a result, a four-wire DV model is proposed, achieving comparable results but requiring a larger and more complex structure with additional gates. The pretrained model is applied to five forecasting problems of varying sizes, demonstrating its effectiveness.

arXiv.org

Impact of Level 2/3 Automated Driving Technology on Road Work Zone Safety arxiv.org/abs/2503.07634 .AI .MA .RO

Impact of Level 2/3 Automated Driving Technology on Road Work Zone Safety

As China's road network enters the maintenance era, work zones will become a common sight on the roads. With the development of automated driving, vehicles equipped with Level 2/3 automated driving capabilities will also become a common presence on the roads. When these vehicles pass through work zones, automated driving may disengage, which can have complex effects on traffic safety. This paper explores the impact of Level 2/3 automated driving technology on road safety in high-speed highway work zone environments. Through microscopic traffic simulation method and using full-type traffic conflict technique, factors such as market penetration rate (MPR), traffic volume level, disengagement threshold, and driver takeover style are studied to understand their impact on work zone safety. The study found that the impact of automated driving technology on work zone safety is complex. Disengagement of automated vehicles in work zones reduces the proportion of vehicles that can maintain automated driving status. If takeover is not timely or adequate, it can easily lead to new traffic conflicts. Different factors have varying degrees of impact on work zone safety. Increasing MPR helps reduce the occurrence of single-vehicle conflicts, but it also increases the possibility of multi-vehicle conflicts. Therefore, future research and improvement directions should focus on optimizing the disengagement detection and takeover mechanisms of automated driving systems.

arXiv.org

OPTIC: Optimizing Patient-Provider Triaging & Improving Communications in Clinical Operations using GPT-4 Data Labeling and Model Distillation arxiv.org/abs/2503.05701 .LG .CL

OPTIC: Optimizing Patient-Provider Triaging & Improving Communications in Clinical Operations using GPT-4 Data Labeling and Model Distillation

The COVID-19 pandemic has accelerated the adoption of telemedicine and patient messaging through electronic medical portals (patient medical advice requests, or PMARs). While these platforms enhance patient access to healthcare, they have also increased the burden on healthcare providers due to the surge in PMARs. This study seeks to develop an efficient tool for message triaging to reduce physician workload and improve patient-provider communication. We developed OPTIC (Optimizing Patient-Provider Triaging & Improving Communications in Clinical Operations), a powerful message triaging tool that utilizes GPT-4 for data labeling and BERT for model distillation. The study used a dataset of 405,487 patient messaging encounters from Johns Hopkins Medicine between January and June 2020. High-quality labeled data was generated through GPT-4-based prompt engineering, which was then used to train a BERT model to classify messages as "Admin" or "Clinical." The BERT model achieved 88.85% accuracy on the test set validated by GPT-4 labeling, with a sensitivity of 88.29%, specificity of 89.38%, and an F1 score of 0.8842. BERTopic analysis identified 81 distinct topics within the test data, with over 80% accuracy in classifying 58 topics. The system was successfully deployed through Epic's Nebula Cloud Platform, demonstrating its practical effectiveness in healthcare settings.

arXiv.org
Show older
Qoto Mastodon

QOTO: Question Others to Teach Ourselves
An inclusive, Academic Freedom, instance
All cultures welcome.
Hate speech and harassment strictly forbidden.