检索结果-内蒙古大学图书馆

Structure-Based Robust Fractal Graph Neural Network with Molecular Fingerprint BERT for Molecular Property Prediction

引用

IEEE Transactions on Emerging Topics in Computational Intelligence 2025年

作者： Dong, Yaguo Xu, Meiling Tang, Lixin Northeastern University National Frontiers Science Center for Industrial Intelligence and Systems Optimization Shenyang110819 China Shenyang110819 China Liaoning Engineering Laboratory of Data Analytics and Optimization for Smart Industry Shenyang110819 China Liaoning Key Laboratory of Manufacturing System and Logistics Optimization Shenyang110819 China

Accurate molecular property prediction is of great importance for AI-based drug design and bioinformatics. Despite recent promising progress, existing methods face challenges due to insufficient data labeling and imbalanced label distribution. Moreover, many current molecular property prediction models are based on 2D molecular graphs, neglecting the 3D characteristics of molecules. Therefore, in this paper, we propose the structure-based robust fractal graph neural network with Molecular Fingerprint Bidirectional Encoder Representations from Transformers (MFBERT) model for molecular property prediction. We construct the pre-trained MFBERT model to explore the use of unlabeled data and obtain representations from molecular extended connectivity fingerprints as the node features of molecular graphs. Then we design the fractal graph neural network that incorporates molecular 3D conformations while ensuring equivariance to molecular rotations and translations. A 3D feature extraction module and a coordinate update module are proposed to enhance the model's ability to capture molecular structural features. Additionally, weighted-gradient distributionally robust optimization is combined with the gradient descent algorithm to update model parameters, which can mitigate issues stemming from imbalanced label distribution and improve the robustness of our model. We conducted experiments on seven datasets from MoleculeNet, comprising three regression tasks and four classification tasks. Our method achieves the state-of-the-art performance compared to the existing models on all these datasets, which demonstrates its effectiveness for molecular property prediction. Additionally, we conducted ablation experiments on our designed modules, further validating the necessity of each component in our method. © 2025 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

TRDM: A Two-stage Real-time Discrimination Method for Spiral Weld Defects under Dynamic Distorted Imaging

引用

IEEE Transactions on Automation Science and Engineering 2025年 22卷 15420-15434页

作者： Cui, Wenqi Song, Kechen Zhang, Yu Jia, Xiujian Liu, Xiaozheng Yan, Yunhui Northeastern University School of Mechanical Engineering and Automation Liaoning Shenyang 110819 China Northeastern University National Frontiers Science Center for Industrial Intelligence and Systems Optimization Shenyang 110819 China Northeastern University Ministry of Education Key Laboratory of Data Analytics and Optimization for Smart Industry China

Non-destructive testing of weld based on radio-graphic images is crucial for quality control of spiral steel pipes. However, accurately discriminating defect images from high-resolution and low-contrast weld images remains a challenging task. Moreover, the real-time imaging of radiography in industrial settings introduces dynamic distorted interferences to weld images, which has received limited attention in existing research. To address these issues, we propose a two-stage real-time discrimination method (TRDM) consisting of two carefully designed networks: an extremely lightweight weld region segmentation network and a semantic reconstruction-based discrimination network. Our method aims to adaptively reduce interference from invalid regions in the weld images to better exploit defect features from a semantic perspective and reconstruct them as defect-free regions as much as possible. To overcome the scarcity of weld defect image data, we construct two publicly available industrial weld datasets, including an image dataset and a video dataset. TRDM achieves competitive performance with state-of-the-art techniques, demonstrating its effectiveness in discriminating weld images. Furthermore, we integrate the TRDM into developed detection software for defect assessment, validating its efficacy in real welding scenarios. © 2004-2012 IEEE.

关键词： Non-destructive testing penetration state recognition quality monitoring weld defect detection

来源：评论

学校读者我要写书评

暂无评论

Robust inference of gravitational wave source parameters in the presence of noise transients using normalizing flows

引用

Physical Review D 2025年第2期111卷 024019-024019页

作者： Chun-Yu Xiong Tian-Yang Sun Jing-Fei Zhang Xin Zhang Liaoning Key Laboratory of Cosmology and Astrophysics College of Sciences Northeastern University Shenyang 110819 China MOE Key Laboratory of Data Analytics and Optimization for Smart Industry Northeastern University Shenyang 110819 China National Frontiers Science Center for Industrial Intelligence and Systems Optimization Northeastern University Shenyang 110819 China

Gravitational wave (GW) detection is of paramount importance in fundamental physics and GW astronomy, yet it presents formidable challenges. One significant challenge is the removal of noise transient artifacts known as “glitches,” which greatly impact the search and identification of GWs. Recent research has achieved remarkable results in data denoising, often using effective modeling methods to remove glitches. However, for glitches from uncertain or unknown sources, current methods cannot completely eliminate them from the GW signal. In this work, we leverage the inherent robustness of machine learning to obtain reliable posterior parameter distributions directly from GW data contaminated by glitches. Our network model provides reasonable and rapid parameter inference even in the presence of glitches, without needing to remove them. We also investigate various factors affecting the rationality of parameter inference in our normalizing flow network, including glitch and GW parameters. The results demonstrate that the normalizing flow can reasonably infer the source parameters of GWs even with unknown contamination. We find that the nature of the glitch itself is the only factor that can affect the rationality of the inferred results. With improvements to our model, we anticipate accelerating the localization of electromagnetic counterparts and providing priors for more accurate deglitching, thereby speeding up subsequent data processing procedures.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Effect of high silicon content in enhancing the creep properties of a PM near-α Ti–6Al–2Sn–4Zr–2Mo–0.5Y–0.5Si alloy

引用

Journal of Materials Research and Technology 2025年 36卷 4864-4881页

作者： Xuemei Yu Fuyang Yu Bowen Zhang Xiaogang Wu Hongzhi Niu Deliang Zhang School of Material Science and Engineering Northeastern University Shenyang 110819 China National Frontiers Science Center for Industrial Intelligence and Systems Optimization Northeastern University Shenyang 110819 China Key Laboratory of Data Analytics and Optimization for Smart Industry (Ministry of Education) Northeastern University Shenyang 110819 China

This study investigates the effect of high Si content on the creep properties and deformation mechanisms of a powder metallurgy (PM) near-α titanium alloy with a composition of Ti–6Al–2Sn–4Zr–2Mo–0.5Y–0.5Si (wt.%) fabricated using high-energy ball milling (HEBM) and thermomechanical powder consolidation (TMC). Under 600 °C/250 MPa, the alloy exhibits a 263 % increase in creep life, a 48 % reduction in steady-state creep rate, and 100 % improvement in creep fracture strain compared with the corresponding titanium alloy containing 0.1 wt% Si under the same fabrication and heat treatment conditions. The superior creep properties are attributed to the stabilized α/β and α/β t interfaces, the uniform dispersion of (Ti, Zr) 6 Si 3 nanoparticles, and the increased Si solubility in both α and β phases, all of which collectively hinder dislocation movement. Additionally, Si addition suppresses the formation of continuous α GB plates, while the presence of higher Si solubility and dispersed nanoscale silicides alleviates stress concentration, delays void and microcrack formation, and ultimately enhances creep fracture strain. These findings underscore the critical role of interface stability, nanoscale silicide dispersion, and enhancing Si solubility in optimizing high-temperature titanium alloys for extreme service environments.

关键词： Near-α titanium alloy Thermomechanical powder consolidation Effect of high silicon content Microstructure Creep property

来源：评论

学校读者我要写书评

暂无评论

Safety Control of Switched Systems via Multiple Barrier Functions

引用

IEEE Transactions on Automatic Control 2025年

作者： Long, Lijun Huang, Chunxiao Sun, Zhendong Northeastern University College of Information Science and Engineering Shenyang110819 China Northeastern University State Key Laboratory of Synthetical Automation for Process Industries Shenyang110819 China Ministry of Education Key Laboratory of Data Analytics and Optimization for Smart Industry Northeastern University China

This paper is concerned with the problem of safety control for switched systems, where different safe sets are allowed for different subsystems and safety is not necessarily possessed for subsystems. A necessary and sufficient condition is presented for safety of switched systems by exploiting a multiple barrier functions (MBFs) method. To reveal the relationship about safety between subsystems and switched systems, an extended Nagumo's Theorem in the switched systems framework is derived. Also, several switched control design conditions are respectively provided to ensure safety of switched systems. Based on the union of MBFs and multiple Lyapunov functions (MLFs), a novel safety-critical control framework is established to simultaneously ensure safety and stability of switched systems. Also, an auxiliary cost function is introduced to transform the safety-critical optimal control (SCOC) problem of switched systems into the one of non-switched systems. Finally, three examples are illustrated to demonstrate the effectiveness of the proposed methods. © 1963-2012 IEEE.

关键词： Lyapunov functions

来源：评论

学校读者我要写书评

暂无评论

Multi-Relational Geometric Regularization Framework for Multi-Modal Emotion Recognition in Conversation

Multi-Relational Geometric Regularization Framework for Mult...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Tao Zhang Zhenhua Tan Software College of Northeastern University Shenyang China National Frontiers Science Center for Industrial Intelligence and Systems Optimization Northeastern University Shenyang China Ministry of Education Key Laboratory of Data Analytics and Optimization for Smart Industry (Northeastern University) China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Existing studies on multi-modal emotion recognition in conversation (MMERC) mainly focus on multi-modal fusion and context modeling for emotion representation, facing limitations in uncovering the intrinsic structure of emotion-related data. The existing geometric consistency regularization (GCR) technique aims to build meaningful latent feature structures in multiple modalities and has been validated for non-conversational data, therefore we further explore its application to the MMERC task, which involves conversational data. However, we find that the geometric consistency in conversational data varies among different speaker and conversation relations (intra-speaker, inter-speaker, and inter-conversation relations), probably due to differences in speaker expressions and conversation topics. This makes the direct application of GCR less effective. To address this issue, we propose a Multi-Relational Geometric Regularization Framework for MMERC (R 4 -MMERC). Our framework constructs geometric structures of conversational data and performs dynamically balanced consistency regularization based on multiple speaker and conversation relations (intra-speaker, interspeaker, and inter-conversation relations). We tested our framework by integrating it with three typical MMERC models on the IEMOCAP benchmark dataset. The results show significant performance improvements, demonstrating the effectiveness of our approach 1 .

关键词： Emotion recognition Computational modeling Oral communication Speech recognition Signal processing Benchmark testing Acoustics Proposals Speech processing Context modeling

来源：评论

学校读者我要写书评

暂无评论

Prospects for measuring neutrino mass with 21-cm forest

arXiv

引用

arXiv 2025年

作者： Shao, Yue Du, Guo-Hong Li, Tian-Nuo Zhang, Xin Liaoning Key Laboratory of Cosmology and Astrophysics College of Sciences Northeastern University Shenyang110819 China National Frontiers Science Center for Industrial Intelligence and Systems Optimization Northeastern University Shenyang110819 China MOE Key Laboratory of Data Analytics and Optimization for Smart Industry Northeastern University Shenyang110819 China

Both particle physics experiments and cosmological observations have been used to explore neutrino properties. Cosmological researches of neutrinos often rely on the early-universe cosmic microwave background observations or other late-universe probes, which mostly focus on large-scale structures. We introduce a distinct probe, the 21-cm forest, that differs from other probes in both time and scale. Actually, the 21-cm forest is a unique tool for studying small-scale structures in the early universe. Below the free-streaming scale, massive neutrinos suppress the matter power spectrum, influencing small-scale fluctuations in the distribution of matter. The one-dimensional (1D) power spectrum of the 21-cm forest can track these fluctuations across different scales, similar to the matter power spectrum, providing an effective method to constrain neutrino mass. Although heating effects in the early universe can also impact the 1D power spectrum of the 21-cm forest, we assess the potential of the 21-cm forest as a tool for measuring neutrino mass, given that the temperature of the intergalactic medium can be constrained using other methods within a certain range. In the ideal scenario, the 21-cm forest observation will have the ability to constrain the total neutrino mass to around 0.1 eV. With the accumulation of observational data and advancements in observational technology, the 21-cm forest holds great promise as an emerging and potent tool for measuring neutrino mass. Copyright © 2025, The Authors. All rights reserved.

关键词： Probes

来源：评论

学校读者我要写书评

暂无评论

Construction of a Neural Network Potential for Fe-Cr-Ni Alloys and its Application in Uniaxial Tension Simulations

SSRN

引用

SSRN 2025年

作者： Wang, Kun Ren, Lin Liu, Zhongqiu Wang, Chun Zhang, Hao National Frontiers Science Center for Industrial Intelligence and Systems Optimization Northeastern University Shenyang110819 China Key Laboratory of Data Analytics and Optimization for Smart Industry Northeastern University Ministry of Education China School of Metallurgy Northeastern University Shenyang110819 China

Fe-Cr-Ni alloys are widely used in industrial applications and serve as crucial high-temperature materials, for which accurate interatomic potential functions are essential for understanding their microstructure and properties. In this study, we developed a machine learning potential (Deep Potential, DP) with high precision for Fe-Cr-Ni alloys using the Deep Potential for Molecular Dynamics (DeePMD) framework combined with an extensive density functional theory (DFT) database. First, eight different crystal structures of the Fe-Cr-Ni system were systematically sampled through high-throughput first-principles calculations. We compared the accuracy of potentials trained on two distinct datasets using the DeepMD model. Subsequently, molecular dynamics simulations were employed to verify the performance of these potentials in predicting crystal structures, thermodynamic properties, and mechanical properties. The results demonstrate that the model trained with heating-process data exhibits superior accuracy in energy and force predictions, achieving root mean square errors (RMSE) of 3.27 meV/atom for atomic energy and 72.4 meV/Å for forces across the eight Fe-Cr-Ni systems. These predictions show excellent agreement with DFT-calculated energies. In large-scale molecular dynamics simulations, the DP demonstrates mechanical accuracy comparable to experimental values. Specifically, the elastic constant of Fe60Cr25Ni15 alloy calculated using the DP is 101.321 GPa, which is within a 1% error compared to the DFT-calculated value of 102.221 GPa. © 2025, The Authors. All rights reserved.

关键词： Crystal atomic structure

来源：评论

学校读者我要写书评

暂无评论

Model-independent H0 within FLRW: Joint constraints from GWTC-3 standard sirens and strong lensing time delays

arXiv

引用

arXiv 2025年

作者： Song, Ji-Yu Qi, Jing-Zhao Zhang, Jing-Fei Zhang, Xin Key Laboratory of Cosmology and Astrophysics Department of Physics College of Sciences Northeastern University Liaoning Province Shenyang110819 China Key Laboratory of Data Analytics and Optimization for Smart Industry Ministry of Education Northeastern University Shenyang110819 China National Frontiers Science Center for Industrial Intelligence and Systems Optimization Northeastern University Shenyang110819 China

The Hubble tension has emerged as a critical crisis in cosmology, with the cause remaining unclear. Determining the Hubble constant (H0) independently of cosmological models and distance ladders will help resolve this crisis. In this letter, we for the first time use 47 gravitational-wave (GW) standard sirens from the third Gravitational-Wave Transient Catalog to calibrate distances in the strong lensing system, RXJ1131-1231, and constrain H0 through the distance-sum rule, with minimal cosmological assumptions. We assume that light propagation over long distances is described by the Friedmann-Lemaitre-Robertson-Walker metric and that geometrical optics holds, but we do not need to assume the universe’s contents or the theory of gravity on cosmological scales. Fixing ΩK = 0, we obtain H0 = 73.22+5−5.9543 km s−1 Mpc−1 and H0 = 70.40+8−5.0360 km s−1 Mpc−1 by using the deflector galaxy’s mass model and kinematic measurements to break mass-sheet transform, respectively. When ΩK is not fixed, the central value of H0 increases further. We find that our results are still dominated by statistical errors, and at the same time, we notice the great potential of using GW dark sirens to provide calibration, owing to their higher redshifts. When using 42 binary black holes and RXJ1131-1231, we obtain a 8.46% H0 constraint precision, which is better than that from the bright siren GW170817 using the Hubble law by about 40%. In the future, as the redshift range of GW dark sirens increases, more and more SGLTDs can be included, and we can achieve high-precision, model-independent measurements of H0 without the need for GW bright sirens. Copyright © 2025, The Authors. All rights reserved.

关键词： Cosmology

来源：评论

学校读者我要写书评

暂无评论

4D-CS: Exploiting Cluster Prior for 4D Spatio-Temporal LiDAR Semantic Segmentation

arXiv

引用

arXiv 2025年

作者： Zhong, Jiexi Li, Zhiheng Cui, Yubo Fang, Zheng The Faculty of Robot Science and Engineering Northeastern University Shenyang110819 China The National Frontiers Science Center for Industrial Intelligence and Systems Optimization Northeastern University Shenyang110819 China Key Laboratory of Data Analytics and Optimization for Smart Industry Ministry of Education Northeastern University Shenyang110819 China

Semantic segmentation of LiDAR points has significant value for autonomous driving and mobile robot systems. Most approaches explore spatio-temporal information of multi-scan to identify the semantic classes and motion states for each point. However, these methods often overlook the segmentation consistency in space and time, which may result in point clouds within the same object being predicted as different categories. To handle this issue, our core idea is to generate cluster labels across multiple frames that can reflect the complete spatial structure and temporal information of objects. These labels serve as explicit guidance for our dual-branch network, 4D-CS, which integrates point-based and cluster-based branches to enable more consistent segmentation. Specifically, in the point-based branch, we leverage historical knowledge to enrich the current feature through temporal fusion on multiple views. In the cluster-based branch, we propose a new strategy to produce cluster labels of foreground objects and apply them to gather point-wise information to derive cluster features. We then merge neighboring clusters across multiple scans to restore missing features due to occlusion. Finally, in the point-cluster fusion stage, we adaptively fuse the information from the two branches to optimize segmentation results. Extensive experiments confirm the effectiveness of the proposed method, and we achieve state-of-the-art results on the multi-scan semantic and moving object segmentation on SemanticKITTI and nuScenes datasets. The code will be available at https://***/NEU-REAL/***. Copyright © 2025, The Authors. All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：