检索结果-内蒙古大学图书馆

Design and hydrodynamic analysis of an automatic deployment device for isolation structure at crossing of offshore oil and gas pipelines

引用

Marine Georesources and Geotechnology 2025年

作者： Luo, Gaosheng Wang, Zhicheng Wang, Fang Liu, Peng Feng, Hu Jiang, Zhe Shanghai Engineering Research Center of Hadal Science and Technology College of Engineering Science and Technology Shanghai Ocean University Shanghai China Offshore Oil Engineering Co. Ltd Installation Company Tianjin China Lanqi Robot Co. Ltd Jiangsu Wuxi China

The development of efficient and safe offshore pipeline isolation systems remains a significant challenge in deep-sea engineering, particularly in mitigating mechanical damage caused by pipeline crossings. This paper proposes an innovative dual-motion (rotational/direct) automatic deployment device to address this challenge. Systematic presentation of the conceptual design and operational workflow is complemented by hydrodynamic analysis via computational fluid dynamics (CFD) simulations using the multiple reference frame (MRF) method. Parametric studies across flow velocities (0.1–1.0 m/s) reveal critical trends: drag force exhibits exponential growth beyond 0.5 m/s during rotational motion, peaking at 22,808.90 N under 1.0 m/s flow, with 99.89% of total drag attributed to flow separation induced by the open-frame structural configuration. During direct motion, a localized high-pressure zone forms on the upstream surface, attaining 781.35 Pa at 1.0 m/s, which necessitates significantly enhanced power output compared to static conditions to ensure stable deployment. These quantitative findings establish a direct linkage between the device’s geometry and hydrodynamic response, providing actionable insights for balancing deployment efficiency and structural resilience. The proposed dual-motion mechanism pioneers a new strategy for deep-sea pipeline protection, demonstrating the viability of adaptive hydrodynamic control in extreme environments. © 2025 Informa UK Limited, trading as Taylor & Francis Group.

关键词： Conceptual design

来源：评论

学校读者我要写书评

暂无评论

SpaGRA:Graph augmentation facilitates domain identification for spatially resolved transcriptomics

引用

Journal of Genetics and Genomics 2025年第1期52卷 93-104页

作者： Xue Sun Wei Zhang Wenrui Li Na Yu Daoliang Zhang Qi Zou Qiongye Dong Xianglin Zhang Zhiping Liu Zhiyuan Yuan Rui Gao Center of Intelligent Medicine School of Control Science and EngineeringShandong UniversityJinanShandong 250061China MOE Key Lab of Bioinformatics and Bioinformatics Division of BNRIST Department of AutomationTsinghua UniversityBeijing 100084China Institute of Precision Medicine Peking University Shenzhen HospitalShenzhenGuangdong 518036China Department of Clinical Laboratory The Second HospitalCheeloo College of MedicineShandong UniversityJinanShandong 250033China Institute of Science and Technology for Brain-Inspired Intelligence Center for Medical Research and InnovationShanghai Pudong HospitalFudan University Pudong Medical CenterFudan UniversityShanghai 200433China

Recent advances in spatially resolved transcriptomics(SRT)have provided new opportunities for characterizing spatial structures of various ***-based geometric deep learning has gained widespread adoption for spatial domain identification ***,most methods define adjacency relation between cells or spots by their spatial distance in SRT data,which overlooks key biological interactions like gene expression similarities,and leads to inaccuracies in spatial domain *** tackle this challenge,we propose a novel method,SpaGRA(https://***/sunxue-yy/SpaGRA),for automatic multi-relationship construction based on graph *** uses spatial distance as prior knowledge and dynamically adjusts edge weights with multi-head graph attention networks(GATs).This helps SpaGRA to uncover diverse node relationships and enhance message passing in geometric contrastive ***,SpaGRA uses these multi-view relationships to construct negative samples,addressing sampling bias posed by random *** results show that SpaGRA presents superior domain identification performance on multiple datasets generated from different *** SpaGRA,we analyze the functional regions in the mouse hypothalamus,identify key genes related to heart development in mouse embryos,and observe cancer-associated fibroblasts enveloping cancer cells in the latest Visium HD ***,SpaGRA can effectively characterize spatial structures across diverse SRT datasets.

关键词： Spatial domain identification Spatially resolved transcriptomics Multi-head graph attention networks Graph augmentation Geometric contrastive learning

来源：评论

学校读者我要写书评

暂无评论

Adaptive Artificial Potential Field Ship Motion Planning Based on DDPG

Adaptive Artificial Potential Field Ship Motion Planning Bas...

引用

International Conference on Artificial Intelligence and Autonomous Transportation, AIAT 2024

作者： Chen, Huimin Liu, Chenguang He, Zhibo Zhang, Guoqing Han, Bing State Key Laboratory of Maritime Technology and Safety Wuhan University of Technology Wuhan430063 China Intelligent Transportation Systems Research Center Wuhan University of Technology Wuhan430063 China School of Transportation and Logistics Engineering Wuhan University of Technology Wuhan430063 China Navigation College Dalian Maritime University Dalian116026 China State Key Laboratory of Maritime Technology and Safety Dalian116026 China National Engineering Research Center of Ship & Shipping Control System Shanghai200134 China

ISBN: (纸本)9789819639601

The paper presents a ship motion planning method that adjusts the attractive and repulsive gain parameters of the artificial potential field (APF) algorithm using the deep deterministic policy gradient (DDPG) algorithm, to address the challenges of parameter design and limited adaptability of traditional APF algorithms. This approach leverages the speed advantage of the APF planning algorithm and the exploration capability of the DDPG reinforcement learning algorithm. By optimizing the parameters of APF with DDPG, the local optima problem can be alleviated in complex obstacle environments. Simulation results demonstrate that the proposed motion planning algorithm can generate reasonable trajectories and exhibit strong adaptability in complex obstacle scenarios. © Beijing Paike Culture Commu. Co., Ltd. 2025.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

VideoPure: Diffusion-based Adversarial Purification for Video Recognition

arXiv

引用

arXiv 2025年

作者： Jiang, Kaixun Chen, Zhaoyu Fu, Jiyuan Hong, Lingyi Li, Jinglun Zhang, Wenqiang Shanghai Engineering Research Center of AI Robotics Academy for Engineering & Technology Fudan University Shanghai China Engineering Research Center of AI & Robotics Ministry of Education Academy for Engineering & Technology Fudan University Shanghai China Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University Shanghai China

—Recent work indicates that video recognition models are vulnerable to adversarial examples, posing a serious security risk to downstream applications. However, current research has primarily focused on adversarial attacks, with limited work exploring defense mechanisms. Furthermore, due to the spatial-temporal complexity of videos, existing video defense methods face issues of high cost, overfitting, and limited defense performance. Recently, diffusion-based adversarial purification methods have achieved robust defense performance in the image domain. However, due to the additional temporal dimension in videos, directly applying these diffusion-based adversarial purification methods to the video domain suffers performance and efficiency degradation. To achieve an efficient and effective video adversarial defense method, we propose the first diffusion-based video purification framework to improve video recognition models’ adversarial robustness: VideoPure. Given an adversarial example, we first employ temporal DDIM inversion to transform the input distribution into a temporally consistent and trajectory-defined distribution, covering adversarial noise while preserving more video structure. Then, during DDIM denoising, we leverage intermediate results at each denoising step and conduct guided spatial-temporal optimization, removing adversarial noise while maintaining temporal consistency. Finally, we input the list of optimized intermediate results into the video recognition model for multi-step voting to obtain the predicted class. We investigate the defense performance of our method against state-of-the-art black-box, gray-box, and adaptive attacks on benchmark datasets and models. Compared with other adversarial purification methods, our method overall demonstrates better defense performance against different attacks. Moreover, our method can be applied as a flexible defense plugin for video recognition models. Our code is available at https://***/deep-kaix

关键词： HTTP

来源：评论

学校读者我要写书评

暂无评论

Distributed Generalized Nash Equilibria Learning for Online Stochastic Aggregative Games

arXiv

引用

arXiv 2025年

作者： Du, Kaixin Meng, Min Shanghai Research Institute for Intelligent Autonomous Systems Tongji University Shanghai200092 China Department of Control Science and Engineering College of Electronics and Information Engineering National Key Laboratory of Autonomous Intelligent Unmanned System Frontiers Science Center for Intelligent Autonomous Systems Ministry of Education Shanghai Research Institute for Intelligent Autonomous Systems Shanghai Institute of Intelligent Science and Technology Tongji University Shanghai China

This paper investigates online stochastic aggregative games subject to local set constraints and time-varying coupled inequality constraints, where each player possesses a time-varying expectation-valued cost function relying on not only its own decision variable but also an aggregation of all the players’ variables. Each player can only access its local individual cost function and constraints, necessitating partial information exchanges with neighboring players through time-varying unbalanced networks. Additionally, local cost functions and constraint functions are not prior knowledge and only revealed gradually. To learn generalized Nash equilibria of such games, a novel distributed online stochastic algorithm is devised based on push-sum and primal-dual strategies. Through rigorous analysis, high probability bounds on the regret and constraint violation are provided by appropriately selecting decreasing stepsizes. Moreover, for a time-invariant stochastic strongly monotone game, it is shown that the generated sequence by the designed algorithm converges to its variational generalized Nash equilibrium (GNE) almost surely, and the time-averaged sequence converges sublinearly with high probability. Finally, the derived theoretical results are illustrated by numerical simulations. Copyright © 2025, The Authors. All rights reserved.

关键词： Nash equilibrium

来源：评论

学校读者我要写书评

暂无评论

Transcriptomic modifications across the genome and potential hazards of pulmonary fibrosis caused by metal-organic frameworks

引用

Science of the Total Environment 2025年 964卷 178504页

作者： Zhang, Yule Yang, Zhijin Chen, Mengya Xue, Zhiwei Chen, Jingwei Zhao, Mantong Li, Yuhao Kang, Shifei Dai, Bo Zheng, Lulu Zhuang, Songlin Zhang, Dawei Engineering Research Center of Optical Instrument and System The Ministry of Education Shanghai Key Laboratory of Modern Optical System Shanghai Engineering Research Center of Environmental Biosafety Instruments and Equipment University of Shanghai for Science and Technology Shanghai200093 China Department of Physics and Electronic Engineering Heze University Heze274015 China College of Science University of Shanghai for Science and Technology Shanghai200093 China Department of Environmental Science and Engineering University of Shanghai for Science and Technology Shanghai200093 China Shanghai Institute of Intelligent Science and Technology Tongji University Shanghai200092 China

Metal-Organic Frameworks (MOFs) have shown great promise in environmental protection, owing to their exceptional properties including ultrahigh surface area and porosity, tunable pore size, and easy chemical functionalization. However, emerging evidence from experimental studies indicates that MOFs have side effects on human health due to metal ions doping, resulting in excessive reactive oxygen species (ROS) production, pro-inflammatory responses, and liver fibrosis. In this study, we investigated the impact of MOF-199 on human bronchial epithelial (HBE) cells by using transcriptome sequencing analysis. The results indicated that the stimulation of MOF-199 enhanced ROS generation, upregulated cytoplasmic Ca2+ levels, then activated the Grb2/SOS/Ras/Raf pathway, induced cell apoptosis, and ultimately resulted in lung fibroblasts through TGF-β secretion. The results were validated in vitro and in vivo. Therefore, it is necessary to carefully evaluate the nanosafety of MOF-199 in environment treatments. © 2025

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

DeTrack: In-model Latent Denoising Learning for Visual Object Tracking

arXiv

引用

arXiv 2025年

作者： Zhou, Xinyu Li, Jinglun Hong, Lingyi Jiang, Kaixun Guo, Pinxue Ge, Weifeng Zhang, Wenqiang Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University Shanghai China Shanghai Engineering Research Center of AI & Robotics Academy for Engineering and Technology Fudan University Shanghai China

Previous visual object tracking methods employ image-feature regression models or coordinate autoregression models for bounding box prediction. Image-feature regression methods heavily depend on matching results and do not utilize positional prior, while the autoregressive approach can only be trained using bounding boxes available in the training set, potentially resulting in suboptimal performance during testing with unseen data. Inspired by the diffusion model, denoising learning enhances the model's robustness to unseen data. Therefore, We introduce noise to bounding boxes, generating noisy boxes for training, thus enhancing model robustness on testing data. We propose a new paradigm to formulate the visual object tracking problem as a denoising learning process. However, tracking algorithms are usually asked to run in real-time, directly applying the diffusion model to object tracking would severely impair tracking speed. Therefore, we decompose the denoising learning process into every denoising block within a model, not by running the model multiple times, and thus we summarize the proposed paradigm as an in-model latent denoising learning process. Specifically, we propose a denoising Vision Transformer (ViT), which is composed of multiple denoising blocks. In the denoising block, template and search embeddings are projected into every denoising block as conditions. A denoising block is responsible for removing the noise in a predicted bounding box, and multiple stacked denoising blocks cooperate to accomplish the whole denoising process. Subsequently, we utilize image features and trajectory information to refine the denoised bounding box. Besides, we also utilize trajectory memory and visual memory to improve tracking stability. Experimental results validate the effectiveness of our approach, achieving competitive performance on several challenging datasets. The proposed in-model latent denoising tracker achieve real-time speed, rendering denoising learning

关键词： Regression analysis

来源：评论

学校读者我要写书评

暂无评论

Leveraging Out-of-Domain Noise for Unsupervised Domain Adaptation in Speech Enhancement

Leveraging Out-of-Domain Noise for Unsupervised Domain Adapt...

引用

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

作者： Yu Liao Haixin Guan Shuang Wei Yanhua Long Shanghai Engineering Research Center of Intelligent Education and Bigdata Shanghai Normal University China Unisound AI Technology Co. Ltd. Beijing China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

When there’s a mismatch between the training and test domains, supervised speech enhancement (SE) models trained on synthetic paired noisy-clean data often struggle in real-world scenarios, highlighting the industry’s strong demand for unsupervised training and domain adaptation methods. In this study, we introduce PHA-ReMixIT, a novel approach for leveraging out-of-domain (OOD) noise signals to enhance unsupervised domain adaptation in SE. Our method builds upon the state-of-the-art ReMixIT by introducing a paired unsupervised remixing technique, which augments the diversity of target domain training data with OOD noise signals. We further propose a heterogeneous noise invariant training to align the OOD augmented noisy mixtures with their paired heterogeneous counterparts, encouraging the model to output cleaner speech. Additionally, an adaptive focal weighting mechanism is also introduced to dynamically emphasize the data importance of both in-domain and OOD noisy mixtures during model adaptation. Experiments on CHiME-7 unsupervised domain adaptation for conversational speech enhancement (UDASE) task demonstrate that PHA-ReMixIT significantly outperforms the ReMixIT baseline, boosting SE performance on both real and synthesized test sets.

关键词： Training Adaptation models Noise Training data Signal processing algorithms Speech enhancement Boosting Data models Acoustics Noise measurement

来源：评论

学校读者我要写书评

暂无评论

Improving Accuracy of the IμUWB Fusion Positioning Approach Utilizing ESEKF and VBUKF for Underground Coal Mining Working Face

引用

IEEE Internet of Things Journal 2025年

作者： Cao, Bo Jiang, Mingrui Li, Menglan Ke, Xuran Zhang, Chao Zhang, Hua Zeng, Qiliang Xu, Biyong Anhui Science and Technology University School of Mechanical Engineering Chuzhou233100 China Hefei University of Technology School of Mechanical Engineering Hefei230041 China Anhui Engineering Research Center on Information Fusion and Control of Intelligent Robot Anhui Wuhu241002 China

The high-precision positioning of the shearer in underground coal mines remains a significant challenge task for realizing automation and intelligent coal mining. Most of the presently conventional positioning approaches, nonetheless, tend to deliver low accuracy and unreliable estimations in the GPSdenied underground coal mine environment. Additionally, the current experiments remain in the simulation verification stage while lacking of the real field experiments. In order to improve reliability and positioning accuracy of target node (TN) in coal mines, this paper proposes a fusion positioning scheme with the combination of the inertial measurement unit (IMU) and Ultrawideband (UWB) based on error state extended Kalman filter (ESEKF) approach with the utilization of the available measurements obtained from IMU system and the established UWB localization system. Subsequently, the VBUKF method that incorporates the variational Bayesian (VB) and unscented Kalman filter (UKF) is implemented to the result of fusion localization with consideration of the changeable measurement noise to further eliminate the trajectory error and refine the final estimation accuracy. Furthermore, to bridge the research gap of the real field experiments using the IμUWB fusion system, the experimental investigation is performed to evaluate the effectiveness of the proposed method in the underground coal mine environment. The experimental results demonstrate that the presented ESEKF method, after applying the VBUKF smoothing, is capable to achieve better performances than the contrasted methods in terms of localization, and also can significantly improve the positioning accuracy of the shearer in the coal mining working face. © 2025 IEEE.

关键词： Coal mines

来源：评论

学校读者我要写书评

暂无评论

Detecting Knowledge Boundary of Vision Large Language Models by Sampling-Based Inference

arXiv

引用

arXiv 2025年

作者： Chen, Zhuo Wang, Xinyu Jiang, Yong Zhang, Zhen Geng, Xinyu Xie, Pengjun Huang, Fei Tu, Kewei School of Information Science and Technology ShanghaiTech University China Shanghai Engineering Research Center of Intelligent Vision and Imaging China Institute for Intelligent Computing Alibaba Group China

Despite the advancements made in Visual Large Language Models (VLLMs), like text Large Language Models (LLMs), they have limitations in addressing questions that require real-time information or are knowledge-intensive. Indiscriminately adopting Retrieval Augmented Generation (RAG) techniques is an effective yet expensive way to enable models to answer queries beyond their knowledge scopes. To mitigate the dependence on retrieval and simultaneously maintain, or even improve, the performance benefits provided by retrieval, we propose a method to detect the knowledge boundary of VLLMs, allowing for more efficient use of techniques like RAG. Specifically, we propose a method with two variants that fine-tunes a VLLM on an automatically constructed dataset for boundary identification. Experimental results on various types of Visual Question Answering datasets show that our method successfully depicts a VLLM’s knowledge boundary based on which we are able to reduce indiscriminate retrieval while maintaining or improving the performance. In addition, we show that the knowledge boundary identified by our method for one VLLM can be used as a surrogate boundary for other VLLMs. Code will be released at https://***/Chord-Chen-30/VLLM-KnowledgeBoundary © 2025, CC BY.

关键词： Visual languages

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：