检索结果-内蒙古大学图书馆

High-Precision Sub-Seafloor Velocity Building Based on Joint Tomography and Deep Learning on OBS Data in the South China Sea

引用

Journal of Earth Science 2025年第2期36卷 830-834页

作者： Guoxin Chen Jun Li Jinxin Chen Rongsen Du Yutao Liu Yuli Qi Chun-Feng Li Xingguo Huang Department of Marine Sciences Zhejiang UniversityZhoushan 316021China Hainan Institute Zhejiang UniversitySanya 572025China Chinese Academy of Sciences Institute of SoftwareNational Key Laboratory of Space Integrated Information SystemBeijing 100190China College of Instrumentation and Electrical Engineering Jilin UniversityChangchun 130026China

*** velocity model is crucial for describing the subsurface composition and structure,and has significant implications in offshore oil and gas exploration and marine geophysical engineering(Xie et al.,2024).Currently,travel time tomography is the most commonly used method for velocity modeling based on ocean bottom seismometer(OBS)data(Zhang et al.,2023;Sambolian et al.,2021).This method usually assumes that the sub-seafloor structure is layered,and therefore faces challenges in high-precision modeling with strong lateral discontinuities.

关键词： velocity modeling time tomography marine geophysical engineering xie joint tomography describing subsurface composition structureand high precision velocity modeling offshore oil gas exploration ocean bottom seismometer obs data zhang

来源：评论

学校读者我要写书评

暂无评论

EagerLog: Active Learning Enhanced Retrieval Augmented Generation for Log-based Anomaly Detection

EagerLog: Active Learning Enhanced Retrieval Augmented Gener...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Duan, Chiming Jia, Tong Yang, Yong Liu, Guiyang Liu, Jinbu Zhang, Huxing Zhou, Qi Li, Ying Huang, Gang School of Software and Microelectronics Peking University Beijing China Institute for Artificial Intelligence Peking University Beijing China National Engineering Research Center for Software Engineering Peking University Beijing China National Key Laboratory of Data Space Technology and System Beijing China Alibaba Cloud Computing Company Hangzhou China

ISBN: (纸本)9798350368741

Logs record essential information about system operations and serve as a critical source for anomaly detection, which has generated growing research interest. Utilizing large language models (LLMs) within a retrieval-augmented generation (RAG) framework for log-based anomaly detection is an effective approach due to its strong generalization capabilities and efficient few-shot performance. However, the effectiveness of this method hinges on the quality of the knowledge source, which can be impacted by noise and changes within the software systems. Facing these problems, in this paper, we propose a novel log-based anomaly detection method named EagerLog, employing active learning to choose the logs for humans to label, thereby adding them to the knowledge source, thus enhancing the knowledge source and maintaining its quality. Our experiments on three open datasets (BGL, Thunderbird, Zookeeper) and one industrial dataset demonstrate that EagerLog can achieve 93.65% F1 score with approximately 10 labeled log sequences, surpassing existing methods by 15.32%. © 2025 IEEE.

关键词： Active Learning Anomaly Detection Log Analysis Retrieval Augmented Generation

来源：评论

学校读者我要写书评

暂无评论

DasAtom: A Divide-and-Shuttle Atom Approach to Quantum Circuit Transformation

引用

IEEE Transactions on Computer-Aided Design of Integrated Circuits and systems 2025年

作者： Huang, Yunqi Gao, Dingchao Ying, Shenggang Li, Sanjiang Faculty of Engineering and Information Technology SydneyNSW2007 Australia Institute of Software Chinese Academy of Sciences Key Laboratory of System Software Chinese Academy of Sciences State Key Laboratory of Computer Science China

Neutral atom (NA) quantum systems are emerging as a leading platform for quantum computation, offering superior or competitive qubit count and gate fidelity compared to superconducting circuits and ion traps. However, the unique features of NA devices, such as long-range interactions, long qubit coherence time, and the ability to physically move qubits, present distinct challenges for quantum circuit compilation. In this paper, we introduce DasAtom, a novel divide-and-shuttle atom approach designed to optimise quantum circuit transformation for NA devices by leveraging these capabilities. DasAtom partitions circuits into subcircuits, each associated with a qubit mapping that allows all gates within the subcircuit to be directly executed. The algorithm then shuttles atoms to transition seamlessly from one mapping to the next, enhancing both execution efficiency and overall fidelity. For a 30-qubit Quantum Fourier Transform (QFT), DasAtom achieves a 415.8x improvement in fidelity over the move-based algorithm Enola and a 10.6x improvement over the SWAP-based algorithm Tetris. Notably, this improvement is expected to increase exponentially with the number of qubits, positioning DasAtom as a highly promising solution for scaling quantum computation on NA platforms. © 1982-2012 IEEE.

关键词： Qubits

来源：评论

学校读者我要写书评

暂无评论

Fast resistivity imaging of transient electromagnetic using an extreme learning machine

引用

Soft Computing 2025年第2期29卷 1121-1131页

作者： Li, Ruiyou Zhang, Yong Li, Guang Li, Ruiheng Hu, Jia Li, Min School of Software and Internet of Things Engineering Jiangxi University of Finance and Economics NanChang330013 China School of Geophysics and Measurement Control Technology East China University of Technology NanChang330013 China School of Information Engineering Hubei University of Economics Wuhan430205 China The State Key Laboratory of Power Transmission Equipment and System Security and New Technology Chongqing University Chongqing400044 China

The transient electromagnetic method (TEM) is widely used in geophysical exploration. In TEM data interpretation, nonlinear inversion plays an important role. However, traditional TEM nonlinear inversion adopts the OCCAM imaging method, which merely presents the approximate shape of the stratum model, with poor inversion accuracy and much iteration time. To solve the above problems, a novel nonlinear inversion approach based on extreme learning machine (ELM) is proposed in this paper. The ELM is required to establish the input–output mapping relationship of the inversion network only once through the analytical method, which is different from the traditional neural network method that demands iterative gradient learning and is prone to fall into the local optimum. Moreover, the ELM inversion network by randomly assigning the hidden layer parameters is capable of mapping the observed TEM data and quickly producing resistivity images, which avoids time-consuming iteration and inversion calculations. The presented approach is applied to both synthetic and field examples. The results show that compared with the traditional nonlinear inversion algorithms (BP and OCCAM), the proposed method achieves better inversion accuracy and significantly reduces the calculation time, which verifies the effectiveness of the ELM algorithm for TEM data interpretation. Additionally, the research provides a new method and technology for TEM data inversion. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： Electromagnetic transients

来源：评论

学校读者我要写书评

暂无评论

Haptic-Aided Navigation Vehicle: Enhancing Obstacle Detection in Blind Spots and Transparent Object Scenarios

引用

Journal of Shanghai Jiaotong University (Science) 2025年 1-9页

作者： Li, Mingwang Li, Xinde Zhang, Zhentong Zhang, Zeyu Zhao, Haoming School of Software Southeast University Suzhou Jiangsu215000 China School of Automation Southeast University Nanjing210018 China School of Cyber Science and Engineering Southeast University Nanjing211102 China Key Laboratory of Measurement and Control of Complex Systems of Engineering of Ministry of Education Nanjing214135 China Nanjing Center for Applied Mathematics Nanjing211135 China Southeast University Shenzhen Research Institute Shenzhen Guangdong518063 China

As autonomous mobile robots are increasingly deployed in complex environments, traditional vision sensors and LiDAR encounter considerable limitations, particularly in detecting obstacles in blind spots or transparent objects. To address the issue of blind spots, we design a specialized haptic sensing structure and develop the haptic-aided navigation vehicle (HANV). This system integrates haptic sensors and LiDAR to deliver comprehensive perception, significantly enhancing close-range obstacle detection in areas that are typically beyond the range of conventional sensors. To tackle the challenge of transparent obstacles, which are often undetected by both vision and LiDAR sensors, we employ a fusion of haptic sensors and LiDAR. The haptic system provides physical contact feedback, ensuring reliable detection of transparent obstacles such as glass, while LiDAR offers long-range sensing capabilities. This combination enables HANV to navigate effectively in environments with transparent obstacles, overcoming the limitations of traditional sensing systems. Experiment results indicate that the proposed haptic and LiDAR integration substantially improves obstacle detection in both blind spots and environments with transparent obstacles. HANV achieves high success rates, minimal collisions, and efficient obstacle avoidance, particularly excelling in complex, confined spaces where conventional systems prove inadequate. These findings emphasize the efficacy of our approach in enhancing navigation performance in dynamic and challenging environments. (Figure presented.) © Shanghai Jiao Tong University 2025.

关键词： Mobile robots

来源：评论

学校读者我要写书评

暂无评论

CODESWIFT: Accelerating LLM Inference for Efficient Code Generation

arXiv

引用

arXiv 2025年

作者： Zhao, Qianhui Zhang, Li Liu, Fang Lian, Xiaoli Meng, Qiaoyuanhe Jiao, Ziqian Zhou, Zetong Zhang, Borui Guo, Runlin Li, Jia School of Computer Science and Engineering State Key Laboratory of Complex & Critical Software Environment Beihang University China Key Lab of High Confidence Software Technology Peking University China

Code generation is a latency-sensitive task that demands high timeliness, but the autoregressive decoding mechanism of Large Language Models (LLMs) leads to poor inference efficiency. Existing LLM inference acceleration methods mainly focus on standalone functions using only built-in components. Moreover, they treat code like natural language sequences, ignoring its unique syntax and semantic characteristics. As a result, the effectiveness of these approaches in code generation tasks remains limited and fails to align with real-world programming scenarios. To alleviate this issue, we propose CODESWIFT, a simple yet highly efficient inference acceleration approach specifically designed for code generation, without comprising the quality of the output. CODESWIFT constructs a multi-source datastore, providing access to both general and project-specific knowledge, facilitating the retrieval of high-quality draft sequences. Moreover, CODESWIFT reduces retrieval cost by controlling retrieval timing, and enhances efficiency through parallel retrieval and a context- and LLM preference-aware cache. Experimental results show that CODESWIFT can reach up to 2.53× and 2.54× speedup compared to autoregressive decoding in repository-level and standalone code generation tasks, respectively, outperforming state-of-the-art inference acceleration approaches by up to 88%. Our code and data are available at https://***/r/CodeSwift. Copyright © 2025, The Authors. All rights reserved.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Less Yet Robust: Crucial Region Selection for Scene Recognition

Less Yet Robust: Crucial Region Selection for Scene Recognit...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Zhang, Jianqi Wang, Mengxuan Wang, Jingyao Si, Lingyu Zheng, Changwen Xu, Fanjiang National Key Laboratory of Space Integrated Information System Institute of Software Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China Shien-Ming Wu School of Intelligent Engineering South China University of Technology Guangzhou China

ISBN: (纸本)9798350368741

Scene recognition, particularly for aerial and underwater images, often suffers from various types of degradation, such as blurring or overexposure. Previous works that focus on convolutional neural networks have been shown to be able to extract panoramic semantic features and perform well on scene recognition tasks. However, low-quality images still impede model performance due to the inappropriate use of high-level semantic features. To address these challenges, we propose an adaptive selection mechanism to identify the most important and robust regions with high-level features. Thus, the model can perform learning via these regions to avoid interference. implement a learnable mask in the neural network, which can filter high-level features by assigning weights to different regions of the feature matrix. We also introduce a regularization term to further enhance the significance of key high-level feature regions. Different from previous methods, our learnable matrix pays extra attention to regions that are important to multiple categories but may cause misclassification and sets constraints to reduce the influence of such regions. This is a plug-and-play architecture that can be easily extended to other methods. Additionally, we construct an Underwater Geological Scene Classification dataset to assess the effectiveness of our model. Extensive experimental results demonstrate the superiority and robustness of our proposed method over state-of-the-art techniques on two datasets. © 2025 IEEE.

关键词： high-level semantic features remote sensing robust method Scene recognition underwater images

来源：评论

学校读者我要写书评

暂无评论

Object Detection and Multiple Objective Optimization Manipulation Planning for Underwater Autonomous Capture in Oceanic Natural Aquatic Farm

引用

Journal of Field Robotics 2025年第0期

作者： Hai, Huang Tao, Jiang Xinyu, Bian Hao, Zhou Xu, Yang Gang, Wang Hongde, Qin Xinyue, Han National Key Laboratory of Science and Technology on Underwater Vehicle Harbin Engineering University Harbin China State Key Laboratory of Management and Control for Complex System Institute of Automation Chinese Academy of Science Bei Jing China

Underwater autonomous capture operations offer significant potential for reducing labor and health risks in sea organism industries. This study presents a comprehensive solution for cross-domain underwater object detection and autonomous capture. A novel unsupervised domain adaptive learning method is proposed, integrating multiscale domain adaptive modules and attention mechanisms into a Faster Region-Convolutional Neural Network framework. This approach enhances feature alignment across diverse aquatic domains without parameter tuning. Additionally, an efficient, parameterless constrained multiobjective optimization algorithm is introduced for underwater autonomous mobile capture, integrating parameterized trajectory planning with innovative features, such as adaptive mutation strategies and constraint violation tolerance. The proposed approaches are extensively validated through simulations, tank experiments, and real-world oceanic trials in the Natural Aquatic Farm of Zhangzidao Island. Results demonstrate the system's robustness in complex underwater environments with varying currents, with experimental outcomes validating the accuracy and reliability of detection and capture capabilities. This research significantly advances autonomous underwater systems' capabilities in object detection and capture tasks, addressing complex challenges in realistic organism capture applications across diverse aquatic environments. © 2025 Wiley Periodicals LLC.

关键词： Health risks

来源：评论

学校读者我要写书评

暂无评论

D-VSync: Decoupled Rendering and Displaying for Smartphone Graphics 25

D-VSync: Decoupled Rendering and Displaying for Smartphone G...

引用

30th ACM International Conference on Architectural Support for Programming Languages and Operating systems, ASPLOS 2025

作者： Wu, Yuanpei Du, Dong Xu, Chao Xia, Yubin Fu, Ming Zang, Binyu Chen, Haibo Ipads Shanghai Jiao Tong University Engineering Research Center for Domain-specific Operating Systems Ministry of Education Shanghai China Fields Lab Huawei Central Software Institute Shanghai China Fields Lab Huawei Central Software Institute Hangzhou China Ipads Shanghai Jiao Tong University Engineering Research Center for Domain-specific Operating Systems Ministry of Education Key Laboratory of System Software Chinese Academy of Science Shanghai China

ISBN: (纸本)9798400706981

Rendering service, which typically orchestrates screen display and UI through Vertical Synchronization (VSync), is an indispensable system service for user experiences of smartphone OSes (e.g., Android, OpenHarmony, and iOS). The recent trend of large high-frame-rate screens, stunning visual effects, and physics-based animations has placed unprecedented pressure on the VSync-based rendering architecture, leading to higher frame drops and longer rendering latency. This paper proposes Decoupled Vertical Synchronization (D-VSync), which decouples execution and displaying in the rendering service. D-VSync allows frames to be rendered a number of VSync periods before being physically displayed on the screen. The key insight behind D-VSync to resolve the limitation of VSync is that, the decoupling enables sporadic long frames to utilize the computational power saved by common short frames, therefore providing a larger time window to tolerate workload fluctuations. Evaluation results of 75 common OS use cases and apps on OpenHarmony (Mate 40 Pro, Mate 60 Pro), 25 popular apps on Android (Google Pixel 5), and simulations of 15 mobile games show that compared to VSync, D-VSync on average reduces frame drops by 72.7%, user-perceptible stutters by 72.3%, and rendering latency by 31.1%, with only 0.13%-0.37% more power consumption. D-VSync has been integrated into HarmonyOS NEXT. © 2025 ACM.

关键词： Rendering (computer graphics)

来源：评论

学校读者我要写书评

暂无评论

A Memetic Algorithm Based Feature Weighting for Metabolomics Data Classification

引用

Chinese Journal of Electronics 2025年第4期23卷 706-711页

作者： Jiarui Zhou Zexuan Zhu Zhen Ji College of Biomedical Engineering and Instrument Science Zhejiang University Hangzhou China Shenzhen City Key Laboratory of Embedded System Design College of Computer Science and Software Engineering Shenzhen University Shenzhen China

A metaheuristic chain based memetic algorithm namely MCMA is proposed for the classification of metabolomics data. MCMA regards both global evolution and local search as equivalent elemental metaheuristics, and searches with a chain of metaheuristics performed alternatively on the target problem. A hidden Markov model based scheduling mechanism is employed in MCMA for the selection of metaheuristics. By using MCMA for optimizing the linkage weight vector, a feature weighting algorithm for metabolomics data is formed to identify relevant metabolite features and reveal their exact relationships with the given physiological states. An extreme learning machine based classifier is utilized in predicting the physiological states according to the weighted metabolite features. Experimental results on real metabolomics data of clinical liver transplantation demonstrate that the proposed feature weighting and classification method obtains better performance than the other compared algorithms.

关键词： Memetics Metabolomics Metaheuristics Urban areas Liver Prediction algorithms Search problems Physiology Vectors Classification algorithms

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：