检索结果-内蒙古大学图书馆

Electrical, Automation and Computer Engineering (ICEACE), International Conference on

作者： Muhammad Aman Qiao Gang Zhigang Shang Zahid ULLAH Khan Muhammad Shoaib Khan Irfan Ullah Wazir-Ur-Rahman Acoustic Science and Technology Laboratory Harbin Engineering University Harbin China Key Laboratory of Marine Information Acquisition Security (Harbin Engineering University) Ministry of Industry and Information Technology Harbin China College of Underwater Acoustic Engineering Harbin Engineering University Harbin China

Wireless node localization is a critical need for many underwater applications, that heavily depends on mobile node position estimation. data is sent between nodes using three main methods of communication-i) acoustic, ii) optical, and iii) magneto inductive-which calls for a reliable communication link, having no impact from organic materials present in the underwater habitat, such as (dirt, sand, rocks, marine animals and plants that includes all kinds irrespective of their size). In order to address the aforementioned need for a reliable link of communication between the anchor Tx and sensor Rx nodes, we will examine magneto inductive communication. It has the ability to avoid phenomena like refraction, scattering, and multi-paths that are associated with the prevalence of unforeseen challenges and poor visibility, which makes communication in underwater networks more challenging. More specifically, we'll focus on the magnetic components (Hx, Hy, and Hz) produced as a result of the current applied to the magneto-inductive tri-directional (MI-TD) coil. That is used between the anchor Tx and sensor Rx nodes in magneto inductive communication.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Constant Beam Width Beamforming Method for Vector Combination Vertical Array

Constant Beam Width Beamforming Method for Vector Combinatio...

引用

International Conference on Computer Science and Network technology (ICCSNT)

作者： Chenyang Gui Yutong Ren Huan Wang Yadong Liu Erzheng Fang Acoustic Science and Technology Laboratory Harbin Engineering University Harbin China Key Laboratory of Marine Information Acquisition Security(Harbin Engineering University) Ministry of Industry and Information Technology Harbin China College of Underwater Acoustic Engineering Harbin Engineering University Harbin China

To address the problem of constant beam width beamforming required for water target radiation noise measurements, a constant beamwidth beamforming method based on a vector combined array is designed. The method uses the correlation of each channel of a single vector sensor to design a vector sound intensity filter, which improves the signal-to-noise ratio of the combined array sound pressure channel data as well as the array spatial gain. The vertical array measurement system is then extended to build a vector combined vertical array to achieve constant beamwidth beamforming, achieving the directivity of a full vector vertical array while also obtaining a certain time processing gain. Simulation experiments verify the effectiveness of the proposed algorithm.

关键词：

来源：评论

学校读者我要写书评

暂无评论

High-Resolution Spectral Estimation Method for Transient Signals Based on AR Model

High-Resolution Spectral Estimation Method for Transient Sig...

引用

IEEE International Conference on Electronic information and Communication technology (ICEICT)

作者： Zherui Wang Yan Wang Ying Li Acoustic Science and Technology Laboratory Harbin Engineering University Harbin China Key Laboratory of Marine Information Acquisition and Security (Harbin Engineering University) Ministry of Industry and Information Technology Harbin China College of Underwater Acoustic Engineering Harbin Engineering University Harbin China

Transient noise, which often occurs in the case of the sudden state change of the water surface or underwater targets, is the main source of the radiated noise for the quiet submarines and ships. This paper proposes an auto-regressive (AR) spectral estimation method based on the $\alpha-\beta$ filtering to accurately identify and analyze the transient noise. The mathematical model of the transient noise is first constructed according to inherent characteristics of the transient noise. Then, the transient signal is truncated in the time-domain, and the AR parameters of each segment data are estimated. In order to eliminate the frequency jump between data segments, the $\alpha-\beta$ filter is introduced in this method to modify the AR parameters, as a result of obtaining the time-frequency spectral with the high accurate and resolution. Finally, simulation results show the superior advantages of this method over other methods in terms of the resolution and accuracy, which is verified by the lake experiment.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Model updating for real time dynamic substructures based on UKF algorithm

引用

Earthquake Engineering and Engineering Vibration 2020年第2期19卷 413-421页

作者： Su Tingli Tang Zhenyun Peng Lingyun Bai Yuting Jin Xuebo Kong Jianlei School of Computer Information and Engineering Beijing Technology and Business UniversityBeijing 100048China The Key Laboratory of Urban Security and Disaster Engineering Ministry of EducationBeijing University of TechnologyBeijing 100124China Beijing Key Laboratory of Big Data Technology for Food Safety Beijing Technology and Business UniversityBeijing 100048China China Light Industry Key Laboratory of Industrial Internet and Big Data Beijing Technology and Business UniversityBeijing 100048China

Combining the advantages of numerical simulation with experimental testing,real-time dynamic substructure(RTDS)testing provides a new experimental method for the investigation of engineered ***,not all unmodeled parts can be physically tested,as testing is often limited by the capacity of the test *** updating is a good option to improve the modeling accuracy for numerical substructures in *** this study,a model updating method is introduced,which has great performance in describing this *** order to determine the optimal parameters in this model,an Unscented Kalman Filter(UKF)-based algorithm was applied to extract the knowledge contained in the sensors *** the parameters that need to be identified are listed as the extended state variables,and the identification was achieved via the step-by-step state prediction and state update *** of the proposed method was verified through a group of experimental data,and results showed good ***,the proposed method was compared with the Extended Kalman Filter(EKF)-based method,and better accuracy was easily *** proposed parameter identification method has great applicability for structural objects with nonlinear behaviors and could be extended to research in other engineering fields.

关键词： dynamic substructure complex nonlinear model nonlinear estimation adaptive updating civil infrastructures

来源：评论

学校读者我要写书评

暂无评论

Q-Learning-Based Energy-Efficient Routing Protocol for Underwater Wireless Sensor Networks

Q-Learning-Based Energy-Efficient Routing Protocol for Under...

引用

IEEE/OES China Ocean Acoustics (COA)

作者： Xuerui Liu Feng Zhou National Key Laboratory of Underwater Acoustic Technology Harbin Engineering University Harbin China Key Laboratory of Marine Information Acquisition and Security Ministry of Industry and Information Technology Harbin Engineering University Harbin China College of Underwater Acoustic Engineering Harbin Engineering University Harbin China Sanya Nanhai Innovation and Development Base of Harbin Engineering University Sanya China

ISBN: (数字)9798350340297

ISBN: (纸本)9798350340303

Underwater wireless sensor networks (UWSNs) have garnered considerable attention in recent years. Subject to constraints such as fixed node locations, limited energy, and harsh communication environments, designing high-performance routing protocols becomes crucial. Herein, we propose a Q-learning-based energy-efficient routing (QEER) protocol for UWSNs. To be specific, the reward function of Q-learning is designed by incorporating the energy, distance, and redundancy factors. Different from existing works ignoring redundant nodes in routing design, we exploit redundant nodes as relay nodes to extend the lifetime of UWSNs. In addition, the Time Division Multiple Access and Code Division Multiple Access protocols are reasonably implemented. Simulations demonstrate that compared with conventional clustering algorithms, the proposed QEER protocol achieves substantial improvements in terms of node lifetime, energy consumption, and the amount of forwarded data.

关键词： Wireless sensor networks Time division multiple access Energy consumption Q-learning Redundancy Routing Routing protocols Energy efficiency Topology Relays

来源：评论

学校读者我要写书评

暂无评论

Sustainability Forecasting for Deep Learning Packages

Sustainability Forecasting for Deep Learning Packages

引用

IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER)

作者： Junxiao Han Yunkun Wang Zhongxin Liu Lingfeng Bao Jiakun Liu David Lo Shuiguang Deng School of Computer & Computing Science Hangzhou City University Hangzhou China College of Computer Science and Technology Zhejiang University Hangzhou China The State Key Laboratory of Blockchain and Data Security Zhejiang University Hangzhou China School of Computing and Information Systems Singapore Management University Singapore Singapore

ISBN: (数字)9798350330663

ISBN: (纸本)9798350330670

Deep Learning (DL) technologies have been widely adopted to tackle various tasks. In this process, through software dependencies, a multi-layer DL supply chain (SC) is formed, with DL frameworks acting as the root, DL packages acting as the bridge nodes, and downstream DL projects acting as the periphery. However, most Open Source Software (OSS) projects may fail. Considering the crucial position of DL packages in the DL SC, to foster the sustainable development of DL SCs and DL packages, we aim to forecast the long-term sustainability of DL packages. Here, sustained activity is adopted as the main proxy of sustainability, and the sustainability status is classified as “sus-tainable” or “dormant”. Relatedly, a DL package is considered as “sustainable” if it has sustained activity in its last 12 months. Otherwise, it is deemed as “dormant”. To this end, we propose an approach that begins with obtaining longitudinal features for each DL package in each month. Then, we develop a model to forecast the sustainability of DL packages by incorporating the longitudinal features, which can aptly predict sustainability with an accuracy of up to 0.81. Subsequently, an interpretable module is developed to interpret the determinants (i.e., important features) that impact the sustainability of DL packages. Finally, we generate sustainability trajectories for each DL package to better understand the monthly changes of their sustainability status. Our findings uncover that for most DL packages, fewer but more centralized developers and a balanced collaboration are more likely to help sustain the DL packages. Furthermore, although some DL packages are sustainable, their sustainability trajectories present statistically decreasing trends over time. Based on the findings, we shed light on the dynamic sustainability of DL packages, highlight future research directions, and provide practical suggestions to DL package maintainers, developers, users, and software engineering researchers.

关键词： Deep learning Supply chains Predictive models Market research Trajectory Sustainable development Task analysis

来源：评论

学校读者我要写书评

暂无评论

Efficient Adaptive Label Refinement for Label Noise Learning

arXiv

引用

arXiv 2025年

作者： Zhang, Wenzhen Cheng, Debo Lu, Guangquan Zhou, Bo Li, Jiaye Zhang, Shichao School of Computer Science and Engineering Guangxi Normal University Guangxi Guilin541004 China Guangxi Key Lab of Multi-Source Information Mining & Security Guangxi Normal University Guangxi Guilin541004 China Key Lab of Education Blockchain and Intelligent Technology Ministry of Education Guangxi Normal University Guangxi Guilin541004 China UniSA STEM University of South Australia AdelaideSA5095 Australia Guangxi Collaborative Innovation Center of Modern Sericulture and Silk Hechi University Guangxi Hechi546300 China The State Key Laboratory of Blockchain and Data Security Zhejiang University Zhejiang Hangzhou310027 China

Deep neural networks are highly susceptible to overfitting noisy labels, which leads to degraded performance. Existing methods address this issue by employing manually defined criteria, aiming to achieve optimal partitioning in each iteration to avoid fitting noisy labels while thoroughly learning clean samples. However, this often results in overly complex and difficult-to-train models. To address this issue, we decouple the tasks of avoiding fitting incorrect labels and thoroughly learning clean samples and propose a simple yet highly applicable method called Adaptive Label Refinement (ALR). First, inspired by label refurbishment techniques, we update the original hard labels to soft labels using the model’s predictions to reduce the risk of fitting incorrect labels. Then, by introducing the entropy loss, we gradually ‘harden’ the high-confidence soft labels, guiding the model to better learn from clean samples. This approach is simple and efficient, requiring no prior knowledge of noise or auxiliary datasets, making it more accessible compared to Copyright © 2025, The Authors. All rights reserved.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Characteristics of Cross-Correlation Function for Receivers at Large Depths and its Application on Broadband Pulse Source Localization

SSRN

引用

SSRN 2023年

作者： Li, Ziyang Piao, Shengchun National Key Laboratory of Underwater Acoustic Technology Harbin Engineering University Harbin150001 China Key Laboratory of Marine Information Acquisition and Security Harbin Engineering University Ministry of Industry and Information Technology Harbin150001 China College of Underwater Acoustic Engineering Harbin Engineering University Harbin150001 China

The characteristics of cross-correlation function for two receivers at different depths in deep sea are analyzed. For the receivers near the surface, peaks in the cross-correlation function are close to the main peak, which is difficult to be distinguished, and their positions change minor with variation in source range and depth. While at large depths, the peaks beyond the main peak are separate and more apart from the main peak when source range decreases, source depth increases or water depth increases. The impact of variations in vertical sound speed profile on peak positions of cross-correlation function is relatively minor. Based on these characteristics, a method of cross-correlation function matching is proposed for broadband source range and depth estimation with two receivers at large depths. The accuracy of the proposed method is validated through simulation analysis and sea experimental data processing. © 2023, The Authors. All rights reserved.

关键词： data handling

来源：评论

学校读者我要写书评

暂无评论

Sparse Bayesian Learning Underwater Source Localization Method Based on Matched Beam

Sparse Bayesian Learning Underwater Source Localization Meth...

引用

Electrical, Automation and Computer Engineering (ICEACE), International Conference on

作者： Qingji Li Xiao Han Guangping Zhu Zexun Wei Acoustic Science and Technology Laboratory Harbin Engineering University Harbin China Key Laboratory of Marine Information Acquisition Security (Harbin Engineering University) Ministry of Industry and Information Technology Harbin China College of Underwater Acoustic Engineering Harbin Engineering University Harbin China First Institute of Oceanography Ministry of Natural Resources Qingdao China

In recent years, compressed sensing algorithms have received great attention in underwater passive source localization, but the classic sparse Bayesian learning localization method does not take into account the situation of environmental mismatch. To solve this problem, this paper proposes sparse Bayesian learning underwater source localization method based on matched beam (MBP-SBL). The method converts the pressure data received by the array into the beam domain through beamforming technology, and improves its robustness and resolution through beam filtering and sparse iteration in the beam domain. Simulation data and sea trial data in north Elba island are used to verify the proposed method. The results show that, compared with the classical Bartlett, MBP, MV-EPC and MFP-SBL methods, the method proposed in this paper is more tolerant to environmental mismatch while ensuring the localization result of high resolution and low side lobe.

关键词：

来源：评论

学校读者我要写书评

暂无评论

AUV-Aided Deep-Sea Internet of Things: A Machine Learning Perspective

引用

IEEE Network 2024年

作者： Men, Wei Wang, Jingjing Li, Zonglin Mi, Weishi Yin, Jingwei Ren, Yong Tsinghua University Department of Electronic Engineering Beijing100084 China Beihang University School of Cyber Science and Technology Beijing100191 China Beihang University Hangzhou Innovation Institute Hangzhou310051 China Tsinghua University Department of Tsinghua Shenzhen International Graduate School Shenzhen518055 China Key Laboratory for Polar Acoustics and Application Ministry of Education Harbin150001 China National Key Laboratory of Underwater Acoustic Technology Harbin150001 China Harbin Engineering University College of Underwater Acoustic Engineering Key Laboratory of Marine Information Acquisition and Security Ministry of Industry and Information Technology Harbin150001 China

The deep-sea Internet of Things (DS-IoT) enhances massive data acquisition capabilities and augments the safety of industrial operations, serving as a powerful technology for exploiting rich and precious natural resources. However, the unique physical environment of the deep sea poses significant challenges in establishing a DS-IoT network. In this article, to improve the capabilities of deep-sea information collection, transmission, and processing, we conceive a six-layer system architecture for the future DS-IoT, which consists of layers for environment sensing, information collection, long-distance information transmission, control and information aggregation, fusion and processing, and application and service. Then, considering the complexity of the deep-sea environment that harms the stability of underwater networks, traditional networking techniques will falter, which motivates this article to propose machine learning-aided key techniques, focusing on communication, sensing, processing, and network aspects. Furthermore, we discuss the research on efficient trajectory planning and task scheduling for multi-autonomous underwater vehicles collaboration. The simulation results indicate that our method achieves reductions of 66.84% and 89.23% in scheduling route length and reasoning time, respectively, compared to traditional methods. Finally, we present the challenges faced by the DS-IoT and potential research trends. © 1986-2012 IEEE.

关键词： Underwater acoustics

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：