检索结果-内蒙古大学图书馆

Low-Cost Fine-Grained interpretation method of remote sensing images based on weakly supervised instance segmentation

引用

National Remote Sensing Bulletin 2025年第4期29卷 1002-1016页

作者： Chen, Man Huang, Yongjie Xu, Lei Pan, Zhisong College of Command and Control Engineering Army Engineering University of PLA Nanjing210007 China

Remote sensing image interpretation has essential application values in various fields, such as urban management, maritime monitoring, and resource planning. As an important and challenging task in remote sensing image interpretation, instance segmentation of remote sensing images can achieve target-level localization and pixel-level classification of objects of interest with fine granularity, making it a current research hotspot. However, most existing remote sensing image instance segmentation methods adopt the fully supervised paradigm and require expensive pixel-level labels. Moreover, remote sensing images often have issues such as mixed foreground and background and complex target contours, making segmentation challenging. To overcome these challenges, we propose a prior information-driven system suitable for weakly supervised instance segmentation tasks in remote sensing images and a multiprior driven weakly supervised instance segmentation network (MPD-WSIS-Net) to address these challenges. The prior information of weakly supervised instance segmentation can be divided into task prior and image prior. The task prior mainly comes from the bounding box detection task, which is closely related to instance segmentation. Specifically, the study obtains prior information from three components: box – mask projection consistency constraint, pixel discrimination difficulty representation function, and center position prior constraint. The image prior comes from summarizing or excavating information about the image itself. In this study, we focus on the relationships between neighboring pixels in the image and the gradient information of targets. By integrating these constraints and the pixel discrimination difficulty representation function, we establish a complete prior information driving system to enable MPD-WSIS-Net effectively to perform instance segmentation tasks under weakly supervised conditions in remote sensing images. MPD-WSIS-Net was compared with weakly

关键词： Photointerpretation

来源：评论

学校读者我要写书评

暂无评论

Aerial Reconfigurable Intelligent Surface-Aided Wireless Communications Against the Moving Jamming 6

Aerial Reconfigurable Intelligent Surface-Aided Wireless Com...

引用

6th IEEE Information Technology, Networking, Electronic and Automation control Conference, ITNEC 2023

作者： Su, Qiao Li, Guoxuan Huang, Ying Song, Xintong Liu, Chaoran Guo, Mingxi Army Engineering University of PLA College of Communications Engineering Nanjing210007 China Army Engineering University of PLA College of Command and Control Engineering Nanjing210007 China

ISBN: (纸本)9781665460033

This paper discusses the problem of anti-jamming communication for combating the moving aerial malicious jamming, where an aerial reconfigurable intelligent surface (ARIS) is considered to assist the ground communications and suppress the malicious jamming. To avoid the destructive attacks, the ARIS flies with a adjusted trajectory. The hierarchical optimization algorithm, which contains two layers, is proposed to optimize the flight trajectory and reflection matrix of ARIS jointly. The first layer utilizes the modified genetic algorithm (MGA) to optimize the flight trajectory of ARIS, and the second layer takes advantage of the manifold optimization method to derive the optimal reflection matrix of ARIS, where the second layer is embedded in the first layer. Simulation results validate that the proposed algorithm can suppress the moving malicious jamming and improve the quality of the legitimate communications effectively. © 2023 IEEE.

关键词： Antennas

来源：评论

学校读者我要写书评

暂无评论

Trustless layer for secure fog computing 23

Trustless layer for secure fog computing

引用

8th International Conference on Cyber Security and Information engineering, ICCSIE 2023

作者： Li, Wen Command and Control Engineering College Army Engineering University of PLA Nanjing Jiangsu210007 China

ISBN: (纸本)9798400708800

Fog computing composes of neighboring devices, which are connected as cluster to collect and compute data via given algorithms. Compared with cloud computing, it collects and processes data at the edge of device layer, instead of remote data transmission and task scheduling. Fog computing reduces the communication and computation overhead in networking and data aggregating, while preserves data privacy against the cloud center. However, due to the different devices capacities, trust relations, security settings, the concerns are that, if the given data is real and sufficient for analyzing program as input, whether the data processing is done as appointed, and how to prevent secret leakage during the computation. This paper proposes a trustless layer for secure data computing in fog network, where the function accepts "hidden"data as input and generates zero-knowledge computing proof which can be easily verified by public. The combination of secure computing functions and blockchain systems escort trustful business in fog environment. © 2023 ACM.

关键词： Fog computing

来源：评论

学校读者我要写书评

暂无评论

A Novel Cross-Project Software Defect Prediction Algorithm Based on Transfer Learning

引用

Tsinghua Science and Technology 2022年第1期27卷 41-57页

作者： Shiqi Tang Song Huang Changyou Zheng Erhu Liu Cheng Zong Yixian Ding Command&Control Engineering College Army Engineering University of PLANanjing 210000China Foreign Language College Liaoning Technical UniversityFuxin 123000China

Software Defect Prediction(SDP) technology is an effective tool for improving software system quality that has attracted much attention in recent ***,the prediction of cross-project data remains a challenge for the traditional SDP method due to the different distributions of the training and testing *** major difficulty is the class imbalance issue that must be addressed in Cross-Project Defect Prediction(CPDP).In this work,we propose a transfer-leaning algorithm(TSboostDF) that considers both knowledge transfer and class imbalance for *** experimental results demonstrate that the performance achieved by TSboostDF is better than those of existing CPDP methods.

关键词： Software Defect Prediction(SDP) transfer learning imbalance class cross-project

来源：评论

学校读者我要写书评

暂无评论

Feature Chirality in Deep Learning Models

Feature Chirality in Deep Learning Models

引用

2023 International Conference on Intelligent Perception and Computer Vision, CIPCV 2023

作者： Ji, Shipeng Li, Yang Fu, Ruizhi Wang, Jiabao Miao, Zhuang Army Engineering University of PLA Command & Control Engineering College Nanjing China No. 32316 Units of PLA Urumqi China

ISBN: (纸本)9798350323382

As deep learning applications extensively increase by leaps and bounds, their interpretability has become increasingly prominent. As a universal property, chirality exists widely in nature, and applying it to the explanatory research of deep learning may be helpful to some extent. Inspired by a recent study that used CNN (convolutional neural network), which applied visual chirality, to distinguish whether an image is flipped or not. In this paper, we study feature chirality innovatively, which shows how the statistics of deep learning models' feature data are changed by training. We rethink the feature-level chirality property, propose the feature chirality, and give the measure. Our analysis of feature chirality on AlexNet, VGG, and ResNet reveals similar but surprising results, including the prevalence of feature chirality in these models, the initialization methods of the models do not affect feature chirality. Our work shows that feature chirality implies model evaluation, interpretability of the model, and model parameters optimization. © 2023 IEEE.

关键词： Chirality

来源：评论

学校读者我要写书评

暂无评论

Non-singular Fast Terminal Sliding Mode and Active Disturbance Rejection control for Quadrotor UAV

Non-singular Fast Terminal Sliding Mode and Active Disturban...

引用

2024 IEEE International Conference on Unmanned Systems, ICUS 2024

作者： Chen, Cheng Liu, Yunping Zhang, Tingting Sun, Yuanxin Shi, Jingwei School of Automation Nanjing University of Information Science and Technology Nanjing China School of Command and Control Engineering Army Engineering University of PLA Nanjing China

ISBN: (纸本)9798350384185

The purpose of this paper is to improve the anti-interference ability of the quadrotor UAV. This paper proposes a non-singular fast terminal sliding mode combined with an active disturbance rejection controller. Firstly, the uncertainty factors, such as model errors and internal and external disturbances of the quadrotor UAV system, are regarded as lumped disturbances, estimated and compensated online by the extended state observer in real-time. According to its underactuated, multivariable, and nonlinear characteristics, it is divided into a position loop and an attitude loop. On this basis, it is transformed into complete drive control by introducing virtual control quantity. The simulation results show that the non-singular fast terminal sliding mode active disturbance rejection controller has better robustness than the cascade active disturbance rejection control. © 2024 IEEE.

关键词： Disturbance rejection

来源：评论

学校读者我要写书评

暂无评论

Abnormal data detection method based on ant colony clustering 6

Abnormal data detection method based on ant colony clusterin...

引用

6th International Conference on Electronic Information Technology and Computer engineering, EITCE 2022

作者： Chen, Lianyong Song, Jinyu College of Command and Control Engineering Army Engineering University of PLA

ISBN: (纸本)9781450397148

With the rapid growth of data, low quality data emerges, and data quality problems are increasingly serious. Abnormal data detection becomes an important aspect of data quality validity measurement. We propose an improved ant colony clustering algorithm based on LF algorithm [8] by optimizing ant position, attribute weight and moving step speed and then apply it to the abnormal data detection. The improved algorithm is programmed by Python, and the experiment is carried out on UCI data set. The results show that the improved algorithm can obtain better clustering effect, and make the accuracy of abnormal data detection results higher. © 2022 Association for Computing Machinery.

关键词： Python

来源：评论

学校读者我要写书评

暂无评论

NAS-based Auxiliary Learning for Fine-grained Vehicle Recognition 22

NAS-based Auxiliary Learning for Fine-grained Vehicle Recogn...

引用

5th International Conference on Signal Processing and Machine Learning, SPML 2022

作者： Wang, Jiabao Wang, Peilong Li, Yunchen Yang, Li Miao, Zhuang Li, Yang Command and Control Engineering College Army Engineering University of PLA China

ISBN: (纸本)9781450396912

Fine grained vehicle recognition is a sub-category classification task, specifically for vehicles. It is faced with the problems of small inter-class differences and large intra-class variants, which is very challenging. In order to obtain better recognition accuracy, based on the network architecture searched by neural architecture search (NAS), this paper proposes a novel auxiliary learning method to help learn a more robust model for fine-grained vehicle recognition. Experimental results verify the effectiveness of the proposed method on the public Stanford-Cars and self-built FGVC_LAV datasets. © 2022 Association for Computing Machinery.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

Modeling the Unmanned Cluster Collaboration Problem and Its Application within the Intelligence Domain

Modeling the Unmanned Cluster Collaboration Problem and Its ...

引用

2024 IEEE International Conference on Unmanned Systems, ICUS 2024

作者： Zhang, Legui Liu, Geng Wang, Bin Wang, Xiaoyan Li, Xuan Hua, Shiling College of Command & Control Engineering Army Engineering University of PLA Nanjing China School of Foreign Languages National University of Defense Technology PLA Nanjing China Unit 31306 of the PLA Chengdu China Unit 33269 of the PLA Lanzhou China

ISBN: (纸本)9798350384185

The study of the unmanned cluster coordination problem helps to realize the efficient coordination between unmanned aircraft, which is conducive to the realization of cross-domain coordinated operations and the improvement of the overall combat *** paper models the unmanned cluster coordination problem from three dimensions of platform coordination, time coordination and space *** the same time, the article combines the unmanned collaborative technology with the current important realities within the intelligence field and analyzes the possible applications. © 2024 IEEE.

关键词： cooperative control intelligence unmanned clusters

来源：评论

学校读者我要写书评

暂无评论

A branch and price algorithm for the robust WSOS scheduling problem

引用

Journal of Systems engineering and Electronics 2021年第3期32卷 658-667页

作者： LI Ruiyang HE Ming HE Hongyue WANG Zhixue YANG Cheng Institute of Command and Control Engineering Army Engineering University of PLANanjing 210007China

To analyze and optimize the weapon system of systems(WSOS)scheduling process,a new method based on robust capabilities for WSOS scheduling optimization is ***,we present an activity network to represent the military *** member systems need to be reasonably assigned to perform different activities in the *** we express the problem as a set partitioning formulation with novel columns(activity flows).A heuristic branch-and-price algorithm is designed based on the model of the WSOS scheduling problem(WSOSSP).The algorithm uses the shortest resource-constrained path planning to generate robust activity flows that meet the capability ***,we discuss this method in several test *** results show that the solution can reduce the makespan of the mission remarkably.

关键词： weapon system of systems(WSOS) robust optimization scheduling decision branch-and-price column generation

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：