检索结果-内蒙古大学图书馆

An additive feature fusion attention based on YOLO network for aircraft skin damage detection

Journal of Supercomputing 2025年第4期81卷 1-27页

作者： Wu, Jun Zhang, Yajing Shan, Tengfei Xing, Zhiwei Chen, Jiusheng Guo, Runxia College of Aeronautical Engineering Civil Aviation University of China Tianjin China College of Electronic Information and Automation Civil Aviation University of China Tianjin China

Aircraft skin damage detection is crucial for ensuring flight safety. This article presents an enhanced object detection algorithm tailored for scenarios with low image complexity. Initially, considering the low image complexity inherent in aircraft skin damage data, an additive feature fusion attention mechanism is proposed to enhance the YOLOv7 neck feature fusion approach, aiming at diminishing the computational and parametric loads of the model. Secondly, the Inner-CIoU loss function is enhanced and the dynamic Inner-CIoU loss function is introduced to substitute the original CIoU loss function in YOLOv7. Subsequently, to validate the proposed method, an Aircraft Skin Damage Dataset encompassing five types of damage, with image backgrounds solely comprising the aircraft skin, is generated. Lastly, experimental results demonstrate that the proposed additive feature fusion attention mechanism, tailored for scenarios like Aircraft Skin Damage Dataset with low image complexity, significantly reduces the model parameters without compromising model accuracy. Compared to the YOLOv7, the proposed method improves the detection accuracy by 1.6% and reduces the number of parameters by 19.4%;the enhanced YOLOv7 model is compared with mainstream object detection models to illustrate the superiority of the improved algorithm. The Pascal VOC2007 Database and Aluminum Profile Surface Detection Database are selected as control groups, which are used to further validate the correctness of the proposed theory, namely the additive feature fusion attention mechanism. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词： Aircraft detection

来源：评论

学校读者我要写书评

暂无评论

A Semisupervised Aircraft Fuselage Defect Detection Network with Dynamic Attention and Class-Aware Adaptive Pseudolabel Assignment

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第7期5卷 3551-3563页

作者： Zhang, Xiaoyu Zhang, Jinping Chen, Jiusheng Guo, Runxia Wu, Jun Civil Aviation University of China College of Electronic Information and Automation Tianjin300300 China Civil Aviation University of China College of Aeronautical Engineering Tianjin300300 China

To track the problem of aircraft fuselage defect detection in complex environments and reduce aviation safety hazards such as careless observation and delayed reporting due to objective factors, a semisupervised aircraft fuselage defect detection network was proposed. First, we constructed a new baseline model that extends one-stage detector with dynamic head and partial convolution named as dynamic decoupled detector, which enhances the representation capability of the model and improves the detection accuracy of small defects. Second, to address the issue of inconsistent pseudolabel distribution in semisupervised learning, we propose a class-aware adaptive pseudolabel assignment strategy that adaptively obtains the pseudolabel filtering threshold during the training iteration to further optimize the pseudolabel assignment process. Finally, to validate the effectiveness of the proposed model, we construct a dataset for aircraft fuselage defect detection for semisupervised training. Experimental results show that the proposed semisupervised aircraft fuselage defect detection network outperforms the current state-of-the-art semisupervised object detection framework on the aircraft fuselage defect dataset. At the same time, the proposed model has better generalization performance and provides more reliable support for real-time visualization of aircraft fuselage defects. © 2020 IEEE.

关键词： Aircraft detection

来源：评论

学校读者我要写书评

暂无评论

A Radial Basis Function-Based Graph Attention Network With Squeeze Loss Optimization for Link Prediction

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第2期5卷 724-736页

作者： Chen, Jiusheng Fang, Chengyuan Zhang, Xiaoyu Wu, Jun Guo, Runxia Civil Aviation University of China College of Electronic Information and Automation Tianjin300300 China Civil Aviation University of China College of Aeronautical Engineering Tianjin300300 China

Graph attention networks are a popular method to deal with link prediction tasks, but the weight assigned to each sample is not focusing on the sample's own performance in training. Moreover, since the number of links is much larger than nodes in a graph, mapping functions are usually used to map the learned node features to link features, whose expression of node similarity determines the quality of link feature learning. To tackle the above issues, a new model graph attention networks based on the radial basis function (RBF) with squeeze loss are proposed, including two improvements. First, RBF function with extended parameters is used to transform the node features output by attention layer into link features. The result of link feature embedding can be improved by shortening the distance of nodes with links and enlarging the distance of nodes without links in vector space. Second, squeeze loss is designed to adjust the loss according to the performance of samples in training and change the proportion of sample loss in the loss function to allocate training resources reasonably. The link prediction task performed on datasets shows that the performance of the proposed method is better than baselines. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Double-branch forgery image detection based on multi-scale feature fusion

引用

Optoelectronics Letters 2024年第5期20卷 307-312页

作者： ZHANG Hongying GUO Chunxing WANG Xuyong College of Electronic Information and Automation Civil Aviation University of ChinaTianjin 300300China

Most of existing methods exhibit poor performance in detecting forged images due to the small size of tampered areas and the limited pixel difference between untampered and tampered regions. To alleviate the above problem, a double-branch tampered image detection based on multi-scale features is proposed. Firstly, we introduce a fusion module based on attention mechanism in the first branch to enhance the network's sensitivity towards tampered regions. Secondly, we construct a second branch specifically designed for detection, aiming to identify subtle differences between tampered and untampered areas by utilizing rich edge information from shallow features as guidance. Compared to the existing methods on the public benchmark datasets CASIA1.0, Columbia and NIST16, the values of F-score reached 0.766, 0.900 and 0.930 on those datasets, respectively. The experimental results show that our method could significantly improve the accuracy on detecting the tampered area.

关键词： branch image utilizing

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Intrusion Detection Method Based on Convolutional Neural Network and AdaBoost

引用

China Communications 2024年第11期21卷 180-189页

作者： Wu Zhijun Li Yuqi Yue Meng School of Safety Science and Engineering Civil Aviation University of ChinaTianjin 300300China School of Electronic Information and Automation Civil Aviation University of ChinaTianjin 300300China

To solve the problem of poor detection and limited application range of current intrusion detection methods,this paper attempts to use deep learning neural network technology to study a new type of intrusion detection ***,we proposed an intrusion detection algorithm based on convolutional neural network(CNN)and AdaBoost *** algorithm uses CNN to extract the characteristics of network traffic data,which is particularly suitable for the analysis of continuous and classified attack *** AdaBoost algorithm is used to classify network attack data that improved the detection effect of unbalanced data *** adopt the UNSW-NB15 dataset to test of this algorithm in the PyCharm *** results show that the detection rate of algorithm is99.27%and the false positive rate is lower than 0.98%.Comparative analysis shows that this algorithm has advantages over existing methods in terms of detection rate and false positive rate for small proportion of attack data.

关键词： AdaBoost CNN detection rate false positive rate feature extraction intrusion detection

来源：评论

学校读者我要写书评

暂无评论

A Method for Constructing an Aerial Image Dataset of civil Aircraft 'Black Box' Using AIGC-Generated Samples 5

A Method for Constructing an Aerial Image Dataset of Civil A...

引用

5th International Conference on Machine Learning and Computer Application, ICMLCA 2024

作者： Luo, Qijun Li, Wenshuo Zhuge, Jingchang Shao, Jiaqi Civil Aviation University of China Electronic Information and Automation College China Electronic Information and Automation College Civil Aviation University of China China

ISBN: (纸本)9798331530334

Using drones for automatic cruise to capture crash sites and employing AI algorithms to automatically detect aircraft wreckage and the 'black box' can significantly improve the efficiency of onsite search and rescue. To address the issue of insufficient 'black box' image samples from crash sites, this paper proposes a method for constructing an aerial image dataset of 'black box' using Artificial Intelligence Generated Content (AIGC) for background generation and target sample synthesis. First, multi-angle images of the 'black box' and background images in typical terrains are collected using drones, and the actual aerial image samples are formed after segmentation and labeling. Next, a virtual aerial background image generation method based on AIGC is proposed. This method uses ChatGPT interactive prompts and large image generation models to generate aerial background images in complex terrain environments. Finally, using collaborative dual-transform automatic image synthesis technology, segmented real target images are randomly embedded into background images, and virtual aerial samples are coordinated and generated, thereby constructing the 'black box' target detection dataset. This dataset achieved good training and testing results on five classic target detection models, and experiments verified its effectiveness. In the ablation experiments on various subsets using YOLOv8n, the detection accuracy on the real sample set improved from 0.76 to 0.976 on the combined sample set, with an accuracy increase of 28.4%. © 2024 IEEE.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

Risk evaluation for the task transfer of an aircraft maintenance program based on a multielement connection number

引用

Frontiers of engineering Management 2024年第1期11卷 16-31页

作者： Tao LIU Zhibo SHI Huifen DONG Jie BAI Yu YAN College of Electronics Information and Automation Civil Aviation University of ChinaTianjin 300300China College of Airworthiness Civil Aviation University of ChinaTianjin 300300China

This paper proposes a framework for evaluating the efficacy and suitability of maintenance programs with a focus on quantitative risk assessment in the domain of aircraft maintenance task transfer. The analysis is anchored in the principles of Maintenance Steering Group-3 (MSG-3) logic decision paradigms. The paper advances a holistic risk assessment index architecture tailored for the task transfer of maintenance programs. Utilizing the analytic network process (ANP), the study quantifies the weight interrelationships among diverse variables, incorporating expert-elicited subjective weighting. A multielement connection number-based evaluative model is employed to characterize decision-specific data, thereby facilitating the quantification of task transfer-associated risk through the appraisal of set-pair potentials. Moreover, the paper conducts a temporal risk trend analysis founded on partial connection numbers of varying orders. This analytical construct serves to streamline the process of risk assessment pertinent to maintenance program task transfer. The empirical component of this research, exemplified through a case study of the Boeing 737NG aircraft maintenance program, corroborates the methodological robustness and pragmatic applicability of the proposed framework in the quantification and analysis of mission transfer risk.

关键词： risk evaluation maintenance steering group analytic network process task transfer maintenance program

来源：评论

学校读者我要写书评

暂无评论

INTERCONNECTION SCHEME FOR A MULTIPROTOCOL HETEROGENEOUS WIRELESS COMMUNICATION SYSTEM IN A civil AIRPORT

引用

Telecommunications and Radio engineering (English translation of Elektrosvyaz and Radiotekhnika) 2024年第6期83卷 79-92页

作者： Zhang, Wei Li, He Ji, Yuchu Wang, Yang College of Electronic Information and Automation Civil Aviation University of China Tianjin300300 China State Key Laboratory of Air Traffic Management System and Technology Nanjing210014 China College of Electronic Information and Automation Civil Aviation University of China Tianjin300300 China

In the movement area of an airport, the wireless communication system is built to satisfy the communication requirements of mobile stations (MSs), which include aircraft, vehicles, staff, passengers, and sensors. However, the actual airport wireless communication system is a heterogeneous wireless network with multiple individual wireless communication systems. In this paper, we design a multiprotocol base station (MPBS) to realize the access and interconnection of the MSs with different protocols. In addition, a direct forwarding scheme of MPBS is proposed to improve the performance of transmissions from one MS to another. Third, a priority order transmission scheme, which can reduce the end-to-end delay of important data, is proposed for direct forwarding MPBS. Simulation results show that the proposed direct forwarding MPBS scheme can improve the transmission performance of interactive data and reduce the load of the core network. © 2024 Begell House Inc.. All rights reserved.

关键词： Aircraft

来源：评论

学校读者我要写书评

暂无评论

Obstacle detection:improved YOLOX-S based on swin transformer-tiny

引用

Optoelectronics Letters 2023年第11期19卷 698-704页

作者： ZHANG Hongying LU Chengjian CHEN Enyao College of Electronic Information and Automation Civil Aviation University of ChinaTianjin300300China

Aiming at the accuracy challenge in obstacle detection for autonomous driving,we propose an improved you only look once X-S(YOLOX-S) model based on swin transformer-tiny YOLOX-S(ST-YOLOX-S) for obstacle detection,which could detect multiple targets,including people,cars,bicycles,motorcycles,and *** method mainly comprises two aspects as *** improve the capability of local feature extraction and then obtain more accurate detection for obstacles under real-world vehicle conditions,the existing backbone of YOLOX-S is replaced with the swin transformer-tiny *** reduced the number of channels between the swin transformer and path aggregation-feature pyramid network(PA-FPN) from [96,192,384,768] to [192,384,768],to decrease the computational cost and then make the swin transformer-tiny more compatible with the ***,on the popular COCO dataset,the proposed ST-YOLOX-S improves the detection mean average precision(mAP) by 6.1% when compared with *** the five types of obstacles that appear in simulated actual vehicle conditions,our ST-YOLOX-S also achieves superior performance compared to ***,our method achieves significant performance over the YOLOv3 on obstacle detection,which shows the effectiveness of the proposed algorithm.

关键词： obstacle network backbone

来源：评论

学校读者我要写书评

暂无评论

Simulation performance analysis of FBMC-OQAM system based on frequency spreading 2

Simulation performance analysis of FBMC-OQAM system based on...

引用

2nd International Conference on Physics, Photonics, and Optical engineering, ICPPOE 2023

作者： Tao, Yuan College of Information Engineering and Automation Civil Aviation University of China Tianjin300300 China

ISBN: (纸本)9781510674684

To cater to the escalating demand for information transmission in today's digital society, prioritizing the development of high-speed wireless communication technologies is essential. Among these, Orthogonal Frequency Division Multiplexing (OFDM) has emerged as one of the most widely adopted multicarrier technologies in the communications arena. OFDM stands out with its high transmission rate and robust anti-interference capabilities. However, it has certain limitations, including low spectrum utilization and a lack of flexibility, which restrict the growth of communication technology. In response to these challenges, Filter Bank-based Multicarrier (FBMC) technology, a cornerstone of the fifth generation (5G) of mobile communication, presents itself as an effective solution to existing multicarrier technology issues. By leveraging Offset Quadrature Amplitude Modulation (OQAM), the FBMC-OQAM system boasts impressive resistance to subcarrier interference and high spectral efficiency. Although the FBMC-OQAM technique is still in its nascent stages, it holds promising potential. Its adoption can significantly enhance communication systems' performance by addressing interference and spectrum efficiency issues plaguing current technologies. Consequently, it is anticipated to become a cornerstone technology in mobile communication's future landscape. As we explore its full potential, the ongoing research in this area is expected to lead to breakthroughs that could redefine the way we think about wireless communications. © COPYRIGHT 2024 SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Filter banks

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：