检索结果-内蒙古大学图书馆

Image Fusion Based on Feature Decoupling and Proportion Preserving 1

18th International Conference on computer-Aided Design and computer Graphics (CAD/Graphics)

作者： Fang, Bin Yi, Ran Ma, Lizhuang Shanghai Jiao Tong Univ Shanghai 200240 Peoples R China Shanghai Key Lab Comp Software Evaluating & Testi Shanghai 201112 Peoples R China

ISBN: (数字)9789819996667

ISBN: (纸本)9789819996650;9789819996667

Image fusion is a widely used technique for generating a new image by combining information from multiple input images. However, existing image fusion algorithms are often domain-specific, which limits their generalization ability and processing capacity. In this paper, we propose a fast unified fusion network called FDF, based on feature decoupling and intensity and gradient feature proportion maintenance. FDF is an end-to-end network that can perform multiple image fusion tasks. We first decouple the features of the source images into intensity features and texture features and then fuse them using the intensity and gradient paths. To improve the generalization ability, we design a unified loss function that can adapt to different fusion tasks. We evaluate FDF on three image fusion tasks, namely visible and infrared image fusion, multi-exposure image fusion, and medical image fusion. Our experimental results show that FDF outperforms state-of-the-art methods in terms of visual effects and multiple quantitative metrics. The proposed method has the potential to be applied to other image fusion tasks and domains, making it a promising approach for future research. Overall, FDF provides a fast and unified solution for image fusion tasks, which can significantly improve the efficiency and effectiveness of image fusion applications.

关键词： Image fusion Feature decoupling Multimodal fusion

来源：评论

学校读者我要写书评

暂无评论

Improved Collaborative Filtering Algorithm Based on Multifactor Fusion and User Features Clustering 16

Improved Collaborative Filtering Algorithm Based on Multifac...

引用

16th IEEE Int Conf on Dependable, Autonom and Secure comp/16th IEEE Int Conf on Pervas Intelligence and comp/4th IEEE Int Conf on Big Data Intelligence and comp/3rd IEEE Cyber Sci and Technol Congress (DASC/PiCom/DataCom/CyberSciTech)

作者： Ni, Luyan Wang, Xiaofeng Jiang, Jiulei North Minzu Univ Coll Comp Sci & Engn Yinchuan Peoples R China Shanghai Key Lab Comp Software Evaluating & Testi Shanghai Peoples R China

ISBN: (纸本)9781538675182

Nowadays, collaborative filtering has become a core technology of personalized recommender systems, but the data sparsity and scalability problems seriously affected the accuracy of similarity computation. To alleviate these problems, a novel effective similarity calculation algorithm combined with user features clustering was proposed in this paper. The newly users similarities calculation model integrated the improved user rating similarity and items category preference similarity. Then, considering the K-means clustering algorithm, we clustered the users based on the user attributes through Euclidean distance so as to the nearest neighbors could be obtained in proper clusters. Experiments on MovieLens dataset are implemented. The experiments show that, compared with other improved algorithms, the method can effectively improve the prediction accuracy and quality of recommendation system.

关键词： recommender system collaborative filtering similarity clustering user feature

来源：评论

学校读者我要写书评

暂无评论

Research on Gearbox Fault Diagnosis of Urban Rail Vehicle Based on SIMPACK 1

引用

International Conference on Electrical and Information Technologies for Rail Transportation - Electrical Traction

作者： Wei, Xiukun Yan, Dong Chen, Jun Beijing Jiaotong Univ State Key Lab Rail Traff Control & Safety Beijing Peoples R China Shanghai Dev Ctr Comp Software Technol Shanghai Key Lab Comp Software Evaluating & Testi Shanghai Peoples R China

ISBN: (数字)9783662493700

ISBN: (纸本)9783662493700;9783662493687

Gearbox, an important component of urban rail vehicles working in the most severe conditions, plays a crucial role in the urban rail vehicle fault diagnosis. It is necessary to detect the fault of gearbox at an early stage to prevent human casualties and reduce maintenance costs. Most of the data-driven fault diagnosis methods are based on an experimental platform, which has many disadvantages such as costly maintenance, limited application, and limited degree of fault simulation. In this paper, a new method based on SIMPACK is proposed and confirmed efficient by testing, which can overcome the disadvantages of the experimental platform. Meanwhile, MATlab was applied to time-frequency domain analysis and wavelet packet analysis. These analysis results demonstrated the feasibility and reliability of this method.

关键词： Gearbox SIMPACK Fault diagnosis Time-frequency domain analysis Wavelet packet analysis

来源：评论

学校读者我要写书评

暂无评论

Glass Makes Blurs: Learning the Visual Blurriness for Glass Surface Detection

引用

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS 2024年第4期20卷 6631-6641页

作者： Qi, Fulin Tan, Xin Zhang, Zhizhong Chen, Mingang Xie, Yuan Ma, Lizhuang East China Normal Univ Sch Comp Sci & Technol Shanghai 200050 Peoples R China East China Normal Univ Chongqing Inst Chongqing 401333 Peoples R China Shanghai Key Lab Comp Software Evaluating & Testin Shanghai 200433 Peoples R China

Glass surface detection is challenging as glass normally borrows similar visual appearances from the arbitrary objects/scenes behind it. Although some methods have been proposed to address this problem, they may fail if the reference objects are nonexistent or the additional annotations are missing. This article aims to address the glass surface detection problem by utilizing the intrinsic glass properties without reference objects and additional annotations. We observe glass makes blurs naturally. Based on the investigation of this intrinsic visual blurriness cue, we propose a novel visual blurriness aggregation module to model visual blurriness as a learnable residual in order to extract and aggregate multiscale valuable visual blurriness features used for guiding the backbone features to detect glass precisely. Besides, we note the ratio of the blurred area assists in utilizing the visual blurriness cue caused by glass and propose a visual blurriness driven refinement module to refine glass maps with this ratio to better leverage the visual blurriness information. Extensive experiments show that the proposed method achieves state-of-the-art performance on popular glass surface datasets.

关键词： Glass surface detection salient object detection visual blurriness

来源：评论

学校读者我要写书评

暂无评论

Detection of Railway Track Squats by Using Bogie Acceleration Measurement 34

Detection of Railway Track Squats by Using Bogie Acceleratio...

引用

34th Chinese Control Conference (CCC)

作者： Yin, Xianxian Wei, Xiukun Jia, Limin Beijing Jiaotong Univ State Key Lab Railway Traff Control & Safety Beijing 100044 Peoples R China Shanghai Dev Ctr Comp Software Technol Shanghai Key Lab Comp Software Evaluating & Testi Shanghai Peoples R China

ISBN: (纸本)9789881563897

The railway track squat is one of the most dangerous track defects, it causes large dynamic contact force at the wheel-rail interface, leading to fast deterioration of the track, bring significant harm to the safety of the passengers. Early detection of such defects is very important for timely maintenance. In this paper, a squats detection method based on bogie acceleration (BA) measurement is presented. A simulation model with acceleration sensors is set up in the SIMPACK simulation environment. Time-frequency analysis and wavelet packet decomposition are applied to analyze these BA data obtained from the simulation model. The effectiveness of the above approach is demonstrated by simulation results.

关键词： squats BA measurement time-frequency domain analysis wavelet packet decomposition

来源：评论

学校读者我要写书评

暂无评论

Surface Defects Detection of Railway Turnouts 34

Surface Defects Detection of Railway Turnouts

引用

34th Chinese Control Conference (CCC)

作者： Shen, Li Wei, Xiukun Jia, Limin Beijing Jiaotong Univ State Key Lab Railway Traff Control & Safety Beijing 100044 Peoples R China Shanghai Dev Ctr Comp Software Technol Shanghai Key Lab Comp Software Evaluating & Testi Shanghai Peoples R China

ISBN: (纸本)9789881563897

As the turnout is a critical part of railway tracks, its surface defects are directly related to the operation safety. The defects detection of turnout is an effect way to ensure the safety and comfort of urban transit railway. In this paper, the feature extraction of the turnout defects is investigated based on the bogie acceleration measurements. The normal turnout model and faulty turnout model based on SIMPACK are established first, from which the vehicle vibration acceleration is obtained. Then, the acceleration signal is analyzed in time-frequency domain. The results show that the power spectral density (PSD) and all the frequency-domain features are useful for detecting the poor fit defect of the switch point. And the peak and PSD features can be used to detect the curve opposite super-elevation. The proposed method provides alternative for the detection of turnout defects by using in-service vehicle.

关键词： turnout defects feature poor fit of switch point curve opposite super-elevation

来源：评论

学校读者我要写书评

暂无评论

Detection of Rail Squats Based on Hilbert-Huang Transform by Using Bogie Acceleration Measurement 28

Detection of Rail Squats Based on Hilbert-Huang Transform by...

引用

28th Chinese Control and Decision Conference

作者： Wei, Xiukun Liu, Yuxin Yin, Xianxian Beijing Jiaotong Univ State Key Lab Rail Traff Control & Safety Beijing 100044 Peoples R China Shanghai Dev Ctr Comp Software Technol Shanghai Key Lab Comp Software Evaluating & Testi Shanghai Peoples R China

ISBN: (纸本)9781467397148

The squat is a type of rolling contact fatigue (RCF) damage, the existence of squats directly impacts the operating condition of urban rail vehicles. The current detection methods of the rail squats damage are mainly based on track inspection car and rail flaw detector. It has some disadvantages, for example, long detection cycle, no real-time detecting and narrow scope, time consuming and etc. In this paper, a new detection method of squats which based on the in-service vehicles is presented. The bogie acceleration signal is used to detect the squats on the track. To validate the possibility of the proposed method. With the help of SIMPACK software, an in-service vehicle-track dynamic model and models of typical squats are built to generate the simulated bogie acceleration signals when the train wheels rolls over the squats. The simulation signals from the normal rail and the rail with squats are studied by HHT, it is found that 0 similar to 50Hz and 300Hz are the feature frequency caused by the squats damages. A unique W-shaped natural vibration mode is decomposed from the acceleration signals which is the feature vibration mode of the squat defect. Finally, the above detection method is applied to the field test data of shanghai metro line 1. The feasibility and reliability of the proposed method are demonstrated. The proposed method provides an alternative for real application.

关键词： Squats In Service Vehicle Acceleration Signals SIMPACK HHT Field Test

来源：评论

学校读者我要写书评

暂无评论

Boosting transferability of adversarial samples via saliency distribution and frequency domain enhancement

引用

KNOWLEDGE-BASED SYSTEMS 2024年 300卷

作者： Wang, Yixuan Hong, Wei Zhang, Xueqin Zhang, Qing Gu, Chunhua East China Univ Sci & Technol Sch Informat Sci & Engn Shanghai 200237 Peoples R China Shanghai Key Lab Comp Software Evaluating & Testin Shanghai 201112 Peoples R China Shanghai Inst Technol Sch Comp Sci & Informat Engn Shanghai 201418 Peoples R China

Deep neural networks (DNNs) perform excellently in various vision tasks, however, they are susceptible to the adversarial samples. These samples are crafted by injecting subtle perturbations into benign images that are barely detectable to humans. Due to the differences between the substitute model and target model, the efficacy of black-box attack still yield suboptimal results. To address this issue, we propose a black-box attack approach, SD-FI2M, 2 M, based on the momentum iterative fast gradient sign method, which can craft potent adversarial samples by inducing diverse inputs in the frequency domain and the saliency distribution of images. To enhance the diversity of input samples in frequency domain, a spectrum transformation technique utilizing the discrete cosine transform was used to craft adversarial samples with higher transferability. Further, Guided Grad-CAM was employed to obtain the saliency distribution of benign images, reducing indiscriminate damage to image features and alleviating the overfitting problem in adversarial samples. Extensive experiments on ImageNet have verified the superior attack performance and transferability of the proposed method.

关键词： Deep neural network Black-box attack Adversarial samples Transferability

来源：评论

学校读者我要写书评

暂无评论

Towards Energy and Time Efficient Resource Allocation in IoT-Fog-Cloud Environment 16th

Towards Energy and Time Efficient Resource Allocation in IoT...

引用

16th International Conference on Service-Oriented computing (ICSOC)

作者： Sun, Huaiying Yu, Huiqun Fan, Guisheng East China Univ Sci & Technol Dept Comp Sci & Engn Shanghai Peoples R China Shanghai Key Lab Comp Software Evaluating & Testi Shanghai Peoples R China

ISBN: (纸本)9783030176426;9783030176419

As the number of IoT devices with limited resources and the corresponding observed data grow exponentially, the method of offloading all tasks to a remote data center becomes expensive, even inefficient. How to optimize the energy consumption of application requests from IoT devices satisfying the deadline constraint is also a challenge. Fog computing is closer to users, featuring the lower service delay but less resource than the remote cloud. Fog does not mean to replace cloud. They are complementary to each other, and cooperation between them is worth studying. The main points of this paper are: (1) Proposing a general IoT-fog-cloud computing architecture that fully exploits the advantages of fog and cloud. (2) Formulating the energy efficient computation offloading and dynamic resource scheduling (eoDS) problem, then proposing an eoDS algorithm to solve the problem, reducing the energy consumption and completion time of application requests (3) compared with cloud nodes, the mobility of fog nodes is higher. For this, we propose the fog functional areas reconstruction method to adaptively deal with the changing environment, improving the resource utilization of fog.

关键词： IoT-fog-cloud Resource scheduling Energy consumption completion time

来源：评论

学校读者我要写书评

暂无评论

WSN Coverage Optimization Based on Two-Stage PSO 16th

WSN Coverage Optimization Based on Two-Stage PSO

引用

16th International Conference on Collaborative computing: Networking Applications and Worksharing

作者： Qi, Wei Yu, Huiqun Fan, Guisheng Chen, Liang Wenl, Xinxiu East China Univ Sci & Technol Dept Comp Sci & Engn Shanghai Peoples R China Shanghai Key Lab Comp Software Evaluating & Testi Shanghai Peoples R China

ISBN: (纸本)9783030675363;9783030675370

Wireless Sensor Networks (WSN) coverage perception is an important basis for communication between the cyber world and the physical world in Cyber-Physical Systems (CPS). To address the coverage redundancy, hole caused by initial random deployment and the energy constraint in redeployment, this paper proposes a multi-objective two-stage particle swarm optimization algorithm (MTPSO) based on coverage rate and moving distance deviation to improve coverage efficiency. This algorithm establishes a multi-objective optimization model for above problems, and determines the candidate deployment scheme by reducing its local convergence probability through improved inertia weight, and then introduces virtual force mechanism to adjust the relative position between nodes. This paper mainly analyzes the influence of different initial deployment category and mobile nodes proportion on multi-objective optimization performance, and gives the corresponding algorithm implement. Simulation experiments show that compared with MVFA, SPSO and OPSO algorithms, MTPSO algorithm has a better redeployment coverage performance, which fully demonstrates its effectiveness.

关键词： Hybrid WSN Multi-objective optimization Two-stage mechanism Area coverage Energy consumption balance

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：