检索结果-内蒙古大学图书馆

CrossFuse: Learning Infrared and Visible Image Fusion by Cross-Sensor Top-K Vision Alignment and Beyond

IEEE Transactions on Circuits and Systems for Video technology 2025年

作者： Shi, Yukai Shi, Cidan Weng, Zhipeng Tian, Yin Xian, Xiaoyu Lin, Liang Guangdong University of Technology School of Information Engineering Guangzhou510006 China Anhui University Anhui Provincial Key Laboratory of Multimodal Cognitive Computation Hefei230601 China CRRC Academy Co. Ltd Beijing China Sun Yat-sen University School of Computer Science Guangzhou510006 China

Infrared and visible image fusion (IVIF) is increasingly applied in critical fields such as video surveillance and autonomous driving systems. Significant progress has been made in deep learning-based fusion methods. However, these models frequently encounter out-of-distribution (OOD) scenes in real-world applications, which severely impact their performance and reliability. Therefore, addressing the challenge of OOD data is crucial for the safe deployment of these models in open-world environments. Unlike existing research, our focus is on the challenges posed by OOD data in real-world applications and on enhancing the robustness and generalization of models. In this paper, we propose an infrared-visible fusion framework based on Multi-View Augmentation. For external data augmentation, Top-k Selective Vision Alignment is employed to mitigate distribution shifts between datasets by performing RGB-wise transformations on visible images. This strategy effectively introduces augmented samples, enhancing the adaptability of the model to complex real-world scenarios. Additionally, for internal data augmentation, self-supervised learning is established using Weak-Aggressive Augmentation. This enables the model to learn more robust and general feature representations during the fusion process, thereby improving robustness and generalization. Extensive experiments demonstrate that the proposed method exhibits superior performance and robustness across various conditions and environments. Our approach significantly enhances the reliability and stability of IVIF tasks in practical applications. © 1991-2012 IEEE.

关键词： Image fusion

来源：评论

学校读者我要写书评

暂无评论

Soil Moisture Prediction with Temporal Convolutional Networks (TCN) for Precision Irrigation

Soil Moisture Prediction with Temporal Convolutional Network...

引用

Automation and Computation (AUTOCOM), International Conference on

作者： Md.Mohammad Shareef Prasath S Himanshu Dhall Ramy Riad Al-Fatlawy K. Ranjith Singh Rajat Kumar Dwibedi Department of CSE (AIML) CMR Technical Campus Hyderabad Telangana India Department of Computer Science and Applications School of Computing VET Institute of Arts and Science (Co-education) College Thindal Erode Uttaranchal University Dehradun India Department of Computers Techniques Engineering College of Technical Engineering The Islamic University Najaf Iraq Department of Computer Science Karpagam Academy of Higher Education Coimbatore India Department of ECE Aarupadai Veedu Institute of Technology Vinayaka Mission's Research Foundation (Deemed to be University) Chennai Tamil Nadu India

ISBN: (数字)9798331542375

ISBN: (纸本)9798331542382

Soil moisture forecast is of great importance for precision irrigation, which stretches water resources, thus encouraging conservation among farmers. On this premise, this study puts forth a model based on a Temporal Convolutional Network (TCN) for enhanced soil moisture forecasting. TCNs are selected for their natural approach of modeling long term temporal dependencies in the temporal data that is crucial to model change in soil moisture level due to changes in weather conditions and type of soil. The model then uses info from the soil moisture sensors, the weather forecast and remote sensing of the land surface. Data pre-processing steps such as, data cleansing, data interpolation, and data normalization makes the raw data fit for modeling. The TCN is then compared with RF and SVM, two other ML models achieving better accuracy, although with comparatively low MAE and RMSE values. This model is trained on the history data and evaluated through cross-validation in order of selecting the hyperparameters of the number of layer, and the rate of dilation of layers. Real-time prediction is done for automatic irrigation systems and afterwards irrigation decisions may be taken based on the soil moisture predicted by the model. The identified system reveals potential for increasing the utilization of water and crop yields and hence promoting sustainable and resource-optimizing farming systems.

关键词： Support vector machines Irrigation Accuracy Soil moisture Weather forecasting Predictive models Data models Real-time systems Convolutional neural networks Water resources

来源：评论

学校读者我要写书评

暂无评论

An Efficient Intra-Inter Pixel Encryption Scheme to Secure Healthcare Images for an Iot Environment

SSRN

引用

SSRN 2023年

作者： Dash, Sachikanta Padhy, Sasmita Devi, S. Anjali Sharna, Savyasachi Patro, K. Abhimanyu Kumar Department of Computer Science and Engineering GIET University Odisha Gunupur765022 India School of Computing Science and Engineering VIT Bhopal University Kothrikalan Madhya Pradesh Sehore466114 India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Guntur Andhra Pradesh Vaddeswaram522502 India Department of Information Technology Lalit Narayan Mishra College of Business Management Bihar Muzaffarpur842001 India Department of Mechatronics Manipal Institute of Technology Manipal Academy of Higher Education Karnataka Manipal576104 India

Digital images are being frequently used for diagnosis in clinics today. Diagnostic images with identifying patient data are stored and transmitted across open networks. Security measures are therefore becoming more and more crucial to safeguard the confidentiality of sensitive patient data. In medical imaging, adjacent pixels show a strong degree of connection. This paper presents an efficient intra-inter bit-level pixel operation-based image encryption method that eliminates pixel correlation and provides strong security. In this method, after gathering medical image data from IoT sensors, the intra bit-level pixel permutation and diffusion operations are executed separately and in parallel in each of the bit planes, and the inter bit-level pixel permutation and diffusion operations are then performed in the concatenated bit-planes. The bit-level operation not only permutes but also diffuses the pixels at the same time. As a result, the security of the algorithm is increased by executing several pixel permutations and diffusions. In addition to this, the approach is effective due to the parallel execution of bit-plane permutation and diffusion. The simulation results and the security analysis indicate the superior performance of the proposed algorithm. © 2023, The Authors. All rights reserved.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

A Novel Dual-Functional Method for Wide-Angle Scanning Phased Array

A Novel Dual-Functional Method for Wide-Angle Scanning Phase...

引用

International Applied Computational Electromagnetics Society Symposium (ACES)

作者： Dongyu Li Feng Gao Guang-Wei Yang China Academy of Launch Vehicle Technology Beijing China School of Electronic Engineering and Computer Science Queen Mary University of London London UK

A novel method to enhance the wide-angle scanning capability (WASC) of the array antenna is introduced in this letter, where can reduce the inter-element mutual coupling of the array and broaden the beam-width of the element in the array. Because of the bent metal plates, the horizontal and vertical currents are produced in the element of the array, which can extend the beam-width of the element in the array. Meanwhile, the decoupling function can be realized by the converse vertical currents from the adjacent antenna elements. Two 1×8 linear arrays are fabricated and tested to demonstrate the proposed method. The measured antenna performance accords with the simulated performance. The proposed array can scan the coverage of ±60° with a realized gain variation under 3 dB and lower side lobe level (SLL) under -7.9dB within the operating band from 4.5 to 5.0 GHz. Therefore, the proposed method has been demonstrated in the linear array and can be promoted to apply in the planar array for wireless communication systems, especially in the large coverage communication system.

关键词： Phased arrays Antenna measurements Wireless communication Mutual coupling Current measurement Metals Planar arrays

来源：评论

学校读者我要写书评

暂无评论

Application of Kronecker convolutions in deep learning technique for automated detection of kidney stones with coronal CT images

引用

Information sciences 2023年 640卷

作者： Patro, Kiran Kumar Allam, Jaya Prakash Neelapu, Bala Chakravarthy Tadeusiewicz, Ryszard Acharya, U Rajendra Hammad, Mohamed Yildirim, Ozal Plawiak, Pawel Department of Electronics and Communication Engineering Aditya Institute of Technology and Management AP Tekkali532201 India Department of Electronics and Communication Engineering National Institute of Technology Rourkela Odisha Rourkela769008 India Department of Biotechnology and Medical Engineering National Institute of Technology Rourkela Odisha Rourkela769008 India AGH University of Science and Technology Department of Biocybernetics and Biomedical Engineering Krakow Poland School of Mathematics Physics and Computing University of Southern Queensland Springfield Australia EIAS Data Science Lab College of Computer and Information Sciences Prince Sultan University Riyadh11586 Saudi Arabia Department of Information Technology Faculty of Computers and Information Menoufia University Shibin El Kom32511 Egypt Department of Software Engineering Firat University Elazig Turkey Department of Computer Science Faculty of Computer Science and Telecommunications Cracow University of Technology Warszawska 24 Krakow31-155 Poland Institute of Theoretical and Applied Informatics Polish Academy of Sciences Baltycka 5 Gliwice44-100 Poland

Kidney stone disease is a serious public health concern that is getting worse with changes in diet, obesity, medical conditions, certain supplements etc. A kidney stone also called a renal calculus, is a hard buildup of urine minerals that form in the kidneys. Computed tomography (CT) is one of the imaging models used to identify kidney stones by clinical experts. Due to the low resolution of these images, sometimes detecting kidney stones is tedious with the naked eye, which may lead to false alarms. In this work, a computer-based diagnosis system with a deep learning technique has been developed as a practical solution to aid clinicians in their diagnosis. The traditional convolutional neural network (CNN)-based deep learning technology can detect stones in the kidney. Still, it suffers from the performance and standard implementation of the convolution operations in convolution layers. A Kronecker product-based convolution technique is incorporated in the proposed deep learning architecture to reduce the redundancy in feature maps without convolution overlapping. Our proposed method helps to make the network more effective by extracting abstract and in-depth features from the input images. The publicly available GitHub kidney stone CT scans are utilized to develop the proposed architecture. Our automated model detected kidney stones with an accuracy of 98.56% utilizing CT images. Our system is more effective than the most recent and cutting-edge techniques developed for identifying kidney stones of any size, including the smallest ones. © 2023 The Author(s)

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

EG-Four$\mathbb {Q}$: An Embedded GPU-Based Efficient ECC Cryptography Accelerator for Edge Computing

引用

IEEE Transactions on Industrial Informatics 2022年第6期19卷 7291-7300页

作者： Jiankuo Dong Pinchang Zhang Kaisheng Sun Fu Xiao Fangyu Zheng Jingqiang Lin School of Computer Science Nanjing University of Posts and Telecommunications Nanjing China State Key Laboratory of Information Security and Institute of Information Engineering Chinese Academy of Sciences Beijing China School of Cyber Security University of Science and Technology of China Hefei China

With the continuous development of Industry 4.0 technology, the embedded devices in Industrial Internet of Things (IIoT) are showing explosive growth, and large-scale cyber attacks or related security incidents continue to sound the alarm bell of information security. IIoT has strict requirements on computing performance and energy consumption, which poses severe challenges to cryptographic algorithms, especially public key cryptographic algorithms with high computational complexity. Embedded graphic processing unit (GPU) devices, always as edge computing nodes or AI accelerators, are widely deployed in IIoT applications. In this article, we propose an embedded GPU-based Four $\mathbb {Q}$ (EG-Four $\mathbb {Q}$ ) elliptic curve public key cryptographic acceleration scheme. As far as we know, EG-Four $\mathbb {Q}$ is the first work to completely implement Four $\mathbb {Q}$ on the GPU platforms, including finite field operations, point arithmetic, and scalar multiplication. Relying only on 36-W power consumption, our scalar multiplication performance reaches 1717 kops/s with the latency of 2.38 ms. In terms of the energy-efficiency ratio, EG-Four $\mathbb {Q}$ has significant advantages over other platforms such as advanced RISC machines (ARM) CPU, Intel CPU, field programmable gate array (FPGA), and desktop GPUs. The throughput of EG-Four $\mathbb {Q}$ is 1.75 times that of the fastest elliptic curve cryptography implementation based on the same platform and even exceeds the performance of Intel top server CPU E5-2699v3 (18-core). Based on the embedded GPU Xavier, EG-Four $\mathbb {Q}$ can act as a cryptographic edge computing module or even a cloud cryptographic accelerator, providing more efficient elliptic curve cryptographic services for IIoT.

关键词： Graphics processing units Cryptography Arithmetic Performance evaluation Industrial Internet of Things Elliptic curve cryptography Edge computing

来源：评论

学校读者我要写书评

暂无评论

Implementation of a Hip Fracture Classification Network Based on CT Tomography Scans 10

Implementation of a Hip Fracture Classification Network Base...

引用

10th International Conference on computer and Communications, ICCC 2024

作者： Zhao, Kui Yang, Meng Zhang, Ti Hu, Die Shenyang Institute of Computing Technology Chinese Academy of Sciences Shenyang China Liaoning Province Human-Computer Interaction System Engineering Research Center Based on Digital Twin Shenyang China University of Chinese Academy of Science Shenyang China Peking University Third Hospital Department of Orthopedics Beijing China

Hip fractures is the most common hip clinical trauma. The majority of elderly patients experience a decrease in bone density due to osteoporosis, making them highly prone to various types of hip fractures. In this context, accurate diagnosis and classification of hip fractures are crucial for guiding clinical decision-making and ensuring the best possible patient outcomes. The BV C- N et proposed in this study is a two-stage model for the identification of hip fracture types, which is based on the integration of the V-Net and ConvNeXt architectures. First, deep learning segmentation model is trained to generate candidate fracture regions, and then, a deep learning classification model is trained in the second stage to classify the segmented local fracture regions according to the candidate fracture regions generated in the first stage to ascertain the type of fracture. The results show that the two-stage deep learning model proposed in this study enhances the accuracy of hip fracture type recognition and reduces the time required for manual classification, which can better assist doctors in fracture region recognition. © 2024 IEEE.

关键词： Classification ConvNeXt Hip Fracture Segmentation V-Net

来源：评论

学校读者我要写书评

暂无评论

AgileShard: Turning the Sharded Blockchain into a Real-Time Transaction Processing System

AgileShard: Turning the Sharded Blockchain into a Real-Time ...

引用

Real-Time Systems Symposium (RTSS)

作者： Jianfeng Shi Heng Wu Wang Liu Heran Gao Wenbo Zhang University of Chinese Academy of Sciences Beijing China Software Engineering Technology Research and Development Center Institute of Software Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Nanjing China Nanjing institute of software technology Nanjing China State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences Beijing China

Blockchain, as an emerging transaction processing system, suffers from low throughput and high latency. Sharded blockchains can significantly increase throughput by dividing nodes into groups (i.e., shards) to process disjoint transactions in parallel. However, the diverse latency requirements of transactions in current sharded blockchains are not well met. Three challenges prevent the sharded blockchain from becoming a real-time transaction processing system, namely, the static block size, the first-come-first-served transaction packing strategy, and the load imbalance. Therefore, this paper proposes 3 methods to help turn the sharded blockchain into a real-time transaction processing system. First, we propose an inter-shard dynamic block size negotiation method that enables shards to adaptively determine the globally optimal block size based on the deadlines of pending transactions. Then, we propose a DAG-based transaction packing method for reducing the number of deadline violations and improving parallelism. Finally, we propose a minimum-cost-flow-based shard reconfiguration method to address load imbalance. Under real datasets on Ethereum, experimental results show that AgileShard using the above three methods can effectively improve the transaction deadline satisfaction rate.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SalFAU-Net: Saliency Fusion Attention U-Net for Salient Object Detection

arXiv

引用

arXiv 2024年

作者： Mulat, Kassaw Abraham Feng, Zhengyong Eshetie, Tegegne Solomon Hasen, Ahmed Endris School of Computer Science China West Normal University Sichuan Nanchong637002 China School of Electronic and Information Engineering China West Normal University Sichuan Nanchong637002 China Paul C. Lauterbur Research Center Shenzhen Institute of Advanced Technology Chinese Academy of Science Guangdong Shenzhen518055 China

Salient object detection (SOD) remains an important task in computer vision, with applications ranging from image segmentation to autonomous driving. Fully convolutional network (FCN)-based methods have made remarkable progress in visual saliency detection over the last few decades. However, these methods have limitations in accurately detecting salient objects, particularly in challenging scenes with multiple objects, small objects, or objects with low resolutions. To address this issue, we proposed a Saliency Fusion Attention U-Net (SalFAU-Net) model, which incorporates a saliency fusion module into each decoder block of the attention U-net model to generate saliency probability maps from each decoder block. SalFAU-Net employs an attention mechanism to selectively focus on the most informative regions of an image and suppress non-salient regions. We train SalFAU-Net on the DUTS dataset using a binary cross-entropy loss function. We conducted experiments on six popular SOD evaluation datasets to evaluate the effectiveness of the proposed method. The experimental results demonstrate that our method, SalFAU-Net, achieves competitive performance compared to other methods in terms of mean absolute error (MAE), F-measure, s-measure, and e-measure. © 2024, CC BY.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

KADEL: Knowledge-Aware Denoising Learning for Commit Message Generation

arXiv

引用

arXiv 2024年

作者： Tao, Wei Zhou, Yucheng Wang, Yanlin Zhang, Hongyu Wang, Haofen Zhang, Wenqiang Shanghai Engineering Research Center of AI and Robotics Academy for Engineering and Technology Fudan University Shanghai China State Key Laboratory of Internet of Things for Smart City Department of Computer and Information Science University of Macau China School of Software Engineering Sun Yat-sen University Guangdong Zhuhai519082 China School of Big Data and Software Engineering Chongqing University Chongqing China College of Design and Innovation Tongji University Shanghai China Engineering Research Center of AI and Robotics Ministry of Education Academy for Engineering and Technology Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University 220 Handan Road Shanghai200433 China

Commit messages are natural language descriptions of code changes, which are important for software evolution such as code understanding and maintenance. However, previous methods are trained on the entire dataset without considering the fact that a portion of commit messages adhere to good practice (i.e., good-practice commits), while the rest do not. On the basis of our empirical study, we discover that training on good-practice commits significantly contributes to the commit message generation. Motivated by this finding, we propose a novel knowledge-aware denoising learning method called KADEL. Considering that good-practice commits constitute only a small proportion of the dataset, we align the remaining training samples with these good-practice commits. To achieve this, we propose a model that learns the commit knowledge by training on good-practice commits. This knowledge model enables supplementing more information for training samples that do not conform to good practice. However, since the supplementary information may contain noise or prediction errors, we propose a dynamic denoising training method. This method composes a distribution-aware confidence function and a dynamic distribution list, which enhances the effectiveness of the training process. Experimental results on the whole MCMD dataset demonstrate that our method overall achieves state-of-the-art performance compared with previous methods. © 2024, CC BY.

关键词： Sampling

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：