检索结果-内蒙古大学图书馆

FusionMamba:dynamic feature enhancement for multimodal image fusion with Mamba

Visual Intelligence 2024年第1期2卷 470-487页

作者： Xinyu Xie Yawen Cui Tao Tan Xubin Zheng Zitong Yu School of Computing and Information Technology Great Bay UniversityDongguanGuangdong523000China Faculty of Applied Sciences Macao Polytechnic UniversityMacaoChina Department of Electrical and Electronic Engineering The Hong Kong Polytechnic UniversityHong KongChina

Multimodal image fusion aims to integrate information from different imaging techniques to produce a comprehensive,detail-rich single image for downstream vision *** methods based on local convolutional neural networks(CNNs)struggle to capture global features efficiently,while Transformer-based models are computationally expensive,although they excel at global *** addresses these limitations by leveraging selective structured state space models(S4)to effectively handle long-range dependencies while maintaining linear *** this paper,we propose FusionMamba,a novel dynamic feature enhancement framework that aims to overcome the challenges faced by CNNs and Vision Transformers(ViTs)in computer vision *** framework improves the visual state-space model Mamba by integrating dynamic convolution and channel attention mechanisms,which not only retains its powerful global feature modeling capability,but also greatly reduces redundancy and enhances the expressiveness of local *** addition,we have developed a new module called the dynamic feature fusion module(DFFM).It combines the dynamic feature enhancement module(DFEM)for texture enhancement and disparity perception with the cross-modal fusion Mamba module(CMFM),which focuses on enhancing the inter-modal correlation while suppressing redundant *** show that FusionMamba achieves state-of-the-art performance in a variety of multimodal image fusion tasks as well as downstream experiments,demonstrating its broad applicability and superiority.

关键词： Multimodal Image fusion Feature enhancement Mamba

来源：评论

学校读者我要写书评

暂无评论

Understanding Safety Risks and Safety Design in Social VR Environments

引用

Proceedings of the ACM on Human-Computer Interaction 2023年第CSCW1期7卷 1-37页

作者： Zheng, Qingxiao Xu, Shengyang Wang, Lingqing Tang, Yiliu Salvi, Rohan C. Freeman, Guo Huang, Yun School of Information Sciences University of Illinois Urbana-Champaign United States College of Fine and Applied Arts University of Illinois Urbana-Champaign United States Department of Industrial Engineering Tsinghua University China School of Informatics University of Illinois Urbana-Champaign United States School of Computing Clemson University Clemson United States

Understanding emerging safety risks in nuanced social VR spaces and how existing safety features are used is crucial for the future development of safe and inclusive 3D social worlds. Prior research on safety risks in social VR is mainly based on interview or survey data about social VR users' experiences and opinions, which lacks "in-situ observations"of how individuals react to these risks. Using two empirical studies, this paper seeks to understand safety risks and safety design in social VR. In Study 1, we investigated 212 YouTube videos and their transcripts that document social VR users' immediate experiences of safety risks as victims, attackers, or bystanders. We also analyzed spectators' reactions to these risks shown in comments to the videos. In Study 2, we summarized 13 safety features across various social VR platforms and mapped how each existing safety feature in social VR can mitigate the risks identified in Study 1. Based on the uniqueness of social VR interaction dynamics and users' multi-modal simulated reactions, we call for further re-thinking and re-approaching safety designs for future social VR environments and propose potential design implications for future safety protection mechanisms in social VR. © 2023 ACM.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

Congruent Feature Selection Method to Improve the Efficacy of Machine Learning-Based Classification in Medical Image Processing

引用

Computer Modeling in engineering & sciences 2025年第1期142卷 357-384页

作者： Mohd Anjum Naoufel Kraiem Hong Min Ashit Kumar Dutta Yousef Ibrahim Daradkeh Department of Computer Engineering Aligarh Muslim UniversityAligarh202002India College of Computer Science King Khalid UniversityAbha61413Saudi Arabia School of Computing Gachon UniversitySeongnam13120Republic of Korea Department of Computer Science and Information Systems College of Applied SciencesAlMaarefa UniversityRiyadh13713Saudi Arabia Department of Computer Engineering and Information College of Engineering in Wadi AlddawasirPrince Sattam bin Abdulaziz UniversityAl-Kharj16273Saudi Arabia

Machine learning(ML)is increasingly applied for medical image processing with appropriate learning *** applications include analyzing images of various organs,such as the brain,lung,eye,etc.,to identify specific flaws/diseases for *** primary concern of ML applications is the precise selection of flexible image features for pattern detection and region *** of the extracted image features are irrelevant and lead to an increase in computation ***,this article uses an analytical learning paradigm to design a Congruent Feature Selection Method to select the most relevant image *** process trains the learning paradigm using similarity and correlation-based features over different textural intensities and pixel *** similarity between the pixels over the various distribution patterns with high indexes is recommended for disease ***,the correlation based on intensity and distribution is analyzed to improve the feature selection ***,the more congruent pixels are sorted in the descending order of the selection,which identifies better regions than the ***,the learning paradigm is trained using intensity and region-based similarity to maximize the chances of ***,the probability of feature selection,regardless of the textures and medical image patterns,is *** process enhances the performance of ML applications for different medical image *** proposed method improves the accuracy,precision,and training rate by 13.19%,10.69%,and 11.06%,respectively,compared to other models for the selected *** mean error and selection time is also reduced by 12.56%and 13.56%,respectively,compared to the same models and dataset.

关键词： Computer vision feature selection machine learning region detection texture analysis image classification medical images

来源：评论

学校读者我要写书评

暂无评论

Flight Delay Prediction Using Machine Learning 8

Flight Delay Prediction Using Machine Learning

引用

8th IEEE International Conference for Convergence in Technology, I2CT 2023

作者： Reddy, Ravula Tarun Basa Pati, Peeta Deepa, K. Sangeetha, S. Tresa Amrita Vishwa Vidyapeetham Amrita School of Computing Department of Computer Science and Engineering Bengaluru India Amrita Vishwa Vidyapeetham Amrita School of Engineering Department of Electrical and Electronics Engineering Bengaluru India University of Technology and Applied Sciences Department of Engineering Al Musannah Oman

ISBN: (纸本)9798350334012

The prediction of flight delay can be considered as one of the most challenging problems to solve. Delay of an aircraft is not only a problem for an airline but also for the passengers. Flights can be delayed due to several reasons, the weather being the primary one. In this paper, our focus is to predict the delay of the flights due to bad weather. The dataset used consists of flight data from JFK airport from the sources Bureau of Transportation statistics and weather data from the National Centers for Environmental Information. The results of different machine learning algorithms like Linear Regression, SVR, Decision Tree Regressor, Random Forest Regressor, Ridge, and Lasso Regressor, for prediction of flight delay, are compared. XGboost regressor had the best performance in all the scenarios with least RMSE score of 0.81. © 2023 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Unifying Robust Activation Functions for Reduced Adversarial Vulnerability with the Parametric Generalized Gamma Function 23

Unifying Robust Activation Functions for Reduced Adversarial...

引用

23rd IEEE International Conference on Machine Learning and Applications, ICMLA 2024

作者： Alemany, Sheila Worthington, Emma Dominguez, Alberto Grapel, Ilan Pissinou, Niki School of Computing and Information Sciences Florida International University United States College of Engineering and Applied Science University of Colorado Boulder United States National Science Foundation Research Experience for Teachers Fellow United States

ISBN: (纸本)9798350374889

Adversaries minimally perturb deep learning input data to reduce a learning model's ability to produce domain-specific data-driven recommendations to solve specialized tasks. This vulnerability to adversarial perturbations has been argued to stem from a learning model's nonlocal generalization over complex input data. Given the incomplete information in a complex dataset, a learning model captures nonlinear patterns between data points with volatility in the loss surface and exploitable areas of low-confidence knowledge. It is the responsibility of activation functions to capture the nonlinearity in data and, thus, has inspired disjointed research efforts to create robust activation functions. This work unifies the properties of activation functions that contribute to robust generalization with the generalized gamma distribution function. We show that combining the disjointed characteristics presented in the literature with our parametric generalized gamma activation function provides more effective robustness than the individual characteristics alone11The source code for this research effort: https://***/sheilaalemany/***. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Enhancing Cyclone Center Identification in Radar Images through Deep Learning and Match Recognition 15

Enhancing Cyclone Center Identification in Radar Images thro...

引用

15th International Conference on computing Communication and Networking Technologies, ICCCNT 2024

作者： Shanmugam, Thirumurugan Chandrashekar, Chirag Subburaj, Maheswari Sivaraman, Arun Kumar Sultana, Ajmery Thangavel, Senthil Kumar University of Technology and Applied Sciences College of Computing and Information Sciences Suhar Oman Vellore Institute of Technology School of Computer Science and Engineering Chennai India Photon Interactive Inc Digital Engineering Solution Center ON Canada Algoma University Brampton School of Computer Science and Technology ON Canada Amrita Vishwa Vidyapeetham Department of Computer Science and Engineering Coimbatore India

ISBN: (纸本)9798350370249

This research focuses on improving the identification of cyclone centers using deep learning and match recognition applied to radar images. Accurately pinpointing the cyclone's center is vital for predicting its intensity and trajectory. However, challenges persist in automatically locating the center due to the diverse nature of cyclone morphology and structure. To address this, the deep convolutional network's capability is leveraged to capture various structural features in images by proposing two-step approach for cyclone center localization. Initially, a pre-trained EfficientDet model is employed using transfer learning to obtain weights. Subsequently, these weights, along with the data, are utilized in a deep learning model to provide precise coordinates of the cyclone center in the respective image. The effectiveness of existing deep learning and machine learning models show that the cyclone prediction systems have an accuracy ranging from 86% to 92% or better, and cyclone eye detection accuracy surpassing 87%. Experiment outcomes indicate that the proposed methodology outperforms conventional methods and existing works, showcasing its potential for enhancing cyclone monitoring and forecasting. © 2024 IEEE.

关键词： Cyclone detection deep learning efficient det and YOLO model transfer learning

来源：评论

学校读者我要写书评

暂无评论

LLCNN-based Image Enhancement with Squeeze and Excitation Network for Improved Visual Quality 16

LLCNN-based Image Enhancement with Squeeze and Excitation Ne...

引用

16th IEEE International Conference on Computational Intelligence and Communication Networks, CICN 2024

作者： Subburaj, Maheswari Shanmugam, Thirumurugan Sivaraman, Arun Kumar Nithiyanantham, Janakiraman Ravindran, Priya Sivam, Babu School of Cse Vellore Institute of Technology Chennai India College of Computing and Information Sciences University of Technology and Applied Sciences Suhar Oman Digital Engineering Solution Centre Photon Interactive Inc. Ontario Canada Department of Ece K L N College of Engineering Tamilnadu India

ISBN: (纸本)9798331505264

Image enhancement, particularly in low-light conditions, has long been a research focus to improve visual quality. Low-light settings often cause visibility issues and detail loss, which recent deep-learning techniques have effectively addressed. This study explores the combination of a low-light convolutional neural network (LLCNN), a convolutional neural network designed explicitly for low-light image enhancement, with a Squeeze and Excitation Network (SEN), which recalibrate features to emphasise critical details and suppress noise. Integrating SEN into LLCNN enhances image details while reducing noise and artefacts typically present in low-light conditions. Experimental results show that this combined approach outperforms existing methods in objective metrics, such as peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM), as well as visual quality. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Fire Hawk Optimization based Multi-objective Dynamic Load Balancing in Cloud computing 2

Fire Hawk Optimization based Multi-objective Dynamic Load Ba...

引用

2nd International Conference on Distributed computing and Optimization Techniques, ICDCOT 2024

作者： Kumari, K. Aruna Soujanya, Thota Alsalami, Zaid Rohini, I. Bala Dhandayuthapani, V. Srkr Engineering College Department of Cse Chinaamiram Bhimavaram India School of Agricultural Sciences Sr University Telangana Warangal India The Islamic University Najaf Iraq Malla Reddy Engineering College for Women Dept of Eee Telangana India College of Computing and Information Sciences University of Technology and Applied Sciences Shinas Branch Department of It Oman

ISBN: (纸本)9798350382952

Load Balancing (LB) of the tasks on Cloud computing (CC) is the significant characteristics of distribution of the resources from data center. LB has to be taken out in such a way that every Virtual Machines (VMs) must have balanced the load to attain an optimal utilization of its capabilities. As an outcome, the LB of tasks on VM is examined as a significant thing of task scheduling in the cloud. The LB in cloud faced various challenges like fault tolerance as well as data security. In this research, Fire Hawk Optimization (FHO) algorithm is proposed for the dynamic LB in cloud environment. The aim of this research is to enhance the system performance and it considers the multi-objective functions named Makespan, Resource Utilization (RU), Response Time (RT), Degree of Imbalance as well as throughput. The experimental results proven that the proposed FHO-based LB had obtained the 2246, 6.7, 134.23, 141 and 5.5 in the number of tasks of 1500 using nakespan, RT, RU, DOI and throughput. These results show better enhancement when compared to the previous approaches like Particle Swarm Optimization (PSO), Q-learning Modified PSO (QMPSO) and Binary JAYA algorithm. © 2024 IEEE.

关键词： Cloud computing

来源：评论

学校读者我要写书评

暂无评论

An Algebraic Multigrid-Based Physical Factorization Preconditioner for the Multi-Group Radiation Diffusion Equations in Three Dimensions

引用

Numerical Mathematics(Theory,Methods and Applications) 2023年第2期16卷 410-432页

作者： Xiaoqiang Yue Zekai Zhang Xiaowen Xu Shuying Zhai Shi Shu National Center for Applied Mathematics in Hunan Key Laboratory of Intelligent Computing&Information Processing of Ministry of EducationHunan Key Laboratory for Computation and Simulation in Science and EngineeringXiangtan UniversityXiangtan 411105China Laboratory of Computational Physics Institute of Applied Physics and Computational MathematicsBeijing 100094China School of Mathematical Sciences Huaqiao UniversityQuanzhou 362021China.

The paper investigates the robustness and parallel scaling properties of a novel physical factorization preconditioner with algebraic multigrid subsolves in the iterative solution of a cell-centered finite volume discretization of the threedimensional multi-group radiation diffusion *** key idea is to take advantage of a particular kind of block factorization of the resulting system matrix and approximate the left-hand block matrix selectively spurred by parallel processing *** spectral property of the preconditioned matrix is then *** practical strategy is considered sequentially and in ***,numerical results illustrate the numerical robustness,computational efficiency and parallel strong and weak scalabilities over the real-world structured and unstructured coupled problems,showing its competitiveness with many existing block preconditioners.

关键词： Radiation diffusion equations physical factorization preconditioning algebraic multigrid parallel and distributed computing

来源：评论

学校读者我要写书评

暂无评论

Microstructure， electrochemical， wear and corrosive wear performance of laser-based powder bed fusion(lpbf) and wrought biomedical Ti-6Al-4V alloys

引用

Transactions of Nonferrous Metals Society of China 2024年

作者： A.G.Lekatou B.V.Efremenko V.Haoui V.G.Efremenko S.Emmanouilidou V.I.Zurnadzhy I.Petryshynets Yu.G.Chabak I.I.Sili Laboratory of Applied Metallurgy， Department of Materials Science and Engineering， School of Engineering， University of Ioannina Institute of Materials Science and Computing， University Research Center of Ioannina (URCI) Pryazovskyi State Technical University， Department of Physics Institute of Materials Research of Slovak Academy of Sciences

Wrought and laser powder bed fusion （LPBF） Ti-6Al-4V specimens were comparatively evaluated， with the objective to determine LPBF Ti-6-4’s suitability for biomedical applications. Testing included nanoindentation， cyclic polarization in simulated body fluid （SBF， 37 ℃ ）， and dry and SBF “Ball-on-Plate” sliding. Wrought Ti-6-4 exhibited a lamellar （α+β） microstructure， whereas LPBF displayed a fine-grained α'-martensite microstructure. LPBF Ti-6-4 demonstrated ～3% higher indentation modulus and ～32% higher hardness， while wrought Ti-6-4 showed ～8% higher plasticity. Both alloys exhibited low corrosion rates (10–5mA/cm2order) and true passivity (10–4mA/cm2order). No localized corrosion was observed in either alloy， except for occasional metastable pitting in the LPBF alloy. However， LPBF Ti-6-4 presented higher corrosion rate and passive current， ascribed to its martensitic structure. During dry sliding， LPBF Ti-6-4 exhibited ～14% lower volume loss compared to wrought Ti-6-4. Sliding in SBF increased volume losses for both alloys， with wear resistances nearly equalized， as the advantage of LPBF Ti-6-4 decreased due to more intensive wear-accelerated corrosion induced by the stressed martensite. Overall， the results demonstrate the suitability of LPBF Ti-6Al-4V for biomedical uses.

关键词：

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：