检索结果-内蒙古大学图书馆

Advancement in Renewable Energy and Intelligent Systems (AREIS), International Conference on

作者： V. Raji S. Maheswari S. Sree Dharinya P. Chinniah Kavin K. S. Kiruba Thangam Raja Dept. of Information Technology S.K.P. Engineering College Tiruvannamalai India Dept. of CSE(IoT) Nandha Engineering College Erode Tamilnadu India Dept. of Software and Systems Engineering School of Computer Science Engineering and Information Systems VIT University Vellore India Dept. of ECE ST. Joseph College of Engineering Sriperumbudur Tamilnadu India Dept. of EEE Government College of Engineering Tirunelveli Tamil Nadu India Dept. of Software and Systems Engineering School of Computer Science Engineering and Information Systems(SCORE) VIT University Vellore India

ISBN: (数字)9798350387230

ISBN: (纸本)9798350387247

Rapid proliferation of aberrant neurons in brain tumors significantly damages organ function or causes death, endangering adult health. These tumors vary widely in terms of their locations, sizes, and textures. Finding malignant tumors requires the use of Magnetic Resonance Imaging (MRI). However, physically diagnosing brain tumors is a timeconsuming and potentially unpredictable technique. Cropping and resizing to fixed dimensions ensures consistency before submitting brain MRI images for analysis using deep learning models such as modified ResNet-50. This study uses the modified ResNet-50 model, a deep Convolutional Neural Network (CNN) renowned for its accuracy and resilience in image recognition tasks, to provide an efficient method for brain tumor diagnosis. Initially trained on Image Net, the modified ResNet-50 model further improved using transfer learning on many annotated brain MRI scan datasets. By adding variation to the dataset, data augmentation makes the model more robust and helps it to generalize. Deeper networks are trained without sacrificing performance to the model's architecture, which addresses the vanishing gradient problem. This work classification model implemented using Python software, which facilitated the development, training, and evaluation processes, allowing for an analysis of their performance. The optimized model outperformed conventional Machine Learning (ML) techniques, demonstrating over 94% accuracy in tumor identification and classification tests. With the potential to enhance patient outcomes and diagnostic efficiency, the integration of modified ResNet-50 in brain tumor identification offers a significant development towards accurate and dependable automated diagnostic systems. The accuracy of the modified Resnet-50 is 94%, and the specificity comparison of the modified ResNet-50 is 93.5%, respectively.

关键词： Deep learning Analytical models Accuracy Magnetic resonance imaging Transfer learning computer architecture Brain modeling Data augmentation Data models Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

PEFN: A Patches Enhancement and Hierarchical Fusion Network for Robust Vehicle Re-Identification

引用

IEEE Internet of Things Journal 2025年

作者： He, Wenying Wang, Feiyu Bai, Yude Xiong, Neal N. Xu, Guangquan Guo, Fei Hebei University of Technology School of Artificial Intelligence Tianjin300401 China Hebei University of Technology Hebei Province Key Laboratory of Big Data Calculation Tianjin300130 China Tiangong University School of Software Tianjin300387 China Northeastern State University Department of Mathematics and Computer Science TahlequahOK74464 United States Tianjin300350 China Central South University School of Computer Science and Engineering Changsha410083 China

Vehicle Re-Identification (Re-ID), which is a significant application in the Internet of Things, aims to accurately retrieve the remaining images of a given vehicle across different cameras views. The improvement in vehicle Re-ID performance largely stems from better addressing the issues of inter-class similarity and intra-class variance. Existing methods, relying solely on max or average pooling after using attention modules, fail to obtain significantly complete and pure global and local features, and neglect the false guidance that some unique individual information on images bring to re-identification. Moreover, models combining global and local features have shown good results in vehicle Re-ID, but these successes neglect the interaction between features across different convolutional layers, resulting in the loss of crucial details for vehicle Re-ID. To tackle these issues, we introduce a Patches Enhancement and hierarchical Fusion Network (PEFN) based on a multi-branch architecture, divided into a Global and Local Attention Supplement (GLAS) branch, and an Enhanced Hierarchical feature fusion (EnHi) branch. The GLAS branch, through the Identity-related Feature Remodeling (IDFR) module’s staged supplementation of spatial and channel features, has achieved the enhancement of both global and local features and effectively mitigated the negative impacts of individual information. The EnHi branch enhances the robustness of feature representation by interacting hierarchical features. Extensive experiments on two large-scale vehicle re-identification datasets demonstrate that our PEFN method outperforms state-of-the-art vehicle re-identification approaches. Specifically, without utilizing extra data and re-ranking, our model achieves 85.15% mAP on the VeRi776 dataset. © 2014 IEEE.

关键词： Reamers

来源：评论

学校读者我要写书评

暂无评论

Global-Semantic Alignment Distillation for Partial Multi-view Classification 39

Global-Semantic Alignment Distillation for Partial Multi-vie...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Wang, Xiaoli Huang, Anqi Wang, Yongli Ke, Guanzhou Hong, Xiaobin Liu, Jun School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210000 China School of Economics and Management Beijing Jiaotong University Beijing100080 China State Key Laboratory for Novel Software Technology Nanjing University Nanjing210023 China School of Computing and Communications Lancaster University Lancaster United Kingdom

ISBN: (纸本)157735897X

Partial multi-view classification (PMvC) poses a significant challenge due to the incomplete nature of multi-view data, which complicates effective information fusion and accurate classification. Existing PMvC methods typically rely on heuristic evaluations of view informativeness to achieve global alignment for downstream classification tasks. However, these approaches suffer from two critical issues: information redundancy and semantic misalignment. The complexity of missing data not only leads to over-reliance on redundant or less informative views but also exacerbates semantic misalignment across views, making it difficult for existing methods to effectively capture and discriminate the task-related features. To address these issues, this work proposes a novel GLobal-semantic Alignment Distillation (GLAD) paradigm for partial multi-view classification, implemented in an imputation-free manner. Our approach incorporates a self-distillation mechanism that enables the model to extract informative features and achieve global semantic alignment across views. The key insight of GLAD is leveraging the ground truth as semantic anchors to guide the alignment of partial multi-view features. By integrating the high-level semantics with extracted features via a cross-attention mechanism, we generate ideal embeddings that consistently capture global semantics across views. These embeddings then serve as intermediate supervision for distilling the student model, ensuring robust semantic alignment even with missing views. Furthermore, we introduce a margin-aware weighting strategy to enhance the model’s discriminative ability. Extensive experimental results validate the effectiveness and superiority of the proposed method, showcasing significant improvements in classification performance over existing techniques. © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Taxonomies

来源：评论

学校读者我要写书评

暂无评论

Evaluating shallow capsule networks on complex images

引用

International Journal of Information Technology (Singapore) 2021年第3期13卷 1047-1057页

作者： Mensah, Patrick Kwabena Weyori, Benjamin Asubam Ayidzoe, Mighty Abra Department of Computer Science and Informatics University of Energy and Natural Resources P.O. Box 214 Sunyani Ghana School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu China

Useful real-life images meant for computer vision applications appear in complex forms with varied backgrounds. Convolutional neural networks with their invariance outperforms capsule networks (CapsNets) on such images. Recent research to improve the accuracy of CapsNets on complex images such as CIFAR10 involves the increase in depth of the networks. However, smaller architectures with efficient feature extractors can perform comparatively well with additional advantages of having less computational cost, reduced risk of overfitting, increased suitability for deployment on devices with smaller memories, and enhanced feasibility to perform distributed training across servers and in the cloud. This paper, therefore, proposes a shallow CapsNet based on dynamic routing with a custom squashing function and normalizer to gain all of these advantages. The model is evaluated on three publicly available datasets;fashion-MNIST, CIFAR-10, and tomato datasets. Experimental results show that the proposed model outperforms the original CapsNet by generating fewer parameters and performing comparably well in terms of accuracy with some state-of-the-art multi-lane and ensemble capsule network models. © 2021, Bharati Vidyapeeth's Institute of computer Applications and Management.

关键词： Capsule network Complex images Convolutional neural networks Dynamic routing Local binary pattern Plant diseases

来源：评论

学校读者我要写书评

暂无评论

Significance of State-of-Art Search Engine in Game Development

Significance of State-of-Art Search Engine in Game Developme...

引用

International Conference on Computing for Sustainable Global Development (INDIACom)

作者： Ritu Dewan Rohith Polishetty Naveen Jagadam Mayank Kumar Goyal Kiran Kumar Ravulakollu Bhagwati Sharan Department of Computer Science and Engineering Galgotias College of Engineering and Technology Greater Noida India Sr. software engineer Migo India limited Hyderabad India CEO N2force Technologies Inc. Naperville IL USA Department of Computer Science & Engineering School of Engineering & Technology Sharda University Greater Noida India School of Technology Woxsen University Hyderabad India Department of Computer Science & Engineering School of Engineering and Sciences SRM University Amaravati AP India

Video game development process is different from other software projects while yet being related to them in software engineering. It is distinctive in that it incorporates the work of teams from several fields (art, music, acting, programming, etc.), and that it seeks to create a compelling gaming experience by using prototypes and iterations. This research study focuses on game development and how it is accomplished utilizing a game engine. The process of creating/developing games from a concept is known as game development. Game engines are software programs that help game developers create games. The literature study discusses about the various game engine. The utility of the “Unity” gaming engine is investigated in this paper. Unity may be utilized in different fields as study subjects, but there can be certain frequent benefits & obstacles of utilizing it in different case studies. Students learn which game engine to use based on their specific requirements.

关键词： Video games Art Prototypes Games Search engines Programming software

来源：评论

学校读者我要写书评

暂无评论

FGNN-Based Improved Resource Distribution Framework for V2X Wireless Networks

FGNN-Based Improved Resource Distribution Framework for V2X ...

引用

IEEE Conference on Vehicular Technology (VTC)

作者： Syed Muhammad Waqas Yazhe Tang Fakhar Abbas Mehboob Hussain Yawar Abbas Bangash School of Computer Science and Technology Xi'an Jiaotong University Xi'an P.R. China Centre for Trusted Internet and Community National University of Singapore (NUS) Singapore School of Information Science and Technology Southwest Jiaotong University Chengdu China Department of Computer Software Engineering National University of Sciences and Technology (NUST) Pak.

ISBN: (数字)9798350387414

ISBN: (纸本)9798350387421

Recently, deep learning has emerged as a promising approach for solving challenging resource distribution (RD) problems in vehicle-to-everything (V2X) wireless networks. How-ever, existing neural network architectures lack scalability, in-terpretability, and generalization. To address these limitations, in this study, we propose a new flexible graph neural network (FGNN)-based resource distribution framework for vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) user selection and power management in V2X networks with several next- generation access points (APs) and a cluster of V2V and V2I communication users. In the proposed framework, we formu-lated an optimization problem with each V2V and V2I user with the least power constraint that adapts to V2X wireless network settings through training inactive users. Likewise, we consider the situation when every V2I user shares the band with a different group of V2V users. Moreover, we introduce a parameterization of the RD framework strategy employing a flexible graph neural network (FGNN) context derived from instantaneous channel conditions to learn the low-dimension features of every user/vehicle. To assess the execution of the framework, we conduct simulation experiments comparing it with baseline methods in terms of efficiency, sum rate, and fairness.

关键词： Training Vehicular and wireless technologies Wireless networks Scalability Power system management Vehicular ad hoc networks Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

DomainAdaptor: A Novel Approach to Test-time Adaptation

arXiv

引用

arXiv 2023年

作者： Zhang, Jian Qi, Lei Shi, Yinghuan Gao, Yang State Key Laboratory for Novel Software Technology Nanjing University China National Institute of Healthcare Data Science Nanjing University China School of Computer Science and Engineering Southeast University China

To deal with the domain shift between training and test samples, current methods have primarily focused on learning generalizable features during training and ignore the specificity of unseen samples that are also critical during the test. In this paper, we investigate a more challenging task that aims to adapt a trained CNN model to unseen domains during the test. To maximumly mine the information in the test data, we propose a unified method called DomainAdaptor for the test-time adaptation, which consists of an AdaMixBN module and a Generalized Entropy Minimization (GEM) loss. Specifically, AdaMixBN addresses the domain shift by adaptively fusing training and test statistics in the normalization layer via a dynamic mixture coefficient and a statistic transformation operation. To further enhance the adaptation ability of AdaMixBN, we design a GEM loss that extends the Entropy Minimization loss to better exploit the information in the test data. Extensive experiments show that DomainAdaptor consistently outperforms the state-of-the-art methods on four benchmarks. Furthermore, our method brings more remarkable improvement against existing methods on the few-data unseen domain. The code is available at https://***/koncle/DomainAdaptor. Copyright © 2023, The Authors. All rights reserved.

关键词： Entropy

来源：评论

学校读者我要写书评

暂无评论

Confidence-aware contrastive learning for selective classification 24

Confidence-aware contrastive learning for selective classifi...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Yu-Chang Wu Shen-Huan Lyu Haopu Shang Xiangyu Wang Chao Qian National Key Laboratory for Novel Software Technology and School of Artificial Intelligence Nanjing University China Key Laboratory of Water Big Data Technology of Ministry of Water Resources and College of Computer Science and Software Engineering Hohai University China and National Key Laboratory for Novel Software Technology Nanjing University China

Selective classification enables models to make predictions only when they are sufficiently confident, aiming to enhance safety and reliability, which is important in high-stakes scenarios. Previous methods mainly use deep neural networks and focus on modifying the architecture of classification layers to enable the model to estimate the confidence of its prediction. This work provides a generalization bound for selective classification, disclosing that optimizing feature layers helps improve the performance of selective classification. Inspired by this theory, we propose to explicitly improve the selective classification model at the feature level for the first time, leading to a novel Confidence-aware Contrastive Learning method for Selective Classification, CCL-SC, which similarizes the features of homogeneous instances and differentiates the features of heterogeneous instances, with the strength controlled by the model's confidence. The experimental results on typical datasets, i.e., CIFAR-10, CIFAR-100, CelebA, and ImageNet, show that CCL-SC achieves significantly lower selective risk than state-of-the-art methods, across almost all coverage degrees. Moreover, it can be combined with existing methods to bring further improvement.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Nudity Detection Algorithm for Web-based Online Networking Platform

A Nudity Detection Algorithm for Web-based Online Networking...

引用

International Conference on Computing for Sustainable Global Development (INDIACom)

作者： Ritu Dewan Rohith Polishetty Naveen Jagadam Kiran Kumar Ravulakollu Mayank Kumar Goyal Bhagwati Sharan Department of Computer Science and Engineering Galgotias College of Engineering and Technology Greater Noida India Sr. Software Engineer Migo India Limited Hyderabad India CEO N2force Technologies Inc. Naperville IL USA School of Technology Woxsen University Hyderabad India Department of Computer Science & Engineering School of Engineering & Technology Sharda University Greater Noida India Department of Computer Science and Engineering School of Engineering and Sciences SRM University Amaravati AP India

Social media and online platforms have become an integral part of the day-to-day life of the people and the organizations, which shows a lot of diversity. Many online platforms allow users to share media extensively, like images, videos, and audio but not all the media content shared on the internet is safe for work or should be restricted from particular platforms. Images with nudity are of big concern when it comes to online media sharing and social platforms must take serious measures to restrict users to share images with nudity. The rate of growth of nudity content over the internet or social media is very high. It affects the mental and physical health of individuals. In this paper, a novel method for nudity detection in images is presented. We aim to develop a Machine Learning algorithm for nudity detection in a community networking platform and how it should be integrated with such a platform so that posted images can be thoroughly checked for nudity and if detected how it should be dealt with.

关键词： Runtime Machine learning algorithms Social networking (online) Organizations Media Mobile applications Reliability

来源：评论

学校读者我要写书评

暂无评论

ALOFT: A Lightweight MLP-like Architecture with Dynamic Low-frequency Transform for Domain Generalization

arXiv

引用

arXiv 2023年

作者： Guo, Jintao Wang, Na Qi, Lei Shi, Yinghuan State Key Laboratory for Novel Software Technology Nanjing University China National Institute of Healthcare Data Science Nanjing University China School of Computer Science and Engineering Southeast University China

Domain generalization (DG) aims to learn a model that generalizes well to unseen target domains utilizing multiple source domains without re-training. Most existing DG works are based on convolutional neural networks (CNNs). However, the local operation of the convolution kernel makes the model focus too much on local representations (e.g., texture), which inherently causes the model more prone to overfit to the source domains and hampers its generalization ability. Recently, several MLP-based methods have achieved promising results in supervised learning tasks by learning global interactions among different patches of the image. Inspired by this, in this paper, we first analyze the difference between CNN and MLP methods in DG and find that MLP methods exhibit a better generalization ability because they can better capture the global representations (e.g., structure) than CNN methods. Then, based on a recent lightweight MLP method, we obtain a strong baseline that outperforms most state-of-the-art CNN-based methods. The baseline can learn global structure representations with a filter to suppress structure-irrelevant information in the frequency space. Moreover, we propose a dynAmic LOw-Frequency spectrum Transform (ALOFT) that can perturb local texture features while preserving global structure features, thus enabling the filter to remove structure-irrelevant information sufficiently. Extensive experiments on four benchmarks have demonstrated that our method can achieve great performance improvement with a small number of parameters compared to SOTA CNN-based DG methods. Our code is available at https://***/lingeringlight/ALOFT/. Copyright © 2023, The Authors. All rights reserved.

关键词： Convolutional neural networks

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：