检索结果-内蒙古大学图书馆

25th International Multi Topic Conference, INMIC 2023

作者： Noor, Muhammad Nouman Nazir, Muhammad Dilshad, Veena Haneef, Farah Hitec University Taxila Department of Computer Science Taxila Pakistan Cust University Department of Software Engineering Islamabad Pakistan

ISBN: (纸本)9798350317701

Endoscopic disease severity assessment is a critical component in the management of ulcerative colitis patients. Endoscopic evaluation, on the other hand, suffers from significant intra-observer and inter-observer differences, reducing the reliability of individual assessments. As a result, we set out to create a deep-learning model capable of distinguishing between distinct endoscopic disease severity levels. Initially, we preprocessed the dataset and then applied data augmentations on the images using various geometric transformations. Subsequently, we have utilized the transfer learning concept by applying modified ResNet-50 by stacking additional layers which further improves the classification performance. Our proposed model achieved an accuracy of 84.21%, 81.06% recall, and 88.33% precision. © 2023 IEEE.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Dual-branch Complementary Multimodal Interaction Mechanism for Joint Video Moment Retrieval and Highlight Detection

Dual-branch Complementary Multimodal Interaction Mechanism f...

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Liang, Xuehui Wang, Ruomei Lin, Ge Feng, Jiawei Luo, Yuanmao School of Computer Science and Engineering Sun Yat-sen University National Engineering Research Center of Digital Life Guangzhou China School of Software Engineering Sun Yat-sen University Zhuhai China

ISBN: (纸本)9781665410205

Joint video moment retrieval and highlight detection is a video understanding task that requires the model to construct multimodal interaction between heterogeneous features. Recent Transformer-based models mainly focus on promoting global interaction between features. However, local interaction and temporal asynchronism modeling are not deeply considered. To solve this problem, this paper proposes a dual-branch complementary multimodal interaction mechanism (DCMI), which consists of a global difference feature activation module (GDFA) and a local information dynamic aggregation module (LIDA). GDFA measures the difference between the target element and the global features, thus activating important information. LIDA designs a multimodal heterogeneous graph and constructs asynchronous interaction between heterogeneous features to dynamically aggregate local information. DCMI adaptively fuses the complementary dual branches to improve the model's cognitive and decision-making abilities of global and local information. Comprehensive comparisons with existing methods on public datasets verify the superiority of the proposed model. Extensive ablation experiments and qualitative analysis show the effectiveness and rationality of DCMI, which can promote the interaction between multimodal features. © 2024 IEEE.

关键词： Video analysis

来源：评论

学校读者我要写书评

暂无评论

3D Atrous Spatial Pyramid Pooling based Multi-Scale Feature Fusion Network for Hyperspectral Image Classification

3D Atrous Spatial Pyramid Pooling based Multi-Scale Feature ...

引用

2023 International Conference on Remote Sensing, Mapping, and Geographic Systems, RSMG 2023

作者： Zhu, Tianxing Liu, Qin Zhang, Lixiang School of Software Engineering Tongji University Shanghai China School of Computer Science Northwestern Polytechnical University Xi’an China

ISBN: (纸本)9781510668898

The convolutional neural network (CNN) has been widely adopted in the processing of hyperspectral images (HSI) due to its remarkable capabilities in feature extraction. However, CNN-based methods for HSI classification still face the challenge of extracting spectral-spatial features that are more effective while considering all spectral bands. This paper reviews various spectral and spectral-spatial classifiers that have been developed to overcome the challenges of HSI classification, including the limitations of handcrafted features and the problems caused by spectral variability and nonlinearity. The paper proposes a novel method, the 3D ASPP Multi-Scale Feature Fusion Network (3A-MFFN), which simultaneously preserves high-resolution spatial detail information and high-level semantic information of HSI. The proposed network extracts and fuses multi-scale features for HSI classification using a multi-scale 3D ASPP convolution block to fuse different levels of feature output. The paper presents experiments and analysis to demonstrate the effectiveness of the proposed method. The results suggest that the 3A-MFFN algorithm can significantly enhance the classification accuracy of HSI with limited samples, making it a valuable contribution to the hyperspectral remote sensing community. © 2023 SPIE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Predicting the Unseen: A Novel Dataset for Hidden Intention Localization in Pre-abnormal Analysis 24

Predicting the Unseen: A Novel Dataset for Hidden Intention ...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Qi, Zehao Zhang, Ruixu Hu, Xinyi Liu, Wenxuan Wang, Zheng National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence Wuhan University Hubei Key Laboratory of Multimedia and Network Communication Engineering School of Computer Science Wuhan China School of Computer Science and Artificial Intelligence Wuhan University of Technology Wuhan China

ISBN: (纸本)9798400706868

Our paper introduces a novel video dataset specifically for Temporal Intention Localization (TIL), aimed at identifying hidden abnormal intention in densely populated and complex environments. Traditional Temporal Action Localization (TAL) frameworks, focusing on overt actions within constrained temporal intervals, often miss subtle pre-abnormal actions that unfold over extended periods. Our dataset comprises 228 videos with 5790 clips, each annotated to capture fine-grained actions within ambiguous temporal boundaries using the Joint-Linear-Assignment methodology. This approach enables detailed analysis of the evolution of abnormal intention over time. To detect subtle, hidden intention, we developed the Intention-Action Fusion module, an creative approach integrating dynamic feature fusion across 11 behavioral subcategories, significantly enhancing the model's ability to discern nuanced intention. This enhancement has led to performance improvements of up to 139% in specific scenarios, dramatically boosting the model's sensitivity and interpretability, crucial for advancing proactive surveillance systems. By pushing the boundaries of technology, our dataset and methodologies foster proactive surveillance systems capable of preemptively identifying potential threats from nuanced behavioral patterns, encouraging further exploration into the complexities of intention beyond observable actions. The dataset is available at https://***/Zzz99999/Hidden-Abnormal-Intention. © 2024 ACM.

关键词： Security systems

来源：评论

学校读者我要写书评

暂无评论

Research on Image Style Transfer Algorithm Based on Structural Consistency 8

Research on Image Style Transfer Algorithm Based on Structur...

引用

8th International Conference on Intelligent Computing and Signal Processing, ICSP 2023

作者： Yang, Chuxiong Chen, Zhuang Chongqing University of Posts and Telecommunications School of Software Engineering Chongqing China Chongqing University of Technology College of Computer Science and Engineering Chongqing China

ISBN: (纸本)9798350302455

The algorithm proposed in this paper aims to address the issue of structural content distortions in images that occur after applying image style transfer. It introduces a structural consistency-based approach called the PoolNet algorithm. This algorithm incorporates saliency regions to perform style transfer at the block level. By employing a saliency detection network, a saliency map is generated for both the synthetic and content images. During the training process, two losses are computed to ensure that the salient regions in the synthetic image remain consistent with those in the content image. Additionally, local affine constraints in the color space are employed to enhance the stylized images by constraining the image transformation. Experimental results demonstrate that the stylized images produced by this style transfer model exhibit improved visual effects and preserve the semantic information of the content images. This improvement is particularly noticeable when dealing with distorted migration images. © 2023 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

WIP: A Systematic Approach for Outcome-Based Assessment 54

WIP: A Systematic Approach for Outcome-Based Assessment

引用

54th IEEE Frontiers in Education Conference, FIE 2024

作者： Belkhouche, F. Bendjilali, K. Shippensburg University of Pennsylvania Department of Computer Electrical and Software Engineering ShippensburgPA United States Raritan Valley Community College Department of Mathematics and Computer Science BranchburgNJ United States

ISBN: (纸本)9798350351507

This research-to-practice WIP paper describes methods for improving assessment. Assessment is crucial for pro-gram accreditation and continuous improvement in engineering education. Outcome-based learning is a recent student-centred approach that can be used perform assessment. Under this paradigm, clear outcomes related to the knowledge and skills that the students should have after completing the course are identified and assessed. The student attainments are measured against the outcomes using clear and well-defined metrics. In this paper, an outcome-based strategy is proposed and used for assessing courses in control systems. In order to improve assessment reliability, the learning outcomes are broken down into sub-outcomes, which are used as performance indicators. The advantage of the proposed method is twofold, first it provides more accurate and reliable metrics for measuring student attainment, and second, the assessment results are personalized, allowing to evaluate individual students and identify means to help them. This approach also allows to identify common mistakes and misconceptions. Data are collected for several semesters and analyzed. It turns out that the proposed approach allows to obtain more accurate and reliable assessment results. © 2024 IEEE.

关键词： engineering education

来源：评论

学校读者我要写书评

暂无评论

A Novel Deep Federated Learning-Based and Profit-Driven Service Caching Method 19th

A Novel Deep Federated Learning-Based and Profit-Driven Ser...

引用

19th EAI International Conference on Collaborative Computing: Networking, Applications and Worksharing, CollaborateCom 2023

作者： Ouyang, Zhaobin Xia, Yunni Peng, Qinglan Li, Yin Chen, Peng Wang, Xu College of Computer Science Chongqing University Chongqing China School of Artificial Intelligence Henan University Zhengzhou China Guangzhou Institute of Software Application Technology Guangzhou China School of Computer and Software Engineering Xihua University Chengdu China College of Mechanical and Vehicle Engineering Chongqing University Chongqing China

ISBN: (纸本)9783031545306

Service caching is an emerging solution to addressing massive service request in a distributed environment for supporting rapidly growing services and applications. With the explosive increases in global mobile data traffic, service caching over the edge computing architecture, Mobile edge computing (MEC), emerges for alleviating traffic congestion as well as for optimizing the efficiency of task processing. In this manuscript, we propose a novel profit-driven service caching method based on a federated learning model for service prediction and a deep reinforcement learning mode for yielding caching decisions (FPDRD) in an edge environment. The proposed method is temporal service popularity and user preference-aware. It aims to ensure quality of service (QoS) of delivery of cached service while maximizing the profits of network service providers. Experimental results clearly demonstrate that the FPDRD method outperforms traditional methods in multiple aspects. © ICST Institute for computer sciences, Social Informatics and Telecommunications engineering 2024.

关键词： Traffic congestion

来源：评论

学校读者我要写书评

暂无评论

Dynamic defenses in cyber security:Techniques,methods and challenges Author links open overlay panel

引用

Digital Communications and Networks 2022年第4期8卷 422-435页

作者： Yu Zheng Zheng Li Xiaolong Xu Qingzhan Zhao School of Computer and Software Nanjing University of Information Science and TechnologyNanjing210044JiangsuChina Key Laboratory for Novel Software Technology Nanjing UniversityNanjing210023JiangsuChina College of Information Science and Technology Shihezi University Geospatial Information Engineering Research CenterChina

Driven by the rapid development of the Internet of Things,cloud computing and other emerging technologies,the connotation of cyberspace is constantly expanding and becoming the fifth dimension of human ***,security problems in cyberspace are becoming serious,and traditional defense measures(e.g.,firewall,intrusion detection systems,and security audits)often fall into a passive situation of being prone to attacks and difficult to take effect when responding to new types of network attacks with a higher and higher degree of coordination and *** constructing and implementing the diverse strategy of dynamic transformation,the configuration characteristics of systems are constantly changing,and the probability of vulnerability exposure is ***,the difficulty and cost of attack are increasing,which provides new ideas for reversing the asymmetric situation of defense and attack in ***,few related works systematically introduce dynamic defense mechanisms for cyber *** related concepts and development strategies of dynamic defense are rarely analyzed and *** bridge this gap,we conduct a comprehensive and concrete survey of recent research efforts on dynamic defense in cyber ***,we firstly introduce basic concepts and define dynamic defense in cyber ***,we review the architectures,enabling techniques and methods for moving target defense and mimic *** is followed by taxonomically summarizing the implementation and evaluation of dynamic ***,we discuss some open challenges and opportunities for dynamic defense in cyber security.

关键词： Cyber security Dynamic defense Moving target defense Mimic defense

来源：评论

学校读者我要写书评

暂无评论

Anomaly Detection of EEG in patients with epilepsy based on Graph Deviation Network 6

Anomaly Detection of EEG in patients with epilepsy based on ...

引用

6th International Conference on computer Information science and Application Technology, CISAT 2023

作者： Chen, Ming Liu, Changyu Gao, Huaijin Tao, Haomin Lin, Siyuan Computer Technology and Software Engineering Wuhan Polytechnic Wuhan430074 China Biomedical Engineering and Instrument Science Zhejiang University Hangzhou310027 China

ISBN: (纸本)9781510668546

A chronic neurological condition called epilepsy affects about 50 million people globally. Although there has been a lot of study on deep neural networks to identify seizures, it is still difficult to precisely define the structural relations between electrodes in EEG signals. The difficulty involved may lead to less accurate prediction. We provide a novel method that combines structured learning methods with graph neural networks and incorporates graph convolution to provide explanations for detected anomalies in EEG signals in order to overcome this constraint. Our investigations on the CHB-MIT dataset show that our approach is more effective and efficient than baseline methods and conventional neural network models at identifying the onset of seizures. © 2023 SPIE.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Unconditional Generation of Scalable Chinese Characters as Bézier Curve Sequences 3

Unconditional Generation of Scalable Chinese Characters as B...

引用

3rd International Conference on Artificial Intelligence and Signal Processing, AISP 2023

作者： Lasrado, Rohan Nolan Vijayasherly, V. VIT University School of Computer Science and Engineering Vellore India VIT University Department of Software Systems Vellore India

ISBN: (纸本)9798350320749

Neural generative modelling of sketches has been an active research direction. SketchRNN set a milestone with their sequence-to-sequence variational autoencoder architecture being able to generate hand drawn sketches in various classes by modelling them as sequences of displacements between consecutive stroke points. The diversity and variety in the set of handwritten Chinese characters makes them a good candidate for such generative modelling enabling their unconditional generation. However, modelling them as sequences of points causes coarse looking strokes and much longer sequences, consequently requiring use of polygonal approximation algorithms to cut down on points. Instead, we propose and investigate the modelling of Chinese characters as sequences of Bézier curves using the SketchRNN architecture with a few modifications, to allow the model to directly generate smooth curves. This way the encoded representation is smaller while more of the stroke's characteristics are retained and the generated characters are truly scalable. We also suggest the appropriate preprocessing strategy for the KanjiVG dataset to make it suitable for this purpose. Qualitative evaluation of the results suggests the model demonstrates generation of characters with mostly well-structured and ordered strokes. This was substantiated by quantitative evaluation based on the FrFréchetchet Inception Distance score. © 2023 IEEE.

关键词： Learning systems

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：