检索结果-内蒙古大学图书馆

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Jie Xiang Chenyu Wu Shaochen Hao Ang Zhao Xubin Wu Xin Wen College of Computer Science and Technology (College of Data Science) Taiyuan University of Technology Taiyuan China School of Software Taiyuan University of Technology Taiyuan China

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

Integrating multicenter resting-state functional magnetic resonance imaging (fMRI) datasets is essential for computer-aided diagnosis of brain diseases. However, differences in scanners and acquisition protocols lead to heterogeneity of data from different centers. To address this problem, we introduce a novel Centralized Limited data Sharing (CLDS) framework for multicenter fMRI-based classification, which contains a centralized server and multiple local models, and propose three mechanisms to improve the classification performance. First, aiming at coordinating the global data without favoring any center, an adversarial network is introduced in the centralized server with limited noise-added data uploaded from each center. Second, a Gradient Adaptive Strategy based on the Tasks Association (GASTA) is proposed to restrict the gradient to a desirable direction. Third, a Correction Factor based on the Cosine Similarity (CFCS) is proposed to reduce the impact of non-independent and identically distributed (non-IID) of data on models. The experimental results show that CLDS exhibits superior classification performance to other related methods on the ADHD-200 dataset, with an accuracy of 70.4%. We also extend CLDS to the ABIDE-I dataset with an accuracy of 73.4%, demonstrating that CLDS has the potential for generalizability of other brain diseases and more centers.

关键词： Adaptation models Correlation Accuracy Protocols Functional magnetic resonance imaging Brain modeling data models Real-time systems Servers Diseases

来源：评论

学校读者我要写书评

暂无评论

Healthcare gamification: science mapping the body of literature 22

Healthcare gamification: Science mapping the body of literat...

引用

22nd International Conference on Electronic Business, ICEB 2022

作者： Machado, Franklin Jean Sanchez, Otávio Próspero Department of Technology and Data Science Fundação Getulio Vargas's Sao Paulo School of Business Administration Sao Paulo Brazil

Healthcare gamification is a research topic being investigated in numerous contexts. As it is an interdisciplinary subject, it is hard for researchers to keep up with the research published in these venues. This paper aims to unveil the intellectual structure of the healthcare gamification research field through a systematic literature review. We apply a science map strategy to a 520-document database. This database was analyzed to build an evolutionary map revealing the most co-cited authors, their publications, and the theories used. Results evidence that referenced research can be classified into six research traditions. Finally, research opportunities are presented. © 2022 International Consortium for Electronic Business. All rights reserved.

关键词： Health care

来源：评论

学校读者我要写书评

暂无评论

Adaptive Graph Attention Network with Temporal Fusion for Micro-Expressions Recognition

Adaptive Graph Attention Network with Temporal Fusion for Mi...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Yiming Zhang Hao Wang Yifan Xu Xinglong Mao Tong Xu Sirui Zhao Enhong Chen School of Data Science University of Science and Technology of China Hefei China School of Computer Science and Technology University of Science and Technology of China Hefei China

Automatic micro-expression recognition (MER) has essential applications in the psychological field. Graph-based models, due to their advantages in analyzing regionalized faces, have become a powerful method for MER. However, how to construct a graph from ME videos remains to be studied. To solve this problem, we design an adaptive graph attention network with temporal fusion to model the dynamic relationships between facial regions of interest (ROIs). Specifically, we first propose adaptive graph attention to establish learnable spatial graphs from ME videos. Then, we adopt an optical-flow-based feature as the suitable input for the graph network. In addition, an implicit semantic data augmentation algorithm is employed and improved as a data-driven weighted loss for better performance. Extensive experiments on SMIC-HS, CASME II and SAMM datasets have demonstrated the effectiveness of the proposed method, and it achieves to be the first graph-based model where UF1 and UAR both exceed 0.90 for 3-classes MER on CASME II. Code will be available at https://***/MEA-LAB-421/ICME2023-Recognition.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Efficient Feature Selection Techniques for Accurate Cancer Analysis Using Krill Heard Optimization 4

Efficient Feature Selection Techniques for Accurate Cancer A...

引用

4th International Conference on Emerging Systems and Intelligent Computing, ESIC 2024

作者： Singh, Shubham Narendra Mishra, Shruti Satapathy, Sandeep Kumar Cho, Sung-Bae Mallick, Pradeep Kumar Vellore Institute of Technology Computer Science and Engg Tamil Nadu Chennai India Vellore Institute of Technology Centre for Advanced Data Science Tamil Nadu Chennai India Yonsei University Department of Computer Science 50 Yonsei-ro Sudaemoon-gu Seoul03722 Korea Republic of Kiit University School of Computer Engineeing Odisha India

ISBN: (纸本)9798350349856

In this research, we introduce a novel biologically-inspired optimization algorithm known as Krill Herd (KH) to address feature selection challenges in cancer analysis. Inspired by the collective behaviour of krill individuals, the KH algorithm optimizes feature subsets by minimizing individual krill distances from food sources and herd density. We model the dynamic positions of krill individuals considering factors such as interactions with peers, foraging behaviour, and random diffusion. To enhance the algorithm's performance, we incorporate adaptive genetic operators. Our method's efficiency is evaluated across various benchmark optimization problems, demonstrating its capability to outperform eight established algorithms. In parallel, we delve into the critical domain of Cancer Feature Selection and classification in computational molecular biology. Identifying cancer-causing genes is pivotal for precise treatments and drug discovery. To address these challenges, we propose an enhanced Krill Herd Optimization (KHO) technique for gene selection, combined with Random Forest (RF) for classification. RF is chosen for its high classification accuracy. This research advances the field of cancer analysis by offering efficient and accurate feature selection techniques, providing insights into cancer-related genes, and facilitating more precise treatments and drug discoveries. © 2024 IEEE.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

A Four-Pronged Defense Against Byzantine Attacks in Federated Learning

arXiv

引用

arXiv 2023年

作者： Wan, Wei Hu, Shengshan Li, Minghui Lu, Jianrong Zhang, Longling Zhang, Leo Yu Jin, Hai School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Software Engineering Huazhong University of Science and Technology China School of Information and Communication Technology Griffith University Australia School of Computer Science and Technology Huazhong University of Science and Technology China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Key Laboratory of Distributed System Security China Hubei Engineering Research Center on Big Data Security China Cluster and Grid Computing Lab

Federated learning (FL) is a nascent distributed learning paradigm to train a shared global model without violating users' privacy. FL has been shown to be vulnerable to various Byzantine attacks, where malicious participants could independently or collusively upload well-crafted updates to deteriorate the performance of the global model. However, existing defenses could only mitigate part of Byzantine attacks, without providing an all-sided shield for FL. It is difficult to simply combine them as they rely on totally contradictory assumptions. In this paper, we propose FPD, a four-pronged defense against both non-colluding and colluding Byzantine attacks. Our main idea is to utilize absolute similarity to filter updates rather than relative similarity used in existingI works. To this end, we first propose a reliable client selection strategy to prevent the majority of threats in the bud. Then we design a simple but effective score-based detection method to mitigate colluding attacks. Third, we construct an enhanced spectral-based outlier detector to accurately discard abnormal updates when the training data is not independent and identically distributed (non-IID). Finally, we design update denoising to rectify the direction of the slightly noisy but harmful updates. The four sequentially combined modules can effectively reconcile the contradiction in addressing non-colluding and colluding Byzantine attacks. Extensive experiments over three benchmark image classification datasets against four state-of-the-art Byzantine attacks demonstrate that FPD drastically outperforms existing defenses in IID and non-IID scenarios (with 30% improvement on model accuracy). © 2023, CC BY.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

MEEL: Multi-Modal Event Evolution Learning

arXiv

引用

arXiv 2024年

作者： Tao, Zhengwei Jin, Zhi Huang, Junqiang Chen, Xiancai Bai, Xiaoying Zhao, Haiyan Zhang, Yifan Tao, Chongyang MOE China School of Computer Science Peking University China Peking University China Advanced Institute of Big Data China Beihang University China

Multi-modal Event Reasoning (MMER) endeavors to endow machines with the ability to comprehend intricate event relations across diverse data modalities. MMER is fundamental and underlies a wide broad of applications. Despite extensive instruction fine-tuning, current multi-modal large language models still fall short in such ability. The disparity stems from that existing models are insufficient to capture underlying principles governing event evolution in various scenarios. In this paper, we introduce Multi-Modal Event Evolution Learning (MEEL) to enable the model to grasp the event evolution mechanism yielding advanced MMER ability. Specifically, we commence with the design of event diversification to gather seed events from a rich spectrum of scenarios. Subsequently, we employ ChatGPT to generate evolving graphs for these seed events. We propose an instruction encapsulation process that formulates the evolving graphs into instruction-tuning data, aligning the comprehension of event reasoning to humans. Finally, we observe that models trained in this way are still struggling to fully comprehend event evolution. In such a case, we propose the guiding discrimination strategy, in which models are trained to discriminate the improper evolution direction. We collect and curate a benchmark M-EV2 for MMER. Extensive experiments on M-EV2 validate the effectiveness of our approach, showcasing competitive performance in open-source multi-modal LLMs. Code and dataset are available on https://***/TZWwww/MEEL. Copyright © 2024, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Sparse Large-Scale High-Order Fuzzy Cognitive Maps Guided by Spearman Correlation Coefficient

SSRN

引用

SSRN 2024年

作者： Li, Xuli Ma, Yingcang Zhou, Qimin Zhang, Xiaohong School of Science Xi’an Polytechnic University Xi’an710048 China School of Mathematics and Data Science Shaanxi University of Science and Technology Xi’an710021 China

Time series prediction is one of the most important applications of fuzzy cognitive maps. In general, the state of FCMs in forecasting depends only on the state of the previous moment, but in fact it is also affected by the past state. Hence higher-order fuzzy cognitive maps (HFCMs) are proposed based on FCMs considering historical information and have been widely used for time series forecasting. However, using HFCM to deal with sparse and large-scale multivariate time series are still a challenge, while large-scale data makes it difficult to determine the causal relationship between variables because of the increased number of nodes, so it is necessary to explore the relationship between conceptual nodes to guide large-scale HFCMs learning. Therefore, a sparse large-scale HFCMs learning algorithm guided by Spearman correlation coefficient, called SG-HFCM, is proposed in the paper. The SG-HFCM model is specified as follows: First, the solving of HFCMs model is transform into a regression model and an adaptive loss function is utilized to enhance the robustness of the model. Second, l1-norm is used to improve the sparsity of the weight matrix. Third, in order to more accurately characterize the correlation relationship between variables, the Spearman correlation coefficients is add as a regular term to guide the learning of weight matrices. When calculating the Spearman correlation coefficient, through splitting domain interval method, we can better understand the characteristics of the data, and get better correlation in different small intervals, and more accurately characterize the relationship between the variables in order to guide the weight matrix. In addition, in this paper, the ADMM method and quadratic programming method are used to solve the algorithms to get better solutions for the SG-HFCM, where the quadratic programming can well ensure that the range of the weights and obtaining the optimal solution. At last, we compare the proposed SG-HFCM method wit

关键词： Fuzzy Cognitive Maps

来源：评论

学校读者我要写书评

暂无评论

Texture, Shape and Order Matter: A New Transformer Design for Sequential DeepFake Detection

Texture, Shape and Order Matter: A New Transformer Design fo...

引用

IEEE Workshop on Applications of Computer Vision (WACV)

作者： Yunfei Li Yuezun Li Xin Wang Baoyuan Wu Jiaran Zhou Junyu Dong School of Computer Science and Technology Ocean University of China University at Albany SUNY School of Data Science The Chinese University of Hong Kong Shenzhen China

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

Sequential DeepFake detection is an emerging task that predicts the manipulation sequence in order. Existing methods typically formulate it as an image-to-sequence problem, employing conventional Transformer architectures. However, these methods lack dedicated design and consequently result in limited performance. As such, this paper describes a new Transformer design, called TSOM, by exploring three perspectives: Texture, Shape, and Order of Manipulations. Our method features four major improvements: we describe a new texture-aware branch that effectively captures subtle manipulation traces with a Diversiform Pixel Difference Attention module. Then we introduce a Multi-source Cross-attention module to seek deep correlations among spatial and sequential features, enabling effective modeling of complex manipulation traces. To further enhance the cross-attention, we describe a Shape-guided Gaussian mapping strategy, providing initial priors of the manipulation shape. Finally, observing that the subsequent manipulation in a sequence may influence traces left in the preceding one, we intriguingly invert the prediction order from forward to backward, leading to notable gains as expected. Extensive experimental results demonstrate that our method outperforms others by a large margin, highlighting the superiority of our method.

关键词： Deepfakes Computer vision Correlation Shape Annotations Design methodology Transformers

来源：评论

学校读者我要写书评

暂无评论

Demystifying Cyber terrorism: Causes, Costs & its impact on individuals' psyche and public confidence

Demystifying Cyber terrorism: Causes, Costs & its impact on ...

引用

2023 International Conference on Recent Advances in Electrical, Electronics and Digital Healthcare Technologies, REEDCON 2023

作者： Zahra, Syed Rameem Saleem, Tausifa Jan Sonia Netaji Subhas University of Technology Department of Computer Science and Engineering Delhi India Indian Institute of Technology Delhi Department of Electrical Engineering Delhi India Shoolini University Yogananda School of Ai Computer and Data Science H.P Solan India

ISBN: (纸本)9781665493826

Just like the game for Information technology (IT) security was turned topsy-turvy by the arrival of mobile devices a few decades ago, the Internet of Things (IoT) today is changing it again a big time. data breaches, loss of productivity and profitability were quite a commonplace when mobile security became an issue. Today as IoT tries to connect everything to the internet, it intensifies the problem (more privacy violations, phishing/skimming attacks, security incidents) by creating a vast attack surface for the rogue players implying that important national (ports, airports, bridges, power-pants etc.) and cyber infrastructure could now be attacked. Moreover, if the network of your company has a weak point, it can easily be compromised to set off an attack. These Cyber terrorism attacks instigate identical responses from individuals as those for conventional terrorism attacks e.g. they heighten anxiety and stress, worsen feelings of vulnerability and harden the political attitudes of people. But this dimension is often overlooked by the policy makers. However, the increase in cyber terrorism cases has increased the research interest in the domain. Researchers are focusing on improving the security of internet and IoT devices. The field is still in its infancy. A lot needs to be done to mitigate these attacks. Motivated to demystify the repercussions of the cyber terrorism, this paper analyzes the distinctive characteristics of the most significant cyberattacks, investigates the expenditures incurred by the industries as a result of these cyber events, and then examines the impact of these attacks on the psychological health of the populace and the trust in public institutions. © 2023 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

An application of the A-4DEnVar to coupled parameter optimization

引用

Acta Oceanologica Sinica 2022年第9期41卷 60-70页

作者： Yantian Gong Kangzhuang Liang Xinrong Wu Qi Shao Wei Li Siyuan Liu Guijun Han Hanyu Liu School of Marine Science and Technology Tianjin UniversityTianjin300072China Key Laboratory of Marine Environmental Information Technology National Marine Data and Information ServiceMinistry of Natural ResourcesTianjin300171China Tianjin Key Laboratory for Oceanic Meteorology Tianjin300074China

In variational methods,coupled parameter optimization(CPO) often needs a long minimization time window(MTW) to fully incorporate observational information,but the optimal MTW somehow depends on the model *** analytical four-dimensional ensemble-variational(A-4DEnVar) considers model nonlinearity well and avoids adjoint *** can theoretically be applied to *** verify the feasibility and the ability of the A-4DEnVar in CPO,“twin” experiments based on A-4DEnVar CPO are conducted for the first time with the comparison of four-dimensional variational(4D-Var).Two algorithms use the same background error covariance matrix and optimization algorithm to control *** experiments are based on a simple coupled oceanatmosphere model,in which the atmospheric part is the highly nonlinear Lorenz-63 model,and the oceanic part is a slab ocean *** results show that both A-4DEnVar and 4D-Var can effectively reduce the error of state variables through ***,two methods produce almost the same results in most cases when the MTW is less than 560 time *** results are similar when the MTW is larger than 560 time steps and less than 880 time *** largest MTW of 4 D-Var and A-4DEnVar are 1 200 time ***,A-4DEnVar is not sensitive to ensemble size when the MTW is less than 720 time steps.A-4DEnVar obtains satisfactory results in the case of highly nonlinear model and long MTW,suggesting that it has the potential to be widely applied to realistic CPO.

关键词： 4D-Var A-4DEnVar coupled parameter optimization “twin”experiments

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：