检索结果-内蒙古大学图书馆

Fuzzy control design for time-delay systems under adaptive event-triggered mechanism

Neural Computing and Applications 2024年第9期36卷 4727-4739页

作者： Du, Zhenbin Qu, Zifang Kao, Yonggui Wu, Zhaojing School of Computer and Control Engineering Yantai University Shandong Yantai264005 China School of Mathematics and Information Science Shandong Technology and Business University Shandong Yantai264005 China Department of Mathematics Harbin Institute of Technology Weihai264209 China School of Mathematics and Information Sciences Yantai University Shandong Yantai264005 China

This manuscript studies the fuzzy H∞ control design problem for nonlinear time-varying delay systems in fuzzy form via adaptive event-triggered mechanism. The fuzzy model and an adaptive event-triggered controller are connected in closed-loop form. A looped-functional is established to conduct stability analysis, and the main feature of this functional can fully reflect the sampling feature of control systems. Thus, the achieved results are less conservative. The Wringter inequality is also used to further relax stability analysis. Finally, sufficient conditions are achieved for the existence of event-triggered fuzzy controller, and the resulting closed-loop system reaches an H∞ control performance. Two examples verify the efficiency of the presented control strategy. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2023.

关键词： Time delay

来源：评论

学校读者我要写书评

暂无评论

Enhancing Healthcare Security Using IoT-Enabled with Continuous Authentication Using Deep Learning

Enhancing Healthcare Security Using IoT-Enabled with Continu...

引用

International Conference on Electrical and Electronics engineering, ICEEE 2023

作者： Singh, Navneet Pratap Ravichandran, R. Ghosh, Soumi Rana, Priya Chaku, Shweta Singh, Jagendra School of Computer Science Engineering and Technology Bennett University Greater Noida India Electronics and Communication Engineering K S R Institute for Engineering and Technology Tiruchengode India Department of Information Technology Maharaja Agrasen Institute of Technology Delhi India Department of Information Technology Raj Kumar Goel Institute of Technology AKTU Lucknow Lucknow India Department of Information Technology Inderprastha Engineering College Ghaziabad AKTU Lucknow Lucknow India

ISBN: (纸本)9789819986606

The Internet of Things (IoT) has transformed healthcare by providing continuous remote patient health monitoring. Ensuring the security and privacy of patient health data in such IoT-enabled contexts, on the other hand, is a critical concern. This study proposes a unique method for improving IoT-based healthcare security via continuous authentication, utilizing deep learning, especially the Long Short-Term Memory (LSTM) model. The suggested system continually analyzes user behavior and health state, using biometric data to provide seamless and secure authentication. Multiple security credentials, including Personal Identity Number (PIN), password, and biometric identity, are used in the architecture to provide effective protection against unauthorized access attempts. Using Arduino Uno and smart devices, data from a broad array of sensors connected to patients are gathered, and a complete dataset is created for training the LSTM model. The performance of the suggested system is assessed using multiple performance measures such as accuracy, precision, recall, specificity, and the F1-score. The findings show that the model is very accurate and efficient at discriminating between legitimate and unauthorized users. The system consistently outperforms previous research efforts, demonstrating its superiority in predicting authentication answers. Furthermore, continuous authentication enables real-time monitoring and proactive identification of suspicious actions. The scalability, versatility, and open-source characteristics of the proposed technology ensure its use in a variety of healthcare contexts. This study helps improve IoT-enabled healthcare security by building confidence in users and stakeholders and increasing the state-of-the-art in safe and trustworthy healthcare data monitoring in the IoT ecosystem. The suggested paradigm sets the groundwork for future improvements in continuous authentication and healthcare security as the IoT ecosystem grows. © The Author(s

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Generating A New Shilling Attack for Recommendation Systems

引用

computers, Materials & Continua 2022年第5期71卷 2827-2846页

作者： Pradeep Kumar Singh Pijush Kanti Dutta Pramanik Madhumita Sardar Anand Nayyar Mehedi Masud Prasenjit Choudhury Department of Computer Science&Engineering National Institute of TechnologyDurgapurIndia Graduate School Duy Tan UniversityDa NangVietnam Faculty of Information Technology Duy Tan UniversityDa NangVietnam Department of Computer Science College of Computers and Information TechnologyTaif UniversityTaif21944Saudi Arabia

A collaborative filtering-based recommendation system has been an integral part of e-commerce and *** keep the recommendation systems reliable,authentic,and superior,the security of these systems is very *** the existing shilling attack detection methods in collaborative filtering are able to detect the standard attacks,in this paper,we prove that they fail to detect a new or unknown *** develop a new attack model,named Obscure attack,with unknown features and observed that it has been successful in biasing the overall top-N list of the target users as *** Obscure attack is able to push target items to the top-N list as well as remove the actual rated items from the *** proposed attack is more effective at a smaller number of k in top-k similar user as compared to other existing *** effectivity of the proposed attack model is tested on the MovieLens dataset,where various classifiers like SVM,J48,random forest,and naïve Bayes are utilized.

关键词： Shilling attack recommendation system collaborative filtering top-N recommendation biasing shuffling hit ratio

来源：评论

学校读者我要写书评

暂无评论

Examining learners’ cognitive processes and learning emotions in digital game-based vocabulary learning: evidence from eye-tracking technology and facial emotion recognition

引用

Interactive technology and Smart Education 2024年第2期22卷 304-331页

作者： Wang, Chun-Chia Chen, Hsuan-Chu Hung, Jason C. School of Information and Design Chang Jung Christian University Tainan Taiwan Department of Digital Media Design Chang Jung Christian University Tainan Taiwan Department of Computer Science and Information Engineering National Taichung University of Science and Technology Taichung Taiwan

Purpose: This research explored the intersection of cognitive processes, emotions and their impacts on digital game-based vocabulary learning (DGVL) among university students. Recognizing the scant research in this area, especially with integrating innovative technologies, this study aims to understand the influence of these elements using advanced monitoring tools. Design/methodology/approach: This inquiry was carried out as an observational study involving 44 university students segmented into three English language proficiency levels: high, intermediate and low based on their English course scores. The methodological tools included a portable eye tracker to observe visual behaviors and deep learning technology to identify and analyze the participants’ emotional responses and engagement with the DGVL during the learning process. Findings: The results showed that distinct fixation sequences and variations in visual attention during DGVL were correlated with different levels of competency, suggesting a direct correlation between visual engagement and language competence. In addition, emotional transitions, predominantly from engagement (“flow”) to challenge (“frustration”), were common among participants, reflecting the emotional dynamics of learning. Furthermore, all participants consistently focused on the English vocabulary definitions, indicative of their targeted approach to understanding and test preparation. These findings highlighted the intricate dynamics between emotions and cognitive processes in learning environments. Originality/value: Contribution of this study shows the interplay of cognitive engagement and emotional experiences in the context of DGVL. It underscored the complex nature of these factors and their collective influence on learners’ visual and emotional engagement, offering valuable implications for educational strategies and technological applications in language learning. © 2024, Emerald Publishing Limited.

关键词： Affective computing Convolutional neural networks Digital game-based learning Eye-tracking technology Transfer learning

来源：评论

学校读者我要写书评

暂无评论

Design a multi-objective optimization with dynamic and global filter pruning strategy for convolutional neural network

引用

Multimedia Tools and Applications 2025年第3期84卷 1345-1358页

作者： Singh, Divya Rao, T. Prabhakara Veeranjaneyulu, N. Reddy, T Sunil Kumar Electronics and Communication Engineering GLA University Mathura India Andhra Pradesh Surampalem53343 India Department of Information Technology VFSTR Deemed to Be University Guntur Dist. Andhra Pradesh Vadlamudi India Department of Computer Science and Engineering Sri Venkatasa Perumal College of Engineering and Technology K.N Road Andhra Pradesh Cherlopalle517583 India

In recent years, the Deep Neural Networks (DNN) have managed tremendous growth and widespread applications. However, their applicability in embedded and mobile devices has been constrained by its complex arrangement, maximal computation, and the storage requirements. This paper designed an Evolutionary Multi-Objective Optimization (EMO) through a Dynamic and Global Filter Pruning (DG-FP) approach (EMO-DGFP) for an effective Convolutional Neural Network (CNN). Initially, Train the CNN in the Python system, then use the DG-FP approach to remove unnecessary filters. Furthermore, the CNN filters were adjusted using an EMO technique. The filter pruning issue has been resolved using an EMO based on non-dominated sorting. Then fine-tuning process was performed to regain its accuracy. The developed model efficiency has been tested against other widely used models, and the results showed 99.96% accuracy, 2% mistake rate, 2.6% compression ratio, and 80.67% pruning rate. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Smartphone-based Road Condition Sensing using Machine Learning techniques 21

Smartphone-based Road Condition Sensing using Machine Learni...

引用

21st International System-on-Chip Design Conference, ISOCC 2024

作者： Pipanmekaporn, Luepol Kamonsantiroj, Suwatchai Sutthaweekul, Ruslee Lee, Wilaiporn Srisomboon, Kanabadee King Mongkut University of Technology North Bangkok Department of Computer and Information Science Bangkok10800 Thailand King Mongkut University of Technology North Bangkok Department of Electrical and Computer Engineering Bangkok10800 Thailand

ISBN: (纸本)9798350377088

To ensure the safety and facilitation of transportation, the road condition should be evaluated continually for determining the maintenance plan and reducing the risk of accidents. In this paper, we propose a low-cost and automated road condition sensing method that uses smart phone as the sensing device and exploits machine learning as the evaluator. To evaluate the road quality, the vibration, vehicle location and vehicle speed are gathered via an accelerometer of the smartphone. Then, this data is preprocessed and fed to the machine learning model for prediction the road condition. Moreover, we compare the road condition prediction performance of three machine learning models including MaxEnt, XGBoost and Support Vector machine (SVM) where the XGBoost shows the best prediction performance among others. Therefore, we implement the XGBoost for our automated road condition sensing system. Then, our proposed device can be used to evaluate the road condition with short evaluation time, high accuracy and low-cost. © 2024 IEEE.

关键词： Smartphones

来源：评论

学校读者我要写书评

暂无评论

Progressive edge-sensing dynamic scene deblurring

引用

Computational Visual Media 2022年第3期8卷 495-508页

作者： Tianlin Zhang Jinjiang Li Hui Fan School of Information and Electronic Engineering Shandong Technology and Business UniversityYantai 264005China School of Computer Science and Technology Shandong Technology and Business UniversityYantai 264005China Institute of ZhongKe Network Technology Yantai 264005China

Deblurring images of dynamic scenes is a challenging task because blurring occurs due to a combination of many *** recent years,the use of multi-scale pyramid methods to recover high-resolution sharp images has been extensively *** have made improvements to the lack of detail recovery in the cascade structure through a network using progressive integration of data *** new multi-scale structure and edge feature perception design deals with changes in blurring at different spatial scales and enhances the sensitivity of the network to blurred *** coarse-to-fine architecture restores the image structure,first performing global adjustments,and then performing local *** this way,not only is global correlation considered,but also residual information is used to significantly improve image restoration and enhance texture *** results show quantitative and qualitative improvements over existing methods.

关键词： image deblurring dynamic scenes multiscale edge features

来源：评论

学校读者我要写书评

暂无评论

Real Rainy Scene Analysis: A Dual-Module Benchmark for Image Deraining and Segmentation

Real Rainy Scene Analysis: A Dual-Module Benchmark for Image...

引用

2023 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2023

作者： Zhao, Shilei Huang, Wenxin Yang, Mingxuan Liu, Wenxuan Wuhan Dashuiyun Technology Co. Ltd China School of Computer Science and Information Engineering Hubei University China School of Computer Science and Artificial Intelligence Wuhan University of Technology China

ISBN: (纸本)9798350313154

Scene understanding in adverse weather conditions (e.g., rainy and foggy days) has drawn increasing attention, raising some specific benchmarks and algorithms. However, rain streaks in images and videos can significantly degrade visual quality and reduce the effectiveness of computer vision algorithms. Concerning on lack of rainy-clean pairs training samples in real rainy scenes, we propose an unsupervised deraining method that does not require any explicit rain-clean image pairs for training. Instead, our approach leverages the statistical properties of rain streaks and clean regions to learn a rain removal model. Specifically, we choose contrastive learning that encourages the generator to produce derained images that are indistinguishable from clean images while the discriminator distinguishes between real clean images and rain streak patterns. Furthermore, we incorporate a semi-supervised mechanism during segmentation module that exploits low-confidence Pseudo-label to be treated as negative samples for certain classes to facilitate contrastive learning. Our experiments demonstrate that our integrated framework achieve better performance on the given challenging scenarios such as heavy rain and dynamic scenes. © 2023 IEEE.

关键词： Rain

来源：评论

学校读者我要写书评

暂无评论

PepTracR: a Centralized Database for Pathogen Peptides and Neoepitopes based on 3D Structures information and Similarity-search in T-cell Immunotherapy Research 12

PepTracR: a Centralized Database for Pathogen Peptides and N...

引用

12th International Conference on Bioinformatics and Biomedical science, ICBBS 2023

作者： Shih, Tao-Chuan Yang, Cing-Han Chen, Ying-Ja Yeh, Li-Tzu Lu, Chi-Wei Pai, Tun-Wen Department of Computer Science and Information Engineering National Taipei University of Technology Taipei Taiwan Department of Computer Science and Engineering National Taiwan Ocean University Keelung Taiwan ACER Taipei Taiwan

ISBN: (纸本)9798400716140

T-cell receptors (TCRs) are essential proteins on T cells recognizing antigens presented by MHC molecules. They're pivotal in immune responses to infections (pathogens) and cancers (neoepitopes). T-cell assays like ELISpot and cytokine production gauge T-cell recognition and responses to these antigens. However, gathering and representing data from IEDB and others are complex due to naming conventions and data issues. To overcome this, a centralized database is crucial, uniting pathogen peptide and neoepitope data with T-cell assay info. PepTracR is our solution - a comprehensive resource for neoepitope data and corresponding T-cell assays. It aids pathogen studies with functions to search against human genome or pathogen protein sequences, supported by sequence alignment. Our script updates old naming conventions. StcrDab and TCR3D integration provides structural data through alignment, displaying interactions with JSmol or graphical diagrams. PepTracR applies sequence motifs, peptide-MHC prediction tools for CDR-pathogen peptide diversity analysis, and peptide-MHC binding affinity evaluation. Regular updates ensure current info. Our aim is to serve the neoepitope research community, organizing curated data and granting T-cell assay access. Utilizing self-similarity and pathogen-similarity tools, PepTracR contributes effectively to pathogen-peptide and neoepitope research. © 2023 ACM.

关键词： T-cells

来源：评论

学校读者我要写书评

暂无评论

An Effective Stroke Prediction based on Cat Boost with Few Short Compound Activity 2

An Effective Stroke Prediction based on Cat Boost with Few S...

引用

2nd IEEE International Conference on Integrated Intelligence and Communication Systems, ICIICS 2024

作者： Rupavath, Rana Veer Samara Sihman Brahmatej Hussein, Ramy R. Mohan, M. Vasanthakumar, G.U. Subburam, S. Indiana Wesleyan University Marion United States Department of Computers Techniques Engineering College of Technical Engineering The Islamic University Najaf Iraq Department of Computer Science and Engineering K P R Institute of Engineering and Technology Coimbatore India Department of Computer Science and Engineering Nitte Meenakshi Institute of Technology Bengaluru India Department of Information Technology New Prince Shri Bhavani College of Engineering and Technology Chennai India

ISBN: (纸本)9798331504960

In recent years, strokes are becoming a major global health concern that affecting the welfare of the population. Many researches have focused on developing predictive models using Machine Learning (ML) and Deep Learning (DL) for strokes. However, the existing method Support Vector Machine (SVM) used to predict the strokes but struggled with sensitivity issues. To overcome this issue, Cat Boost with Few-Shot Compound Activity Prediction (CB-FSCAP) is proposed for stroke prediction. The Few-Shot Compound Activity Prediction (FSCAP) effectively learns the representation from labeled data to reduce the sensitivity issues. Primarily, the input data is taken from healthcare-dataset-stroke-data dataset and the further processed into preprocessing. The stop words are removed and imputation, lemmatization are utilized to reduce dimensionality in preprocessing. Then, the preprocessed data is fed into Cat Boost (CB) for selecting the optimal features. Finally, prediction is done with the help of FSCAP to predict the strokes in various emergency conditions. From the results, the Proposed CB-FSCAP established better results when compared to existing Random Forest (RF) by providing results in terms of accuracy (98.4%), precision (95.1%), recall (96.5%) and F1-score (95.7%) respectively. © 2024 IEEE.

关键词： Prediction models

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：