检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Xie, Wenwen Sun, Geng Li, Jiahui Wang, Jiacheng Du, Hongyang Niyato, Dusit Dobre, Octavia A. The College of Computer Science and Technology Jilin University Changchun130012 China The College of Computing and Data Science Nanyang Technological University Singapore639798 Singapore The Faculty of Engineering and Applied Science Memorial University Canada

Internet of Things (IoT) devices are typically powered by small-sized batteries with limited energy storage capacity, requiring regular replacement or recharging. To reduce costs and maintain connectivity in IoT networks, energy harvesting technologies are regarded as a promising solution. Notably, due to its robust analytical and generative capabilities, generative artificial intelligence (GenAI) has demonstrated significant potential in optimizing energy harvesting networks. Therefore, we discuss key applications of GenAI in improving energy harvesting wireless networks for IoT in this article. Specifically, we first review the key technologies of GenAI and the architecture of energy harvesting wireless networks. Then, we show how GenAI can address different problems to improve the performance of the energy harvesting wireless networks. Subsequently, we present a case study of unmanned aerial vehicle (UAV)-enabled data collection and energy transfer. The case study shows distinctively the necessity of energy harvesting technology and verify the effectiveness of GenAI-based methods. Finally, we discuss some important open directions. Copyright © 2024, The Authors. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

The Evolution of Zero Trust Architecture (ZTA) from Concept to Implementation

The Evolution of Zero Trust Architecture (ZTA) from Concept ...

引用

International Scientific-Professional Conference on Information Technology (IT)

作者： Md Nasiruzzaman Maaruf Ali Iftekhar Salam Mahdi H. Miraz School of Computing and Data Science Xiamen University Malaysia Malaysia Faculty of Computer Science and IT Universiteti Metropolitan Tirana Albania The Doctoral College University of Wales Trinity Saint David (UWTSD) Wales UK Mahdi H. Miraz is with the School of Computing and Data Science Xiamen University Malaysia Malaysia School of Computing Faculty of Arts Science and Technology Wrexham University UK Faculty of Computing Engineering and Science University of South Wales UK

ISBN: (数字)9798331517649

ISBN: (纸本)9798331517656

Zero Trust Architecture (ZTA) is one of the paradigm changes in cybersecurity, from the traditional perimeter-based model to perimeterless. This article studies the core concepts of ZTA, its beginning, a few use cases and future trends. Emphasising the always-verify and least privilege access, some key tenets of ZTA have grown to be integration technologies like Identity Management, Multi-Factor Authentication (MFA) and real-time analytics. ZTA is expected to strengthen cloud environments, education, work environments (including from home) while controlling other risks like lateral movement and insider threats. Despite ZTA’s benefits, it comes with challenges in the form of complexity, performance overhead and vulnerabilities in the control plane. These require phased implementation and continuous refinement to keep up with evolving organisational needs and threat landscapes. Emerging technologies, such as Artificial Intelligence (AI) and Machine Learning (ML) will further automate policy enforcement and threat detection in keeping up with dynamic cyber threats.

关键词： Multi-factor authentication Education Machine learning Market research Threat assessment Real-time systems Zero Trust Complexity theory Information technology Identity management systems

来源：评论

学校读者我要写书评

暂无评论

Resisting Noise in Pseudo Labels: Audible Video Event Parsing With Evidential Learning

引用

IEEE Transactions on Neural Networks and Learning Systems 2024年第6期36卷 10874-10888页

作者： Xun Jiang Xing Xu Liqing Zhu Zhe Sun Andrzej Cichocki Heng Tao Shen Center for Future Media School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China School of Computer Science and Technology Tongji University Shanghai China Graduate School of Medicine Faculty of Health Data Science Juntendo University Tokyo Japan Systems Research Institute Polish Academy of Sciences Warsaw Poland Nicolaus Copernicus University (UMK) Toruń Poland

Perceiving temporal events and discriminating their modality types in audible videos, which is also called audio-visual video parsing (AVVP), is becoming a research hotspot in multimodal video understanding. The AVVP task generally follows weakly supervised learning settings, since only video-level labels are provided. Most existing works usually generate modalitywise pseudo labels (PLs) first and then learn to parse audio or visual events from the audible videos. However, this paradigm inevitably results in two defects: 1) the generated PLs for each modality are not fully reliable, which may confuse models if they are adopted as supervision signals for discriminating modalities; and 2) the absence of temporal annotations increases the ambiguities in localizing foregrounds in videos, furtherly causing models prone to being disturbed by noisy labels. To tackle these problems, we propose a novel AVVP framework termed noise-resistant event parsing (NREP), which introduces evidential deep learning (EDL) to overcome the limitations of noisy pseudo supervision. Specifically, our NREP framework consists of three key components: 1) modalitywise evidential learning (MEL) that discriminates the modality-class dependency; 2) temporalwise evidential learning (TEL) that explores meaningful foregrounds; and 3) foreground-background consistency learning (FBCL) for collaborating two evidential learning branches above. Through perceiving meaningful video content and learning evidence for modality dependencies, our method suppresses the disturbance of noise in generated PLs thus achieving remarkable performance with different PL generation strategies. We evaluate our NREP method on two AVVP benchmark datasets and demonstrate it consistently to establish new state-of-the-art. Our implementation codes are available at https://***/CFM-MSG/NREP .

关键词： Noise Visualization Noise measurement Annotations Location awareness Sun Logic Deep learning Semantics computer science

来源：评论

学校读者我要写书评

暂无评论

Multi Label Classification Algorithm Based on Conditional Local Correlations among Labels and Ensemble Learning

Multi Label Classification Algorithm Based on Conditional Lo...

引用

Information Technology (ACIT)

作者： Raed Alazaidah Ola Nasir Wael Hadi Ghassan Samara Essam Al Daoud Mohammad Aljaidi Mohammed Talat Khouj Esraa Abu Elsoud Haneen Alzoubi Department of Data Science and AI Faculty of Information Technology Zarqa University Zarqa Jordan Department of Computer Science Faculty of Information Technology Zarqa University Zarqa Jordan Department of Cyber Security Faculty of Information Technology Petra University Amman Jordan Department of Electrical Engineering University of Business and Technology Jeddah Saudi Arabia Department of Computer Science Faculty of IT Zarqa University Zarqa Jordan Department of Computer Science Faculty of Information Technology Applied Science Private University Amman Jordan

ISBN: (数字)9798331540012

ISBN: (纸本)9798331540029

Multi-Label Classification (MLC) is an advanced form of traditional classification, where each data instance is simultaneously associated with multiple labels. The importance of MLC has increased significantly in recent years, due to its wide range of application areas. Modern algorithms, when faced with the challenge of multiple labels, continue to show suboptimal performance, conversely, they show significantly superior performance when processing single-label datasets. This paper proposes a new algorithm to deal with the problem of transforming datasets from multiple labels to single labels by exploiting conditional and local correlations between labels after applying the Apriori predictive algorithm to extract relationships. Six ensemble learning models: Voting Hard, Voting Soft, Voting Weighted, Stacking LR, Stacking RF, and Stacking SVM, along with four classification models: SMO, DecisionStump, Random Forest, and Random Committee, were applied to three datasets. The algorithm showed effective and good performance by comparing the results of the proposed Multi Label Classification algorithm based on Conditional Local Correlations among Labels (MLC-CLCL) with several popular algorithms for dealing with multiple labels.

关键词： Support vector machines Radio frequency Correlation Stacking Multi label classification Prediction algorithms Ensemble learning Information technology Random forests

来源：评论

学校读者我要写书评

暂无评论

A Graph-Transformer for Whole Slide Image Classification

引用

IEEE Transactions on Medical Imaging 2022年第11期41卷 3003-3015页

作者： Zheng, Yi Gindra, Rushin H. Green, Emily J. Burks, Eric J. Betke, Margrit Beane, Jennifer E. Kolachalama, Vijaya B. Boston University Department of Computer Science BostonMA02215 United States Boston University School of Medicine Department of Medicine BostonMA02218 United States Boston University School of Medicine Department of Pathology and Laboratory Medicine BostonMA02218 United States Boston University Faculty of Computing and Data Sciences Department of Computer Science BostonMA02215 United States

Deep learning is a powerful tool for whole slide image (WSI) analysis. Typically, when performing supervised deep learning, a WSI is divided into small patches, trained and the outcomes are aggregated to estimate disease grade. However, patch-based methods introduce label noise during training by assuming that each patch is independent with the same label as the WSI and neglect overall WSI-level information that is significant in disease grading. Here we present a Graph-Transformer (GT) that fuses a graph-based representation of an WSI and a vision transformer for processing pathology images, called GTP, to predict disease grade. We selected 4,818 WSIs from the Clinical Proteomic Tumor Analysis Consortium (CPTAC), the National Lung Screening Trial (NLST), and The Cancer Genome Atlas (TCGA), and used GTP to distinguish adenocarcinoma (LUAD) and squamous cell carcinoma (LSCC) from adjacent non-cancerous tissue (normal). First, using NLST data, we developed a contrastive learning framework to generate a feature extractor. This allowed us to compute feature vectors of individual WSI patches, which were used to represent the nodes of the graph followed by construction of the GTP framework. Our model trained on the CPTAC data achieved consistently high performance on three-label classification (normal versus LUAD versus LSCC: mean accuracy = 91.2 ± 2.5%) based on five-fold cross-validation, and mean accuracy = 82.3 ± 1.0% on external test data (TCGA). We also introduced a graph-based saliency mapping technique, called GraphCAM, that can identify regions that are highly associated with the class label. Our findings demonstrate GTP as an interpretable and effective deep learning framework for WSI-level classification. © 1982-2012 IEEE.

关键词： Tumors

来源：评论

学校读者我要写书评

暂无评论

Predicting Hand Injury Severity Using Bayesian Networks in Cloud-Based Emergency Medicine 10

Predicting Hand Injury Severity Using Bayesian Networks in C...

引用

10th International Conference on Communication and Signal Processing, ICCSP 2024

作者： Yuvaraj, S. Thinakaran, K. Srinivas, S. Porandla Sivakumar, S. Ishwarya, M.V. Thirumaraiselvan, P. Srm Institute of Science and Technology Faculty of Engineering and Technology Department of Electronics and Communication Engineering Chennai Tamil Nadu Kattankulathur India Saveetha Institute of Medical and Technical Sciences Saveetha School of Engineering Department of Computer Science and Engineering Tamil Nadu Chennai India Malla Reddy Institute of Engineering and Technology Department of Information Technology Telangana Hyderabad India Department of Computer Science Tamil Nadu Perambalur India Agni College of Technology Artificial Intelligence and Data Science Department Tamil Nadu Thazhambur India Adhiparasakthi Engineering College Department of Electronics and Communication Engineering Tamil Nadu Melmaruvathur India

ISBN: (纸本)9798350353068

Predicting the severity of hand injuries in emergency care is the focus of this study, which suggests using cloud-based Bayesian networks. It is crucial to have accurate severity prediction in order to treat emergency hand injuries promptly since they are prevalent. By using the scalability and flexibility of cloud computing, this method constructs a Bayesian severity assessment network with patient data, injury characteristics, and historical medical records. The model's training data comes from a massive database of hand injury cases with different results. Emergency medical professionals may use real-time parameter modifications to strengthen and adapt the Bayesian network. Through the use of the cloud, healthcare providers may simply exchange data and reach consensus. It demonstrates that, compared to other well-established methods of evaluating hand injury severity, the model performs better in making predictions. The suggested method improves severity forecasts and advances cloud-based emergency care. The method for emergency hand injury care uses Bayesian networks in the cloud to improve scalability and accessibility. The findings show that the data-driven and efficient hand injury severity prediction method might transform emergency care by improving patient outcomes. © 2024 IEEE.

关键词： Bayesian networks

来源：评论

学校读者我要写书评

暂无评论

Determining Variables Associated with Annual Oil Palm Yield: An Explainable Gradient Boosting Approach

引用

Procedia computer science 2023年 227卷 262-271页

作者： Gregorius Natanael Elwirehardja Teddy Suparyanto Miftakhurrokhmat Bens Pardamean Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta Indonesia 11480 Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia 11480 Faculty of Agricultural Technology Institute of Agriculture STIPER Yogyakarta Indonesia 55282 Faculty of Industrial Technology Universitas Islam Indonesia Yogyakarta Indonesia 55584 Computer Science Department BINUS Graduate Program – Master of Computer Science Program Bina Nusantara University Jakarta Indonesia 11480

With the growing demands for Precision Agriculture (PA) in Indonesia, researchers have evaluated the utilization of Machine Learning for predicting oil palm yields and determining variables affecting them. Previous studies showed that meteorological variables, including rainfalls and wind speed, are associated with oil palm yields. In this research, the Extreme Gradient Boosting (XGBoost) model and the Shapley Additive exPlanations (SHAP) were deployed for analyzing the importance of 15 agrometeorological variables in predicting oil palm yield. The best model attained 1.911 RMSE and 0.855 R2. By analyzing the weights and gains of the XGBoost model along with the SHAP values, it was found that the yield in the previous year, the age and number of plants, the area of peat lands, and meteorological parameters such as rainfall rates and the number of rainy days in the previous three years were considered important. The previous year's yield in particular possesses the greatest weight and gain values according to the model, and the highest SHAP value among all input variables. However, the meteorological data used in this research are only limited to rainfall rates and the number of rainy days. In the future, more diverse variables can be analyzed.

关键词： Oil Palm Yield Machine Learning XGBoost XAI SHAP

来源：评论

学校读者我要写书评

暂无评论

An Early Detection Model of Prostate Cancer Based on MRI 9

An Early Detection Model of Prostate Cancer Based on MRI

引用

9th IEEE International Conference on data science in Cyberspace, DSC 2024

作者： Liu, Yuankun Xing, Lumin Wang, Di Nie, Xin Zhang, Xueyan Wu, Di Liu, Wenjian The First Affiliated Hospital of Shandong First Medical University Shandong Provincial Qianfoshan Hospital Jinan China City University of Macau Faculty of Data Science China Qilu University of Technology Shandong Academy of Sciences Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Jinan China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computer Networks Jinan China Chongqing Jianzhu College Chongqing China Shandong Youth University of Political Science School of Information Work Office Jinan China University of Southern Queensland School of Mathematics Physics and Computing QLD Australia

ISBN: (纸本)9798350391367

Prostate cancer is a prevalent form of cancer among men, with a high rate of occurrence but relatively lower mortality compared to other types of cancer. Early detection is crucial because it allows for earlier intervention, potentially preventing progression to more severe stages, and improving patient outcomes. However, human diagnosis is time-consuming and inefficient, an autonomous early detection system is essential for saving lives. To address this challenge, we propose a novel MoE-MRIViT framework that uses advanced machine learning and computer vision techniques to analyze MRI images and identify features indicative of prostate cancer. The system processes the data using a vision transformer to extract precise prostate cancer features from MRI scans, and uses attention mechanisms to focus on significant areas. Through the MoE-MRIViT intervention in two stages, we have achieved superior results compared to the state-of-the-art (SOTA) methods. Experimental results demonstrate that our model achieves an impressive accuracy of 94.84%, outperforming the ResNet-101 and the basic ViT models, which achieve accuracies of 89.4% and 92.31%, respectively. © 2024 IEEE.

关键词： Urology

来源：评论

学校读者我要写书评

暂无评论

Factor Analysis: Uncovering Factor Structure in the Indonesian Teacher Engagement Index (ITEI) Survey Results data

Factor Analysis: Uncovering Factor Structure in the Indonesi...

引用

International Conference on computer, Control, Informatics and Its Applications (IC3INA)

作者： Grace Shirley Cam Sasmoko Yasinta Indrianti Sonya Rapinta Manalu Jurike V Moniaga Data Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia Primary Teacher Education Department Faculty Humanities Bina Nusantara University Jakarta Indonesia Entrepreneurship Department Podomoro University Jakarta Indonesia Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9798331542313

ISBN: (纸本)9798331542320

This study aims to explore the latent structure of the Indonesian Teacher Engagement Index (ITEI) based on the ITEI survey results of primary school teachers in various regions of Indonesia. Exploration of the ITEI structure is obtained by identifying the main factors hidden in the ITEI survey data with machine learning. The machine learning method used is Exploratory factor analysis (EFA) with Principal Component Analysis (PCA). The ITEI dataset consists of 10,365 records, covering 44 items from 6 ITEI dimensions. The machine learning analysis yielded 4 main factors that became new dimensions, explaining the variation of 29 items. The four new factors found are summarized into the dimensions of Values and Ethics in Education, Personal and Social Development in Education, Character and Leadership in Education, and Social Competence and Justice in Education. This exploration was conducted to show the latent structure of the ITEI that matches the real situation and provide a deeper understanding of the main components that make up the teacher engagement index in Indonesia, so that conclusions can be drawn accurately from the survey results. The implications of these findings can be used to improve understanding and development of more effective education policies in the future.

关键词： Surveys Digital control Ethics Leadership Correlation Education Machine learning Indexes Informatics Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Analysis of Device-To-Device Communication in Iot System 1st

Analysis of Device-To-Device Communication in Iot System

引用

1st International Conference on Computing and Emerging Technologies, ICCET 2023

作者： Nawaz, Usman Rehman, Faisal Ullah, Kainat Azmat Raza, Usman Ahmed Sharif, Hanan Rafique, Furqan Ali, Abid Ashiq, Masood Iqbal, Junaid Department of Computer Science Lahore Leads University Lahore Pakistan Department of Statistics and Data Science University of Mianwali Mianwali Pakistan Faculty of Information Technology University of Central Punjab Lahore Pakistan

ISBN: (纸本)9783031776199

Peer-to-Peer communication is based on an important feature of communication which is Device-to-Device (D2D) communication. IoT is a computational device that is equipped with accurate identifiers and the capacity to speak data across a network without the assistance of a human. D2D communication is referred to as "Direct verbal exchange among the taking part gadgets without the use of the centralized infrastructure". This research study examines the advantages and barriers of D2D communication as a means of meeting the IoT's requirements. Many companies and quality management organizations have demonstrated a strong interest in implementing the D2D approach in wireless networks. The thought of working without the necessary control of centralized supervision and making Wi-Fi networks wider as well as energy saving can be made possible with D2D communication in IoT. These devices’ technical limitations and the connection's support limitations provide an upward push to numerous problems that must be addressed. Some of the IoT studies Electricity production, connectivity, security, scenario technologies, and so forth are all issues. We cognizance’s on troubles that in the IoT there is an influence in D2D communication surroundings. We also discovered some important stumbling blocks to the success of smart D2D speech communication in the Internet of Things. We talked about how to deal with these difficult situations. This research explains the idea of a tool to tool verbal exchange and IoT system and defines its predominant techniques and applications imparting a subsequent era therefore as procedure strategy to the demanding situations. To boost research and development in the domains IoT problems have been studied. Every cited research work's contribution and limitations are discussed as well as any potential problem statement and open rely. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Wi-Fi

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：