检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Pakmehr, Amir Asmuth, Andreas Neumann, Christoph P. Pirkl, Gerald Department of Computer and Information Technology Engineering Qazvin Branch Islamic Azad University Qazvin Iran Department of Electrical Engineering Media and Computer Science Ostbayerische Technische Hochschule Amberg-Weiden Amberg Germany

Security challenges for cloud or fog-based machine learning services pose several concerns. Securing the underlying cloud or fog services is essential, as successful attacks against these services, on which machine learning applications rely, can lead to significant impairments of these applications. Because the requirements for Artificial Intelligence applications can also be different, we differentiate according to whether they are used in the cloud or in a fog computing network. This then also results in different threats or attack possibilities. For cloud platforms, the responsibility for security can be divided between different parties. Security deficiencies at a lower level can have a direct impact on the higher level where user data is stored. While responsibilities are simpler for fog computing networks, by moving services to the edge of the network, we have to secure them against physical access to the devices. We conclude by outlining specific information security requirements for Artificial Intelligence applications. Copyright © 2023, The Authors. All rights reserved.

关键词： Fog

来源：评论

学校读者我要写书评

暂无评论

Improving fuzzy clustering algorithm for overlapping elements and its application

引用

International Journal of Information technology (Singapore) 2024年第4期16卷 2595-2602页

作者： PhamThi, Bich VoThiHang, Nga Vu, Quyen Tuong PhamToan, Dinh Nam Can Tho University Nguyen Van Cu Street Ninh Kieu District Can Tho City Viet Nam Faculty of Social Science and Humanities Van Lang University Ho Chi Minh City Viet Nam School of Media Design College of Technology and Design University of Economics Ho Chi Minh City Viet Nam Faculty of Mechanical-Electrical and Computer Engineering School of Technology Van Lang University Ho Chi Minh City Viet Nam

This paper proposes an improved fuzzy cluster analysis algorithm for processing overlapping elements. The algorithm employs a novel measure called the H index as the optimal criterion in the fuzzy clustering problem. It aims to capitalize on the advantages of fuzzy relationships, thereby facilitating the processing of overlapping elements. The approach is grounded in compactness and/or separation measures of centroid elements. The calculations of fuzzy information are sufficient to distinguish the geometric structures of clusters with overlapping elements. Moreover, this study develops an algorithm capable of identifying the optimal number of clusters for overlapping elements, providing advantages over the Elbow method. The developed algorithm is tested and implemented through numerical examples using Matlab software. Additionally, it is applied to construct a forecasting model for fuzzy time series. The experimental results demonstrate the superiority of the developed algorithm over certain existing algorithms. © The Author(s), under exclusive licence to Bharati Vidyapeeth's Institute of computer Applications and Management 2024.

关键词： Fuzzy clustering H index Optimal number of cluster Overlapping elements

来源：评论

学校读者我要写书评

暂无评论

Guiding Wireless Signals with Arrays of Metallic Linear Fresnel Reflectors: A Low-cost, Frequency-versatile, and Practical Approach 100

Guiding Wireless Signals with Arrays of Metallic Linear Fres...

引用

100th IEEE Vehicular technology Conference, VTC 2024-Fall

作者： Le, Hieu Bedir, Oguz Ibrahim, Mostafa Tao, Jian Ekin, Sabit Texas A&m University Electrical and Computer Engineering College StationTX United States Texas A&m University Engineering Technology and Industrial Distribution College StationTX United States Texas A&m University School of Performance Visualization and Fine Arts College StationTX United States Texas A&m University College StationTX United States

ISBN: (纸本)9798331517786

This study presents a novel mechanical metallic reflector array to guide wireless signals to the point of interest, thereby enhancing received signal quality. Comprised of numerous individual units, this device, which acts as a linear Fresnel reflector (LFR), facilitates the reflection of incoming signals to a desired location. Leveraging geometric principles, we present a systematic approach for redirecting beams from an Access Point (AP) toward User Equipment (UE) positions. This methodology is geared towards optimizing beam allocation, thereby maximizing the number of beams directed towards the UE. Ray tracing simulations conducted for two 3D wireless communication scenarios demonstrate significant increases in path gains and received signal strengths (RSS) by at least 50 dB with strategically positioned devices. © 2024 IEEE.

关键词： coverage map path gain ray tracing received signal strength (RSS) reconfigurable intelligent surfaces (RIS) specular reflections

来源：评论

学校读者我要写书评

暂无评论

Dynamic convolution with complementary attention for image classification

Dynamic convolution with complementary attention for image c...

引用

2024 International Conference on computer Application and Information Security, ICCAIS 2024

作者： Zheng, Chusan Liu, Jingming Fan, Haoru Li, Yafeng Li, Jian Li, Ning Fan, Pan Sun, Jieqi School of Mathematics and Information Sciences Baoji University of Arts and Science Baoji721013 China Cigarette Factory Shaanxi Tobacco Industry Co. Ltd. Baoji721013 China Chengdu University of Technology Oxford Brookes College Chengdu610051 China School of Computer Baoji University of Arts and Science Baoji721016 China School of Electrical and Control Engineering School of Mathematics and Data Science Shaanxi University of Science and Technology Xi’an710016 China

ISBN: (纸本)9781510689312

Convolution is the fundamental unit of operation in convolutional neural networks. However, traditional static convolution is subject to two significant limitations: a weak ability to effectively integrate global and local features and a high computational overhead. This paper introduces an innovative and efficient approach, the Complementary Attention Dynamic Convolution (CADC), to tackle the limitations of traditional static convolution in convolutional neural networks. CADC comprises a three-part architecture: two branches of attention and a fusion module. The dynamic convolution kernels are generated by integrating the results of the two branches of attention, which are weighted and fused. CADC is correlated with the input samples, efficiently integrates global and local features, and generates convolution kernels specific to the spatial location and channel domain. Extensive experiments have been conducted on popular benchmark datasets, and the experimental results demonstrate that the CADC method exhibits excellent performance in terms of the number of model parameters, computational complexity, and classification accuracy. © The Authors.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Transactional Dependency for Failure Recovery in Web Services Composition System

引用

Chinese Journal of Electronics 2023年第2期21卷 241-248页

作者： Xiaoyong Mei Shixian Li Changqin Huang Xiaolin Zheng School of Information Science and Technology Sun Yat-sen University Guangzhou China School of Computer Science and Technology Hunan University of Arts and Science Changde China Department of Electrical Engineering and Computer Sience University of California Irvine CA USA College of Computer Science and Technology Zhejiang University Hangzhou China

With the advanced Internet technology, business applications across multiple enterprises based on Composition web services (CWS) paradigm are widely used. Since business processes among enterprises become complex, loosely coupled, long running and unpredictable, tasks collaborate in a peer-to-peer fashion without central control, in which task dependency is inevitable. And when a system crash occurs, some tasks of the transaction flow may be committed while others unscheduled, in this situation, it is important to accurately specify the dependency between tasks in Transactional composition service (TCS), contemporary technologies usually statically specify dependency point and avoid implicit interaction in parallel aggregation. In this paper, we propose a task dependency analysis method based on transaction execution logs. We present the formal description of atomic Web service (WS) and discuss properties of the atomic WS such as pivot, compensability, retriability and vitalness, then analyze execution logs of transactions, specify data flow dependency and behavior dependency between tasks in TCS, behavior dependency and properties of aggregation patterns. The TCS based application of Trip reservation process (TRP) shows that it is feasible to ensure consistent execution of reliable TCS.

关键词： Web services Process control computer crashes Behavioral sciences Peer-to-peer computing technology planning Reliability

来源：评论

学校读者我要写书评

暂无评论

Bismuth-Based Double Perovskites for Solar-Powered EVs using ResNet and Long Short-Term Memory 3

Bismuth-Based Double Perovskites for Solar-Powered EVs using...

引用

3rd International Conference on Integrated Circuits and Communication Systems, ICICACS 2025

作者： Kiran, C.H. Gupta, Raj Kumar Kumar, Neeraj Devi, Rukmani Bhoopathy, V. Kathiravan, A. Mijar India Sardar Vallabhbhai Patel College Department of Physics Ara India Doon Institute of Engineering and Technology Department of Electrical Engineering Rishikesh India Saveetha College of Liberal Arts and Sciences Simats Deemed to be University Department of Computer Science Chennai India Sree Rama Engineering College Department of Computer Science and Engineering Tirupathi India Rajiv Gandhi College of Engineering and Technology Department of Electrical and Electronics Engineering Puducherry India

ISBN: (纸本)9798331508456

As people rely more on cars for transportation, greenhouse gas emissions and ozone layer depletion rise. For shorter rides, solar-powered e-bikes are affordable and environmentally friendly. This proposed approached a ResLSTM hybrid model with LSTM. The methodology involves preprocessing, feature extraction, and model training. Remove duplicates and missing values before k-means grouping and training. Consistency requires scaling, normalizing, and standardizing features. With an average accuracy of 93.45%, the ResLSTM model surpassed current approaches. The recommended method effectively estimates solar energy and vehicle energy consumption to maximize energy use for solar-powered e-bikes. The results suggest that ResLSTM can provide efficient and eco-friendly transportation options. Resolving data anomalies and ensuring accurate projections helps solar-powered electric bikes become more popular as a sustainable transportation choice. © 2025 IEEE.

关键词： Electric bikes

来源：评论

学校读者我要写书评

暂无评论

A Novel Way of Finding the Irregularity Present in the System Through Design of CPS System 4

A Novel Way of Finding the Irregularity Present in the Syste...

引用

4th IEEE International Conference on Advance Computing and Innovative Technologies in engineering, ICACITE 2024

作者： Santosh, J. Dhananjaya Babu, K. Nair, Jayashree Agarwal, Swathi Sakr, Dalal Kadim Al-Azzawi, Waleed Sri Krishna Adithya College of Arts and Science Department of Computer Applications Coimbatore India Department of Electrical and Electronics Engineering Rajampet India Acharya Institute of Management & Sciences School of It Bangalore India Cvr College of Engineering It Department Hyderabad India National University of Science and Technology Dalal Kadim Sakr Collage of Nursing Dhi Qar64001 Iraq Al-Farahidi University Baghdad Iraq

ISBN: (纸本)9798350360165

Strong security measures are required as Cyber-Physical Systems (CPSs) have developed into extremely sophisticated and complicated systems. However, classic anomaly detection approaches are facing difficulties because to the increase of sophisticated assaults and the growing complexity of CPSs. Furthermore, a major obstacle is the increase in data volume, which necessitates domain-specific expertise for efficient analysis. To address these issues, several deep learning-based anomaly detection systems have been created. In this work, we provide a unique approach to anomaly detection by the combination of a powerful deep learning technique, Convolutional Neural Network (CNN), with a Gaussian-Mixture Model (GMM) based on the Kalman Filter and ontology (KF). Our proposed method seeks to detect and distinguish odd behavior in CPSs. The framework has two crucial processes. The first stage in data preparation is to securely prepare the original data for usage in a new format. We provide our second introduction, the GMM-KF-BiLSTM integrated deep CNN model for anomaly detection, which enables precise estimation of posterior probability for both anomalous and normal events in CPSs. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Bismuth-Based Double Perovskites for Solar-Powered EVs using ResNet and Long Short-Term Memory

Bismuth-Based Double Perovskites for Solar-Powered EVs using...

引用

Integrated Circuits and Communication Systems (ICICACS), IEEE International Conference on

作者： Kiran C H Raj Kumar Gupta Neeraj Kumar Rukmani Devi V. Bhoopathy A. Kathiravan Department of Mechanical Engineering Alva's Institute of Engineering and Technology Mijar (DK) India Department of Physics Sardar Vallabhbhai Patel College Ara India Department of Electrical Engineering Doon Institute of Engineering and Technology Rishikesh India Department of Computer Science Saveetha College of Liberal Arts and Sciences SIMATS Deemed to be University Chennai India Department of Computer Science and Engineering Sree Rama Engineering College Tirupathi India Department of Electrical and Electronics Engineering Rajiv Gandhi College of Engineering and Technology Puducherry India

ISBN: (数字)9798331508456

ISBN: (纸本)9798331508463

关键词： Training Photovoltaic systems Accuracy Reviews Transportation Standardization Solar energy Integrated circuit modeling Greenhouse gases Long short term memory

来源：评论

学校读者我要写书评

暂无评论

Enhanced Artificial Algae Algorithm based Distributed Generation Placement for Voltage Profile Enhancement 2

Enhanced Artificial Algae Algorithm based Distributed Genera...

引用

2nd International Conference on Applied Artificial Intelligence and Computing, ICAAIC 2023

作者： Hussain, K. Mulani, Umar Mubarak Kumar, B.Suresh Parte, Smita Athanere Patra, Jyoti Prasad Kumar Reddy, P. Naresh Department of Electrical Engineering Maharashtra Kolhapur India Padmabhooshan Vasantraodada Patil Institute of Technology Department of Computer Science and Engineering Maharashtra Budhgaon India Chaitanya Bharathi Institute of Technology Department of Eee Telangana Hyderabad India Mits Gwalior Department of Cse Madhya Pradesh India Faculty Electrical Odisha University of Technology and Research Outr Govt of Odisha Mahalaxmi Vihar Techno Campus Ghatikia odisha Bhubaneswar India Mohan Babu University Department of Liberal Arts and Science Andhra Pradesh Tirupathi India

ISBN: (纸本)9781665456302

Power loss and voltage variability are main challenges in distribution systems. But, these difficulties are normally reduced by effectual network reconfiguration comprising the fusion of distributed generation (DG) units from the distribution network. Accordingly, the optimum size and placement of DGs are fundamental. Then, the network efficacy is reduced. This study was conducted to optimal place and size of DGs as a radial distribution network after and before reconfigurations. This study designs an Enhanced Artificial Algae Algorithm based Distributed Generation Placement for Voltage Profile Enhancement (EAAADG-VPE) technique. The presented EAAADG-VPE technique initially designs the EAAA by the integration of AAA with quasi-oppositional based learning (QOBL) concept. The presented EAAADG-VPE technique aims to regularize voltage, and minimizes power losses and penalty costs. For examining the real power system situation, the penalty factor was considered which roles a vital part in the minimized of power loss and increment of voltage profile. The performance validation of the EAAADG-VPE technique stated the enhanced performance over other recent state of art approaches. © 2023 IEEE.

关键词： Algae

来源：评论

学校读者我要写书评

暂无评论

Advanced Stock Market Prediction Using Unsupervised Federated Learning Techniques

Advanced Stock Market Prediction Using Unsupervised Federate...

引用

International CSI computer Conference, CSICC

作者： Mohsen Tajgardan Atena Shiranzaei Mahtab Jamali Reza Khoshkangini Mahdi Rabbani Faculty of Electrical and Computer Engineering Qom University of Technology Qom Iran Department of Computer Engineering Faculty of Industry and Mining (Khash) University of Sistan and Baluchestan Sistan and Baluchestan Iran Department of Computer Science and Media Technology Sustainable Digitalisation Research Centre Malmö University Malmö Sweden Canadian Institute for Cybersecurity University of New Brunswick NB Canada

ISBN: (数字)9798331523114

ISBN: (纸本)9798331523121

In the realm of stock market prediction, traditional supervised learning approaches often struggle with the vast and diverse nature of financial data, coupled with privacy concerns. This paper explores a novel methodology that combines unsupervised learning techniques with federated learning system to enhance stock market prediction models. We present a comprehensive system where local models, trained using unsupervised methods, contribute to a global model through federated aggregation. By leveraging federated learning, our approach allows multiple financial institutions to collaboratively train models on their decentralized data while preserving data privacy. This approach addresses the challenges of data heterogeneity and communication efficiency, providing a robust and scalable solution for advanced stock market forecasting. Our experiments demonstrate that integrating unsupervised learning with federated learning not only improves predictive accuracy but also enhances the model's ability to identify emerging market trends and anomalies. Finally, we compare our distributed data model with other machine learning models that use local data.

关键词： Data privacy Federated learning Supervised learning Predictive models Parallel processing Data models Security Stock markets Forecasting Unsupervised learning

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：