检索结果-内蒙古大学图书馆

SSRN 2024年

作者： Goldstein-Tweg, Tom Ginzburg-Ganz, Elinor Belikov, Juri Levron, Yoash The Andrew and Erna Viterbi Faculty of Electrical and Computer Engineering Technion—Israel Institute of Technology Haifa3200003 Israel Department of Software Science Tallinn University of Technology Akadeemia tee 15a Tallinn12618 Estonia

The current paper belongs to a class of research works that aim to find analytic and semi-analytic solutions to optimal power flow problems that involve storage systems. The main contribution of this work is a rigorous proof for the uniqueness of the ``shortest-path" optimal solution, which is a cornerstone in this class of algorithms, and relies upon a graphical design procedure presented in an earlier work. The proof builds upon five consequential lemmas, each provides a different characteristic of the optimal solution. These characteristics are then merged to prove the uniqueness of the optimal solution, which is given by the shortest path of the generated energy within bounds. The presented proof provides not only a sound theoretical foundation for this class of algorithms, but may also help develop additional analytic solutions for more complex optimal control problems involving storage systems. © 2024, The Authors. All rights reserved.

关键词： Power management

来源：评论

学校读者我要写书评

暂无评论

Flexibility and Privacy: A Multi-Head Federated Continual Learning Framework for Dynamic Edge Environments

Flexibility and Privacy: A Multi-Head Federated Continual Le...

引用

International Symposium on Computing and Networking (CANDAR)

作者： Chunlu Chen Kevin I-Kai Wang Peng Li Kouichi Sakurai Graduate School of Information Science and Electrical Engineering Kyushu University Fukuoka Japan dept. of Electrical Computer and Software Engineering The University of Auckland Auckland New Zealand School of Computer Science and Engineering The University of Aizu Aizuwakamatsu Japan Faculty of Information Science and Electrical Engineering Kyushu University Fukuoka Japan

Federated Learning (FL) and the Internet of Things (IoT) have revolutionized data processing and analysis, overcoming the traditional limitations of cloud computing. However, traditional machine learning strategies lead to increased costs and catastrophic forgetting due to model retraining with new datasets. Continual learning has been proposed to counter this, enabling models to adapt to new data while preserving previous knowledge, which is beneficial for dynamic edge environments. Despite these advantages, the retention of previous knowledge during the continual learning process may lead to the information leakage. To address the inherent challenges of multitask scenarios, we present a Federated Continual Learning (FCL) framework that integrates the privacy-preserving benefits of Federated Learning (FL) into a continual learning system, ensuring both continual learning and privacy preservation in edge computing data processing and analysis. Specifically, our architecture introduces dedicated fully-connected layers for each task. This architecture ensures that distinctive features pertinent to each task are not only captured but also preserved throughout the model’s lifespan. Within our framework, data is processed via task-specific layers. Subsequently, the final label is determined by associating it with the paramount prediction value, thus capitalizing on the model’s comprehensive knowledge reservoir to bolster prediction accuracy. We subjected our FCL framework to rigorous validation using two benchmark datasets: MNIST and CFAR-10. Experimental outcomes unequivocally substantiate the efficacy of our proposed methodology.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fuzzy Logic-Based Temperature and Humidity Measurement for Pharmacy Warehouses

SSRN

引用

SSRN 2022年

作者： Avuçlu, Emre Basciftci, Fatih Elen, Abdullah Department of Software Engineering Aksaray University Aksaray Turkey Department of Computer Engineering Technology Faculty Selçuk University Selçuklu Konya42003 Turkey Bandirma Onyedi Eylul University Faculty of Engineering and Naturel Sciences Department of Software Engineering Balikesir Bandirma Turkey

Drugs are dispensed to pharmacies when necessary, by keeping pharmaceutical storage cabinets and the drugs should be kept in suitable environments to preserve the structure of the drug in this process. To create this favourable environment, they should be maintained in a certain level of humidity and temperature. To ensure this, there are two input parameters including temperature and humidity in a designed system and there are two outputs to control these parameters, including coolers and humectants. The temperature and humidity values of real-time running fuzzy expert system-based medicine cabinets are maintained in the appropriate range. The purpose of the application is to keep the environment values which are necessary to preserve the structure of the drugs in the pharmacy warehouse, at the required level and to ensure a longer lifespan. The values are determined according to the instructions for tracking temperature and humidity in pharmacy warehouses by Ministry. © 2022, The Authors. All rights reserved.

关键词： Fuzzy logic

来源：评论

学校读者我要写书评

暂无评论

Metaverse with Mobile Twin Edge Computing: Empowering Optimal Efficiency and Accuracy

Metaverse with Mobile Twin Edge Computing: Empowering Optima...

引用

engineering & Computing Technologies (ICECT), International Conference on

作者： Asma Bibi Umara Noor Zahid Rashid Department of Software Engineering Faculty of Computing and Information Technology International Islamic University Islamabad Pakistan Department of Computer Science Kohsar University Murree Pakistan Technology Management Economics and Policy Program College of Engineering Seoul National University Seoul South Korea

ISBN: (数字)9798350349719

ISBN: (纸本)9798350349726

The concept of Digital Twin has been widely used by researchers to represent physical entities in computer-generated reality in the metaverse. In this research, a novel concept of “Mobile Twin” is coined. Mobile Twin serves as a replica of a mobile device in the virtual environment enabling communication. The purpose of introducing Mobile Twin in the metaverse is to bring mobility and benefits similar to tangible mobile devices while eliminating the need for individual energy sources, storage limitations, resource usage, and efficiency. The true benefits of a mobile twin can be achieved with an architecture where computing nodes are decentralized, data processing is near the network's edge with faster response times and reduced latency. For this purpose, the mobile twin-based applications of metaverse are built over edge computing-based network architecture. This idea introduced the aspect of “Revolutionary Ultra-low latency (RULL)” in the metaverse.

关键词： computers Metaverse computer architecture Network architecture Data processing Mobile handsets Digital twins

来源：评论

学校读者我要写书评

暂无评论

Multi-Camera Multi-Object Tracking on the Move via Single-Stage Global Association Approach

arXiv

引用

arXiv 2022年

作者： Nguyen, Pha Quach, Kha Gia Duong, Chi Nhan Phung, Son Lam Le, Ngan Luu, Khoa Computer Science and Computer Engineering Department University of Arkansas Fayetteville United States Computer Science and Software Engineering Department Concordia University MontrealQC Canada Faculty of Engineering and Information Sciences University of Wollongong NSW Australia

The development of autonomous vehicles generates a tremendous demand for a low-cost solution with a complete set of camera sensors capturing the environment around the car. It is essential for object detection and tracking to address these new challenges in multi-camera settings. In order to address these challenges, this work introduces novel Single-Stage Global Association Tracking approaches to associate one or more detection from multi-cameras with tracked objects. These approaches aim to solve fragment-tracking issues caused by inconsistent 3D object detection. Moreover, our models also improve the detection accuracy of the standard vision-based 3D object detectors in the nuScenes detection challenge. The experimental results on the nuScenes dataset demonstrate the benefits of the proposed method by outperforming prior vision-based tracking methods in multi-camera settings. Copyright © 2022, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

A Novel Gooseneck Barnacle Optimizer Based Machine Learning Approach for Rainfall Prediction

A Novel Gooseneck Barnacle Optimizer Based Machine Learning ...

引用

Sustainable Technologies for Industry 4.0 (STI), International Conference on

作者： Marzia Ahmed Mohd Herwan Sulaiman Mostafijur Rahman Ahmad Johari Mohamad Faculty of Electrical & Electronics Engineering Technology Universiti Malaysia Pahang Al-Sultan Abdullah (UMPSA) Pahang Malaysia Department of Software Engineering Daffodil International university Dhaka Bangladesh Department of Computer Science and Engineering Green University of Bangladesh

In dynamic meteorological prediction, accurate rainfall forecasting is a mystery. In a complex and dynamic natural environment with unpredictable sky movements, we propose an innovative methodology that forecasts weekly average rainfall patterns using the Gooseneck Barnacle Optimizer and the Least Squares Support Vector Machine (LSSVM). The significance of rainfall prediction is shown by its widespread implications, including public health. However, conventional single-model techniques and machine-learning methods must represent rainfall pattern changes, limiting our preparation. With a 2014–2018 dataset from reliable meteorological libraries, our research explores the possibility of this novel combination. The Gooseneck Barnacle Optimizer (GBO) serves as the bedrock of our methodology, introducing a novel evolutionary algorithm inspired by the intricate mating behaviors of gooseneck barnacles. GBO aptly captures the dynamic interplay of factors such as navigational sperm casting properties, food availability, food attractiveness, wind direction, and intertidal zone wave movement during mating, culminating in two crucial optimization stages: exploration and exploitation. In contrast to previous algorithms like the Barnacle Mating Optimizer (BMO), GBO stands out by more accurately emulating the unique mating behaviors of gooseneck barnacles. The prediction job is performed by integrating the Least Squares Support Vector Machines (LSSVM) algorithm with GBO as an objective function, using the optimized hyper-parameter values. The results suggest that the GBO algorithm exhibits superior performance compared to existing methodologies. This is accomplished by efficiently augmenting the original random population for a particular problem, resulting in a convergence towards the global optimum and producing significantly enhanced optimization outcomes.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Robust Anonymous Authentication Scheme for Securing IoT-Enabled Healthcare Services

A Robust Anonymous Authentication Scheme for Securing IoT-En...

引用

Cyber Security in Networking Conference (CSNet)

作者： Sana Ullah Shanshan Tu Akhtar Badshah Muhammad Waqas Department of Enterprise and Technology Atlantic Technological University Galway Ireland College of Computer Science Beijing University of Technology Beijing China Department of Software Engineering Faculty of Engineering University of Malakand Dir Lower Pakistan Faculty of Engineering and Science School of Computing and Mathematical Sciences University of Greenwich U.K. School of Engineering Edith Cowan University Perth WA Australia

ISBN: (数字)9798331534103

ISBN: (纸本)9798331534110

Smart wearables and body implanted IoT devices continuously track and transmit health metrics wirelessly to a central controller, such as a personal server, enabling real-time monitoring, proactive treatment and timely assistance. However, the security of IoT-enabled healthcare systems remains a concern, particularly regarding the protection of sensitive patient data. To address the aforementioned issue and enhance security in IoT-enabled healthcare services, we propose a robust anonymous authentication scheme in this work. By leveraging lightweight cryptographic primitives including hash functions and XOR operations coupled with physical unclonable functions (PUFs) and fuzzy extractors, the proposed scheme introduces a novel authentication and key agreement mechanism for secure communication in IoT-enabled healthcare systems. The integration of PUF technology ensure the physical security of resource constrained implantable medical devices (IMDs) against various attacks including device physical capture and impersonation attacks that compromise the IoT-enabled healthcare operations. A thorough security analysis demonstrated the robustness and resilience of the proposed scheme against various active and pas-sive security attacks, thus ensure the integrity and confidentiality of sensitive healthcare data. Finally, comparative analysis of the proposed scheme with other state-of-the-art highlighted that our scheme outperformed other approaches in terms of providing security and additional features, positioning it as a comprehensive solution for authentication in IoT-enabled healthcare services.

关键词： Hash functions Medical devices Authentication Medical services Physical unclonable function Security Internet of Things Servers Wearable devices Resilience

来源：评论

学校读者我要写书评

暂无评论

Air Pollutant (CO) Forecasting: A Hybrid Approach Using Gooseneck Barnacle Optimization and Artificial Neural Networks

Air Pollutant (CO) Forecasting: A Hybrid Approach Using Goos...

引用

AI in Cybersecurity (ICAIC), International Conference on

作者： Marzia Ahmed Ahmad Johari Mohamad Md Maruf Hassan Touhid Bhuiyan Department of Software Engineering Daffodil International University (DIU) Dhaka Bangladesh Faculty of Electrical & Electronics Engineering Technology Universiti Malaysia Pahang Al-Sultan Abdullah (UMPSA) Malaysia Department of Computer Science and Engineering Southeast University Dhaka Bangladesh School of IT Washington University of Science and Technology (WUST) Virginia USA

ISBN: (数字)9798331518882

ISBN: (纸本)9798331518899

Air quality forecasting is critical for environmental monitoring and public health, and in this study, we propose a hybrid approach utilizing Gooseneck Barnacle Optimization (GBO) and Artificial Neural Networks (ANN) to enhance predictive accuracy. The air quality dataset, comprising pollutant concentrations (CO, NOx, benzene) and meteorological factors (temperature, humidity), is sourced from the UCI Machine Learning Repository. GBO is employed to fine-tune the ANN’s hyperparameters (especially the weight and bias), as well as the number of layers, neurons, and activation functions, to improve regression-based forecasting. The GBOANN model achieves a Mean Squared Error (MSE) of 0.562 and a Root Mean Squared Percentage Error (RMSPE) of 5.63%, outperforming other metaheuristic methods like BMO, SSA, DA, MVO, and EMA. This study demonstrates the GBO-ANN model’s potential for accurate real-time air quality forecasting, offering a robust, sustainable solution.

关键词： Accuracy Atmospheric modeling Artificial neural networks Predictive models Air quality Data models Real-time systems Environmental monitoring Forecasting Public healthcare

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Approach for Automatic Categorization of Service Support Requests on University Information Management System

Machine Learning Approach for Automatic Categorization of Se...

引用

International Conference on Intelligent and Fuzzy Systems, INFUS 2020

作者： Onan, Aytuğ Atik, Erdem Yalçın, Adnan Faculty of Engineering and Architecture Department of Computer Engineering İzmir Katip Çelebi University İzmir35620 Turkey Graduate School of Natural Sciences Division of Software Engineering İzmir Katip Çelebi University İzmir35620 Turkey

ISBN: (纸本)9783030511555

The bug reports and service support requests provided by users to software developers serve as an important source of information for software maintenance. For large software projects, the number of users involved may be high. As a result, large number of service support requests may be generated. In this study, we present a machine learning approach for automatic categorization of service support requests on university information management system of Izmir Katip Celebi University. We have collected a text corpus, which contains 17,831 bug reports and service support requests. On the corpus, preprocessing stages, such as, tokenization, stop word filtering and stemming have been employed. To represent text documents, TF-IDF term weighting scheme has been utilized in conjunction with 1-gram model. In the empirical analysis, five conventional classification algorithms (i.e., Naïve Bayes, k-nearest neighbor algorithm, C4.5 decision tree algorithm, random forest algorithm and support vector machines) have been taken into consideration. The experimental results indicate that the presented machine learning scheme can yield promising results on assigning service support requests to one of the related modules, as student information system, personnel information system, electronic document management system and scientific research projects system. We achieved a classification accuracy of 92.26% with support vector machines. © 2021, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Malware Attacks Detection in IoT Using Recurrent Neural Network(RNN)

引用

Intelligent Automation & Soft Computing 2024年第2期39卷 135-155页

作者： Abeer Abdullah Alsadhan Abdullah A.Al-Atawi Hanen karamti Abid Jameel Islam Zada Tan N.Nguyen Computer Science Department Imam Abdulrahman Bin Faisal UniversityDamam32232Saudi Arabia Department of Computer Science Applied CollegeUniversity of TabukTabuk47512Saudi Arabia Department of Computer Sciences College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Computer Sciences and Information Technology Hazara UniversityMansehraPakistan Faculty of Computing Department of Software EngineeringInternational Islamic UniversityIslamabadPakistan Department of Architectural Engineering Sejong UniversitySeoul05006Korea

IoT(Internet of Things)devices are being used more and more in a variety of businesses and for a variety of tasks,such as environmental data collection in both civilian and military *** are a desirable attack target for malware intended to infect specific IoT devices due to their growing use in a variety of applications and their increasing computational and processing *** this study,we investigate the possibility of detecting IoT malware using recurrent neural networks(RNNs).RNNis used in the proposed method to investigate the execution operation codes of ARM-based Internet of Things apps(OpCodes).To train our algorithms,we employ a dataset of IoT applications that includes 281 malicious and 270 benign pieces of *** trained model is then put to the test using 100 brand-new IoT malware samples across three separate LSTM *** exposure was not previously conducted on these *** newly crafted malware samples with 2-layer neurons had the highest accuracy(98.18%)in the 10-fold cross validation experiment.A comparison of the LSTMtechnique to other machine learning classifiers shows that it yields the best results.

关键词： Malware malicious code code obfuscation IoT machine learning deep 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：