检索结果-内蒙古大学图书馆

International Conference on Advanced Science and engineering (ICOASE)

作者： Basheer Husham Ali Nasri Sulaiman S.A.R. Al-Haddad Rodziah Atan Siti Lailatul Mohd Hassan Department of Electrical and Electronic Engineering Universiti Putra Malaysia (UPM) Serdang Malaysia Department of Electrical and Electronic Engineering Faculty of Engineering Universiti Putra Malaysia (UPM) Serdang Malaysia Department of Computer and Communication Systems Engineering Universiti Putra Malaysia (UPM) Serdang Malaysia Software Eng. and Information Systems Dept Universiti Putra Malaysia (UPM) Serdang Malaysia School of Electrical Engineering Universiti Teknologi MARA Shah Alam Malaysia

Distributed Denial of services (DDoS) attack is one of the most dangerous attacks that targeted servers. The main consequence of this attack is to prevent users from getting their legitimate services by bringing down targeted victim. CICFlowMeter tool generates bi-directional flows from packets. Each flow generates 83 of different features. The research focuses on 8 features which are active min (f1), active mean (f2), active max (f3), active std (f4), idle min (f5), idle mean (f6), idle max (f7), and idle std (f8). CICFlowMeter tool has several problems that affected on the detection accuracy of DDoS attacks. The idle and active based feature of Shannon entropy and sequential probability ratio test (SE-SPRT) approach was implemented in this research. The problems of original CICFlowMeter were presented, and the differences between original and revised version of CICFlowMeter tool were explored. The DARPA database and confusion matrix were used to evaluate the detection technique and present the comparison between two versions of CICFlowMeter. The detection method detected neptune and smurf attacks and had higher accuracy, f1-score, sensitivity, specificity, and precision when revised version of CICFlowMeter used to generate flows. However, the detection method failed to detect neptune attack and had higher miss-rate, lower accuracy, lower f1-score, and lower specificity, and lower precision when original version used in generating flows.

关键词： Sensitivity Databases Scalability Bidirectional control Denial-of-service attack Feature extraction Entropy

来源：评论

学校读者我要写书评

暂无评论

Brain tumor recognition using an integrated bat algorithm with a convolutional neural network approach

引用

Measurement: Sensors 2022年 24卷

作者： Chawla, Riddhi Beram, Shehab Mohamed Murthy, C Ravindra Thiruvenkadam, T. Bhavani, N.P.G. Saravanakumar, R. Sathishkumar, P.J. Medical School Akfa University Tashkent Uzbekistan Department of Computing and Information Systems School of Engineering and Technology Sunway University Kuala Lumpur Malaysia Electronics and Instrumentation Engineering Sreevidyanikethan Engineering College Tirupati India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Andhra Pradesh Vaddeswaram India Department of ECE SIMATS School of Engineering Saveetha Institute of Medical and Technical Sciences Tamilnadu Chennai India Department of Wireless Communication Institute of ECE SIMATS School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai India Dept of Computer Science and Engineering Panimalar Engineering College India

Tumors are uncontrolled growth of nerve cells that can lead to *** ability to separate malignancies in the brain is critical for better diagnosis. As a result, there are a few research initiatives aimed at improving patient care. The manual method takes time and is only available in a few medical facilities. Treatment choices for brain cancer differ depending on the specific, shape, and position of the tumor, as well as your general health and *** on MRI input images, the system can automatically recognize a type of brain tumor. A Convolutional neural network and Bat algorithm are used in the proposed method to detect brain tumors in MRI images (B–CNN).To eliminate the noise the data is first pre-processed. To extract features from MRI brain pictures, the 2-D Gabor filter is utilized. For better accuracy, feature selection is based on the Bat *** data for this research were obtained from Nanfang Hospital and Tianjing Medical University's General *** proposed BCNN method results in a 99.5% accuracy rate when compared to the existing system. © 2022

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Spatial photonic reservoir computing based on non-linear phase-to-amplitude conversion in micro-ring resonators

arXiv

引用

arXiv 2021年

作者： Mesaritakis, Charis Sozos, Kostas Dermanis, Dimitris Bogris, Adonis University of the Aegean Dept. of Information and Communication Systems Engineering Palama 2 Karlovassi Samos83200 Greece University of West Attica Dept. of Informatics and Computer Engineering. Aghiou Spiridonos Egaleo Athens12243 Greece

We present a photonic reservoir computing, relying on a non-linear phase-to-amplitude mapping process, able to classify in real-time multi-Gbaud time traces subject to transmission effects. This approach delivers an a... 详细信息

关键词： Optical resonators

来源：评论

学校读者我要写书评

暂无评论

Hybrid Gromov-Wasserstein Embedding for Capsule Learning

arXiv

引用

arXiv 2022年

作者： Shamsolmoali, Pourya Zareapoor, Masoumeh Das, Swagatam Granger, Eric García, Salvador Dept. of Automation Shanghai Jiao Tong University Shanghai China Electronics and Communication Sciences Unit Indian Statistical Institute Kolkata India Dept. of Systems Engineering Ecole de tech-nologie supérieure Université du Québec Montreal Canada Dept. of Computer Science and Artificial Intelligence University of Granada Granada Spain

Capsule networks (CapsNets) aim to parse images into a hierarchy of objects, parts, and their relations using a two-step process involving part-whole transformation and hierarchical component routing. However, this hierarchical relationship modeling is computationally expensive, which has limited the wider use of CapsNet despite its potential advantages. The current state of CapsNet models primarily focuses on comparing their performance with capsule baselines, falling short of achieving the same level of proficiency as deep CNN variants in intricate tasks. To address this limitation, we present an efficient approach for learning capsules that surpasses canonical baseline models and even demonstrates superior performance compared to high-performing convolution models. Our contribution can be outlined in two aspects: firstly, we introduce a group of subcapsules onto which an input vector is projected. Subsequently, we present the Hybrid Gromov-Wasserstein framework, which initially quantifies the dissimilarity between the input and the components modeled by the subcapsules, followed by determining their alignment degree through optimal transport. This innovative mechanism capitalizes on new insights into defining alignment between the input and subcapsules, based on the similarity of their respective component distributions. This approach enhances CapsNets’ capacity to learn from intricate, high-dimensional data while retaining their interpretability and hierarchical structure. Our proposed model offers two distinct advantages: (i) its lightweight nature facilitates the application of capsules to more intricate vision tasks, including object detection;(ii) it outperforms baseline approaches in these demanding tasks. Our empirical findings illustrate that Hybrid Gromov-Wasserstein Capsules (HGWCapsules) exhibit enhanced robustness against affine transformations, scale effectively to larger datasets, and surpass CNN and CapsNet models across various vision tasks. © 202

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

State Augmented Constrained Reinforcement Learning: Overcoming the Limitations of Learning with Rewards

arXiv

引用

arXiv 2021年

作者： Calvo-Fullana, Miguel Paternain, Santiago Chamon, Luiz F.O. Ribeiro, Alejandro The Dept. of Information and Communication Technologies Universitat Pompeu Fabra Barcelona Spain The Dept. of Electrical Computer and Systems Engineering Rensselaer Polytechnic Institute TroyNY United States The Excellence Cluster for Simulation Technology University of Stuttgart Stuttgart Germany The Dept. of Electrical and Systems Engineering University of Pennsylvania PhiladelphiaPA United States

A common formulation of constrained reinforcement learning involves multiple rewards that must individually accumulate to given thresholds. In this class of problems, we show a simple example in which the desired optimal policy cannot be induced by any weighted linear combination of rewards. Hence, there exist constrained reinforcement learning problems for which neither regularized nor classical primal-dual methods yield optimal policies. This work addresses this shortcoming by augmenting the state with Lagrange multipliers and reinterpreting primal-dual methods as the portion of the dynamics that drives the multipliers evolution. This approach provides a systematic state augmentation procedure that is guaranteed to solve reinforcement learning problems with constraints. Thus, as we illustrate by an example, while previous methods can fail at finding optimal policies, running the dual dynamics while executing the augmented policy yields an algorithm that provably samples actions from the optimal policy. Copyright © 2021, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Healthier and Independent Living of the Elderly: Interoperability in a Cross-Project Pilot

Healthier and Independent Living of the Elderly: Interoperab...

引用

2022 Interoperability for Enterprise systems and Applications Workshops, I-ESA Workshops 2022

作者： Agostinho, Carlos Pimenta, Andreia Marques, Maria Tsiouris, Kostas M. Kalatzis, Fanis Nikitas, Christos Iliadou, Eleftheria Occhipinti, Mattia Kouris, Ioannis Koutsouris, Dimitrios Basdekis, Ioannis Koloutsou, Konstantina Gallo, Luigi de Pietro, Giueppe Jardim-Goncalves, Ricardo FCT-Campus Caparica2829-516 Portugal NOVA School of Science and Technology Caparica2829-516 Portugal Secretaria Regional de Saúde e Ptroteção Civil Rua da Carreira nº107 Funchal9000-042 Portugal Unit of Medical Technology and Intelligent Information Systems Dept. of Material Science and Engineering University of Ioannina IoanninaGR45110 Greece National Kapodistrian University of Athens First Department of Otolaryngology-Head and Neck Surgery ‘Hippokrateio’ General Hospital Athens Greece Università degli Studi di Milano Computer Science Department Milan Italy Biomedical Engineering Laboratory Institute of Communication and Computer Systems National Technical University of Athens Heroon Polytechneiou 9 15780 Greece SPHYNX Technology Solutions AG Zug Switzerland National Research Council of Italy Via P. Bucci cubo 8/9C Rende87036 Italy

The ageing of the population creates new heterogeneous challenges for age-friendly living. The progressive decline in physical and cognitive skills tends to prevent elderly people from performing basic instrumental activities of daily living and there is a growing interest in technology for aging support. Digital health today can be exercised by anyone owning a smartphone and parameters such as heart rate, step counts, calorie intake, sleep quality, can be collected and used not only to monitor and improve the individual’s health condition but also to prevent illnesses. However, for the benefits of e-health to take place, digital health data, either Electronic Health Records (EHR) or sensor data from the IoMT, must be shared, maintaining privacy and security requirements but unlocking the potential for research an innovation throughout EU. This paper demonstrates the added value of such interoperability requirements, and a form of accomplishing them through a cross-project pilot. © 2022 CEUR-WS. All rights reserved.

关键词： Interoperability

来源：评论

学校读者我要写书评

暂无评论

Performance Optimization of a Proposed Piezoelectric Cantilever Energy Harvester Using Genetic Algorithm 7

Performance Optimization of a Proposed Piezoelectric Cantile...

引用

7th International Japan-Africa Conference on Electronics, communications and Computations, JAC-ECC 2019

作者： Ahmed, Shimaa M. Salem, Marwa S. Eladawy, Mohamed I. Faculty of Engineering Helwan University Department Communication and Electronics Engineering Dept. Systems Engineering Cairo Egypt Computer College Hail University Department of Computer Engineering Hail Saudi Arabia

ISBN: (数字)9781728156170

ISBN: (纸本)9781728156170

This paper aims to present the performance optimization of a proposed single beam piezoelectric cantilever structure. The design optimization technique is based on genetic algorithms. It optimizes the structure geometrical parameters. By this optimization, the optimum value of the product of output power and bandwidth in a certain frequency domain is found. In the proposed structure, the piezoelectric material is split into different segment. The optimum number and dimension of these segments that maximizing the power bandwidth product is determined. A comparison between the proposed and the conventional structure is presented. Both structures are simulated using Comsol Multi-physics 5. The power bandwidth product in the proposed structure is enhanced. in the proposed structure is enhanced over the traditional structure. The simulation results indicate that the optimum value of the proposed structure is higher than the conventional structure by 9.46 %. In addition, the volume of the proposed structure is less than the conventional structure by 7.65%. © 2019 IEEE.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Intra-Datacenter Load Balancing in a Federated Cloud with Throttled Algorithm

Intra-Datacenter Load Balancing in a Federated Cloud with Th...

引用

Science, engineering and Business for Sustainable Development Goals (SEB-SDG), International Conference on

作者： Damola Gideon Akinola Emmanuel Adetiba Abdultaofeek Abayomi Uche Nnaji Surendra Thakur Sibusiso Moyo Department of Electrical and Information Engineering Covenant Applied Informatics and Communications African Center of Excellence Covenant University Ota Nigeria HRA Institute for Systems Science Durban University of Technology Durban South Africa Department of Information and Communication Technology Mangosuthu University of Technology Durban South Africa Dept. of Computer and Information Science Covenant Applied Informatics and Communications African Center of Excellence Covenant University Ota Nigeria KZN e-Skills CoLab Durban University of Technology Durban South Africa School for Data Science and Computational Thinking and Department of Mathematical Sciences Stellenbosch University Stellenbosch South Africa

ISBN: (数字)9798350358155

ISBN: (纸本)9798350358162

The emergence of cloud computing technology has motivated a very high number of users in different organizations to access its services in running and delivering their various operations and services. However, this surge of cloud users has led to the problem of uneven load sharing among the cloud computing infrastructures. As a result, federated cloud infrastructure was initiated to provide more cloud computing resources to accommodate more cloud users’ requests and also to provide equal requests mapping with the available cloud resources. Nevertheless, the issue of unequal allocation of requests within the datacenter(s) that makes up the federated cloud environment still persists. This research work presents an intra-datacenter load balancing algorithm in a federated cloud environment named; the intra-balancer adapted throttled algorithm to evenly distribute requests in each datacenter that formulate the federated cloud infrastructures. The simulation of the intra-balancer was carried out in CloudAnalyst, the results of the implementation showed that the intra-balancer outperformed the Round-Robin and ESCE with 98.93ms and 2.26ms for the response and processing time respectively. The results assert that the intra-balancer algorithm provides a better load balancing solution in a federated cloud environment.

关键词： computers Cloud computing Organizations Load management Resource management Time factors Task analysis

来源：评论

学校读者我要写书评

暂无评论

GA-optimized JT-CoMP F-NOMA in HetNets: Adaptive resource allocation with imperfect SIC

引用

Physical communication 2025年 72卷

作者： Aamina Akbar Ashfaq Ahmed Adnan Zafar Sobia Jangsher Wireless and Signal Processing (WiSP) Lab Institute of Space Technology (IST) Islamabad Pakistan Center for Cyber-Physical Systems (C2PS) Dept. of Computer & Communication Engineering Khalifa University Abu Dhabi 127788 United Arab Emirates School of Electronic Engineering Dublin City University Dublin Ireland

Power domain non-orthogonal multiple access has emerged as a critical solution to address the spectral inefficiency of orthogonal multiple access and to meet the demands of next-generation multiple access in 5G and beyond 5G and 6G internet of things networks. Coordinated multi-point-non-orthogonal multiple access can effectively manage interference and enhance spectral efficiency in densely populated heterogeneous networks particularly for cell-edge users. However, relying solely on non-orthogonal multiple access for all users across varying and practical channel conditions, especially under imperfect successive interference cancellation, is often impractical. An adaptable approach is required to serve a broader range of users. To address this need, we propose a joint transmission-coordinated multi-point enabled flexible-non-orthogonal multiple access framework that maximizes the network’s sum-rate and dynamically optimizes power allocation. Our approach mitigates challenges posed by paired non-orthogonal multiple access users who fail to meet minimum quality of service requirements due to practical issues like successive interference cancellation imperfections or by presence of unpaired users. The study focuses on jointly optimizing Coordinated multi-point and non-coordinated multi-point user selection, non-orthogonal multiple access user pairing, orthogonal multiple access/non-orthogonal multiple access mode selection, and power allocation using a Genetic algorithm to enhance sum-rate performance across the network. We introduce a Genetic Algorithm-based flexible non-orthogonal multiple access with adaptive quality of service and orthogonal multiple access switching algorithm to solve this joint optimization problem, ensuring reliable service provision and reducing disruptions caused by suboptimal channel conditions and interference. By combining joint transmission-coordinated multi-point with flexible-non-orthogonal multiple access, our proposed framework signif

关键词：

来源：评论

学校读者我要写书评

暂无评论

Lightweight Task-Oriented Semantic communication Empowered by Large-Scale AI Models

引用

IEEE Transactions on Vehicular Technology 2025年

作者： Liu, Chuanhong Guo, Caili Yang, Yang Chen, Mingzhe Quek, Tony Q. S. Beijing University of Posts and Telecommunications Beijing Key Laboratory of Network System Architecture and Convergence School of Information and Communication Engineering Beijing100876 China Beijing University of Posts and Telecommunications Beijing Laboratory of Advanced Information Networks School of Information and Communication Engineering Beijing100876 China University of Miami Department of Electrical and Computer Engineering Institute for Data Science and Computing Coral GablesFL United States Singapore University of Technology and Design Dept. of Information Systems Technology and Design 487372 Singapore

Recent studies have focused on leveraging large-scale artificial intelligence (LAI) models to improve semantic representation and compression capabilities. However, the substantial computational demands of LAI models pose significant challenges for real-time communication scenarios. To address this, this paper proposes utilizing knowledge distillation (KD) techniques to extract and condense knowledge from LAI models, effectively reducing model complexity and computation latency. Nevertheless, the inherent complexity of LAI models leads to prolonged inference times during distillation, while their lack of channel awareness compromises the distillation performance. These limitations make standard KD methods unsuitable for task-oriented semantic communication scenarios. To address these issues, we propose a fast distillation method featuring a pre-stored compression mechanism that eliminates the need for repetitive inference, significantly improving efficiency. Furthermore, a channel adaptive module is incorporated to dynamically adjust the transmitted semantic information based on varying channel conditions, enhancing communication reliability and adaptability. In addition, an information bottleneck-based loss function is derived to guide the fast distillation process. Simulation results verify that the proposed scheme outperform baselines in term of task accuracy, model size, computation latency, and training data requirements. © 1967-2012 IEEE.

关键词： NP-hard

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：