检索结果-内蒙古大学图书馆

AQROM:A quality of service aware routing optimization mechanism based on asynchronous advantage actor-critic in software-defined networks

引用

Digital communications and Networks 2024年第5期10卷 1405-1414页

作者： Wei Zhou Xing Jiang Qingsong Luo Bingli Guo Xiang Sun Fengyuan Sun Lingyu Meng School of Information and Communication Guilin University of Electronic TechnologyGuilin541004China The 34th Research Institute of China Electronics Technology Group Corporation Guilin541004China Guangxi Key Laboratory of Optical Network and Optical Information Security Guilin541004China State Key Laboratory of Information Photonics and Optical Communications BeijingUniversity of Posts and TelecommunicationsBeijing100876China Department of Electrical and Computer Engineering University of New MexicoAlbuquerqueNM87131USA

In Software-Defined Networks(SDNs),determining how to efficiently achieve Quality of Service(QoS)-aware routing is challenging but critical for significantly improving the performance of a network,where the metrics of QoS can be defined as,for example,average latency,packet loss ratio,and *** SDN controller can use network statistics and a Deep Reinforcement Learning(DRL)method to resolve this *** this paper,we formulate dynamic routing in an SDN as a Markov decision process and propose a DRL algorithm called the Asynchronous Advantage Actor-Critic QoS-aware Routing Optimization Mechanism(AQROM)to determine routing strategies that balance the traffic loads in the *** can improve the QoS of the network and reduce the training time via dynamic routing strategy updates;that is,the reward function can be dynamically and promptly altered based on the optimization objective regardless of the network topology and traffic *** can be considered as one-step optimization and a black-box routing mechanism in high-dimensional input and output sets for both discrete and continuous states,and actions with respect to the operations in the *** simulations were conducted using OMNeT++and the results demonstrated that AQROM 1)achieved much faster and stable convergence than the Deep Deterministic Policy Gradient(DDPG)and Advantage Actor-Critic(A2C),2)incurred a lower packet loss ratio and latency than Open Shortest Path First(OSPF),DDPG,and A2C,and 3)resulted in higher and more stable throughput than OSPF,DDPG,and A2C.

关键词： Software-defined networks Asynchronous advantage actor-critic QoS-aware routing optimization mechanism

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Learning Approaches for Zooplankton Classification: Recent Trends and Advances 17

Unsupervised Learning Approaches for Zooplankton Classificat...

引用

17th International Symposium on Ocean Technology, SYMPOL 2023

作者： Ansari, Sadaf Nisheeth Charan Reddy, K.Y. Desai, Dattesh V. Computer Vision & Ai CSIR-National Institute of Oceanography Marine Instrumentation Division Goa India Chaitanya Bharathi Institute of Technology Department of Electronics & Communication Engineering Hyderabad India CSIR-National Institute of Oceanography Biological Oceanography Division Goa India

ISBN: (纸本)9798350338744

Zooplankton are key components of the aquatic food web and present a lot of taxonomic diversity. Over the years, various Machine Learning techniques have been employed for the classification of zooplankton. Supervised Learning has been widely utilised in zooplankton classification, presenting commendable performance. However, it requires a substantial amount of manually labelled images, and the volume of collected zooplankton images is extensive. Consequently, Unsupervised Learning techniques have proven exceptionally valuable and popular for clustering unlabelled zooplankton data. Our study compiles and elucidates the Unsupervised Learning methods applied to zooplankton classification, while also comparing their performance and popularity over the years, based on observations from respective experimental studies. © 2023 IEEE.

关键词： Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Diffusive molecular communication for bacterium propagation over human gut track

引用

International Journal of Information Technology (Singapore) 2024年第5期16卷 3101-3108页

作者： Asim, Masood Jaiswal, Raghvendra Chugh, Urvashi Agarwal, Prabhakar Singh, S. Pratap Galgotia College of Engineering & amp Information Technology KIET Group of Institutions Meerut Road UP Ghaziabad 201206 India Electrical Electronics and Communication Engineering Galgotias University Sector-17A Yamuna Expressway GB Nagar UP Greater Noida 203201 India Symbiosis Institute of Technology Nagpur Campus Department of Computer Science & amp

Diffusive Molecular communication (DMC), is the most common approach employed in analysis and replication of different types of communication systems existing in nature. Exchange of Molecular Information (MI) using Bacterium, which is based on DMC and may be termed as Bacterial communication (BC), is being used to model detection and cure processes of various decreases due to the Bacteria. DMC is being developed to serve almost each and every aspect of humanity. Also, various approaches to detect and cure the Bacterial disease are proposed in literature. It is noticeable that the complete Human Gut Track (HGT) is responsible to grade the severity of the disease. And therefore, literature presents the propagation of Bacteria in the HGT. Further, it is most important to mention that the impulse response of the system which characterizes bacteria propagation per unit area (f(y)) plays a major role in modeling viral transmission over the (HGT). In this work we analyzed bacterial concentration (N(y)) at different time points (t = 0.3, 0.5, 0.7, 0.9, 1.2). Our findings show that as time (t) increases, N(y) also increases. Additionally, we examined bacterial distribution (V(y)) for varying values of v (λ = 0.2, 0.3, 0.4, 0.6, 0.8). Results indicate that as v increases, V(y) decreases due to fixed distance, where mucus influences bacterial concentration. Increasing mucus flow rate for a fixed distance results in a decrease in Bacteria distribution. In particular we provided analytical expressions of Bacterial concentration (N(y)) and Bacterial distribution (V(y)) under certain impulse responses. Also, the effect of different physical parameters on (N(y)) and (V(y)) have been quantified with the help of numerical simulation. Presented analysis shows perfect agreement with the theoretical background. © Bharati Vidyapeeth's Institute of computer Applications and Management 2024.

关键词： Bacteria Propagation Bacterial Distribution Bacterium Concentration Diffusive Molecular communication Human Gut Track

来源：评论

学校读者我要写书评

暂无评论

Design of Intelligent Medical Integrity Authentication and Secure Information for Public Cloud in Hospital Administration 2

Design of Intelligent Medical Integrity Authentication and S...

引用

2nd International Conference on Edge Computing and Applications, ICECAA 2023

作者： Jyothi, E.V.N. Kranthi, M. Dankan Gowda, V. Tanguturi, Rama Chaithanya Pace Institute of Technology & Sciences Department of Computer Science & Engineering Andhra Pradesh Ongole India Karunya Institute of Technology and Sciences Tamilnadu Coimbatore India Rise Krishna Sai Prakasam Group of Institutions Department of Computer Science & Engineering A.P Ongole India Bms Institute of Technology and Management Department of Electronics and Communication Engineering Karnataka Bangalore India

ISBN: (纸本)9798350347579

Due to political and financial considerations, large hospitals are also less likely to share their patient information with outside healthcare providers. To get around the barriers that prevent an efficient process of exchanging medical data. The integrated computerized clinical information system is part of the Hospital Information System (HIS), which aims to improve hospital operations and clinical management. Furthermore, the patient has access to an accurate electronic medical record that has been stored. For research and statistical applications, such records can be utilized in a data warehouse. The architecture of a centralized information system, on which HIS was established intended for the rapid transmission of both operational and administrative information. It would be difficult and It requires a lot of money and resources to set up an independent information management system for a small village hospital. The hospital information system in use presently, information is only shared within the same hospital. The theory of cloud computing serves as the proposal's basis. The 'cloud' makes it possible for greater analysis, sharing, and exchange of medical data from images. Doctors may be able to get the data they need due to cloud-based medical image storage, patient will be able to get treatment across hospital departments automating the management of hospital information and computational resources. Hence, this system develops of intelligent medical integrity authentication and it is more effective for hospital administration to use secure information on public clouds, low-cost and time saving. © 2023 IEEE.

关键词： Hospitals

来源：评论

学校读者我要写书评

暂无评论

A Detailed Analysis of Cloud Storage and Key Management Techniques in IoT Driven Smart Grids

A Detailed Analysis of Cloud Storage and Key Management Tech...

引用

International Conference on Circuit, Power and Computing Technologies (ICCPCT)

作者： I. Sivaprasad Manivannan A. Andrew Roobert N. Muthukumaran Department of Computer Science and Engineering Rohini College of Engineering and Technology Tamil Nadu India Department of Electronics and Communication Engineering Francis Xavier Engineering College Tirunelveli India Department of Electronics and Communication Engineering Centre for Computational Imaging and Machine Vision Sri Eshwar College of Engineering Coimbatore Tamil Nadu India

ISBN: (数字)9798350372816

ISBN: (纸本)9798350372823

The Internet of Things (IoT) technology has revolutionized smart grid settings, enhancing efficiency and enabling advanced data analytics. However, the integration of IoT devices within smart grids introduces significant challenges related to data storage and security. This survey provides a comprehensive review of the various classifiers and optimization algorithms employed to enhance cloud storage solutions and key management systems within smart grid environments. Moreover, it symmetrically examines different classifiers, like Machine Learning (ML) and Deep Learning (DL) methods, which are designed for managing cryptographic keys, focusing on their ability to secure communications, authenticate devices, and ensure data integrity in the presence of cyber threats. Additionally, it categorizes and evaluates a wide range of optimization methods, including evolutionary algorithms, particle swarm optimization (PSO), gray wolf optimization (GWO) and firefly algorithm (FFA) based techniques for optimizing the classifiers, highlighting their applicability in optimizing storage capacities, data retrieval speeds, and cost-effectiveness. By synthesizing recent advancements and comparing the efficacy of these techniques, the survey identifies the best individuals and emerging trends that promise to strengthen the resilience and efficiency of IoT-enabled smart grids. The findings promote the critical role of integrated classifiers and optimization techniques in achieving scalable, secure, and reliable smart grid infrastructures.

关键词： Surveys Cloud computing Reviews Memory Market research Smart grids Classification algorithms

来源：评论

学校读者我要写书评

暂无评论

Smart Helmet and Bike Tracking System

Smart Helmet and Bike Tracking System

引用

Power, Instrumentation, Energy and Control (PIECON), International Conference on

作者： Smriti Vikas Tiwari Richa Srivastava Ms. Swati Sharma Department of Electronics And Communication Engineering KIET Group of Institutions Ghaziabad India Department of Computer Science And Engineering KIET Group of Institutions Ghaziabad India

India is a country that is going to become the most populated country in the world in the coming years. It has a large population of youth. Today’s youth enjoy riding bikes and often disregard safety precautions such as wearing a helmet. Because of these, two-wheelers accidents are increasing day by day, which causes deaths and several types of serious injuries. Significant causes of death are head injuries, which can be prevented by wearing a helmet and taking proper safety precautions. One can also see that drinking and driving have also increased, leading to road accidents. Overspeeding is also one of the major factors. The increasing rate of road accidents made us develop a smart helmet using the internet of things, which reduces accidents and the risk of death. It has a feature where the bike starts only if the rider wears a helmet. If the rider is over-drunk or not wearing the helmet, the ignition will automatically switch off. If any accident occurs, the GSM modem and the GPS modem will send the message to the registered contact number by using a SIM card. In addition, if the bike or helmet is stolen, the owner can easily find out the exact location of the bike and the helmet using this device. This feature is necessary for a country like India, where bike theft cases are frequent and high.

关键词： Head Road accidents Instruments Sociology Switches Modems Safety

来源：评论

学校读者我要写书评

暂无评论

WiLiConnect: A Novel CSI Sharing Technique in Hybrid WiFi/LiFi Networks

WiLiConnect: A Novel CSI Sharing Technique in Hybrid WiFi/Li...

引用

IEEE Conference on Vehicular Technology (VTC)

作者： Saswati Paramita Arani Bhattacharya Vivek Ashok Bohara Anand Srivastava Department of Electronics and Communication Engineering Wirocomm Research Group Department of Computer Science and Engineering Indraprastha Institute of Information Technology (IIIT) Delhi New Delhi India

ISBN: (数字)9798350387414

ISBN: (纸本)9798350387421

In recent years, LiFi has become increasingly pop-ular as an indoor communication technology that utilizes the unlicensed visible light and infra-red spectrum to transmit data. A major challenge of utilizing LiFi is that its area of coverage is limited. Thus, a large number of LiFi access points (APs) is often complemented by deploying a WiFi AP to form a hybrid WiFilLiFi network. However, such deployment does not lead to any additional improvement in the performance of WiFi or LiFi APs. Recent WiFi APs are known to have high overhead due to the requirement of channel state information (CSI), which is essential for utilizing spatial multiplexing. Thus, in this work, we propose a system called WiLiConnect (WiFi-LiFi Connectivity with CSI), which communicates the CSI requirement of the WiFi channel through the LiFi APs, thereby reducing the overhead of WiFi APs. We formulate this problem of load-balancing the overhead of CSI sharing across the LiFi APs, and show that the general problem is NP-Hard. We then propose a round-robin algorithm to solve a special case of the problem, where all the users are assumed to have a single antenna. We further utilize extensive simulation to show that WiLiConnect significantly reduces the overhead of sending CSI. Specifically, WiLiConnect incurs only 0.06% overhead on a WiFi AP having 8 antennas on the total sum rate.

关键词： Vehicular and wireless technologies Indoor communication Transmitting antennas Bandwidth Light fidelity Antenna feeds Space division multiplexing

来源：评论

学校读者我要写书评

暂无评论

Accuracy and Performance of Heart Failure Prediction System by Using Backpropagation Network (BPN) 1

引用

International Conference on Modern electronics Devices and communication Systems, MEDCOM 2021

作者： Singh, Pawan Kumar Yadav, Piyush Sharma, Pankaj Singh, Virendra Pal Kumar, Durgesh Department of Computer Science and Engineering G. L. Bajaj Institute of Technology and Management Greater Noida India Department of Electronics and Communication Engineering G. L. Bajaj Institute of Technology and Management Greater Noida India Department of Computer Science and Engineering Ajay Kumar Garg Engineering College Ghaziabad India Department of Information Technology Ajay Kumar Garg Engineering College Ghaziabad India Department of Computer Science and Engineering GNIOT Group of Institutions Greater Noida India

ISBN: (数字)9789811963834

ISBN: (纸本)9789811963827

Heart failure is a dangerous and highly prevalent disease (about 2% in the adult population in developed countries, and more than 8% in patients older than 75 years). Roughly 3–5% of hospital admissions are related to accidents involving heart disease. In their clinical career, heart disease is the first reason for healthcare practitioners to join. The expenditure in the developing world amounts to up to 2% of all health costs. To build an efficient disease management plan, it is necessary to analyze vast quantities of data, diagnose disease early, and to anticipate adverse effects early on. This would prevent the development of the illness, increase patients’ quality of life, and lower hospital costs. Artificial intelligence and machine learning methods have been used in this way. This paper aims to present state-of-the-art methodologies for learning machines used for assessing cardiovascular failure, including the following: Naïve Bayes, REPTree, AdaBoost, logistical regression, J48, and the support vector machines. We trained and test above model on WEKA tool, and it has been observed that artificial neural network model (ANN) like backpropagation network is best model to predict and provide good accuracy and performance of the heart failure patients. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Adaptive boosting

来源：评论

学校读者我要写书评

暂无评论

Applying Artificial Bee Colony Algorithm to Improve UWSNs communication

Applying Artificial Bee Colony Algorithm to Improve UWSNs Co...

引用

2024 IEEE International Conference on communication, Computing and Signal Processing, IICCCS 2024

作者： Habelalmateen, Mohammed I. Kaur, Amandeep Tiwari, Annapurnanand Shalini, M. Victor, Melvin Kumar, Neelam Sanjeev The Islamic University College of Technical Engineering Department of Computers Techniques Engineering Najaf Iraq The Islamic University of Al Diwaniyah College of Technical Engineering Department of Computers Techniques Engineering Al Diwaniyah Iraq Chandigarh Group of Colleges Chandigarh Engineering College Department of Computer Science Engineering Punjab Mohali India Ies College of Technology Department of Electronics & Communication Engineering M.P. Bhopal India Prince Shri Venkateshwara Padmavathy Engineering College Chennai India School of Business and Management India Srm Institute of Science & Technology Department of Computer Science & Engineering Chennai26 India

ISBN: (纸本)9798350390759

The research in this study aims at implementing the ABC algorithm to enhance the communication within UWSNs. The ABC algorithm, motivated by the CPG approach being analogous to that of honey bees searching for food, specifies optimal values for critical parameters of the network such as energy consumption, reliability in data transfer, and scalability. From the analyses conducted in this exposition, it is apparent that the envisaged methodology outperforms other conventional routing parlances in the following ways: minimal energy usage, high data delivery ratios, low packet drops, and longest network lifetime. Therefore, from the above results it can be concluded that, the said ABC algorithm is helping in achieving a better result in terms of improved underwater communication as well as in mitigating with the difficulties of UWSNs. © 2024 IEEE.

关键词： Interpolation

来源：评论

学校读者我要写书评

暂无评论

Cloud Computing Improved Clustering using Intrusion Detection

Cloud Computing Improved Clustering using Intrusion Detectio...

引用

2023 International Conference in Advances in Power, Signal, and Information Technology, APSIT 2023

作者： Bansal, Saloni Singh, Amandeep Bijlwan, Sheela Goyal, Bhawna Dogra, Ayush Lepcha, Dawa Chyophel GLA University Department of Electronics and Communication Engineering Mathura India Gulzar Group of Institutions Computer Science and Engineering Punjab Ludhiana India Uttaranchal Institute of Technology Uttaranchal University Computing Sciences Dehradun248007 India University Center for Research and Development Chandigarh University Punjab Mohali India Chitkara University Institute of Engineering and Technology Chitkara University Punjab India Chandigarh University Department of Electronics and Communication Engineering Punjab Mohali India

ISBN: (纸本)9798350339369

It is one of the more difficult tasks and calls for highly skilled specialists to deal with the aspects and systems of action of intruders and then unauthorized users who attempt to restrict the data with the computer network. The development of the computer network, the number of intruders, and then the infiltration are all possible effects of incorporating cloud computing. Generally speaking, the updating that comes from properly managed vocations is wasted through its count above the time and it rises before it manifests with the technique. There are many unthinkable state gaps for spotting invasions, and then the numerous communications are what matter most. In order to achieve infiltration through the capture of many capability systems (maximum and less expensive tasking), the usage of advanced detection with the new then the discovering systems is utilized with many than the previous in the cloud. The network warning identification and variation systems based on machine learning, which is a demanding warning identification technology, were separately examined in research and development with research precision. Where there is still room for improvement, the work detailed here elaborates on the forest by choosing its merits and then uses an improved density-based spatial clustering of applications with noise (DBSCAN) through grouping and then the intrusion identification with the cloud environment to remove these flaws. © 2023 IEEE.

关键词： Cloud computing

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：