检索结果-内蒙古大学图书馆

Communication, Computing and Signal Processing (IICCCS), IEEE International Conference on

作者： myasar mundher Adnan N.maheshKumar Praveena J Deepak Patidar Aarju Ambika Department of Computers Techniques Engineering College of Technical Engineering The Islamic University Najaf Iraq Department of Computers Techniques Engineering College of Technical Engineering The Islamic University of Al Diwaniyah Al Diwaniyah Iraq Department of Science and Humanities Faculty of Engineering Karpagam Academy of Higher Education Coimbatore Tamilnadu Prince Shri Venkateshwara Padmavathy Engineering College Chennai Department of Electronics & Communication Engineering IES College of Technology Bhopal M.P. India Department of Computer Science Engineering Chandigarh Engineering College Chandigarh Group of Colleges Mohali Punjab India Dapartment of CSE Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai India

ISBN: (数字)9798350390759

ISBN: (纸本)9798350390766

The aim of this research therefore is to propose and design bio-inspired routing protocols in UWSNs using PSO. High latency and low bandwidth, coupled with high error rates, make underwater routing a different ball game than routing in normal situations and traditional mediums. The proposed PSO-based protocols also consider factors like power utilization, coverage distance, and priority of data packets to make better routing choices thus helping to improve the efficiency and responsiveness of the UWSNs. The compare analysis of the proposed protocols with the earlier protocols, which are also developed based on AODV and DSR, proves high performance of the PSO based protocols in the energy consumption, data delivery ratio, end to end delay and the network lifetime within all the realistic underwater environments analyzed by the simulations. Such advancement would help to improve the communication system in UWSNs, presenting new approaches for efficient communication in the underwater environment.

关键词： Wireless communication Wireless sensor networks Underwater communication Signal processing algorithms Signal processing Routing Routing protocols Delays Telecommunication computing Reliability

来源：评论

学校读者我要写书评

暂无评论

Clustered Scheduling and Communication Pipelining For Efficient Resource management Of Wireless Federated Learning

arXiv

引用

arXiv 2022年

作者： Keçeci, Cihat Shaqfeh, mohammad Al-Qahtani, Fawaz Ismail, muhammad Serpedin, Erchin the Department of Electrical and Computer Engineering Texas A&M University College StationTX77843 United States the Department of Electrical and Computer Engineering Texas A&M University at Qatar Doha Qatar Qatar Foundation Research Development and Innovation RDI Doha Qatar the Department of Computer Science Tennessee Tech University CookevilleTN38505 United States

This paper proposes using communication pipelining to enhance the wireless spectrum utilization efficiency and convergence speed of federated learning in mobile edge computing applications. Due to limited wireless sub-channels, a subset of the total clients is scheduled in each iteration of federated learning algorithms. On the other hand, the scheduled clients wait for the slowest client to finish its computation. We propose to first cluster the clients based on the time they need per iteration to compute the local gradients of the federated learning model. Then, we schedule a mixture of clients from all clusters to send their local updates in a pipelined manner. In this way, instead of just waiting for the slower clients to finish their computation, more clients can participate in each iteration. While the time duration of a single iteration does not change, the proposed method can significantly reduce the number of required iterations to achieve a target accuracy. We provide a generic formulation for optimal client clustering under different settings, and we analytically derive an efficient algorithm for obtaining the optimal solution. We also provide numerical results to demonstrate the gains of the proposed method for different datasets and deep learning architectures. Copyright © 2022, The Authors. All rights reserved.

关键词： Scheduling

来源：评论

学校读者我要写书评

暂无评论

Advancements and Applications of Li-Fi technology: an In-Depth Exploration

Advancements and Applications of Li-Fi Technology: an In-Dep...

引用

Communication, Computing and Energy Efficient technologies (I3CEET), International Conference on

作者： V.Saravanan K.Niranjana Talluri Upender Chidambaranathan C. m Balamurugan Annamalai Jayanthi S Department of Nano Electronics Materials and Sensors Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai Tamilnadu India Department of Saveetha School of Law Saveetha Institute of Medical and Technical Science Department of CSE CMR College of Engineering and Technology Hyderabad Telangana Department of Computer Science and Engineering School of Computing Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai India Department of EEE Shree Sathyam College of Engineering and Technology Department of ECE R.M.D Engineering College Chennai Tamilnadu India

ISBN: (数字)9798331541583

ISBN: (纸本)9798331541590

The evolution of Li-Fi technology has been marked by milestones such as the pioneering work of Harald Haas, who coined the term "Li-Fi" and demonstrated its feasibility in 2011. Since then, research and development efforts have focused on optimizing transmission speeds, expanding coverage, and integrating Li-Fi with existing wireless networks to create seamless hybrid systems. Li-Fi holds promise in enhancing connectivity for the Internet of Things (IoT). By leveraging existing infrastructure of LED lighting, Li-Fi can facilitate seamless communication among IoT devices, contributing to the realization of smart cities and interconnected smart environments. Recent research has also explored Li-Fi's potential in specialized domains such as healthcare, where secure and high-speed data transmission is critical for medical imaging and patient monitoring applications. moreover, Li-Fi's integration with emerging technologies like LiDAR (Light Detection and Ranging) promises to revolutionize autonomous vehicle navigation and communication. Despite its numerous advantages, Li-Fi faces challenges such as limited range compared to Wi-Fi and susceptibility to obstacles that can block light signals. Overcoming these challenges requires continued innovation in signal processing, light modulation techniques, and infrastructure development. By elucidating these aspects, it seeks to contribute to the understanding and advancement of this transformative technology in the realm of wireless communication.

关键词： Smart cities Wireless networks modulation medical services Light fidelity Light emitting diodes Telecommunication computing Internet of Things Wireless fidelity Visible light communication

来源：评论

学校读者我要写书评

暂无评论

Text Localization and Recognition from Natural Scene Images using AI

Text Localization and Recognition from Natural Scene Images ...

引用

Automation, Computing and Renewable Systems (ICACRS), International Conference on

作者： D. Shekar Goud m Vigneshwari P Aparna G Vijayasekaran Ajay Singh Yadav Ashok Kumar Department of Electronics and Communication Engineering Ellenki College of Engineering and Technology Patelguda Telangana India Department of Information Technology Vel Tech Multi Tech Dr. Rangarajan Dr. Sakunthala Engineering College Chennai Tamil Nadu India Department of Computer Science Engineering R. M. K. College of Engineering and Technology Thiruvallur Tamil Nadu India Department of Computer Science and Engineering Sir Issac Newton College of Engineering and Technology Nagapattinam Tamil Nadu India Department of Mathematics SRM Institute of Science and Technology Ghaziabad Utter Pradesh India Department of Computer Science Banasthali Vidyapith Rajasthan India

ISBN: (纸本)9781665460859

In computer vision systems, text detection and recognition (TDR) in natural scene images can be used for things like license plate recognition, automated street sign interpretation, and assisting blind people. Accordingly, finding text within an image is a time-based challenge in the field of computer vision. Because of factors like cluttered backgrounds, image blurring, partially obscured text, various fonts, noise, and fluctuating lighting, text identification in natural scenes has become a significant task with the increase in the use of actual vision systems. Images and videos with accompanying textual data can be leveraged for automatic annotation. This study provides a system for automatically identifying the text from images, and it discusses the methodology behind locating and recognizing text in images of natural scenes. This article handles the scene text recognition challenge from start to finish, breaking it down into text localization and recognition. The maximally Stable Extremal Regions (mSER) technique is used to detect text and non-text regions in images for localization purposes. Convolutional Neural Networks (CNNs) and convolutional recurrent neural networks (CRNNs) are utilized for text recognition. By evaluating the accuracy, precision, and F1 score, the CRNN is determined to be the best.

关键词： Location awareness measurement computer vision Image recognition Text recognition Speech recognition Blindness

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning Driven Smart Charging Algorithms to Enhance Battery Lifespan and Grid Sustainability

Reinforcement Learning Driven Smart Charging Algorithms to E...

引用

Advances in modern Age technologies for Health and engineering science (AmATHE), International Conference on

作者： S. Sivakumar mali Ram Yadav A. Bharathi D Akila Dineshkumar P V. Banupriya Department of Electrical and Electronics Engineering Vel Tech Rangarajan Dr.Sagunthala R and D Institute of Science and Technology Chennai India Department of Physical Education Lovely Professional University Punjab India Department of Information Technology Vels Institute of Science Technology and Advanced Studies Pallavaram India Department of Computer Applications Saveetha College of Liberal Arts and Sciences SIMATS Chennai India Department of Information Technology Sona College of Technology Salem Tamil Nadu India Department of Computer Science and Business Systems M. Kumarasamy College of Engineering Karur India

ISBN: (数字)9798350371567

ISBN: (纸本)9798350371574

This study investigates the use of RL-driven smart charging algorithms, particularly the Deep Deterministic Policy Gradients (DDPG) model, to maximise grid sustainability and battery lifetime. The current state of this field's study is lacking in real-time adaptation to different settings and in handling the ever-changing nature of charging profiles. By comparison, the suggested approach demonstrates a significant efficiency boost through the use of RL principles, which allow the model to learn and adjust its charging tactics. In specifically, the strategy contributes to a 10% improvement in total grid efficiency while cutting peak demand by 25%, minimising charge-discharge cycles by 20%, and reducing battery degradation rates by 15%. Not only do these measurements show that the suggested method works, but they also show how unique it is in offering a smart charging solution that is both sensitive and adaptive. This research fills in the gaps left by other studies and proposes an optimisation technique that is more dynamic and works in real-time. Its influence on the health of individual batteries and the sustainability of the grid as a whole is noteworthy.

关键词： Degradation Adaptation models Scalability Reinforcement learning Solids Real-time systems Batteries

来源：评论

学校读者我要写书评

暂无评论

Synchronized Optimization of Smart Home Appliance Scheduling and Cost-Effective Energy management Using Harris-Hawks Algorithm in Smart Grids

Synchronized Optimization of Smart Home Appliance Scheduling...

引用

technological engineering and its Applications in Sustainable Development (ICTEASD), International Conference for

作者： A. Sundar Raj Saloni Bansal Hassan m. Al-Jawahr T. Blesslin Sheeba m. Sasikumar J.B. Sapaev Balappagari. Indu Priya Biomedical Engineering E.G.S. Pillay Engineering College Nagapattinam Tamil Nadu India Computer Engineering and Applications GLA University Mathura India The Islamic University Najaf Iraq Electronics and Communication Engineering R.M.K. Engineering College Kavaraipettai India Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai Tamil Nadu India Tashkent Institute of Irrigation and Agricultural Mechanization Engineers National Research University Tashkent Azerbaijan GRIET Hyderabad Telangana India

ISBN: (数字)9798350336474

ISBN: (纸本)9798350336481

This work utilizes the Harris Hawks Optimization Algorithm (HHOA) to optimize Smart Home Appliance scheduling and construct an independent smart grid. The aim is to showcase that the HHOA is used to create smart grids that are both cost-effective and dependable. A smart grid has been constructed explicitly for the Ankara Gazi University technology Park structure. The structure's energy use and weather data have been observed and documented over a year. The suggested smart grid configuration incorporates Photovoltaics (PV), Wind Turbines (WT), Battery Energy Storing Systems (BESS), and Diesel Generators (DG), according to the available data. Determining these components' optimal capacity is essential to accomplish the desired goals of cost-effectiveness and dependability while maintaining full autonomous capabilities. Random evaluations without scheduling optimization lead to oversizing, increasing investment, functioning, and repair expenses. Inadequate capacity scheduling resulting from hasty judgments leads to difficulties in ensuring an uninterrupted energy supply. Hence, optimizing the schedule is crucial for the design of a smart grid to be efficient. After resolving the scheduling issue using the HHOA method, the outcomes are used to develop the suggested smart grid. The mATLAB modeling of the planned smart grid has shown a good performance, resulting in savings varying from 1.28% to 19.53% in the Total Net Present Cost (TNPC) value compared to alternative methods.

关键词： Photovoltaic systems Home appliances Schedules Smart homes Scheduling Smart grids Wind turbines

来源：评论

学校读者我要写书评

暂无评论

HNCS: A Robust Development of Deep Learning Based Potato Plant Disease Identification Using Hybrid Neural Classification Strategy

HNCS: A Robust Development of Deep Learning Based Potato Pla...

引用

Innovation in technology (ASIANCON), Asian Conference on

作者： L. Priyadharshini P Kalaiselvi S. Sujatha Uma maheswari S Vijay Anand Kandaswamy R. Suganthi Department of Saveetha School of Law Saveetha Institute of Medical and Technical Science Chennai Tamil Nadu India Department of Computer Science and Engineering Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology Chennai Tamil Nadu India Department of EEE Sri Sairam College of Engineering Bangalore Karnataka India Department of Biosciences Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai Tamil Nadu India Department of Electronics and Communication Engineering R.M.K. Engineering College Chennai Tamil Nadu India Department of Electronics and Communication Engineering Panimalar Engineering College Poonamallee Chennai Tamil Nadu India

ISBN: (数字)9798350354218

ISBN: (纸本)9798350354225

In recent decades, potato farming has exploded in popularity across India. On the other hand, diseases such as early stages of blight and later blight are making the production of potatoes more challenging and consequently more expensive. The goal here is to digitalize the system and automate the process of disease identification in potatoes so that production can grow. Our proposed algorithm, Hybrid Neural Classification Strategy (HNCS), will be cross-validated with an existing learning algorithm, Convolutional Neural Network (CNN), to assess the efficacy of the proposed scheme in diagnosing potato disease using leaf pictures. This article provides a picture of how automated systems based on processing and deep learning may identify and categorize illnesses affecting potato leaves. Image processing is the most effective method for identifying and studying these disorders. Over 4500 images of diseased potato leaves were used for this research; the images came from the plant town database, an open-source dataset on the Kaggle website, and a few pre-built models were used for recognition and characterization. The program's result demonstrates that deep learning outperforms all current tasks in potato disease detection, and it makes predictions with an accuracy of 98.73%.

关键词： Deep learning Hands technological innovation Plant diseases Accuracy Image recognition Production Classification algorithms Convolutional neural networks Diseases

来源：评论

学校读者我要写书评

暂无评论

A Novel Framework for Efficient Handover mechanism in D2D Communication Using Networking Principles

A Novel Framework for Efficient Handover Mechanism in D2D Co...

引用

Smart Electronics and Communication (ICOSEC), International Conference on

作者： Jayanthi S mandapati Raja Beulah Jackson S. Jayasree A. Nithya Jeneetha Jebanazer J Department of Electronics and Communication Engineering R. M. D Engineering College Chennai Tamil Nadu India Department of Electronics and Communication Engineering CMR Engineering College Telangana India Department of Electronics and Communication Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai Tamil Nadu India Department of Chemistry Prince Shri Venkateshwara Padmavathy Engineering College Tamil Nadu India Department of Computer Science and Engineering R. M. K College of Engineering and Technology Chennai Tamil Nadu India Department of ECE Panimalar Engineering College Chennai Tamilnadu India

Software Defined Networking (SDN) technology utilizes software to manage and alter the current networks to improve the networking and interfacing capabilities. It does this by providing a split between the control plane and the data plane. On the SDN controller, each function is run as an application. This paper suggests a structure made up of a unified RAN and an SDN-based core network. For mobile terminals to access the services of the network operator, as well as the Internet and other cloud-based apps, all radio access points in the RAN are connected with the aid of OpenFlow interfaces. Decentralized Content Delivery Networks (CDN) manage mobility without requiring data to pass via the core network, which minimizes signaling. To gauge the signaling burden, traffic steering between the framework's different entities is examined. The suggested work establishes criteria based on a combination of fundamental factors, such as Signal Strength, Distance, and Speed, to assure service continuity of mobile nodes in heterogeneous networks. The parametric analysis of the handover is contrasted with that of the current designs. The suggested framework also provides ProSe capability for a select number of desirable mobile devices in the network and is configured for D2D connection.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Investigation of a Novel Triangle-Shaped Sierpinski microstrip Patch Antenna for Implantable Biomedical Applications

An Investigation of a Novel Triangle-Shaped Sierpinski Micro...

引用

International conference of Electronics, Communication and Aerospace technology (ICECA)

作者： Sengottaiyan N m. Sathesh Ravikumar Gurusamy m Brindha P Kalyanasundaram m Rajasekar Computer Science Faculty of Science and Technology Alliance College of Engineering and Design Alliance University Anekal Karnataka Department of ECE Vel Tech Rangarajan Dr. Sagunthala Rand D Institute of Science and Technology Avadi Chennai Tamilnadu Department of ECE M.P.Nachimuthu M.Jaganathan Engineering college Tamilnadu Erode Department of BME K S R Institute for Engineering and Technology Tiruchengode Tamilnadu Department of IT K S R Institute for Engineering and Technology Tiruchengode Tamilnadu Institute of CSE SIMATS School of Engineering Saveetha Institute for Medical and Technical Sciences Chennai Tamilnadu

This research study's objective is to develop a unique, high gain triangle-shaped Sierpinski fractal antenna utilizing a FR4 epoxy substrate at frequencies between 1.0 GHz and 3.0 GHz, and to evaluate its performance in comparison to a square-shaped microstrip patch antenna (mPA). There are 2 groups in this study. Group 1 refers to the triangle-shaped Sierpinski fractal antenna with 26 samples and Group 2 refers to square shaped microstrip patch antenna with 26 samples. The confidence interval is 95%, the threshold is 0.05%, and the G Power value is 80%. The observed gain from the novel triangle-shaped Sierpinski fractal antenna has 27.3709 dB to 68.6663 dB and the gain of the square shaped mP A have -21.0381 dB to - 0.1775 dB. The novel triangle-shaped Sierpinski fractal antenna's best frequency for maximum gain was 1.5 GHz, with a significance level of around 0.000423 (p 0.05). In this work, it is observed that the gain of novel triangle-shaped Sierpinski fractal antenna is significantly better than square shaped microstrip patch antenna for implantable biomedical applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Android malware detection amid COVID-19 9

Android malware detection amid COVID-19

引用

9th International Conference on System modeling and Advancement in Research Trends, SmART 2020

作者： Srivastava, Rohit mishra, R.P. Kumar, Vivek Shukla, Himanshu Kumar Goyal, Neha Singh, Chandrabhan Computer Science and Engineering F.O.E.T. University Lucknow India Electronics and Communication Dr R.M.L. Awadh University Ayodhya India Computer Science and Engineering Teerthanker Mahaveer University Moradabad India Computer Science and Engineering K.M. C. Language University Lucknow India Computer Science and Engineering B.N. College of Engg. and Tech. Lucknow India

ISBN: (纸本)9781728189086

mobile is a rapidly growing web environment that attracts malware developers around the world. Smart phones, especially android phones are widely used and are the most popular new target for malware attacks. most common type of malware found to attack android users was an unauthorized app repackaged as a normal app through a third party, unofficial app store. New apps found in the app store are hard to identify as malicious. Our work develops a malware detector and analyzer. This paper also links insights about malware attacks in COVID-19 on mobile devices. To meet the objectives, a model is implemented that extracts the inherent features of android application file and analyzes them for quick and accurate analysis. The model classifies the apps more accurately as benign or malicious. © 2020 IEEE.

关键词： COVID-19

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：