检索结果-内蒙古大学图书馆

Electrical, Electronics, Information and Communication Technologies (ICEEICT), International Conference on

作者： Seethalakshmi K Bhagyalakshmi A G Anitha S. Priyadarshini Pavithra Department of Computer Science & Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai Tamil Nadu India Department of Computer Science and Business Systems S.A Engineering College Chennai Tamil Nadu India Department of Information & Technology St Peter's Institute of Higher Education and Research Chennai Tamil Nadu India

ISBN: (数字)9798350369083

ISBN: (纸本)9798350369090

Crop like cassava plays a crucial role in regions facing food insecurity, serving as a primary food source. However, the susceptibility of cassava to various diseases poses a significant threat to crop yields and livelihoods. In this methodology, the input images undergoes a series of preprocessing steps initially. Scaling and Gaussian smoothing filters are applied to cancel out noise. After preprocessing, the images are subjected to segmentation using the UNet architecture to remove background. Next, feature extraction is conducted utilizing Convolutional Neural Networks (CNNs) to capture relevant features. After future extraction, a dense network is used for classification, facilitating the identification of affected images. With cassava root dataset images, the system achieves an impressive accuracy rate of 99.25%, outperforming existing methods. This advancement not only aids in safeguarding cassava production but also holds promise for the cassava production and export industries by providing an efficient means of detecting diseased crops, thus enabling prompt action to mitigate losses and ensure food security. Additionally, the ease of disease detection offered by the proposed system facilitates quality control in cassava production and enhances the competitiveness of cassava exports in the global market.

关键词： Industries Accuracy Smoothing methods Food security Production Feature extraction Convolutional neural networks Crop yield Viruses (medical) Diseases

来源：评论

学校读者我要写书评

暂无评论

Towards Faster Graph Partitioning via Pre-training and Inductive Inference

arXiv

引用

arXiv 2024年

作者： Qin, Meng Zhang, Chaorui Gao, Yu Ding, Yibin Jiang, Weipeng Zhang, Weixi Han, Wei Bai, Bo Department of Computer Science & Engineering The Hong Kong University of Science & Technology Hong Kong Theory Lab Central Research Institute 2012 Labs Huawei Technologies Co. Ltd. China

Graph partitioning (GP) is a classic problem that divides the node set of a graph into densely-connected blocks. Following the IEEE HPEC Graph Challenge and recent advances in pre-training techniques (e.g., large-language models), we propose PR-GPT (Pre-trained & Refined Graph ParTitioning) based on a novel pre-training & refinement paradigm. We first conduct the offline pre-training of a deep graph learning (DGL) model on small synthetic graphs with various topology properties. By using the inductive inference of DGL, one can directly generalize the pre-trained model (with frozen model parameters) to large graphs and derive feasible GP results. We also use the derived partition as a good initialization of an efficient GP method (e.g., InfoMap) to further refine the quality of partitioning. In this setting, the online generalization and refinement of PR-GPT can not only benefit from the transfer ability regarding quality but also ensure high inference efficiency without re-training. Based on a mechanism of reducing the scale of a graph to be processed by the refinement method, PR-GPT also has the potential to support streaming GP. Experiments on the Graph Challenge benchmark demonstrate that PR-GPT can ensure faster GP on large-scale graphs without significant quality degradation, compared with running a refinement method from scratch. We will make our code public at https://***/KuroginQin/PRGPT. Copyright © 2024, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Wireless Sensor Network using Control Communication and Monitoring of Smart Grid 2

Wireless Sensor Network using Control Communication and Moni...

引用

2nd International Conference on Advance Computing and Innovative Technologies in engineering, ICACITE 2022

作者： Kumar, T. C. H. Anil Dixit, Ganesh Kumar Singh, Rajesh Narukullapati, Bharath Kumar Chakravarthi, M. Kalyan Gangodkar, Durgaprasad Vignan's Foundation for Science Technology and Research Department of Mechanical Engineering Andhra Pradesh Guntur Dt. India Department of Engg. & Tech MP Bhopal India Uttaranchal University Uttaranchal Institute of Technology India Vignan's Foundation for Science Technology and Research Department of Electrical and Electronics Engineering Guntur India VIT-AP University School of Electronics Engineering Amaravathi India Graphic Era Deemed to Be University Department of Computer Science & Engineering Uttarakhand Dehradun248002 India

ISBN: (纸本)9781665437899

For some countries around the world, meeting demand is a serious concern. Power supply market is increasingly increasing, posing a big challenge for various countries throughout the world. The increasing expansion in the market for power needs upgrading system dependability to increase the smart grid's resilience. This smart electric grid has a sensor that analyses grid power availability and sends regular updates to the organisation. The internet is currently being utilized to monitor processes and place orders for running variables from faraway places. A large number of scanners have been used to activate electrical equipment for domestic robotics for a long period in the last several days. Conversely, if it is not correctly implemented, it will have a negative impact on cost-effectiveness as well as productivity. For something like a long time, home automation has relied on a large number of sensor nodes to control electrical equipment. Since there are so many detectors, this isn't cost-effective. In this article, develop and accept a wireless communication component and a management system suitable for managing independent efficient network units from voltage rises and voltage control technologies in simultaneous analyzing system reliability in this study. This research paper has considered secondary method to collect relevant and in-depth data related to the wireless sensor network and its usage in smart grid monitoring. © 2022 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

IntSHU: A Security-Enabled Intelligent Soft Handover Approach for UAV-Aided 5G and Beyond

引用

IEEE Transactions on Cognitive Communications and Networking 2025年

作者： Karmakar, Raja Kaddoum, Georges Akhrif, Ouassima Heritage Institute of Technology Department of Computer Science and Engineering IoT and Cyber Security including Blockchain Technology Kolkata700107 India University of Quebec Department of Electrical Engineering ETS Montreal Canada Lebanese American University Cyber Security Systems and Applied AI Research Center Beirut Lebanon

Unmanned aerial vehicles (UAVs) play a significant role in serving as gNodeBs (gNBs), or user devices (UDs). However, considering the high data rates and low latency required by fifth generation (5G) and beyond, it is essential to maintain a reliable connection at UAVs, particularly due to frequent handovers. To minimize handover failures, the hysteresis margin and time-to-trigger (TTT) should be dynamically adjusted. Furthermore, to prevent vulnerabilities to threats, UAV and gNB authentication and secure communication should be addressed during handovers. However, available literature uses a learning-based approach to handover management in UAV-aided 5G networks, thereby neglecting security, or offers a handover authentication mechanism, but lacks a novel handover strategy. To fill this gap in the literature, in this study, we design an Intelligent Soft Handover for UAV-enabled cellular networks (IntSHU), a generative adversarial network (GAN)-based scheme designed for intelligent soft handovers in UAV-enabled 5G and beyond. IntSHU uses adapted hysteresis margins and TTT values, dynamically generated through an -greedy policy. In addition, we implement a lightweight, physically unclonable function (PUF)-based message encryption and authentication scheme via blockchain for streamlined access control during handovers. The results of our simulation indicate that IntSHU significantly enhances network performance by facilitating reliable soft handovers. © 2015 IEEE.

关键词： 5G mobile communication systems

来源：评论

学校读者我要写书评

暂无评论

Efficient Detection of DDoS Attacks in E-Government Clouds Using Sparse Neural Networks 4

Efficient Detection of DDoS Attacks in E-Government Clouds U...

引用

4th IEEE International Conference on ICT in Business Industry and Government, ICTBIG 2024

作者： Bixapathi, A. Ali, H. Mohammed Maranan, R. Sudhakar, A.V.V. Beschi, I.S. Ramya, M. T.S Medchal district501301 India Srm Institute of Science and Technology Department Mechanical Engineering Ramapuram Campus Chennai89 India Simats Saveetha School of Engineering Department of Research and Innovation Tamil Nadu Chennai602105 India Sr University Department of Electrical and Electronics Engineering Telangana Warangal506371 India Department of Computer Applications Kovur Chennai India Lovely Professional University Division of Research and Development Jalandhar - Delhi G.T.Road Punjab Jalandhar144411 India

ISBN: (纸本)9798331518981

E-government (Electronic Government) refers to the use of information and communication technology (ICT) by governmental bodies to provide public services, manage government operations, and facilitate communication with citizens, businesses, and other government entities. E-government platforms have expanded significantly in recent years, offering a range of services such as online tax filing, license renewals, healthcare services, and more. These services, often hosted on cloud-based infrastructures, benefit from improved scalability, efficiency, and accessibility through the use of cloud computing technologies. However, the growing volume of legitimate traffic from a diverse range of users on e-government platforms makes distinguishing between normal and malicious traffic, such as DDoS (Distributed Denial of Service) attacks, increasingly difficult. To address this challenge, this manuscript proposes the use of Sparse Neural Networks (SNN) for DDoS attack detection in cloud-based e-government systems. Initially, data from the CSE-CIC-IDS2018 dataset is collected and processed through a feature selection phase. The selected features are selected using the Energy Valley Optimizer. These optimized features are fed into the Sparse Neural Network, which categorizes traffic as benign, DDoS, or DoS. To further enhance the accuracy of DDoS detection, the Ladybug Beetle Optimization (LBOA) is employed to optimize the Sparse Neural Network's parameters, ensuring optimal performance in classifying attacks. This approach aims to safeguard cloud-based e-government systems from cyber threats while maintaining reliable public service delivery. In comparison to current methods such as data clustering for the detection of DDoS attacks in the cloud for e-government (DBSCAN), e-government impact factor analysis cleverly using enhanced machine learning (ML-EGOV), and Problems with Machine Learning in Cloud Computing E-Government Models in Developing Nations, the proposed DCNN-QSA-PDO

关键词： Cloud platforms

来源：评论

学校读者我要写书评

暂无评论

Uncertainty-Aware Deep Learning for Segmenting Ultrasound Images of Breast Tumours

Uncertainty-Aware Deep Learning for Segmenting Ultrasound Im...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Afsana Ahmed Munia Ibrahim Hossain Seyed Mohammad Jalali Pegah Tabarisaadi Ashikur Rahman Saeid Nahavandi Institute for Intelligent Systems Research and Innovation Deakin University VIC Australia Dept. of Computer Science and Engineering Bangladesh University of Engineering and Technology Dhaka Bangladesh

Precise image segmentation is one of the dominant factors in disease diagnosis. A typical application is the segmentation of breast ultrasound images, allowing radiologists to suggest what to do next. After emerging deep learning technology especially convolutional neural networks (CNNs), the image segmentation model achieved state-of-the-art performance in various medical applications such as cancer detection and classification, lung node segmentation, cell segmentation and so on. However, despite these successes, a big question arises: to what extent is the model certain about the predicted result? Generally, most deep learning models focus on high accuracy but not on uncertainty of predicted results, which is not enough to make a critical real-life decision such as a disease diagnosis, where a wrong decision can be life-threatening. Hence for making a crucial decision, it is essential that the predicted result will provide not only accuracy but also estimate model uncertainty. Our contribution to this research is to build a system that predicts pixel-wise semantic segmentation and provides uncertainty estimation of the predicted results. It is achieved by adding a dropout layer during training and using Monte Carlo dropout in inference. We evaluate our model with the breast ultrasound image dataset (BUSI) and compare the results with a few other state-of-the-art methods where our method outperforms others in terms of IoU.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Novel 3D Object Classification Paradigm through Reconfigurable Intelligent Surfaces

A Novel 3D Object Classification Paradigm through Reconfigur...

引用

IEEE Conference on Standards for Communications and Networking (CSCN)

作者： Stavros Tsimpoukis Dimitrios Tyrovolas George Karagiannidis Sotirios Ioannidis Christos Liaskos Institute of Computer Science – Foundation for Research and Technology Hellas Greece Dept. of Electrical and Computer Engineering Aristotle University of Thessaloniki Greece Dept. of Electrical Engineering Technical University of Crete Greece Dept. of Computer Science and Engineering University of Ioannina Greece

Programmable Wireless Environments (PWEs) leverage Reconfigurable Intelligent Surfaces (RIS) to convert the wireless propagation into a deterministic process. Recently, PWEs have shown promising results in boosting the efficiency of Radio-Frequency (RF) imaging, creating a novel, lightweight object detection and visualization approach for Extended Reality (XR). As a first step towards optimizing the PWE-XR synergy, this work proposes and compares a set of four PWE configuration policies. The goal is to deduce which policy yields the optimal classification of a set of arbitrary 3D objects present within the PWE. The rationale is that the PWE configuration policy that yields optimal object classification, will also yield the best XR quality in subsequent studies. Evaluation results regarding the performance of the proposed policies, based on ray-tracing, are demonstrated and discussed.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Expression of Concern for: Exploring the Use of Machine Learning Techniques for Enhancing Real-Time Data Access

Expression of Concern for: Exploring the Use of Machine Lear...

引用

Smart Generation Computing, Communication and Networking (SMART GENCON), International Conference on

作者： Sourav Rampal Shreenidhi H S Manish Shrivastava Akhilendra Pratap Singh Reena R Santosh D. Kumar Centre of Interdisciplinary Research in Business and Technology Chitkara University Institute of Engineering and technology Chitkara University Punjab India Computer Science and Engineering Faculty of Engineering and Technology JAIN (Deemed-to-be University) Bangalore Karnataka India Department of Computer Science & Engineering Vivekananda Global University Jaipur India Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh India Department of Computer Science and Engineering Prince Shri Venkateshwara Padmavathy Engineering College Chennai Department of Artificial Intelligence & Data Science Vishwakarma Institute of Information Technology Pune INDIA

ISBN: (数字)9798350319125

ISBN: (纸本)9798350319132

Actual-time statistics to date has updated, increasingly vital as the quantity of virtual information maintains updated growth. Effective choice-making depends on the capability to update access and analyze records. Device up-to-date techniques provide the capacity up-to-date enhance actual-time statistics up-to-date by using offering insights from disparate pieces of information. This paper addresses the potential benefits of using a system with date knowledge and updated, up-to-date strategies to broaden extra clever statistics up to date updated systems. It summarizes the contemporary nation of the art and highlights studies in machine learning and up-to-date imaginative and prescient real-time information up-to-date. It additionally discusses present-day challenges and shows viable instructions for future studies. The studies network up-to-date recall how gadgets are up to date know that updated strategies may be used to facilitate real-time get entry updated the maximum precious pieces of facts.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Lookup Parameter Optimization for Kademlia DHT Alternative in IPFS

Lookup Parameter Optimization for Kademlia DHT Alternative i...

引用

IEEE International Symposium on Parallel and Distributed Processing Workshops and Phd Forum (IPDPSW)

作者： Hidehiro Kanemitsu Kenji Kanai Hidenori Nakazato School of Computer Science Tokyo University of Technology Tokyo Japan Waseda Research Institute for Science and Engineering Waseda University Tokyo Japan School of Fundamental Science and Engineering Waseda University Tokyo Japan

Peer-to-peer networks, such as IPFS, adopt the distributed hash table (DHT) to efficiently find contents. In particular, Kademlia, which is used in IPFS, requires parameters regarding the lookup concurrency, the number of next hops, and the k-bucket size. However, such values are manually set and then the configuration is not optimal for minimizing the network latency in any network dynamics. In this paper, we present a method for automatically deriving the optimal lookup parameters for KadRTT, which is a modified version of Kademlia to improve the lookup latency. We derive the optimal values for the k-bucket size, lookup concurrency, and the number of next hops using the lookup message arrival rate, initial ID distance, and lookup iteration count. From the experimental comparisons by both a simulation and an emulation, we show that our proposal contributes to the lookup latency, and overlay hop count.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Cognitive Congestion Alleviation Framework in IoT-Enabled WSN for Next-Gen Intelligent Transport Systems via Optimized Capsule Attention Network

Cognitive Congestion Alleviation Framework in IoT-Enabled WS...

引用

Intelligent Data Communication Technologies and Internet of Things (IDCIoT), International Conference on

作者： R. Mohandas Sudha Y Narmatha P P.Venkata Prasad N. Manikandan Department of Electronics & Communication Engineering Chennai Institute of Technology Chennai Tamil Nadu India Department of Computer Science and Engineering Presidency University Bangalore Karnataka India Department of Computer Science and Engineering Sri Sairam College of Engineering Bangalore Karnataka India Department of Electrical and Electronics Engineering Chaitanya Bharathi Institute of Technology Hyderabad Telangana India Department of Business Administration Kalasalingam Academy of Research and Education Kalasalingam Business School Krishnankoil Viruthunagar India

ISBN: (数字)9798331527549

ISBN: (纸本)9798331527556

The rapid advancement of Intelligent Transportation Systems (ITS) has heightened the importance of reliable, real-time data transmission in Wireless Sensor Networks (WSNs). However, congestion in data-heavy Internet of Things (IoT)-enabled networks remains a critical challenge, impacting communication efficiency and decision-making in ITS. In high-density IoT-ITS applications, traditional congestion control methods are insufficient to address the complexity and dynamics of data flows. Existing solutions often fail to adapt in real time to varying traffic loads, leading to delays and data loss. There is a strong need for a congestion alleviation framework capable of intelligently prioritizing data while dynamically managing network resources to ensure seamless information exchange in large-scale deployments. This study presents a Cognitive Congestion Alleviation Framework in IoT-Enabled WSN for Next-Gen Intelligent Transport Systems via Optimized Capsule Attention Network (V-CapMiAN-Parr), which combines the Vectorized Adaptive Capsule Neural Network (V-AdCapNet) and Multi-instance Attention Network (MAN), fine-tuned by the Parrot Optimizer (ParrOpt). This integration aims to effectively detect, mitigate, and prevent congestion through an advanced capsule-based attention mechanism with adaptive optimization. The suggested V-CapMiAN-Parr framework demonstrated significant improvements in congestion control, achieving data throughput efficiencies above 99.7%, packet delivery rates above 99.5%, and network reliability reaching 99.2% under high traffic loads. The model's adaptive weighting mechanism ensures real-time responsiveness and reliability, crucial for next-gen ITS applications. The V-CapMiAN-Parr framework effectively addresses congestion issues in IoT-enabled WSNs, providing a robust, scalable solution for ITS applications. This cognitive framework's advanced data prioritization and adaptive optimization capabilities are well-suited for enhancing the performanc

关键词： Wireless communication Wireless sensor networks Adaptive systems Transportation Telecommunication traffic Real-time systems Internet of Things Data communication Optimization Next generation networking

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：