检索结果-内蒙古大学图书馆

EGANet: Elevation-guided attention network for scene classification in panchromatic remote sensing images

Neural Computing and Applications 2024年第29期36卷 18251-18264页

作者： Datla, Rajeshreddy Swetha, G. Gayathri, C. Department of Space Akbar Road Tarbund Manovikas Nagar Telangana Secunderabad500009 India Department of Computer Science and Engineering Indian Institute of Technology Hyderabad TelanganaKandi Hyderabad502284 India Department of Computer Science and Engineering Mahindra University TelanganaBahadurpally Hyderabad500043 India

Scene classification in panchromatic (PAN) remote sensing images is a challenging task due to arbitrary spatial arrangement of a variety of objects with complex background in the absence of RGB-channel information. In this paper, we propose an elevation-guided attention network (EGANet) for multimodal scene classification in panchromatic images by leveraging elevation information from digital elevation model (DEM). The proposed network helps to identify the potential regions containing prominent class-specific features in the panchromatic image scene with the attention of elevation features extracted from a convolution neural network (CNN). Then, elevation-guided features in panchromatic image scene are obtained by the correlation of these two modalities for effective scene classification. The efficacy of the proposed method is demonstrated on Cartosat-1 panchromatic remote sensing image datasets with a lot of variations in view-angle, occlusion, background, and illumination conditions. The experimental results show that our proposed EGANet achieves scene classification accuracy with an improvement of 5% in comparison with the state-of-the-art approaches. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

ElectRA-Decentralized Voting Application 9

ElectRA-Decentralized Voting Application

引用

9th International Conference on Smart Computing and Communications, ICSCC 2023

作者： Mohan, Anila Rakhee, M. Muthoot Institute of Technology and Science Computer Science and Engineering Kerala Kochi India

ISBN: (纸本)9798350314090

Blockchain technology is one of the most promising modem technologies. The decentralization principle is used to distribute data among the active nodes of the network. There are many different use cases in the contemporary digital era because of the technology's ability to assure confidentiality, privacy, and immutability. The existing electoral process is centralized and unreliable in operation. Elections must therefore be conducted using secure online methods. The most effective method for guaranteeing election anonymity, security, privacy, and dependability is blockchain technology. The goal of this work is to implement an online voting system based on blockchain technology. It looks for examples of how blockchain technology might be used in the Indian electoral system, how to do it, and what other considerations need to be made. Scalability, application methodology, implementation criteria, blockchain characteristics, and technological components must all be taken into account while managing an online voting application using smart contract writing. © 2023 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

High-Frequency Performance with Microwave and Millimeter-Wave Methods 1

High-Frequency Performance with Microwave and Millimeter-Wav...

引用

1st IEEE International Conference on Emerging Research in Computational science, ICERCS 2023

作者： Poornima, D. Jany Shabu, S.L. Refonaa, J. Karunya, K. Bobby, M.P. Sathyabama Institute of Science & Technology Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350359756

Modern wireless communication, radar systems, and the realization of new technologies like 5G and beyond all rely heavily on high-frequency performance. The use of microwave and millimeter-wave techniques (MMWT) could provide revolutionary new uses for vast amounts of data at extremely low latency. High-frequency performance optimization is still a challenging and essential problem. Interference Mitigation, Antenna Design, Signal Processing, and Regulatory Compliance are all considered to be sizeable obstacles towards accomplishing High-Frequency Performance. The motive of the research is to advocate the use of Regulatory Compliance Frequency Band Analysis (RCFBA) for the purpose of figuring out target frequencies in accordance with utility necessities and acting spectrum scanning and evaluation with the intention to assess regulatory constraints and available channels. Maximizing signal energy even as keeping off interference via cautiously choosing and positioning antennas. Enabling higher data throughput, decrease latency, and a wider variety of applications for high-frequency systems by way of easing their adoption and deployment in fields like telecommunications, radar systems, satellite communique, and 5G networks. High-frequency performance can be modelled and evaluated with the help of present day modeling tools, that may then be used to optimize gadget parameters, propagation, and antenna designs. It equips users with the way for thorough simulation evaluation, optimization, and fulfillment in excessive-frequency packages, taking into account the deployment of excessive-frequency structures that healthy the desires of contemporary packages and regulatory standards. © 2023 IEEE.

关键词： Regulatory compliance

来源：评论

学校读者我要写书评

暂无评论

Software Defect Prediction for Reliability Analysis Using Machine Learning Approach 3

Software Defect Prediction for Reliability Analysis Using Ma...

引用

3rd IEEE International Conference on ICT in Business Industry and Government, ICTBIG 2023

作者： Baronia, Preeti Baderiya Gupta, Chetan Computer Science & Engineering Sagar Institute of Research Technology and Science Bhopal India

ISBN: (纸本)9798350343274

Ensuring software dependability is of utmost importance in today's technology-driven world, given the increasing significance of software and the potential consequences of defects, such as financial losses and security breaches. The substantial contribution of the software industry to the global economy further emphasizes the need for reliable software. While various methodologies and techniques have been introduced to enhance software reliability, challenges persist, including accurate failure parameter estimation, statistical significance determination, and dealing with imbalanced data. This paper explores machine learning algorithms and defect prediction approaches to address these challenges. The research aims to improve the accuracy of software reliability predictions by utilizing advanced techniques and methodologies. The results demonstrate a substantial improvement in accuracy, with an average of 99.36% across all software systems. The proposed technique showcases its capability to make highly accurate predictions for diverse software projects, offering valuable insights to software development teams and stakeholders. Identifying potential issues and improving software quality become more achievable with the help of the proposed approach. © 2023 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Multi-Agent Systems for Autonomous IoT Network Management Using Distributed Reinforcement Learning 3

Multi-Agent Systems for Autonomous IoT Network Management Us...

引用

3rd International Conference on Intelligent Systems, Advanced Computing, and Communication, ISACC 2025

作者： Neelamegam, G. Venkatesan, Rajaram Ramya, S.R. Ramya, R.S. Akshya, J. Sundarrajan, M. Choudhry, Mani Deepak VSB College of Engineering and Technology Department of Computer Science and Engineering Tamil Nadu Coimbatore India Builders Engineering College Department of Artificial Intelligence and Data Science Tamil Nadu Tirupur India Dr NGP Institute of Technology Department of Computer Science and Engineering Tamil Nadu Coimbatore India Sri Ramakrishna Engineering College Department of Computer Science and Engineering Tamil Nadu Coimbatore India SRM Institute of Science and Technology Department of Computational Intelligence Tamil Nadu Chennai India SRM Institute of Science and Technology Department of Networking and Communications Tamil Nadu Chennai India SRM Institute of Science and Technology Department of Computing Technologies Tamil Nadu Chennai India

ISBN: (纸本)9798331523893

The ever-growing complexity of IoT networks ignited by their wide scale adoption in applications such as smart cities, the industrial automation, and health care, compelled to develop sophisticated yet resource efficient and scalable network management solution. Centralized systems are traditional in architecture, which leads to higher latency and bottlenecks, while decentralized systems can distribute workloads however the lack of adaptability to real time, along with the difficulty of extracting maximum resource usage, are limitations. In recent years, reinforcement learning (RL) based approaches have taken shape as a promising alternative to facilitate the automated learning and optimisation of task management. However, there are two challenges for existing RL based methods: slow convergence, inefficient priority assignment of tasks, and poor coordination amongst agents in the case of dynamic, large scale IoT environment. To solve these challenges, in this research we propose a distributed reinforcement learning based multi agent framework for managing IoT network. The framework also integrates a task prioritization mechanism to dynamically choose an optimal task allocation solution. Further validation was performed in a simulated IoT environment where real world inspired datasets were used. The proposed framework demonstrated 30% more task throughput than centralized, 25% less latency than decentralized, and 40% more energy efficiency than current RL based systems. The system was further validated using advanced visualizations such as anomaly detection maps and resource allocation efficiency graphs, demonstrating its capacity to manage dynamic load of tasks and resource allocation. The proposed framework addresses the critical limitations of current methods, through scalable, adaptive, and energy efficient framework for managing IoT network, and accordingly helps advancing the intelligent and autonomous IoT systems. © 2025 IEEE.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

Supremal and Robust Control Against Actuator Jamming Attacks in Cyber-Physical Systems

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on Intelligent Vehicles 2024年第9期9卷 5435-5447页

作者： Duo, Wenli Wang, Shouguang Zhou, MengChu You, Dan Winiewski, Remigiusz Bazydlo, Grzegorz Albeshri, Aiiad Macau University of Science and Technology Institute of Systems Engineering 999078 China Zhejiang Gongshang University School of Information and Electronic Engineering Hangzhou310018 China New Jersey Institute of Technology Helen and John C. Hartmann Department of Electrical and Computer Engineering NewarkNJ07102 United States University of Zielona Góra Institute of Control and Computation Engineering Zielona Góra65-516 Poland King Abdulaziz University Department of Computer Science Jeddah21481 Saudi Arabia

Cyber-physical systems, such as unmanned aerial vehicles and connected and autonomous vehicles, are vulnerable to cyber attacks, which can cause significant damage to society. This paper examines the attack issue in cyber-physical systems within the framework of discrete event systems. Specifically, we consider a scenario where a malicious intruder injects a jamming signal into an actuator channel. It disrupts the transmission of control commands and prevents an actuator from receiving them. This is termed an actuator jamming attack. In the paper, we first analyze the closed-loop system behavior under such an attack. An attack structure is constructed to illustrate how an intruder exploits a jamming attack to drive a system into unsafe states. Then, we study the supervisory control problem for a system exposed to such an attack. The problem is reduced to a basic supervisory control one in discrete event systems by introducing the concept of dynamically controllable language. A solution to this problem is explored, where we establish an existence condition for a supremal and robust supervisor that is capable of defending against actuator jamming attacks, and design an algorithm to derive it. Finally, the effectiveness of our method is illustrated by an intelligent automated guided vehicle system. © 2016 IEEE.

关键词： Discrete event simulation

来源：评论

学校读者我要写书评

暂无评论

Automatic Detection and Classification of Wild Animal Species Using YOLO Models 3

Automatic Detection and Classification of Wild Animal Specie...

引用

3rd International Conference on Pervasive Computing and Social Networking, ICPCSN 2023

作者： Thangaraj, Rajasekaran Charly Jerome, J. Sanjith, M. Rithick Saran, K. Sasikumar, Sudev Vijayakumar, S. Kpr Institute of Engineering and Technology Department of Computer Science and Engineering Coimbatore India Kpr Institute of Engineering and Technology Department of English Coimbatore India

ISBN: (纸本)9798350322842

Using a camera trapping framework, which employs cameras activated by sensors to record a burst of pictures of animals in their habitat, it is feasible to monitor animals in the open. This paper explores the effectiveness of YOLOv3 and YOLOv5 object detection algorithms in automated animal tracking through the use of computer vision. A dataset of six animal classes was utilized to train and test both models. The results demonstrate that YOLOv5-m achieves an 81% detection accuracy rate, surpassing that of YOLOv3. In addition, the two models were evaluated based on detection speed and model size, with YOLOv5-m providing higher accuracy and comparable speed and model size to YOLOv3. Overall, these findings highlight the potential of computer vision and deep learning in automated animal tracking, and emphasize the importance of selecting appropriate algorithms for various use cases. © 2023 IEEE.

关键词： Animals

来源：评论

学校读者我要写书评

暂无评论

Advancements in Drug Discovery Through Machine and Deep Learning Concepts in Early-Stage of Drug Discovery for Apoptosis 3

Advancements in Drug Discovery Through Machine and Deep Lear...

引用

3rd International Conference on Disruptive Technologies, ICDT 2025

作者： Saxena, Kushagra Srivastava, Ankita Kumar, Hemant Indian Institute of Information Technology Department of Computer Science and Engineering Jharkhand Ranchi India Department of Computer Science and Engineering Indian Institute of Information Technology Lucknow India Babasaheb Bhimrao Ambedkar University Department of Computer Science Vidya Vihar Rae Bareli Road Lucknow226025 India

ISBN: (纸本)9798331519582

Within the rapidly shifting field of drug discovery, ML and DL techniques have opened new directions for identifying potential therapeutic compounds with higher efficiency and accuracy. The present work explores the integration of ML and DL algorithms for drug discovery in apoptosis, by utilizing PaDEL and Lipinski descriptors for feature extraction. PaDEL is widely used open-source software that helps in generating the molecular descriptors and fingerprints of a chemical compound while Lipinski's descriptors depend on the 'Rule of Five' which explores critical analysis of drug-likeness of molecules. The present article provides a comparative analysis of different ML and DL algorithms which include SVM, RF, GBM, KNN, ANN, and GNN. The performance of each one is evaluated based on key metrics such as adjustment of r2 score and mean square error. This presented work shall help in predicting the chemical compounds at the early stage of drug discovery using the QSAR method. Computed results are depicted graphically. © 2025 IEEE.

关键词： Apoptosis Deep Learning Descriptors Drug Discovery Lipinski Machine Learning PaDEL QSAR

来源：评论

学校读者我要写书评

暂无评论

Interactive Learning using Mobile based Augmented Reality Application 2

Interactive Learning using Mobile based Augmented Reality Ap...

引用

2nd IEEE International Conference on Advances in Computing, Communication and Applied Informatics, ACCAI 2023

作者： Nazeer, Shaik Somu, K.B. Roobini, M.S. Sathyabama Institute of Science and Technology Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350315905

Augmented Reality has become a state-of-the-art technology that enhances the real-world environment with interactive and immersive virtual objects. This technology mixes the real and virtual worlds, enabling realtime interaction and accurate 3D registration of real and virtual objects. One of the most significant uses of Augmented Reality is in the educational system, especially for primary classes, where it brings imagination to life and increases children's interest and excitement in their studies. The technology can also be incorporated into mobile apps that are accessible and user-friendly. Software such as Unity and Vuforia are leading the development of Augmented Reality. In education, this technology has made a significant impact and made learning more engaging and interesting. The augmented reality application can be used to teach geometric figures, the solar system, wild animals, automobiles, and more. It uses target images and software that can detect special markers. 3D objects, animations, and other interactive elements come to life when the target image is placed in front of a mobile device's camera, making learning more enjoyable. The application has received positive feedback from both teachers and students in initial tests. © 2023 IEEE.

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

Voice Assistant with Emotion Recognition

Voice Assistant with Emotion Recognition

引用

2023 International Conference on Circuit Power and Computing Technologies, ICCPCT 2023

作者： Srikanth, S. Sravana Manikantan, Sreenivasan Posonia, A. Mary Mary, S. Prince Revathy, S. Sathyabama Institute of Science and Technology Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350333244

Voice assistants have become a essential part in our daily life, which helps to provide essential tasks in a hands free manner. Here the voice assistant helps the user with hands free experience that includes setting reminders, playing music, alarm, wishes etc. The voice assistant is powerful ones of cutting-edge speech recognition and natural language processing technique. The system will be intended to interpret and respond to a wide range of spoken instructions and enquiries in a natural and intuitive manner. Furthermore, the initiative intends to improve the user experience by giving tailored replies and suggestions depending on the user's preferences and history. For forecasting emotions, features such as emotion recognition, which detects a person's feelings through their face, are implemented. The goal of this project is to create a voice assistant that interacts with and shorten the burden of activities. © 2023 IEEE.

关键词： Emotion Recognition

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：