检索结果-内蒙古大学图书馆

2023 International Conference on Power Energy, Environment and Intelligent Control, PEEIC 2023

作者： Kumar, Jambi Ratna Raja Mondal, Dipannita Ravivarman, G. Latha, B. Yadav, Gitanjali B. Dwivedi, Shivangi Genba Sopanrao Moze College of Engineering Department of Computer Engineering Maharashtra Pune India Dr. D.Y. Patil College of Engineering and Innovation Artificial Intelligence and Data Science Department Talegaon India Karpagam Academy of Higher Education Department of Electrical and Electronics Engineering Coimbatore641021 India Prince Shri Venkateshwara Padmavathy Engineering College Department of Information Technology Chennai India Vishwakarma Institute of Information Technology Department of Artificial Intelligence & Data Science Pune India Mangalayatan University Department of Commerce Jabalpur India

ISBN: (纸本)9798350357769

Information retrieval (IR) is an essential aspect of modern-day generation, especially with the fast increase and expansion of the net and its related technologies. IR aims to broaden systems that can correctly and appropriately retrieve applicable statistics from considerable data, assisting customers in their search and records accumulating wishes. AI has performed a tremendous function in advancing IR techniques, making systems more innovative and efficient in retrieving data. However, with the ever-growing extent of facts on the net and the want for real-time admission to statistics, there may be a growing desire for side computing in IR systems. Area computing refers to the processing and garage of records at the brink of the community instead of sending them to a critical area for processing. This method gives numerous advantages, including reduced latency, stepped-forward information privacy and safety, and efficient use of community bandwidth. In recent years, researchers have explored superior side strategies in AI to broaden high-overall performance IR systems. These techniques include aspect caching, facet gadget mastering, and edge-based statistics filtering, Part caching entails storing frequently accessed data at the community's edge, reducing the need to retrieve information from a critical server. This technique can improve IR systems' performance by reducing latency and community congestion. © 2023 IEEE.

关键词： appreciably congestion numerous performance processing

来源：评论

学校读者我要写书评

暂无评论

Sensor Placement in Water Distribution Networks using Graph Neural Networks

引用

IFAC-PapersOnLine 2024年 57卷 268-273页

作者： Aaradhy Sirothia Dr. Sridharakumar Narasimhan Indian Institute of Technology Madras Chennai India Department of Chemical Engineering and the Robert Bosch Center of Data Science and Artificial Intelligence Indian Institute of Technology Madras Chennai India

Graph Neural networks have shown the potential to solve large-scale combinatorial optimisation problems. The following work demonstrates how the graph neural networks can be utilised to solve the sensor placement problem, a combinatorial optimisation problem. This paper focuses on the problem of placing pressure sensors optimally in a Water Distribution Network (WDN). The problem is formulated as a Quadratic Unconstrained Binary Optimization (QUBO) or Ising model, a combinatorial optimisation problem. The paper outlines the QUBO and Ising formulations for the sensor placement problem, starting from the network topology and other relevant features. A detailed procedure is presented for solving the problem by minimising its Hamiltonian using PyQUBO, an open-source Python Library. Finally, the proposed methods are applied to a real Water Distribution Network for evaluation.

关键词： GNNs (Graph Neural Networks) optimisation binary Hamiltonian WDNs (Water Distribution Networks) QUBO (Quadratic Unconstrained Binary Optimisation)

来源：评论

学校读者我要写书评

暂无评论

Free vibration analysis of functionally graded porous curved nanobeams on elastic foundation in hygro-thermo-magnetic environment

引用

Frontiers of Structural and Civil engineering 2023年第4期17卷 584-605页

作者： Quoc-Hoa PHAM Parviz MALEKZADEH Van Ke TRAN Trung NGUYEN-THOI Faculty of Engineering and Technology Nguyen Tat Thanh UniversityHo Chi Minh City 700000Vietnam Department of Mechanical Engineering Persian Gulf UniversityBushehr ***Iran Faculty of Mechanical Engineering Le Quy Don Technical UniversityHanoi 100000Vietnam Laboratory for Applied and Industrial Mathematics Institute for Computational Science and Artificial IntelligenceVan Lang UniversityHo Chi Minh City 700000Vietnam Faculty of Mechanical-Electrical and Computer Engineering School of TechnologyVan Lang UniversityHo Chi Minh City 700000Vietnam Bualuang ASEAN Chair Professor Thammasat School of EngineeringThammasat UniversityPathumtani 12120Thailand

Herein,a two-node beam element enriched based on the Lagrange and Hermite interpolation function is proposed to solve the governing equation of a functionally graded porous(FGP)curved nanobeam on an elastic foundation in a hygro–thermo–magnetic *** material properties of curved nanobeams change continuously along the thickness via a power-law distribution,and the porosity distributions are described by an uneven porosity *** effects of magnetic fields,temperature,and moisture on the curved nanobeam are assumed to result in axial loads and not affect the mechanical properties of the *** equilibrium equations of the curved nanobeam are derived using Hamilton’s principle based on various beam theories,including the classical theory,first-order shear deformation theory,and higher-order shear deformation theory,and the nonlocal elasticity *** accuracy of the proposed method is verified by comparing the results obtained with those of previous reliable ***,the effects of different parameters on the free vibration behavior of the FGP curved nanobeams are investigated comprehensively.

关键词： functionally graded porous material curved nanobeam hygro-thermo-magnetic enriched finite element method

来源：评论

学校读者我要写书评

暂无评论

AI-Driven Indoor Farming: An Algorithmic Approach to Sustainable Agriculture 1st

AI-Driven Indoor Farming: An Algorithmic Approach to Sustain...

引用

1st International Conference on Intelligent Computing, Smart Communication, and Network Technologies, ICICSCNT 2023

作者： Veeramalai, S. Saranya, K. Computer Science and Engineering Chennai İnstitute of Technology Chennai India Artificial Intelligence and Data Science Panimalar Engineering College Poonamallee Chennai India

ISBN: (纸本)9783031759567

Indoor farming has emerged as a promising alternative to traditional farming methods, offering a controlled and optimized environment for crop growth that can improve yield and reduce the environmental impact of agriculture. However, indoor farming can be resource-intensive and labor-intensive, and optimizing the growing conditions for each crop can be challenging. In this project, we propose an AI-based autonomous indoor farming system that uses advanced algorithms to manage the environmental conditions, monitor crop growth and health, and optimize crop yield. The system will use machine learning to analyze various data points such as temperature, humidity, light intensity, and nutrient levels to create an optimal growing environment for each crop. Additionally, computer vision will be used to monitor plant health and growth patterns, and adjust the environmental conditions accordingly. Our system will also provide a user interface for farmers to input their crop preferences, monitor crop growth and health, and receive real-time feedback and coaching from the algorithm. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

An Innovative Secure and Privacy-Preserving Federated Learning Based Hybrid Deep Learning Model for Intrusion Detection in Internet-Enabled Wireless Sensor Networks

引用

IEEE Transactions on Consumer Electronics 2024年第1期71卷 1-1页

作者： Jena, Soumya Ranjan Rahman, Mohammad Zia Ur Sinha, Deepak K. kumar, P. Rajendra Vimal, Vrince Singh, Kamred Udham Syamsundararao, Thalakola Kumar, J.N.V.R. Swarup J, Balajee School of Computing and Artificial Intelligence NIMS University Jaipur Rajasthan India Department of Electronics and Communication Engineering Koneru Lakshmaiah Education Foundation Vaddeswaram Guntur Dist A.P. India University Bengaluru NRI Institute of Technology Agiripalli India Computer Science and Engineering Graphic Era Hill University Dehradun India School of Computing Graphic Era Hill University Dehradun India Department of CSE-Data Science KKR and KSR Institute of Technology and Sciences Guntur Andhra Pradesh India Visakhapatnam India

Cyberspace faces numerous security challenges, necessitating advanced research in intrusion detection systems (IDS) to mitigate vulnerabilities. Wireless Sensor Networks (WSNs) connected to the Internet are particularly vulnerable, requiring robust protection mechanisms. Traditional IDS struggle with identifying unknown attacks and maintaining data privacy, especially in WSNs. This study proposes a novel approach integrating Stacked Convolutional Neural Networks (SCNN), Bidirectional Long Short Term Memory (Bi-LSTM), and the African Vulture Optimization Algorithm (AVOA) within a framework of Federated Learning (FL). The integrated model, SCNN-Bi-LSTM-AVOA-FL, aims to enhance intrusion detection efficacy while preserving data privacy. A tailored AVOA optimization method fine-tunes SCNN-Bi-LSTM hyperparameters, leveraging specialized datasets (WSN-DS, CIC-IDS-2017, and WSN-BFSF) for attack detection and categorization. Evaluations compare variants with and without FL techniques (proposed-1 and proposed-2) across metrics such as accuracy, precision, recall, and F1-Score. Results demonstrate significant improvements in prediction performance, validating the efficacy of the proposed approach in enhancing IDS capabilities for WSNs. This research contributes a comprehensive framework for addressing security challenges in WSNs through advanced machine learning and optimization techniques. IEEE

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Blockchain-Based Solutions for Enhancing data Integrity and Security 7

Blockchain-Based Solutions for Enhancing Data Integrity and ...

引用

7th International Conference on Contemporary Computing and Informatics, IC3I 2024

作者： Mohan, Chinnem Rama Saxena, Rashi Thilagham, K.T. Solleti, Phani Kumar Sivasubramanian, S. Dharamvir Narayana Engineering College Department of Computer Science and Engineering Andhra Pradesh Nellore524004 India Gokaraju Rangaraju Institute of Engineering and technology Department of Data Science Hyderabad India Government College of Engineering Tamil Nadi Salem11 India 522302 India New Prince Shri Bhavani College Autonomous to Anna University Artificial Intelligence and Data Science Tamil Nadu Chennai India The Oxford College of Engineering Department of Mca Bommanhalli Bengaluru560068 India

ISBN: (纸本)9798350350067

The study emphasizes evaluating the effectiveness of blockchain-based solutions in improving data security and data integrity. By analysing the fundamental aspects of blockchain technologies, the significant roles of blockchain have been discussed in ensuring data transparency, auditability, and immutability. The study also investigates the potential business solutions across various industries along with its contribution in safeguarding sensitive information. The potential limitations and challenges of implementing blockchain-enabled solutions are effectively addressed while providing significant mitigation strategies. The analysis highlights the potential of blockehain in transforming the data landscape by enhancing data integrity and security. © 2024 IEEE.

关键词： data integrity

来源：评论

学校读者我要写书评

暂无评论

Multi-task Convolutional Neural Network Approach for Automatic Alzheimer Disease Classification 3

Multi-task Convolutional Neural Network Approach for Automat...

引用

3rd International Conference for Innovation in technology, INOCON 2024

作者： Zope, Minal A. Deshmukh, Rakesh K. Pise, Priya Bhopale, Shrikant D. Kalinga University Raipur India AISSMS's Institute of Information Technology Dept. of Computer Engineering Pune India Indira College of Engineering and Management Artificial Intelligence and Data Science Pune India Dr.D.Y.Patil Pratisthan's Colleg of Engineering Salokhenagar Kolhapur India

ISBN: (纸本)9798350381931

While CNN-based Alzheimer's disease (AD) classification has showed some encouraging results, it will need high accuracy, fast processing time, and generalizability to a number of population types before it can be used in clinical settings. The brain disorder known as Alzheimer's disease (AD) is progressive and currently has no cure. Alzheimer's disease (AD) is characterized by a decline in memory and other mental abilities as well as a loss of autonomy in daily life. The results of this study suggest that using statistical learning and ensemble learning strategies, an image feature extraction technique like the Auto color correlogram Filter methods may be used successfully to an Alzheimer's photos dataset. Dementia caused by Alzheimer's disease (AD) is a progressive form of the neurodegenerative brain disorder. It's not always obvious at first since there are usually so few symptoms at the outset, and they might be similar to those of other disorders. Distinguishing Alzheimer's disease from mild cognitive deterioration, which may be appreciated in normal aging, may be challenging. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

MCT-Net: a multi-branch hybrid CNN-transformer model for medical image segmentation

引用

Pattern Analysis and Applications 2025年第2期28卷 1-21页

作者： Shen, Longfeng Diao, Liangjin Peng, Rui Chen, Jiacong Lu, Zhengtian Ge, Fangzhen Anhui Engineering Research Center for Intelligent Computing and Application on Cognitive Behavior (ICACB) College of Computer Science and Technology Huaibei Normal University Anhui Huaibei China Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei China Anhui Big-Data Research Center on University Management Huaibei Normal University Anhui Huaibei China

In recent years, neural networks have demonstrated substantial progress in medical image segmentation. However, accurately segmenting objects in medical images is often restricted by edge blurring, which complicates the delineation of structures of interest. The purpose of this study is to develop a multi-branch hybrid CNN-transformer model to address the issue of edge blurring in medical image segmentation. This approach enables more precise edge detection and segmentation. Integrating hybrid CNN and transformer decoders facilitates detailed recovery while preserving global structures, thus minimizing errors in regions with blurred edges. Additionally, we incorporate a hybrid attention mechanism at the model’s bottleneck to enhance feature transfer between the encoder and decoder. The model was trained using the ACDC, Synapse, and polyp datasets, with a focus on improving segmentation accuracy in regions with blurry edges. Experimental results reveal that the proposed model surpasses existing state-of-the-art methods on the ACDC, Synapse, and polyp datasets, demonstrating its superior performance and effectiveness. These results suggest that the proposed model offers a significant improvement in handling edge blurring, with potential applications in enhancing medical image analysis and diagnostics. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Attention mechanism Convolutional neural network Edge information Medical image segmentation Transformer

来源：评论

学校读者我要写书评

暂无评论

Decentralized Network for Cloud Storage 2

Decentralized Network for Cloud Storage

引用

2nd Edition of IEEE Delhi Section Owned Conference, DELCON 2023

作者： Chirag, N. Kshitij, K. Gupta, Gaurav Sir M Visvesvaraya Institute of Technology Dept. of Information Science Engineering Bangalore India Shoolini University Yogananda School of Artificial Intelligence Computer and Data Sciences H.P Solan India

ISBN: (纸本)9798350322064

The amount of data loss on corporate servers in cloud environments has increased significantly. In the cloud, there are many security compromises and account hijackings, resulting in severe vulnerabilities for the service. Cloud computing is one of the most popular on-demand services. Over the past decade, cloud computing has been incorporated into various industries, including health care and the military. Security has, however, been a major concern with cloud computing. There have been many approaches and security implications implemented. However, when it comes to the security and privacy of data, there are loopholes. By decentralizing the cloud, which is currently a centralized entity, the authors attempt to improve cloud security. It is possible to solve these problems by deploying a decentralized cloud. Client software encrypts, fragments data, and then a client engine distributes the data among a number of hosting nodes (servers) spread throughout the world. As a result, the user has complete ownership of his data. In their study, the authors found that decentralizing cloud solved most of the problems of centralized cloud, since it increases the security of data by fragmenting and encrypting fragments. © 2023 IEEE.

关键词： Cloud security

来源：评论

学校读者我要写书评

暂无评论

Application of A Long Short-Term Memory Neural Network Algorithm Fused with ResNet in UWB Indoor Positioning

IAENG International Journal of Computer Science

引用

IAENG International Journal of Computer science 2025年第5期52卷 1417-1423页

作者： Zhu, Chunhua Li, Manyi Cui, Mingyang School of Artificial Intelligence and Big Data Henan University of Technology Zhengzhou450001 China College of Information Science and Engineering Henan University of Technology Zhengzhou450001 China College of Information Science and Engineering Henan University of Technology Zhengzhou450001 China

Ultra-wideband (UWB) signals are susceptible to multipath effects and non-line-of-sight (NLOS) propagation in indoor environments, necessitating the simultaneous capture of the signal's temporal dynamic changes and spatial structural characteristics. To improve the localization accuracy and real-time tracking capability, a novel UWB indoor localization algorithm is proposed that integrates ResNet and LSTM neural networks, fusing the spatiotemporal characteristics of UWB signals. Initially, the distance data collected by the UWB device is transformed into the time series, then, the ResNet is employed to extract high-dimensional features and suppress the impact of noise and multipath effects, and the LSTM network is integrated with ResNet to capture temporal dependencies, thereby enhancing positioning accuracy. Simulation results indicate that the proposed ResNet-LSTM algorithm outperforms traditional BP neural networks and LSTM networks in terms of localization accuracy, error stability, and noise immunity, effectively improving the performance of UWB indoor positioning. © (2025), (International Association of Engineers). All Rights Reserved.

关键词： Long short-term memory

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：