检索结果-内蒙古大学图书馆

6th International Conference on Renewable Energies Offshore, RENEW 2024

作者： Holcombe, A. Hann, M. Brown, S. Cheng, S. Rawlinson-Smith, R. Nicholls-Lee, R. School of Engineering Computing and Mathematics University of Plymouth Plymouth United Kingdom Flotation Energy Hobart House Edinburgh United Kingdom

ISBN: (纸本)9781032905570

Dynamic power cables transmit electricity from floating offshore renewable energy devices to seabed connections. While global numerical models are commonly used to design cable configurations, smallscale wave tank experiments offer an alternative approach. This study investigates the effects of bending and axial stiffness on key results, providing guidance for selecting materials for scale models of dynamic power cables. Simulations of a 15 MW floating offshore wind turbine were conducted in OrcaFlex, varying stiffness values. The findings show that changing axial stiffness has no impact. Bending stiffness within five times the target value maintains a similar static shape, whereas a range of 0.9 to 4 times the target value is needed to keep maximum curvature within a 20% increase. Lower bending stiffness produces similar maximum tension, but higher stiffness reduces it by up to 12%. This study informs how much stiffness properties can deviate from target scale values while ensuring reliable results. © 2025 The Author(s).

关键词： Windmill

来源：评论

学校读者我要写书评

暂无评论

Speaker Identification Using CNN-LSTM Model on RAVDESS Dataset: A Deep Learning Approach 4

Speaker Identification Using CNN-LSTM Model on RAVDESS Datas...

引用

4th International Conference on Intelligent Technologies, CONIT 2024

作者： Suryamritha, M. Balaji, Varshini Kannan, Srinidhi Murali, K. Amrita School of Computing Department of Computer Science and Engineering Bengaluru India Department of Mathematics Amrita Vishwa Vidyapeetham India

ISBN: (纸本)9798350349900

Speaker identification is used for identifying an individual based on their voice. Signal processing and deep neural networks are used for feature extraction. This paper presents a method that combines CNN and LSTM for speaker identification. Multiple models such as GMM, CNN, SVM were compared and CNN+LSTM outperformed with an accuracy of 96.52% and F1 measure of 97%. The CNN+LSTM model combines spatial and temporal information extracted by the CNN and LSTM layers which allows to capture of both local and long-term dependencies in the audio data hence making this model very efficient. The above models were evaluated on the RAVDESS (Ryerson AudioVisual Database of Emotional Speech and Song) dataset. The results highlight their potential for practical applications within speaker identification systems. © 2024 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

An anti-aliasing filtering of quantum images in spatial domain using a pyramid structure

引用

Chinese Physics B 2024年第5期33卷 223-237页

作者：吴凯周日贵罗佳 College of Information Engineering Shanghai Maritime UniversityShanghai 201306China Research Center of Intelligent Information Processing and Quantum Intelligent Computing Shanghai 201306China School of Mathematics and Computational Science Shangrao Normal UniversityShangrao 334001China

As a part of quantum image processing,quantum image filtering is a crucial technology in the development of quantum ***-pass filtering can effectively achieve anti-aliasing effects on ***,most quantum image filterings are based on classical domains and grayscale images,and there are relatively fewer studies on anti-aliasing in the quantum *** paper proposes a scheme for anti-aliasing filtering based on quantum grayscale and color image scaling in the spatial *** achieves the effect of anti-aliasing filtering on quantum images during the scaling ***,we use the novel enhanced quantum representation(NEQR)and the improved quantum representation of color images(INCQI)to represent classical *** aliasing phenomena are more pronounced when images are scaled down,this paper focuses only on the anti-aliasing effects in the case of ***,we perform anti-aliasing filtering on the quantum representation of the original image and then use bilinear interpolation to scale down the image,achieving the anti-aliasing *** constructed pyramid model is then used to select an appropriate image for upscaling to the original image ***,the complexity of the circuit is *** to the images experiencing aliasing effects solely due to scaling,applying anti-aliasing filtering to the images results in smoother and clearer ***,the anti-aliasing filtering allows for manual intervention to select the desired level of image smoothness.

关键词： quantum color image processing anti-aliasing filtering algorithm quantum multiplier pyramid model

来源：评论

学校读者我要写书评

暂无评论

Supply Chain Logistics With Hybrid Optimization using ADMM and Vehicle Routing Problem 1

Supply Chain Logistics With Hybrid Optimization using ADMM a...

引用

1st International Conference on Innovations in Communications, Electrical and Computer engineering, ICICEC 2024

作者： Reddy, T. Sudeep Dhanush, D. Krithin, T. Jayan, Sarada Amrita School of Computing Dept. of Computer Science and Engineering Bengaluru India Amrita Vishwa Vidyapeetham Amrita School of Engineering Dept. of Mathematics Bengaluru India

ISBN: (纸本)9798350376517

Delivery routing and truck assignment for transportation resources are essential elements in the dynamic world of supply chain management and logistics. This study proposes a framework for maximising the number of trucks assigned and the delivery routes by using OR-Tools to solve the Vehicle Routing Problem (VRP) and the Alternating Direction Method of Multipliers (ADMM) for demand assignment. With consideration for each vehicle's capacity, air conditioning condition, and demand priority, we created a realistic dataset that included warehouse locations, truck specifications, and delivery demand priorities. A time matrix was created by converting a distance matrix and assuming a constant speed of movement between the warehouses. Based on compatibility restrictions including vehicle capacity, air conditioning requirements, demand priority, and overall cost reduction, the ADMM algorithm allocates delivery demands to trucks. To successfully balance these aspects, the objective function incorporates weights for cost, priority, and distance. Following demand assignment, delivery routes are optimised using OR-Tools. Time windows and vehicle capacities are included as limitations to guarantee that deliveries are made within predetermined windows while reducing travel time and distance. In addition, a web application that offers an interactive platform for managing trucks, warehouses, and needs was created utilising the Flask framework. Through an easy-to-use interface, users can examine optimised routes, add new entries, and view extensive informative dashboard. By meeting delivery deadlines and maximising resource utilisation, this integrated approach produces notable operational efficiencies. This illustrates the potential of fusing cutting-edge optimisation techniques with useful application to handle real-world logistics problems. © 2024 IEEE.

关键词： Travel time

来源：评论

学校读者我要写书评

暂无评论

Privacy Inference Attack and Defense in Centralized and Federated Learning: A Comprehensive Survey

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年第2期6卷 333-353页

作者： Rao, Bosen Zhang, Jiale Wu, Di Zhu, Chengcheng Sun, Xiaobing Chen, Bing Yangzhou University School of Information Engineering Yangzhou225127 China University of Southern Queensland School of Mathematics Physics and Computing ToowoombaQLD4350 Australia Nanjing University of Aeronautics and Astronautics College of Computer Science and Technology Nanjing211106 China

The emergence of new machine learning methods has led to their widespread application across various domains, significantly advancing the field of artificial intelligence. However, the process of training and inferring machine learning models relies on vast amounts of data, which often include sensitive private information. Consequently, the privacy and security of machine learning have encountered significant challenges. Several studies have demonstrated the vulnerability of machine learning to privacy inference attacks, but they often focus on specific scenarios, leaving a gap in understanding the broader picture. We provide a comprehensive review of privacy attacks in machine learning, focusing on two scenarios: centralized learning and federated learning. This article begins by presenting the architectures of both centralized learning and federated learning, along with their respective application scenarios. It then conducts a comprehensive review and categorization of related inference attacks, providing a detailed analysis of the different stages involved in these attacks. Moreover, the article thoroughly describes and compares the existing defense methods. Finally, the article concludes by highlighting open questions and potential future research directions, aiming to contribute to the ongoing competition between privacy attackers and defenders. © 2020 IEEE.

关键词： Data privacy

来源：评论

学校读者我要写书评

暂无评论

Privacy Focused Classification of Prostate Cancer Using Federated Learning 17th

Privacy Focused Classification of Prostate Cancer Using Fede...

引用

17th International Conference on Information Technology and Applications, ICITA 2023

作者： Salma, Syeda Umme Sakib, Md Sadman Yasaar, Nahiyan Alvee, Mohammed Moinul Morshed Reza, Md Tanzim Parvez, Mohammad Zavid Department of Computer Science and Engineering BRAC University Dhaka Bangladesh School of Computing Mathematics and Engineering Charles Sturt University BathurstNSW Australia

ISBN: (纸本)9789819983230

Prostate cancer detection is an extremely challenging problem due to the socially sensitive nature of the data. As such, it negatively impacts early detection, including new procedures becoming difficult to develop owing to a lack of enough datasets. The proposed approach, which is based on Federated Learning, is a decentralized strategy that uses weight averaging and can quickly find anomalies while retaining data confidentiality. Additionally, the results of the customized basic CNN model with three Conv2D layers and two state-of-the-art models, VGG19 and Xception, were compared to those obtained in centralized and decentralized configurations. To recapitulate, this research’s findings indicate that the decentralized technique yields results that are very consistent with those yielded by state-of-the-art centralized methods. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

Privacy-Preserving Spatial Crowdsourcing in Smart Cities Using Federated and Incremental Learning Approach 100

Privacy-Preserving Spatial Crowdsourcing in Smart Cities Usi...

引用

100th IEEE Vehicular Technology Conference, VTC 2024-Fall

作者： Rahman, Md Mujibur Mamun, Quazi Wu, Jun Charles Sturt University School of Computing Mathematics and Engineering NSW Australia Waseda University Graduate School of Information Production and Systems Tokyo Japan

ISBN: (纸本)9798331517786

Spatial crowdsourcing (SC) systems have emerged as an advanced crowdsourcing paradigm to revolutionise the efficient development of smart city services. SC engages participants and their sensitive data to accomplish spatiotemporal tasks on platforms. However, revealing sensitive data in SC for smart cities exacerbates cybersecurity and privacy concerns, especially Membership Inference Attacks (MIA). To address the problems, this research proposes a Federated Learning (FL) and Incremental Learning (IL) based framework in SC that integrates advanced privacy-preserving techniques. By leveraging FL and adaptive differential privacy, sensitive data remains in decentralised devices while local models are trained without exchanging raw data to a server. We integrate additive secret sharing, a secure multi-party computation technique to protect data during transmission and aggregation. IL enhances the framework using a generative replay approach to ensure continuous adaptation to new data without forgetting existing knowledge to overcome catastrophic forgetting. We broadly evaluate our work against MIA and catastrophic forgetting using Yelp datasets. Compared with other baseline approaches, our experimental results demonstrate that the proposed framework significantly mitigates the risk of MIAs by around 50% and improves forgetting accuracy by up to 13%, thereby providing robust privacy-preserving mechanisms. © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Positive definiteness of real quadratic forms resulting from the variable-step L1-type approximations of convolution operators

引用

Science China mathematics 2024年第2期67卷 237-252页

作者： Hong-Lin Liao Tao Tang Tao Zhou School of Mathematics Nanjing University of Aeronautics and AstronauticsNanjing 211106China Division of Science and Technology BNU-HKBU United International CollegeZhuhai 519087China SUSTech International Center for Mathematics Shenzhen 518055China NCMIS&LSEC Institute of Computational Mathematics and Scientific/Engineering ComputingAcademy of Mathematics and Systems ScienceChinese Academy of SciencesBeijing 100190China

The positive definiteness of real quadratic forms with convolution structures plays an important rolein stability analysis for time-stepping schemes for nonlocal operators. In this work, we present a novel analysistool to handle discrete convolution kernels resulting from variable-step approximations for convolution *** precisely, for a class of discrete convolution kernels relevant to variable-step L1-type time discretizations, weshow that the associated quadratic form is positive definite under some easy-to-check algebraic conditions. Ourproof is based on an elementary constructing strategy by using the properties of discrete orthogonal convolutionkernels and discrete complementary convolution kernels. To our knowledge, this is the first general result onsimple algebraic conditions for the positive definiteness of variable-step discrete convolution kernels. Using theunified theory, we obtain the stability for some simple nonuniform time-stepping schemes straightforwardly.

关键词： discrete convolution kernels positive definiteness variable time-stepping orthogonal convolution kernels complementary convolution kernels

来源：评论

学校读者我要写书评

暂无评论

Machine learning analysis of shear stress over a symmetrically stenosed arterial wall under the impact of magnetic field 2

Machine learning analysis of shear stress over a symmetrical...

引用

2nd IEEE International Conference on Vision Towards Emerging Trends in Communication and Networking Technologies, ViTECoN 2023

作者： Selladurai, Spurthi Joanna Srivastava, Neetu Pati, Peeta Basa Amrita School of Engineering Department of Mathematics Bengaluru India Amrita School of Computing Department of CSE Bengaluru India

ISBN: (纸本)9798350347982

This study provides a framework to predict the shear stress over a symmetrically stenosed arterial wall under the impact of magnetic field using machine learning algorithms. We investigated the magnetohydrodynamics blood flow with the help of machine learning techniques. The considered model is governed by the principles of MHD. To predict the flow patterns and velocity of the blood flow it is important to study the relationship between the blood shear stress rate with the six blood flow input variables: flow rate (q), viscosity, radius (r), height(h), pressure (P) and velocity (v). We presented the correlation graph of shear stress with the six blood flow input variables. The machine learning models (CatBoost regressor, Random Forest regressor, Regressor tree, MLP regressor and Lasso model) were used to validate the dataset. Radar graphs have been plotted to visualize and compare the accuracy measured for all the five machine learning models. Our conclusion pretends that the random forest regressor analyze this problem accurately with noise free data. © 2023 IEEE.

关键词： Reynolds number

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Approach for Medical Image Fusion using SVD and PCA 4

A Hybrid Approach for Medical Image Fusion using SVD and PCA

引用

4th International Conference on Innovative Practices in Technology and Management, ICIPTM 2024

作者： Kusuma, J. Meera, K.N. Amrita School of Computing Department of Computer Science and Engineering Amrita Vishwa Vidyapeetham Bengaluru India Amrita School of Engineering Department of Mathematics Amrita Vishwa Vidyapeetham Bengaluru India

ISBN: (纸本)9798350307757

The process of combining multiple images into a single one is called image fusion. This facilitates extracting the information from one image instead of collating the information from multiple images. Image fusion reduces the randomness and redundancy and gives better clarity for human perception especially in the field of medical sciences. In order to improve the information contained in an image, we provide a novel technique in this study termed SVDPCA. We choose two distinct types of images for this experiment, namely Magnetic Resonance Imaging (MRI) and Positron Emission Tomography (PET). Initially singular value decomposition (SVD) is used on the two input images. The final image is created by processing the SVD result with the Principal Component Analysis (PCA) technique. To perform the experiment, we used 30 image sets. The results are compared with other techniques like PCA, SVD and maximum method. The experiments show that the proposed method SVDPCA which combines both methods gives the best result. © 2024 IEEE.

关键词： Magnetic resonance imaging

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：