检索结果-内蒙古大学图书馆

A robust deformed convolutional neural network(CNN)for image denoising

CAAI Transactions on Intelligence technology 2023年第2期8卷 331-342页

作者： Qi Zhang Jingyu xiao Chunwei Tian Jerry Chun‐Wei Lin Shichao Zhang School of Economics and Management Harbin Institute of Technology at WeihaiWeihaiChina School of Computer Science Central South UniversityChangshaChina School of Software Northwestern Polytechnical UniversityXi'anShaanxiChina Research&Development Institute Northwestern Polytechnical UniversityShenzhenChina Yangtze River Delta Research Institute Northwestern Polytechnical UniversityTaicangChina Department of Computer Science Electrical Engineering and Mathematical SciencesWestern Norway University of Applied SciencesBergenNorway

Due to strong learning ability,convolutional neural networks(CNNs)have been developed in image ***,convolutional operations may change original distributions of noise in corrupted images,which may increase training difficulty in image *** relations of surrounding pixels can effectively resolve this *** by that,we propose a robust deformed denoising CNN(RDDCNN)in this *** proposed RDDCNN contains three blocks:a deformable block(DB),an enhanced block(EB)and a residual block(RB).The DB can extract more representative noise features via a deformable learnable kernel and stacked convolutional architecture,according to relations of surrounding *** EB can facilitate contextual interaction through a dilated convolution and a novel combination of convolutional layers,batch normalisation(BN)and ReLU,which can enhance the learning ability of the proposed *** address long-term dependency problem,the RB is used to enhance the memory ability of shallow layer on deep layers and construct a clean ***,we implement a blind denoising *** results demonstrate that our denoising model outperforms popular denoising methods in terms of qualitative and quantitative *** can be obtained at https://***/hellloxiaotian/RDDCNN.

关键词： blind denoising CNN deformed block enhanced block

来源：评论

学校读者我要写书评

暂无评论

Unveiling the Nexus: Exploring the Societal Implications of AI-Driven Cybersecurity and Data Analysis 13

Unveiling the Nexus: Exploring the Societal Implications of ...

引用

13th International Conference on System Modeling and Advancement in Research Trends, SMART 2024

作者： Arif, Mohd Ahmad, Shahnawaz Nazim, Mohd Ahmad, Javed Onyarin, Ogala Justin Galgotias University Department of Computer Science Engineering and Technology Greater Noida India School of Computer Science Engineering and Technology Bennett University Greater Noida India Noida Institute of Engineering and Technology Department of Computer Science Greater Noida India University of Delta Pmb Cyber Security Department Delta State Agbor2090 Nigeria

ISBN: (纸本)9798350380583

AI when integrated with cybersecurity and data analysis forms a new field that will have great impact on the society. The present research focuses on the social consequences of integrating AI for cybersecurity and big data analytics, thus filling the gap in the existing literature. Using both qualitative and quantitative points of view, quantitative analysis and qualitative examination, the research offers an all-embracing understanding of this convergence. It aims to review and analyze the history, present usage, future prognosis of AI related cybersecurity and data analysis, including the reflection of ethical issues, privacy aspects and relevant laws. The lessons learnt are discussed based on case studies, best practices analysis, and the study provides recommendations for the effective use of AI-based solutions throughout their life cycle. The analysis broadens the knowledge on the effects of AI technology for cybersecurity and data analytics, and helps researchers, policymakers, and industry stakeholders apply the new knowledge. © 2024 IEEE.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

Decentralized Generative AI Model Deployment Using Microservices

Decentralized Generative AI Model Deployment Using Microserv...

引用

2024 International Conference on Artificial Intelligence and Quantum Computation-Based Sensor Applications, ICAIQSA 2024

作者： Jhingran, Sushant Bansal, Nidhi Chaturvedi, Rekha Singh, Ajeet Arora, Yojna School of Engineering and Technology Sharda University Department of Computer Science & Engineering Uttar Pradesh Greater Noida India Pune India School of Information Security and Data Science Manipal University Jaipur Department of Data Science and Engineering Jaipur India Moradabad Institute of Technology Department of Computer Science & Engineering Uttar Pradesh Moradabad India

ISBN: (纸本)9798331517953

The microservices are continuously growing in domains of communication using cloud and AI. Access to microservice can be done using any respective cloud environment. Access microservices using cloud require multiple configurations. These configurations can be set up in Kubernetes or containerized environments to lightweight any application which increases the performance of microservices. Multiple requests can create a concurrent call, which causes slow response. Generative AI models can be used to solve concurrent calls. Generative AI used a modular approach for microservice communications with API gateway. This allows microservices to function in a variety of contexts, including cloud, edge devices, and containers. This process refers to a decentralized approach which can only be implemented in the case of microservices and provide improvement in latency along with bandwidth. © 2024 IEEE.

关键词： Cloud Container Docker Generative AI Microservices

来源：评论

学校读者我要写书评

暂无评论

GS-PT: Exploiting 3D Gaussian Splatting for Comprehensive Point Cloud Understanding via Self-supervised Learning

GS-PT: Exploiting 3D Gaussian Splatting for Comprehensive Po...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Liu, Keyi Luo, Yeqi Yang, Weidong Xu, Jingyi Li, Zhijun Chen, Wen-Ming Fei, Ben School of Computer Science Fudan University China School of Mechanical Engineering Tongji University China Academy for Engineering and Technology Fudan University China

ISBN: (纸本)9798350368741

Self-supervised learning of point cloud aims to leverage unlabeled 3D data to learn meaningful representations without reliance on manual annotations. However, current approaches face challenges such as limited data diversity and inadequate augmentation for effective feature learning. To address these challenges, we propose GS-PT, which integrates 3D Gaussian Splatting (3DGS) into point cloud self-supervised learning for the first time. Our pipeline utilizes transformers as the backbone for self-supervised pre-training and introduces novel contrastive learning tasks through 3DGS. Specifically, the transformers aim to reconstruct the masked point cloud. 3DGS utilizes multi-view rendered images as input to generate enhanced point cloud distributions and novel view images, facilitating data augmentation and cross-modal contrastive learning. Additionally, we incorporate features from depth maps. By optimizing these tasks collectively, our method enriches the tri-modal self-supervised learning process, enabling the model to leverage the correlation across 3D point clouds and 2D images from various modalities. We freeze the encoder after pre-training and test the model's performance on multiple downstream tasks. Experimental results indicate that GS-PT outperforms the off-the-shelf self-supervised learning methods on various downstream tasks including 3D object classification, real-world classifications, and few-shot learning and segmentation. Project page: https://***/Luoyeqi1/***. © 2025 IEEE.

关键词： 3D Gaussian Splatting 3D understanding point clouds pre-training self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Secure communication routing and attack detection in UAV networks using Gannet Walruses optimization algorithm and Sheppard Convolutional Spinal Network

引用

Peer-to-Peer Networking and Applications 2024年第5期17卷 3269-3285页

作者： Renu, Yuvaraj Sarveshwaran, Velliangiri Department of Computational Intelligence School of Computing SRM Institute of Science and Technology Kattankulathur Campus Chengalpattu India Department of Computer Science and Information Engineering National Chung Cheng University Minxiong Chiayi Taiwan

Unmanned Aerial vehicles (UAV) are high-speed moving machines that attained rapid growth in various activities and are considered an integral component in the Satellite-Air -Ground-Sea (SAGS) incorporated network. However, UAVs are affected by communication delays and malicious attacks. Therefore, an adequate and secure communication routing and attack detection model is necessary for UAV communication networks. This research described a novel approach for initiating secure communication in UAV networks namely Gannet Walruses Optimization Algorithm + Sheppard Convolutional Spinal Network (GWOA + ShCSpinalNet). Initially, the UAV network is simulated, and the data packets are transmitted among the nodes using optimal routing paths. An optimal routing path is computed using the Gannet Walruses Optimization Algorithm (GWOA) by considering some multi-objective functions through the Deep Recurrent Neural Network (DRNN). The developed GWAO integrates Gannet Optimization (GOA) and Walruses Optimization (WaOA). The data communication is done through monitoring agents. The newly devised Sheppard Convolutional Spinal Network (ShCSpinalNet) is utilized as a decision-making agent for malicious attack detection. The attributes considered for decision-making are round trip time, packet delivery ratio, the strength of the signal, the size of the packet, and the number of incoming packets. Once the SpinalNet categorizes the normal and attacked nodes the defense agent is implemented for attack migration. The ShCSpinalNet is devised by the combination of the Sheppard Convolutional Neural Network and Spinal Network. The GWOA + ShCSpinalNet accomplishes a diminished delay of 0.614 s, an increased detection rate of 0.930%, an energy of 0.439 J, and a Packet Delivery Ratio (PDR) of 0.749. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Design and beam dynamics study of a magnet system for an 11 MeV superconducting isochronous cyclotron

引用

Nuclear science and Techniques 2025年第6期 193-202页

作者： Pan-Pan Zheng xiang-Hui Wang Zi-Feng He Yue Wu Zhi-Min Dai Wei-Shi Wan School of Physical Science and Technology ShanghaiTech University Shanghai Institute of Applied Physics Chinese Academy of Sciences School of Computer Engineering Wefang University

In recent years, due to the scarcity of domestic radioisotopes, the Chinese government has strongly supported the development of dedicated radioisotope production facilities. This paper presents conceptual design simulations of an 11 MeV, 50 μA,H-compact superconducting cyclotron for radioisotope production. This paper focuses primarily on four aspects: magnet system design, central region configuration, beam dynamics analysis, and extraction system design. This paper outlines the cyclotron's primary parameters and key steps in the development process.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Prediction of Stochastic Properties of Low-Frequency Sky-Wave in the Earth-Ionosphere Waveguide Based on the S-FDTD Method

Prediction of Stochastic Properties of Low-Frequency Sky-Wav...

引用

2023 International Applied Computational Electromagnetics Society Symposium, ACES-China 2023

作者： Hu, xinyue Zhou, Lili Mu, Zhonglin Guo, Wenqiang School of Electronic Information and Artificial Intelligence Shaanxi University of Science and Technology Xi'an China Air Force Engineering University Engineering Department Xi'an China

ISBN: (纸本)9781733509657

This letter focuses on the prediction of low-frequency (LF) wave propagation characteristics in the Earth-ionosphere waveguide under complex and stochastic ionospheric conditions. Based on the stochastic finite-difference time-domain (S-FDTD) method of a single simulation, we construct a hierarchical numerical model of LF wave propagation under isotropic stochastic ionosphere conditions. The Monte Carlo FDTD (MC-FDTD) method and the wave-hop theory are respectively used to compare the statistical characteristics of the sky-wave obtained by the S-FDTD method under short-range or long-range conditions. The effectiveness and efficiency of the S-FDTD method are verified, which can quickly measure the time-domain uncertainty of the LF sky-wave mode in the complex and stochastic Earth-ionosphere waveguide. © 2023 Applied Computational Electromagnetics Society (ACES).

关键词： Finite difference time domain method

来源：评论

学校读者我要写书评

暂无评论

Design and simulation of adaptive control system for telescopic pipeline robot

引用

International Journal of Mechatronics and Manufacturing Systems 2023年第1期16卷 55-82页

作者： Zheng, Jie Bai, Yangjie Zheng, Yong Zhang, Yarong Li, Zhenzhen School of Mechanical Engineering Xi'An Shiyou University Shaanxi Xi'an710065 China School of Power and Energy Northwestern Polytechnical University Shaanxi Xi'an710072 China Xi'An Special Equipment Inspection Institute Shaanxi Xi'an710065 China Baoji Oilfield Machinery Co. Ltd. Shaanxi Baoji721015 China National Engineering Research Center for Oil and Gas Drilling Equipment Shaanxi Baoji721015 China School of Science Xi'An University of Architecture and Technology Shaanxi Xi'an710055 China

When continuous tubing encounters excessive frictional resistance in the horizontal section and cannot reach its predetermined position, or self-locking occurs, drag reduction measures such as a pipeline traction robot can be utilised. By controlling the speed and traction force of the robot, the ultimate downstream depth of the continuous tubing can be increased, allowing it to reach its intended operating position. To address the speed regulation and error suppression issues of the downhole traction robot control system, a fuzzy neural network-based proportional-integral-differential (PID) controller was designed and simulated in Simulink. The results demonstrate that the downhole tractor control system with a fuzzy neural network PID controller has superior dynamic and static performance, with 61% less overshoot and 47.5% shorter adjustment time. This indicates high robustness and improved control of the pipeline robot, enabling the continuous tubing to reach its predetermined operating position in a more stable, accurate, and efficient manner. © 2023 Inderscience Enterprises Ltd.. All rights reserved.

关键词： Controllers

来源：评论

学校读者我要写书评

暂无评论

Construction of PCOS Prediction Model based on BP Neural Network 6

Construction of PCOS Prediction Model based on BP Neural Net...

引用

6th International Conference on Mobile Computing and Sustainable Informatics, ICMCSI 2025

作者： Hu, xianqing Yadav, Amit Khan, Asif Sah, Abhishek Pratap Azam, Sami School of Computer and Software Chengdu Neusoft University Chengdu China Faculty of Science and Technology Charles Darwin University NT Australia Department of Computer Application Integral University Lucknow India School of Management Science and Engineering University of Electronic Science and Technology of China Chengdu China

ISBN: (纸本)9798331522667

Polycystic ovary syndrome (PCOS), a common endocrine-metabolic disorder affecting about 10-13% of women during reproductive age worldwide, often leads to irregular menstruation, infertility, obesity, and long-term health risks such as diabetes and cardiovascular disease. In this paper, clinical data from PCOS patients and healthy control group were collected from ten hospitals containing 37 key indicators such as age, weight, BMI, menstrual cycle, etc. BP (Back Propagation) Neural Network prediction models were constructed and compared using the collected data and the cross-validation method was used for parameter tuning. It was found that BP Neural Network performed particularly well on the test set, and both demonstrated high prediction accuracy and generalization ability which provided strong evidence for the early identification and early valuable intervention opportunities for PCOS patients. © 2025 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Unveiling the Power of Dual Positional Encoding in Point Cloud Learning with DPAtteNet 17

Unveiling the Power of Dual Positional Encoding in Point Clo...

引用

17th IEEE International Conference on Signal Processing, ICSP 2024

作者： Zhou, Wei Jin, Weiwei Wang, Qian Liu, Kunlong She, Yunfeng Yu, Yongxiang Ma, Caiwen Northwest University School of Information Science and Technology Xi'an China East China Jiaotong University School of Electrical and Automation Engineering Nanchang China Chinese Academy of Sciences Xi'an Institute of Optics and Precision Mechanics Xi'an China

ISBN: (纸本)9798350387384

Traditional attention mechanisms in point cloud learning typically use a single type of positional encoding, which captures positional relationships within individual neighborhoods but neglects the spatial relationships between neighborhoods. Understanding these spatial relationships is crucial for grasping the overall shape of the point cloud and improving feature extraction. To address this, we propose Dual Positional Encoding Attention (DPAttention). DPAttention combines global positional encoding to capture spatial relationships between neighborhoods with local positional encoding to address positional relationships within neighborhoods. This approach enables the model to effectively understand both the global geometric structure and the local details of the point cloud, thus enriching feature extraction through the attention mechanism. Building on DPAttention, we introduce DPAtteNet, a deep learning network designed for point cloud classification and segmentation. We evaluated DPAtteNet on the ModelNet40, ScanObjectNN, and ShapeNet Part datasets. The experimental results confirm the effectiveness of our method. The code will be available at https://***/NWUzhouwei/DPAtteNet. © 2024 IEEE.

关键词： Feature extraction

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：