检索结果-内蒙古大学图书馆

5th IEEE Global Conference for Advancement in Technology, GCAT 2024

作者： Kalpana, S. Kanimozhi, K.V. Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350376685

Cloud, sky, and sun segmentation is a crucial task for various applications, including weather analysis, environmental monitoring, and image enhancement. Motivated by the need for accurate and efficient segmentation methods, the proposed ImageNet-Architect model, a robust encoder-decoder architecture designed to segment images into three distinct classes: clouds, sky, and sun. The aim of this study is to establish a reliable segmentation standard that can accurately classify each pixel in an image into the respective categories, thereby facilitating more precise analysis and interpretation of sky conditions. The model employs convolutional layers, batch normalization, ReLU activations, and skip connections to capture high-resolution features and maintain spatial information. The ImageNet-Architect model on a dataset comprising 512 images and their corresponding ground truth masks. The model was trained using data augmentation techniques to enhance its robustness to varying conditions. The results demonstrate the model's high accuracy, with Intersection over Union (IoU) scores of 0.88 for clouds, 0.91 for sky, and 0.87 for sun. Visual comparisons between the segmented outputs and ground truth masks indicate that the model can effectively delineate the boundaries of clouds, sky, and sun under diverse conditions. The total parameters of the model are 31, 055, 297, of which 31, 043, 521 are trainable, reflecting the model's capacity for detailed feature learning. © 2024 IEEE.

关键词： Environmental monitoring

来源：评论

学校读者我要写书评

暂无评论

Design of data processing scheme of 5G terminal protocol conformance test system 4

Design of data processing scheme of 5G terminal protocol con...

引用

4th International Conference on Advances in Electrical, Computing, Communication and Sustainable Technologies, ICAECT 2024

作者： Jingyao, Cao Yadav, Amit Khan, Asif Sah, Abhishek Pratap Chengdu Neusoft University School of Computer and Software Chengdu China Charles Darwin University College of Engineering It and Environment NT Australia Integral University Department of Computer Application Lucknow India University of Electronic Science and Technology of China School of Management Science and Engineering Chengdu China

ISBN: (纸本)9798350343670

Considering the fact that the test case runs abnormally and the test case execution fails during the development and debugging of the 5G terminal protocol conformance test system. Here useful approach is implemented by embedding data copy and storage module in the system, which completes the encapsulation, copy and storage of massive data generated during the operation of the system, so that equipment developers can correctly locate the errors in the system according to the data, and repair the system loopholes to ensure the stability and accuracy of the system. © 2024 IEEE.

关键词： 5G Terminal copy and storage module protocol conformance

来源：评论

学校读者我要写书评

暂无评论

A Complex Network Analysis of Image Watermarking Scheme Based on SVD and DWT

引用

SN computer science 2024年第8期5卷 1009页

作者： Singh, Manoj Kumar Kumar, Sanoj Saini, Deepika School of Computer Science Engineering and Technology Bennett University TechZone 2 Uttar Pradesh Greater Noida 201310 India Data Science Cluster SOCS UPES Bidholi Uttarakhand Dehradun 248007 India Department of Mathematics Graphic Era (Deemed to be) University Clement Town Uttarakhand Dehradun 248002 India

An investigation of the impact that watermarking has on image statistics is presented here. This paper provides a fresh methodology that is based on the degrees of visibility graphs, in contrast to other methods that investigate variations in intensity levels. The experiment utilizes the use of twelve standard images in addition to three watermarks. The findings indicate that the conventional method of intensity difference analysis produces distributions that are inconsistent across images. As an alternative, the method that has been offered, which makes use of degrees of visibility graphs, displays normal distributions that are more consistent across all images, regardless of the watermark. In light of this, it appears that the degrees of visibility graph provides a promising independent metric for watermarking analysis that is independent of both the image and the watermark. According to the findings, the difference in degrees between the original and watermarked images occurs according to a normal distribution, with the mean falling somewhere between -0.98 and -25.93. This range appears to be quite broad, and the reason for this is the outlier. After the outliers have been removed, this range is now -0.98 to -3.54 degrees. Overall, the study indicates that analyzing the degrees of visibility graph is a more robust and informative method of evaluating the effectiveness of watermarking than directly comparing intensity levels. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Discrete wavelet transform Image moments Image watermarking Singular value decomposition Topological data analysis

来源：评论

学校读者我要写书评

暂无评论

Medical Diagnoses: Heart Disease Prediction 2

Medical Diagnoses: Heart Disease Prediction

引用

2nd International Conference on Business Analytics for Technology and Security, ICBATS 2023

作者： Mahfuri, Mahmoud Ghazal, Taher M. Mudassar, Muhammad Siddiqui, Shahan Yamin Farooq, Sajid Kanwal, Nayab Ahmad, Munir International University for Science and Technolgy Computer and Information Technolgy Department Faculty of Engineering Syria Center for Cyber Security Faculty of Information Science and Technology Selangor Bangi43600 Malaysia Skyline University College School of Information Technology University City Sharjah 1797 United Arab Emirates The University of Lahore Lahore Pakistan Minhaj University Department of Computer Science Lahore Pakistan School of Computer Science National College of Business Administration & Economics Lahore Pakistan NCBA&E School of Computer Science Lahore Pakistan Applied Science Private University Applied Science Research Center Amman11937 Jordan

ISBN: (纸本)9798350335644

The successful and continuously increasing applications of machine learning (ML) and data mining (DM) in the wide range of fields such as e-businesses, public or private sectors, marketing and retails has led the ML and DM applications in other industries and health sectors. In the health sector the data is information wise too rich but not knowledge rich. It can be due to the lack of effective tools and research study in this era. In this research work, an efficient model is proposed based on the machine learning and data mining tools to predict a particular medical disease that is the heart disease. The solution for the problem which is addressed that data is not knowledge-rich, is presented in this paper. Waikato Environment and Python is used for to analyze the data, so that an automation system can be formed. Several experiments are to be implemented to compare the performance through Supervised Learning and Unsupervised Learning. Bayesian learning (Naïve Bayes), Tree's algorithm (Decision Tree), and Neural Networks (MLPNN) are applied on the same dataset. Comparatively, Decision Tree gives best accuracy when compared with Naïve Bayes, ANN performs more effective when compared with others two Bayesian algorithms (Naïve Bayes) and Tree's algorithm (Decision tree). © 2023 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Optimizing the Performance of UAV-Based Searching Missing Persons Process Using Deep Learning 8

Optimizing the Performance of UAV-Based Searching Missing Pe...

引用

8th IEEE International Conference on Computing, Engineering and Design, ICCED 2022

作者： Javed, Hina Mantoro, Teddy Aditiawarman, Umar Nusa Putra University School of Computer Science Sukabumi Indonesia Sampoerna University Department of Computer Science Jakarta Indonesia

ISBN: (纸本)9781665453899

Searching missing persons in forest is a challenging for rescuers because of lack of guidance in area and internet connectivity. Dense forest makes it difficult for rescuers while exploring the area using any method because some time it is difficult to capture presence of human in forest area due to density (sparse) of forest area. Previous techniques using GPS and RFID searching methods sometime does not produce accurate results. For this purpose, a new technique is proposed in this research paper a UAV-Based searching missing persons process in dense forests that uses deep learning technique applied on data collected in real time to optimize the performance and searching operation with high accuracy. Searching operation needs high efficiency, reliability, and accuracy as to fast response time. So, in this research new optimized technique is purposed for efficiency in search operation. With the development artificial intelligence and drone technology Unmanned aerial vehicles (UAVs) are become increasingly popular for used in SAR operations. UAV has the overcome the issue faced in forest area search and rescue operation like fixed coverage and reach out difficult accessible areas. Therefore, it will help with for collecting missing persons data then deep learning is applied to collected images to extract human features from collected information or dataset [5]. Experiment is performed to check performance of this method that results in promised output. © 2022 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Towards Privacy-Aware and Trustworthy data Sharing Using Blockchain for Edge Intelligence

引用

Big data Mining and Analytics 2023年第4期6卷 443-464页

作者： Youyang Qu Lichuan Ma Wenjie Ye Xuemeng Zhai Shui Yu Yunfeng Li David Smith with Data61 Commonwealth Scientific and Industrial Research Organization(CSIRO)Sydney 2015Australia School of Cyber Engineering Xidian UniversityXi’an 710126China the College of Engineering and Science Victoria UniversityMelbourne 3000Australia School of Information and Communication Engineering University of Electronic Science and Technology of ChinaChengdu 610054China School of Computer Science University of Technology SydneySydney 2007Australia CNPIEC KEXIN LTD. Beijing 100020China.

The popularization of intelligent healthcare devices and big data analytics significantly boosts the development of Smart Healthcare Networks(SHNs).To enhance the precision of diagnosis,different participants in SHNs share health data that contain sensitive ***,the data exchange process raises privacy concerns,especially when the integration of health data from multiple sources(linkage attack)results in further *** attack is a type of dominant attack in the privacy domain,which can leverage various data sources for private data ***,adversaries launch poisoning attacks to falsify the health data,which leads to misdiagnosing or even physical *** protect private health data,we propose a personalized differential privacy model based on the trust levels among *** trust is evaluated by a defined community density,while the corresponding privacy protection level is mapped to controllable randomized noise constrained by differential *** avoid linkage attacks in personalized differential privacy,we design a noise correlation decoupling mechanism using a Markov stochastic *** addition,we build the community model on a blockchain,which can mitigate the risk of poisoning attacks during differentially private data transmission over *** experiments and analysis on real-world datasets have testified the proposed model,and achieved better performance compared with existing research from perspectives of privacy protection and effectiveness.

关键词： edge intelligence blockchain personalized privacy preservation differential privacy Smart Healthcare Networks(SHNs)

来源：评论

学校读者我要写书评

暂无评论

3D-HRFC: 3D-Aware Image Generation at High Resolution with Faster Convergence 21st

3D-HRFC: 3D-Aware Image Generation at High Resolution with...

引用

21st Pacific Rim International Conference on Artificial Intelligence, PRICAI 2024

作者： Xia, Qiqiang Chen, Junhong Li, Tianxiao Huang, Yiheng Asim, Muhammad Michiels, Nick Liu, Wenyin School of Computer Science and Technology Guangdong University of Technology Guangzhou510006 China Hasselt University - Flanders Make - Expertise Centre for Digital Media Diepenbeek Belgium EIAS Data Science Lab College of Computer and Information Sciences Prince Sultan University Riyadh11586 Saudi Arabia Zhongguancun Laboratory Beijing China

ISBN: (纸本)9789819601219

Learning 3D-aware generators from 2D image collections has attracted significant attention in the field of generative modeling. However, there are several challenges in generating high-resolution multi-view consistent images, e.g., 2D CNN-based approaches leverage upsampling layers to generate high-resolution images, easily resulting in inconsistencies across multi-view images;methods that generate images based on NeRF require tremendous memory space and a long time to converge. To this end, we propose a novel 3D-aware generative method named 3D-HRFC to generate high-resolution consistent images with faster convergence. Specifically, we first propose a depth fusion based super-resolution module that integrates the depth maps into the low-resolution images in order to generate consistent multi-view images. And then a skip super-resolution module is devised to enhance the generation of the high-resolution images. To generate high-resolution consistent images and accelerate the model convergence, we devise a composite loss function that consists of adversarial loss, super-resolution loss, and content consistency. Extensive experiments conducted on FFHQ and AFHQ-v2 Cats datasets illustrate that our proposed method can generate high-quality 3D-consistent images. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： 3D-aware Generation Feature Super-Resolution High-Resolution

来源：评论

学校读者我要写书评

暂无评论

Unraveling the Prediction of Fine Particulate Matter over Jaipur, India using Long Short-Term Memory Neural Network 4

Unraveling the Prediction of Fine Particulate Matter over Ja...

引用

4th International Conference on Information Management and Machine Intelligence, ICIMMI 2022

作者： Singh, Uday Pratap Saxena, Vivek Kumar, Anil Bhari, Purushottam Saxena, Deepika Department of Artificial Intelligence and Data Science Piet Rajasthan Jaipur India Department of Computer Science and Engineering Piet Rajasthan Jaipur India Department of Computer Science and Engineering Pu Rajasthan Jaipur India

ISBN: (纸本)9781450399937

Fine particulate matter (PM2.5) is a perilous air pollutant for human health, especially when present at high airborne concentrations. The national clean air program (NCAP) aims at a 40 % reduction in particulate matter by 2026. Therefore, the prediction of PM2.5 has great significance in order to cope with challenges and taking counter majors to cope with air quality issues. The annual change in PM2.5 in Jaipur from 2018 to 2019 shows a sharp decreasing trend but from 2019 to 2020 gradual increasing trend is evident. On the other hand, a sharp increasing trend from 2020 to 2021 is evident while it again starts to fall between 2021 to 2022. The air quality of Jaipur reached a good level during the lockdown period as in all other parts of the country. But now it is reaching toward Hazardous level. As most natural systems exhibit nonlinearity, the prediction of PM2.5 in this study is accomplished by utilizing the Long Short-Term Memory (LSTM) model. The model employed in this study uses several LSTM layers along with dropout and dense layers. The result of the study shows that the model used in the study captures the internal dynamics of the underlying dynamical system, which governs PM2.5. © 2022 ACM.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Multiscale Wavelet-Driven Transformer for Blade Icing Detection MWT 3

Multiscale Wavelet-Driven Transformer for Blade Icing Detect...

引用

2024 3rd International Conference on Frontiers of Artificial Intelligence and Machine Learning, FAIML 2024

作者： Xiang, Dong Cheng, Xu Chen, Sizhuo Liu, Mengna Shi, Fan Liu, Xiufeng School of Computer Science and Engineering Tianjin University of Technology China Department of Technology Management and Economics Technical University of Denmark Denmark

ISBN: (纸本)9798400709777

Currently, the global demand for green wind power generation is increasing day by day. However, the icing of fan blades can significantly reduce the efficiency of fan power generation, highlighting the increasing importance of efficiently detecting whether the wind turbine is icing. In the traditional approach, the operation status of wind turbines is manually collected. However, with technological advancements, the SCADA system now automatically collects the continuous operational status of wind turbines. Nevertheless, However, the monitored operational data suffers from data imbalance. In this study, we introduce a multi-level neural network built upon the Trans- former architecture. Specifically, to extract multi-level features from the time and frequency domains, we utilize discrete wavelet decomposition. By leveraging the self-attention mechanism of the Transformer, we enhance the feature extraction capabilities for predictive tasks. We investigate data resampling methods to address the data imbalance problem. Comprehensive studies demonstrate that our proposed algorithm improves F1 scores to 90.08%, 81.70%, and 76.21% on datasets processed using data resampling algorithms. The obtained icing detection results validate the applicability of our approach and demonstrate that adopting this algorithm can enhance the accuracy. © 2024 Copyright held by the owner/author(s).

关键词： Wavelet decomposition

来源：评论

学校读者我要写书评

暂无评论

Target Recognition Using Pre-Trained Convolutional Neural Networks and Transfer Learning 2

Target Recognition Using Pre-Trained Convolutional Neural Ne...

引用

2nd International Conference on Machine Learning and data Engineering, ICMLDE 2023

作者： Mishra, Gangeshwar Gupta, Prinima Tanwar, Rohit Department of CST MRU Haryana Faridabad India School of Computer Science University of Petroleum and Energy Studies Uttarakhand Dehradun India

In modern surveillance, automatic target recognition (ATR) is a critical challenge, necessitating rapid and precise object identification, especially in military and disaster response scenarios. This research presents a comprehensive framework for ground target classification, focusing on Synthetic Aperture Radar (SAR) imagery. Harnessing the Moving and Stationary Target Acquisition and Recognition (MSTAR) Mixed Targets dataset, this study integrates Convolutional Neural Networks (CNNs) into SAR image analysis. Transfer learning emerges as a key strategy, adapting insights from pre-trained CNNs to the intricacies of target recognition in SAR imagery. This approach outperforms traditional methods, enhancing efficiency amid dataset annotation challenges. Noteworthy CNN architectures including DarkNet-19, DenseNet-121, InceptionV4, ResNet-152, and VGG19 are explored. The ResNet-152 model demonstrates exceptional performance, emerging as a leading contender with a remarkable testing accuracy of 98.56% when trained from scratch. Furthermore, by employing transfer learning, the model's accuracy may be further enhanced to reach 98.81% on the testing dataset. This research signifies a transformative SAR imagery path guided by pre-trained CNNs and transfer learning. It reshapes ATR's accuracy and efficiency, pointing to a future where innovation surmounts challenges previously deemed insurmountable. © 2024 Elsevier B.V.. All rights reserved.

关键词： Efficiency

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：