检索结果-内蒙古大学图书馆

Communication, computer sciences and engineering (IC3SE), International Conference on

作者： Swathi Baswaraju M Geeta Yadav Ginni Nijhawan Ajay Rana T K. Pushpa Rani Taqi Mohammed Khattab Al-Rubaye Department of Computer Science – Data Science New Horizon College of Engineering Bangalore India Department of Computer Science And Engineering Institute Of Aeronautical Engineering Hyderabad Telangana India Lovely Professional University Phagwara India Amity School of Engineering and Technology Amity University Greater Noida India Department of Computer Science and Engineering MLR Institute of Technology Hyderabad Telangana India Department of Medical Laboratory Technology College Of Medical Technologies The Islamic University Najaf Iraq

ISBN: (数字)9798350366846

ISBN: (纸本)9798350366853

data analysis, private protection, detecting unusual things, identifying people, and transferring data are part of the study's unique security design. The major system method is AUA. Your authentication level depends on your activity, device, and location. Context-aware Privacy uses AUA to tailor user privacy options. Encrypting AES data transfers with Secure data Transfer (SDT) is offered. Machine learning anomaly detection (ADML) analyzes user behavior and implements security measures to uncover vulnerabilities rapidly. DPDA employs controlled noise to make it statistically tougher to identify a person while processing data to safeguard privacy. Ablation study indicates adaptive security design strategies function better together. The recommended design may be safer and easier to employ with visual models and performance testing. With this knowledge, managers may be able to create business-friendly security solutions. Finally, the framework's extensive and adaptable security models boost digital safety. It offers new privacy protection in the internet age.

关键词： Privacy data privacy Adaptation models Visualization data analysis Machine learning data transfer

来源：评论

学校读者我要写书评

暂无评论

Channel-wise attention based binarization for CNN Architectures

Channel-wise attention based binarization for CNN Architectu...

引用

Emerging Systems and Intelligent Computing (ESIC), International Conference on

作者： Ipsita Paul Mainak Bandyopadhyay Satya Ranjan Dash Tanjim Taharat Aurpa School of Computer Engineering KIIT D.U. Bhubaneswar India School of Computer Applications KIIT D.U. Bhubaneswar India Department of Data Science Engineering BSMR Digital University Bangladesh

ISBN: (数字)9798331522100

ISBN: (纸本)9798331522117

Attention mechanisms are known to effectively increase the performance of a model by focusing on specific sections of the input while executing a task. Squeeze and Excitation module (SE-Net) and Efficient channel attention module (ECA-Net) are well-known Channel Attention networks that only involve a few parameters to achieve a clear performance gain. In order to further improve the model’s accuracy, Binarized Neural Networks (BNNs) can be introduced in the same. BNNs are deep learning models that use binarized values for activation functions and training weights, instead of fully precised values that leads to much faster computation, occupying less memory and power. Motivated by this, a method of binarization of the convolutional network is proposed in this paper that can enhance the overall model accuracy. In our work, we focused on evaluating the performance of our binarized attention module over the pre-existing ones. Thus, the objective of this work is to design, implement, and evaluate efficient neural network models that balance accuracy and computational efficiency for image classification tasks on datasets with differing complexity levels, such as CIFAR-10 and CIFAR-100. By exploring various backbone architectures (e.g., MobileNetV2 and ResNet50), attention mechanisms (e.g., ECANet and SENet), and binarization techniques, this study aims to understand the impact of these components on model performance and resource requirements. Ultimately, the goal is to develop optimized models that achieve high accuracy with minimal computational overhead, making them suitable for deployment in resource-constrained environments.

关键词： Deep learning Training Attention mechanisms Accuracy Computational modeling Neural networks Transfer learning Convolutional neural networks Image classification Residual neural networks

来源：评论

学校读者我要写书评

暂无评论

Exploring the Potential of Large Vision-Language Models for Unsupervised Text-Based Person Retrieval 39

Exploring the Potential of Large Vision-Language Models for ...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Li, Zongyi Jianbo, Li Shi, Yuxuan Chen, Jiazhong Huang, Shijuan Tu, Linnan Shen, Fei Ling, Hefei Department of Computer Science and Technology Huazhong University of Science and Technology China National Engineering Research Center of Educational Big Data The Faculty of Artificial Intelligence in Education Central China Normal University China Nanjing University of Science and Technology China

ISBN: (纸本)157735897X

The aim of text-based person retrieval is to identify pedestrians using natural language descriptions within a large-scale image gallery. Traditional methods rely heavily on manually annotated image-text pairs, which are resource-intensive to obtain. With the emergence of Large Vision-Language Models (LVLMs), the advanced capabilities of contemporary models in image understanding have led to the generation of highly accurate captions. Therefore, this paper explores the potential of employing Large Vision-Language Models for unsupervised text-based pedestrian image retrieval and proposes a Multi-grained Uncertainty Modeling and Alignment framework (MUMA). Initially, multiple Large Vision-Language Models are employed to generate diverse and hierarchically structured pedestrian descriptions across different styles and granularities. However, the generated captions inevitably introduce noise. To address this issue, an uncertainty-guided sample filtration module is proposed to estimate and filter out unreliable image-text pairs. Additionally, to simulate the diversity of styles and granularities in captions, a multi-grained uncertainty modeling approach is applied to model the distributions of captions, with each caption represented as a multivariate Gaussian distribution. Finally, a multi-level consistency distillation loss is employed to integrate and align the multi-grained captions, aiming to transfer knowledge across different granularities. Experimental evaluations conducted on three widely-used datasets demonstrate the significant advancements achieved by our approach. © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Gaussian distribution

来源：评论

学校读者我要写书评

暂无评论

Earthquake Damage Prediction and Rapid Assessment of Building Damage Using Machine Learning.

Earthquake Damage Prediction and Rapid Assessment of Buildin...

引用

Advancement in Technology (ICONAT), International Conference for

作者： Yuvaraj Natarajan Gitanjali Wadhwa Preethi Akshaya Ranganathan Karthika Natarajan Dept. of Computer Science and Engineering KPR Institute of Engineering and Technology Coimbatore India Dept. of Artificial Intelligence and Data Science KPR Institute of Engineering and Technology Coimbatore India

A quick forecast of the region’s structural damage following an earthquake is crucial for community relief and rescue efforts. Following an earthquake, getting detailed information about buildings in seismic disaster zones is frequently impossible. The information available is essential to estimate seismic damage to urban structures accurately. To address the aforementioned issues, we propose a novel method for quickly assessing building damage through extensive use of field research and data collected from earth observation. A model is created and trained to predict building damage from an earthquake. The algorithm used to indicate the building damage from the quake is Elastic net regression. The elastic net is a regularized regression method used to predict building damage from an earthquake. The proposed Elastic net regression is validated with standard accuracy and effectiveness compared with the Random forest and decision tree methods. The proposed model’s outcomes show that elastic net regression is the most effective predictive model for predicting building damage.

关键词： Measurement Machine learning algorithms Buildings Earthquakes Predictive models Prediction algorithms data models

来源：评论

学校读者我要写书评

暂无评论

An Encoder-Based Framework for Privacy-Preserving Machine Learning 24th

An Encoder-Based Framework for Privacy-Preserving Machine L...

引用

24th International Conference on Algorithms and Architectures for Parallel Processing, ICA3PP 2024

作者： Wu, Jiayun Ren, Wei Zhang, Xianchao Zheng, Xianghan School of Computer Science China University of Geosciences Wuhan430074 China State Key Laboratory of Geo-Information Engineering and Key Laboratory of Surveying and Mapping Science and Geospatial Information Technology of MNR CASM Beijing China Ministry of Education Chengdu China Key Laboratory of Medical Electronics and Digital Health of Zhejiang Province Jiaxing University Jiaxing China Engineering Research Center of Intelligent Human Health Situation Awareness of Zhejiang Province Jiaxing University Jiaxing China College of Computer and Big Data Fuzhou University Fujian Fuzhou China School of Information and Intelligent Engineering Sanya College Hainan China

ISBN: (纸本)9789819615506

As a data-driven science, machine learning requires vast amounts of training data and computational resources. However, for highly privacy-sensitive data, it is crucial to protect the privacy of the data during both the training and utilization of machine learning models. In this paper, we propose a privacy-preserving machine learning approach using autoencoders and differential privacy mechanisms to safeguard data privacy while minimizing the impact on data availability. Specifically, we augment logistic regression and ResNet18 models with different architectures of autoencoders to perform data encryption? without compromising the machine learning tasks. Additionally, we employ differential privacy mechanisms to introduce gradient perturbations in the encoding part of the autoencoder, enhancing the algorithm’s security and further protecting data privacy. We also design the cosine similarity between the encoded and original data as a metric for evaluating data privacy, considering model performance, privacy budget, and data privacy collectively to balance data availability and privacy. Extensive experiments conducted on MNIST, CIFAR-10, PathMNIST, and BloodMNIST datasets demonstrate that for simple logistic regression models handling easily classifiable datasets, employing simple autoencoder structures can enhance classification accuracy, with significant performance impact after adding differential privacy. For ResNet18, utilizing convolutional autoencoders for data encryption generally has minimal impact on model classification performance and can even improve accuracy in most cases. Adding differential privacy has minor effects on model classification performance. Selecting appropriate model structures and privacy budgets for different usage scenarios can ensure both data availability and privacy. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

An Attention-Based Model for Clinical Time Series Prediction: Enhancing ICU Readmission Prediction

An Attention-Based Model for Clinical Time Series Prediction...

引用

International eConference on computer and Knowledge engineering (ICCKE)

作者： Hananeh Sadat Madinei Mohammad Reza Keyvanpour Seyed Vahab Shojaedini Department of Computer Engineering Data Mining Laboratory Faculty of Engineering Alzahra University Tehran Iran Department of Electrical Engineering Iranian Research Organization for Science and Technology Tehran Iran

ISBN: (数字)9798331511272

ISBN: (纸本)9798331511289

In recent years, time series prediction has become a highly interesting topic in various applied areas, including clinical time series analysis. Hospitals and other clinical healthcare systems collect Electronic Health Records. These records contain important information that needs to be mined. This information provides a solid basis for predicting hospital readmission, helping to improve healthcare, enhance patient outcomes, and optimize hospital resources. This study introduces a novel deep learning attention-based approach for predicting 30-day ICU readmissions using clinical time series information extracted from the MIMIC III dataset. This approach incorporates time-aware positional encoding into the attention mechanism to enhance predictive performance by capturing the temporal representation of data and considering the temporal order of clinical time series data. This model is compared with cutting-edge models. The significant enhancements in the model performance achieved by the proposed method highlight the effectiveness of incorporating time-aware positional encoding in capturing temporal dependencies and improving prediction outcomes. These results underscore the potential of advanced attention mechanisms in clinical time series analysis.

关键词： Deep learning Analytical models Attention mechanisms Hospitals Computational modeling Time series analysis Predictive models Encoding data models Electronic medical records

来源：评论

学校读者我要写书评

暂无评论

Video Stabilization via Prediction with Time-Series Network and Image Inpainting with Pyramid Fusion

引用

Chinese Journal of Electronics 2021年第6期30卷 1103-1110页

作者： CHENG Keyang LI Shichao RONG Lan WANG Wenshan SHI Wenxi ZHAN Yongzhao School of Computer Science and Communication Engineering Jiangsu University Jiangsu Province Big Data Ubiquitous Perception and Intelligent Agricultural Application Engineering Research Center Cyber Space Security Academy of Jiangsu University National Engineering Laboratory for Public Safety Risk Perception and Control by Big Data Xinjiang Lianhaichuangzhi Information Technology Co. Ltd.

Due to the poor filling effect of the video image defect commonly used in the video stabilization field, the video is seemed still unstable after the image stabilization process, which seriously affects the visual effect. To solve this problem, we improve a video stabilization method based on time-series network prediction and pyramid fusion restoration is proposed to optimize the visual effect after image *** flow of the proposed method is as follows: First,it is adaptive to determine whether the defect of the corresponding frame at the current time needs padding inpainting. Then, for the frame that needs to be inpainting,the frames generated before the current moment are sent to the model combining the convolutional neural networks and the gate recurrent unit to predict the part to be filled. Next the current defect image and the complete image to be filled are brought into the Laplacian pyramid reconstruction, and the improved weighted optimal suture is introduced for splicing during the fusion. Finally, the video frame is cut after reconstruction. The method is tested on a data set composed of videos commonly used in the field of video stabilization. The experimental results show that the average peak signal to noise ratio of the method is 2 to 5 d B higher than that of the comparison algorithm, and the average structural similarity index is improved by about 2% to 7% compared with the contrast algorithm.

关键词： image restoration image sequences video frame cutting improved weighted optimal suture gate recurrent unit video signal processing video stabilization method image fusion Laplacian pyramid reconstruction padding inpainting image resolution neural nets convolutional neural networks video image defect pyramid fusion restoration image inpainting visual effect optimization image reconstruction time-series network prediction image stabilization process

来源：评论

学校读者我要写书评

暂无评论

Negative Adversarial Example Generation Against Naver's Celebrity Recognition API 1

Negative Adversarial Example Generation Against Naver's Cele...

引用

1st ACM Workshop on Security Implications of Deepfakes and Cheapfakes, WDC 2022, co-located with ACM AsiaCCS 2022

作者： Kim, Keeyoung Woo, Simon S. State University of New York Korea Republic of Stony Brook University & IngenioAI Seoul Korea Republic of Department of Artificial Intelligence Applied Data Science Department Computer Science & Engineering Department Sungkyunkwan University Suwon Korea Republic of

ISBN: (纸本)9781450391788

Deep Neural Networks (DNNs) are very effective in image classification, detection and recognition due to a large number of available data. However, they can be easily fooled by adversarial examples and produce incorrect results, which can cause problems for many applications. In this work, we focus on generating adversarial images and exploring and assessing possible negative impacts caused by these examples. As a case study, we create adversarial images against Naver's celebrity recognition (NCR) API, as Naver is the leading machine learning APIs service provider in South Korea. We demonstrate that it is extremely easy to fool the online DNN-based APIs using adversarial examples and discuss possible negative impacts resulting from these adversarial examples. © 2022 ACM.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Deep learning Arabic printed document knowledge extraction 5

Deep learning Arabic printed document knowledge extraction

引用

5th International Conference on Future Networks and Distributed Systems: The Premier Conference on Smart Next Generation Networking Technologies, ICFNDS 2021

作者： Alghamdi, Taghreed Snoussi, Samia Hsairi, Lobna Department of Computer Science College of Computer Science and Engineering University of Jeddah Jeddah Saudi Arabia Data Science Department University of Jeddah Saudi Arabia University of Tunis ElManar University Tunisia

ISBN: (纸本)9781450387347

This paper presents how to utilize deep learning to extract knowledge from Arabic printed document images. The fundamental goal of deep learning is automatically extracting significant features from images, eliminating the need for a classic feature extraction method. We describe how to extract high-quality and coherent knowledge from Arabic printed document images using deep learning. This system is constructed on keywords used to classify Arabic document images according to these keywords. We used A questionnaire to choose valuable words according to historical, scientific, or religious documents. The evaluation of the proposed system is applied to Arabic printed document images to extract keywords. The accuracy of the proposed deep learning extraction approach is hugely affected by image preprocessing and image quality. The proposed system has a higher level of accuracy while extracting keywords. We achieve a 3.78% character error rate in the proposed system and a 15.46% word error rate. © 2021 ACM.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

A consensus model for linguistic group decision making considering emotion analysis 10

A consensus model for linguistic group decision making consi...

引用

10th International Conference on Information Technology and Quantitative Management, ITQM 2023

作者： Xu, Mengru Jing, Fuying Chao, Xiangrui Herrera-Viedma, Enrique School of Management Science and Engineering Chongqing Technology and Business University Chongqing400067 China National Research Base of Intelligent Manufacturing Service Chongqing Technology and Business University Chongqing400067 China School of Business Sichuan University Chengdu610065 China Andalusian Research Institute in Data Science and Computational Intelligence Department of Computer Science and Artificial Intelligence University of Granada Granada18071 Spain

In a problem of linguistic group decision-making (GDM), various emotional characteristics of decision-makers' (DMs) behind their preference series, which is defined as emotion factor, can impact consensus reaching process. As words mean different things to different people, this study comprehensively proposes a novel consensus model with emotion factors based on personalized individual semantics. An improved grey clustering method facilitates to obtain emotion factors. Finally, the proposal model can provide more accurate judgments for moderator's management and further promote consensus. © 2023 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (https://***/licenses/by-nc-nd/4.0) Peer-review under responsibility of the scientific committee of the Tenth International Conference on Information Technology and Quantitative Management.

关键词： Semantics

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：