检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Baumann, Lena Einkemmer, Lukas Klingenberg, Christian Kusch, Jonas University of Wuerzburg Department of Mathematics Wuerzburg Germany University of Innsbruck Numerical Analysis and Scientific Computing Innsbruck Austria Norwegian University of Life Sciences Department of Data Science Ås Norway

computing numerical solutions of the thermal radiative transfer equations on a finely resolved grid can be costly due to high computational and memory requirements. A numerical reduced order method that has recently been applied to a wide variety of kinetic partial differential equations is the concept of dynamical low-rank approximation (DLRA). In this paper, we consider the thermal radiative transfer equations with Su-Olson closure, leading to a linearized kinetic model. For the conducted theoretical and practical considerations we use a multiplicative splitting of the distribution function that poses additional challenges in finding an energy stable discretization and deriving a hyperbolic Courant-Friedrichs-Lewy (CFL) condition. We propose such an energy stable DLRA scheme that makes use of the augmented basis update & Galerkin integrator. This integrator allows for additional basis augmentations, enabling us to give a mathematically rigorous proof of energy stability and local mass conservation. Numerical examples confirm the derived properties and show the computational advantages of the DLRA scheme compared to a numerical solution of the full system of *** Codes 35L65, 35Q49, 65M12, 65M22 © 2025, CC BY-NC-ND.

关键词： Radiative transfer

来源：评论

学校读者我要写书评

暂无评论

Black-box Backdoor Defense via Zero-shot Image Purification

arXiv

引用

arXiv 2023年

作者： Shi, Yucheng Du, Mengnan Wu, Xuansheng Guan, Zihan Sun, Jin Liu, Ninghao School of Computing University of Georgia United States Department of Data Science New Jersey Institute of Technology United States

Backdoor attacks inject poisoned samples into the training data, resulting in the misclassification of the poisoned input during a model’s deployment. Defending against such attacks is challenging, especially for real-world black-box models where only query access is permitted. In this paper, we propose a novel defense framework against backdoor attacks through Zero-shot Image Purification (ZIP). Our framework can be applied to poisoned models without requiring internal information about the model or any prior knowledge of the clean/poisoned samples. Our defense framework involves two steps. First, we apply a linear transformation (e.g., blurring) on the poisoned image to destroy the backdoor pattern. Then, we use a pre-trained diffusion model to recover the missing semantic information removed by the transformation. In particular, we design a new reverse process by using the transformed image to guide the generation of high-fidelity purified images, which works in zero-shot settings. We evaluate our ZIP framework on multiple datasets with different types of attacks. Experimental results demonstrate the superiority of our ZIP framework compared to state-of-the-art backdoor defense baselines. We believe that our results will provide valuable insights for future defense methods for black-box models. Our code is available at https://***/sycny/ZIP. © 2023, CC BY-NC-ND.

关键词： Purification

来源：评论

学校读者我要写书评

暂无评论

SOCA-DOM:A Mobile System-on-Chip Array System for Analyzing Big data on the Move

引用

Journal of Computer science & Technology 2022年第6期37卷 1271-1289页

作者： Le-Le Li Jiang-Yi Liu Jian-Ping Fan Xue-Hai Qian Kai Hwang Yeh-Ching Chung Zhi-Bin Yu Center for Heterogeneous and Intelligent Computing Shenzhen Institutes of Advanced Technology Chinese Academy of SciencesShenzhen 518055China School of Science and Engineering The Chinese University of Hong KongShenzhenShenzhen 518172China Center for High Performance Computing Shenzhen Institutes of Advanced TechnologyChinese Academy of Sciences Shenzhen 518055China Ming Hsieh Department of Electrical and Computer Engineering University of Southern CaliforniaLos Angeles CA 90089-0001U.S.A. Department of Computer Science University of Southern CaliforniaLos AngelesCA 90089-0001U.S.A. School of Data and Science The Chinese University of Hong KongShenzhenShenzhen 518172China

Recently,analyzing big data on the move is *** requires that the hardware resource should be low volume,low power,light in weight,high-performance,and highly scalable whereas the management software should be flexible and consume little hardware *** meet these requirements,we present a system named SOCA-DOM that encompasses a mobile system-on-chip array architecture and a two-tier“software-defined”resource manager named ***,we design an Ethernet communication board to support an array of mobile ***,we propose a two-tier software architecture for Chameleon to make it ***,we devise data,configuration,and control planes for Chameleon to make it“software-defined”and in turn consume hardware resources on ***,we design an accurate synthetic metric that represents the computational power of a computing *** employ 12 Apache Spark benchmarks to evaluate ***,SOCA-DOM consumes up to 9.4x less CPU resources and 13.5x less memory than Mesos which is an existing resource *** addition,we show that a 16-node SOCA-DOM consumes up to 4x less energy than two standard Xeon *** on the results,we conclude that an array architecture with fine-grained hardware resources and a software-defined resource manager works well for analyzing big data on the move.

关键词： edge computing mobile architecture resource management big data analytics software-defined systems

来源：评论

学校读者我要写书评

暂无评论

Know Your Chemistry Set: Exploring Chemical Laboratory Object Detection Using YOLOv8 and YOLOv9

Know Your Chemistry Set: Exploring Chemical Laboratory Objec...

引用

International Conference on Computer and Information Technology (ICCIT)

作者： Jahid Hasan Siddiqui Raihan Uddin Ahmed Adnan Ferdous Ashrafi Sumiya Arafin School of Computing Mathematics and Data Science Coventry University United Kingdom Department of Electrical and Electronic Engineering Stamford University Bangladesh Department of Computer Science and Engineering Stamford University Bangladesh Department of Computer Science and Engineering Brac University Bangladesh

ISBN: (数字)9798331519094

ISBN: (纸本)9798331519100

Image object detection (IOD) has proven its usefulness from diagnosing critical diseases from medical image analysis to pedestrian recognition in autonomous vehicle tracking. Considering the potential applications of object detection in real-life scenarios, various deep learning-based algorithms have been used in recent years. However, one unexplored sector of object detection is its application in critical environments like a chemical lab. Automatic apparatus/chemical reagent/machine detection can lessen the effect of chemical hazards in these environments as well as can be used to ensure efficient usage of laboratory resources. In this study, the potential of you only look once (YOLO) has been explored for the detection of chemical apparatus from a comprehensive image dataset. The study was validated against a dataset of 5078 images containing 7 different most commonly used chemistry laboratory apparatus that are used chemical laboratory. Our experimentation demonstrates state-of-the-art performance on the detection of objects with an impressive mAP of 0.818 and 0.865 using YOLOv8 and YOLOv9 architectures respectively.

关键词： YOLO Chemistry Pedestrians Laboratories Transformers Real-time systems Safety Information technology Chemicals Medical diagnostic imaging

来源：评论

学校读者我要写书评

暂无评论

Intelligent Posture Detection System for Improved Ergonomics

Intelligent Posture Detection System for Improved Ergonomics

引用

2025 International Conference on Intelligent Control, computing and Communications, IC3 2025

作者： Patil, Jay Joshi, Suvarna Mulla, Rahesha Yadav, Kushal Mit School of Computing Mit Adt University Department of Computer Science and Eng. Pune India University Department of Artificial Intelligence and Machine Learning Pune India Indian Institute of Technology Madras Department of Data Science India

ISBN: (纸本)9798331527495

This paper introduces a cost-effective smart posture detection system aimed at promoting ergonomic sitting habits and preventing musculoskeletal disorders. The system integrates ultrasonic sensors for backrest proximity measurement and load cells for seat weight distribution analysis. By analyzing these inputs, it identifies posture irregularities and provides real-time feedback for corrective action. Testing results demonstrate the system's reliability, achieving a detection accuracy of 99% across users with varying body types and postures. The proposed hybrid approach ensures simplicity, affordability, and scalability, making it a viable solution for homes, workplaces, and schools. This research contributes to the growing field of smart health monitoring systems, offering a practical alternative to traditional posture correction methods. © 2025 IEEE.

关键词： Ultrasonic testing

来源：评论

学校读者我要写书评

暂无评论

Continuous Tweet Stream Analysis using Apache Spark Streaming API & Kafka 15

Continuous Tweet Stream Analysis using Apache Spark Streamin...

引用

15th International Conference on Advances in computing, Control, and Telecommunication Technologies, ACT 2024

作者： Nisha, A.G. Shivaprasad, N. Nischitha, C.B. Shashikala, B.M. Sujithra, M. Chaba, Yogesh Electronics & Communications Engineering JSS Science & Technology University Mysuru India Dept.of Electronics & Communications Engineering Sri Jayachamarajendra College of Engineering JSS Science & Technology University Mysuru India Dept.of Computer Science St.Joseph's First Grade College Mysore India Dept.of Computer Applications Sri Jayachamarajendra College of Engineering JSS Science & Technology University Mysuru India Department of Computing-Data Science Coimbatore Institute of Technology Coimbatore India Department of Computer Science and Engineering Guru Jambeshwar University of Science and Technology Haryana Hisar India

ISBN: (纸本)9798331300579

Social media has become a trend nowadays people are spending more time in social media platform like Facebook, Twitter, Instagram to share their opinions, creating new interests, ideas and generate *** provide a major platform for collecting information which helps us to analyze them for our *** such microblogging social network is twitter which allows information collaboration and quick information sharing that provides relief from rising *** has several millions of people tweeting and expressing their perspectives on a due to its distinctively brief and straightforward expressing *** enormous volume of raw data from tweets can be utilised for analysis and processing based on industrial or business *** this technical paper, the application of tweet sentiment analysis by extracting a vast number of tweets using continuous tweet stream provided by Spark and Kafka has been *** system fetches live tweets from Twitter based on the search criteria, process the tweets, by using text mining techniques and classify them based on different labels. © Grenze Scientific Society, 2024.

关键词： Tweets

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Method for the Diagnosis of Retinal Diseases using Convolutional Neural Network

Machine Learning Method for the Diagnosis of Retinal Disease...

引用

2023 International Conference on data science, Agents and Artificial Intelligence, ICDSAAI 2023

作者： Kushwaha, Sumit Boga, Jayaram Rao, Bairaboina Sai Sambasiva Taqui, Syed Noeman Vidhya, R.G. Surendiran, J. University Institute of Computing Chandigarh University Department of Computer Applications Punjab India Marri Laxman Reddy Institute of Technology and Management Department of Computer Science and Data Science Telangana Hyderabad India Koneru Lakshmaiah Education Foundation Department of Computer Science and Engineering Andhra Vaddeswaram India Saveetha Institute of Medical and Technical Sciences Saveetha School of Engineering Department of Vlsi Microelectronics Tamil Nadu Chennai India Hkbk College of Engineering Department of Ece Bangalore India

ISBN: (纸本)9798350348910

The early diagnosis of visual problems such as diabetic retinopathy and glaucoma relies on the successful completion of medical image processing tasks such as the segmentation of retinal blood vessels. The process of isolating retinal blood vessels from images of the retinal fundus is a challenging one because of the similarities in intensity that exist between blood vessels and the surrounding tissues. In addition, there are differences in the size, shape, and intensity of the vessels. In recent times, a number of different algorithms based on deep learning have been presented for the segmentation of retinal blood vessels. These techniques have been shown to be more accurate and dependable when compared to the traditional computer vision methods that have been used. In this abstract, we present the U-Net deep learning model as well as a technique for segmenting retinal blood vessels that is based on the programming language Python. A U-Net model is trained using a series of retinal fundus images so that the features of retinal blood vessels may be comprehended. As part of the inference process, the image of the retinal fundus is loaded into a trained version of the U-Net model. This model then generates a probability map that illustrates the chance that each pixel represents an artery in the human body. The final segmentation is produced by applying a threshold to the probability map. When it comes to the process of segmenting retinal blood vessels, our python-based solution outperforms methods that are considered to be state-of-the-art in studies comparing accuracy and speed. The scientific and medical communities have unrestricted access to the software that may be used to put the suggested strategy into action since it is an open-source initiative. In conclusion, the python-based approach for retinal blood vessel segmentation that makes use of U-Net provides a potentially helpful solution for identifying retinal illnesses and has the potential to serve as a stan

关键词： Python

来源：评论

学校读者我要写书评

暂无评论

XGBD: Explanation-Guided Graph Backdoor Detection

arXiv

引用

arXiv 2023年

作者： Guan, Zihan Du, Mengnan Liu, Ninghao School of Computing University of Georgia United States Department of Data Science New Jersey Institute of Technology United States

Backdoor attacks pose a significant security risk to graph learning models. Backdoors can be embedded into the target model by inserting backdoor triggers into the training dataset, causing the model to make incorrect predictions when the trigger is present. To counter backdoor attacks, backdoor detection has been proposed. An emerging detection strategy in the vision and NLP domains is based on an intriguing phenomenon: when training models on a mixture of backdoor and clean samples, the loss on backdoor samples drops significantly faster than on clean samples, allowing backdoor samples to be easily detected by selecting samples with the lowest loss values. However, the ignorance of topological feature information on graph data limits its detection effectiveness when applied directly to the graph domain. To this end, we propose an explanation-guided backdoor detection method to take advantage of the topological information. Specifically, we train a helper model on the graph dataset, feed graph samples into the model, and then adopt explanation methods to attribute model prediction to an important subgraph. We observe that backdoor samples have distinct attribution distribution than clean samples, so the explanatory subgraph could serve as more discriminative features for detecting backdoor samples. Comprehensive experiments on multiple popular datasets and attack methods demonstrate the effectiveness and explainability of our method. Our code is available: https://***/GuanZihan/GNN_backdoor_detection. © 2023, CC BY.

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of GCN, GNN, and GAT Models with Differentiable Pooling for Detection of Fake News

Performance Analysis of GCN, GNN, and GAT Models with Differ...

引用

Delhi Section Conference (DELCON), IEEE

作者： Prisha Gupta P. K. Gupta Amrita School of Artificial Intelligence Amrita Vishwa Vidhyapeetham Coimbatore India Department of Data Science School of Computing Mohan Babu University Tirupati India

ISBN: (数字)9798331518592

ISBN: (纸本)9798331518608

In the era of social networks, the spread of fake news has become a critical issue that poses significant challenges to society. It is often difficult to distinguish between real news and fake news due to the sophisticated methods used to create misleading information. This paper presents a comprehensive approach to detecting fake news. The study conducts a systematic review of the performance of the Graph Convolutional Networks (GCN), Graph Attention Networks (GAT), and Graph Neural Networks using DiffPool (GNN-DP) in Twitter data. It takes into account the limitations identified in the previous studies and fine-tunes the parameters to obtain better results. Performance evaluation of the proposed model was done using metrics such as accuracy, F1 score, and area under the curve (AUC). In the results obtained, it is found that GCN, with its dynamic attention mechanism, outperforms GAT and GNN-DP by effectively highlighting the most relevant information within the graph. Next, we discuss the practical implications of fake news detection and the GCN model. Finally, we present the future scope in this area for further research.

关键词： Performance evaluation Analytical models Social networking (online) Graph convolutional networks Directed graphs Manuals Chatbots Performance analysis Fake news Systematic literature review

来源：评论

学校读者我要写书评

暂无评论

Truly Multivariate Structured Additive Distributional Regression

arXiv

引用

arXiv 2023年

作者： Kock, Lucas Klein, Nadja Department of Statistics and Data Science National University of Singapore Singapore Scientific Computing Center Karlsruhe Institute of Technology Germany

Generalized additive models for location, scale and shape (GAMLSS) are a popular extension to mean regression models where each parameter of an arbitrary parametric distribution is modelled through covariates. While such models have been developed for univariate and bivariate responses, the truly multivariate case remains extremely challenging for both computational and theoretical reasons. Alternative approaches to GAMLSS may allow for higher-dimensional response vectors to be modelled jointly but often assume a fixed dependence structure not depending on covariates or are limited with respect to modelling flexibility or computational aspects. We contribute to this gap in the literature and propose a truly multivariate distributional model, which allows one to benefit from the flexibility of GAMLSS even when the response has dimension larger than two or three. Building on copula regression, we model the dependence structure of the response through a Gaussian copula, while the marginal distributions can vary across components. Our model is highly parameterized but estimation becomes feasible with Bayesian inference employing shrinkage priors. We demonstrate the competitiveness of our approach in a simulation study and illustrate how it complements existing approaches along the examples of childhood malnutrition and a yet unexplored data set on traffic detection in Berlin. Copyright © 2023, The Authors. All rights reserved.

关键词： Additives

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：