检索结果-内蒙古大学图书馆

3rd International Mobile, Intelligent, and Ubiquitous Computing Conference, MIUCC 2023

作者： Abdelminaam, Diaa Salama Madbouly, Magda M. Zeid, Magdy Abd-Elghany Abualigah, Laith Misr International University Faculty of Computer Science Cairo Egypt Benha University Faculty of Computers and Artificial Intelligence Benha Egypt Alexandria University Faculty of Computer and Data Science Alexandria Egypt Alobour High Institute for Computer and Informatics Ibrahim Abd Elatif Gomaa Computer Science Department Cairo Egypt Lebanese American University Department of Electrical and Computer Engineering Byblos13-5053 Lebanon Hourani Center for Applied Scientific Research Al-Ahliyya Amman University Amman19328 Jordan Middle East University Meu Research Unit Amman11831 Jordan School of Computer Sciences Universiti Sains Malaysia Pulau Pinang11800 Malaysia

ISBN: (纸本)9798350306231

Handwritten digit recognition is a branch of machine learning in which a computer is taught to recognize hand-written numbers. Classification and regression are applied using deep learning and machine learning algorithms. In this paper, we discussed the efficiency of different algorithms: Random Forest, KNN, Naive Bayes, SVM, CNN, and Decision Tree Algorithm. Those algorithms were applied in the handwritten digit recognition process using the MINIST data set. By comparing each algorithm by training every one of them on the data set, then by testing, we got the best algorithm to get the optimal results with the highest accuracy. After comparing the results of each algorithm, it has shown that the neural network has the best results with 97.3% classification accuracy followed by K- the nearest neighbor with 97.2%. © 2023 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Optimal Green Energy Estimation for Sustainable Electric Vehicle Networks Using Queueing-Based Retrial Process

Optimal Green Energy Estimation for Sustainable Electric Veh...

引用

Sustainable Energy Technologies and Computational Intelligence (SETCOM), International Conference on

作者： Shreekant Varshney Jainit Raval Rahul Priyadarshi Vidhi Manek Yash Dadheech Manthan Shah Department of Mathematics School of Technology Pandit Deendayal Energy University Gandhinagar Gujarat India Department of Electrical Engineering School of Energy Technology Pandit Deendayal Energy University Gandhinagar Gujarat India Symbiosis Institute of International Business Symbiosis International University Hinjewadi Pune Maharashtra India Department of Center for Data Science Center for Data Science New York University New York NY USA Department of Computer Science and Engineering School of Technology Pandit Deendayal Energy University Gandhinagar Gujarat India Department of Mechanical Engineering School of Technology Pandit Deendayal Energy University Gandhinagar Gujarat India

ISBN: (数字)9798331520540

ISBN: (纸本)9798331520557

This paper presents a stochastic model for addressing a single-server service station offering both EV charging and battery swapping services, considering the realistic retrial-based queueing behavior of the waiting individuals. A computationally efficient method is proposed for determining the steady-state probability distribution of the charging network. The approach involves analyzing the governing differential-difference equations and employing a matrix method to derive the steady-state probability distribution. Further, straightforward formulae are derived for critical system performance indicators, considering both server and system characteristics. Numerical results are visualized in the form of different graphical representations to demonstrate the influence of various parameters on system performance. Finally, the paper concludes with significant findings and future research directions to apprise researchers, decision-makers, and system designers in optimizing combined charging/swapping infrastructure.

关键词： Visualization System performance Computational modeling Stochastic processes Probability distribution Mathematical models Electric vehicle charging Steady-state Batteries Servers

来源：评论

学校读者我要写书评

暂无评论

Why Does Little Robustness Help? A Further Step Towards Understanding Adversarial Transferability

arXiv

引用

arXiv 2023年

作者： Zhang, Yechao Hu, Shengshan Zhang, Leo Yu Shi, Junyu Li, Minghui Liu, Xiaogeng Wan, Wei Jin, Hai School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Software Engineering Huazhong University of Science and Technology China School of Information and Communication Technology Griffith University Australia School of Computer Science and Technology Huazhong University of Science and Technology China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Key Laboratory of Distributed System Security China Hubei Engineering Research Center on Big Data Security China Cluster and Grid Computing Lab

Adversarial examples for deep neural networks (DNNs) have been shown to be transferable: examples that successfully fool one white-box surrogate model can also deceive other black-box models with different architectures. Although a bunch of empirical studies have provided guidance on generating highly transferable adversarial examples, many of these findings fail to be well explained and even lead to confusing or inconsistent advice for practical use. In this paper, we take a further step towards understanding adversarial transferability, with a particular focus on surrogate aspects. Starting from the intriguing "little robustness" phenomenon, where models adversarially trained with mildly perturbed adversarial samples can serve as better surrogates for transfer attacks, we attribute it to a trade-off between two dominant factors: model smoothness and gradient similarity. Our research focuses on their joint effects on transferability, rather than demonstrating the separate relationships alone. Through a combination of theoretical and empirical analyses, we hypothesize that the data distribution shift induced by off-manifold samples in adversarial training is the reason that impairs gradient similarity. Building on these insights, we further explore the impacts of prevalent data augmentation and gradient regularization on transferability and analyze how the trade-off manifest in various training methods, thus building a comprehensive blueprint for the regulation mechanisms behind transferability. Finally, we provide a general route for constructing superior surrogates to boost transferability, which optimizes both model smoothness and gradient similarity simultaneously, e.g., the combination of input gradient regularization and sharpness-aware minimization (SAM), validated by extensive experiments. In summary, we call for attention to the united impacts of these two factors for launching effective transfer attacks, rather than optimizing one while ignoring the other,

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

A Four-Pronged Defense Against Byzantine Attacks in Federated Learning

arXiv

引用

arXiv 2023年

作者： Wan, Wei Hu, Shengshan Li, Minghui Lu, Jianrong Zhang, Longling Zhang, Leo Yu Jin, Hai School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Software Engineering Huazhong University of Science and Technology China School of Information and Communication Technology Griffith University Australia School of Computer Science and Technology Huazhong University of Science and Technology China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Key Laboratory of Distributed System Security China Hubei Engineering Research Center on Big Data Security China Cluster and Grid Computing Lab

Federated learning (FL) is a nascent distributed learning paradigm to train a shared global model without violating users' privacy. FL has been shown to be vulnerable to various Byzantine attacks, where malicious participants could independently or collusively upload well-crafted updates to deteriorate the performance of the global model. However, existing defenses could only mitigate part of Byzantine attacks, without providing an all-sided shield for FL. It is difficult to simply combine them as they rely on totally contradictory assumptions. In this paper, we propose FPD, a four-pronged defense against both non-colluding and colluding Byzantine attacks. Our main idea is to utilize absolute similarity to filter updates rather than relative similarity used in existingI works. To this end, we first propose a reliable client selection strategy to prevent the majority of threats in the bud. Then we design a simple but effective score-based detection method to mitigate colluding attacks. Third, we construct an enhanced spectral-based outlier detector to accurately discard abnormal updates when the training data is not independent and identically distributed (non-IID). Finally, we design update denoising to rectify the direction of the slightly noisy but harmful updates. The four sequentially combined modules can effectively reconcile the contradiction in addressing non-colluding and colluding Byzantine attacks. Extensive experiments over three benchmark image classification datasets against four state-of-the-art Byzantine attacks demonstrate that FPD drastically outperforms existing defenses in IID and non-IID scenarios (with 30% improvement on model accuracy). © 2023, CC BY.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Scalable Optimal Margin Distribution Machine

arXiv

引用

arXiv 2023年

作者： Wang, Yilin Cao, Nan Zhang, Teng Shi, Xuanhua Jin, Hai National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology China

Optimal margin Distribution Machine (ODM) is a newly proposed statistical learning framework rooting in the latest margin theory, which demonstrates better generalization performance than the traditional large margin based counterparts. However, it suffers from the ubiquitous scalability problem regarding both computation time and memory storage as other kernel methods. This paper proposes a scalable ODM, which can achieve nearly ten times speedup compared to the original ODM training method. For nonlinear kernels, we put forward a novel distribution-aware partition method to make the local ODM trained on each partition be close and converge fast to the global one. When linear kernel is applied, we extend a communication efficient SVRG method to accelerate the training further. Extensive empirical studies validate that our proposed method is highly computational efficient and almost never worsen the generalization. Copyright © 2023, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Machine learning applications in scaffold based bioprinting

Machine learning applications in scaffold based bioprinting

引用

作者： Sun, Jie Yao, Kai Huang, Kaizhu Huang, Dejian School of Advanced Technology Xi'an Jiaotong-Liverpool University 111 Ren'ai Road Jiangsu Suzhou215123 China School of Engineering University of Liverpool The Quadrangle Brownlow HillL69 3GH Australia Data Science Research Center Duke Kunshan University Kunshan China Department of Food Science and Technology National University of Singapore 3 Science Drive 2 117542 Singapore

Bioprinting has tremendous potential to fabricate biomimetic architectures or living tissue constructs for applications in cell biology, tissue engineering and drug screening. Bioprinted constructs, called scaffolds have been extensively used in 3D cell culture systems to establish in vitro models. Diverse materials and printing mechanisms are involved in bioprinting, especially extrusion-based printing and electrohydrodynamic printing. With traditional theoretical and analytical models, it is difficult to build a scaffold biological/mechanical performance model using process parameters, fabrication structures and material properties. To link process-material-performance in a specific bioprinting process, various machine learning (ML) algorithms have been introduced because of their strong computational capability in pattern recognition and regression analysis. This paper overviews the status and progress of ML applications from several aspects: parameter optimization in the fabrication model, in situ monitoring and control, scaffold performance evaluation, and material design. Current challenges and potential solutions are also outlined, which may possibly pave the way to create a general framework that digitally integrates scaffold design, bioprinting, and performance evaluation. © 2022

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Enabling Efficient Large Recommendation Model Training with Near CXL Memory Processing

Enabling Efficient Large Recommendation Model Training with ...

引用

Annual International Symposium on computer Architecture, ISCA

作者： Haifeng Liu Long Zheng Yu Huang Jingyi Zhou Chaoqiang Liu Runze Wang Xiaofei Liaot Hai Jinf Jingling Xue National Engineering Research Center for Big Data Technology and System/Services Computing Technology and System Lab/Cluster and Grid Computing Lab Huazhong University of Science and Technology China School of Computer Science and Engineering University of New South Wales Australia Zhejiang Lab Hangzhou China

ISBN: (数字)9798350326581

ISBN: (纸本)9798350326598

Personalized recommendation systems have become one of the most important Internet services nowadays. A critical challenge of training and deploying the recommendation models is their high memory capacity and bandwidth demands, with the embedding layers occupying hundreds of GBs to TBs of storage. The advent of memory disaggregation technology and Compute Express Link (CXL) provides a promising solution for memory capacity scaling. However, relocating memory-intensive embedding layers to CXL memory incurs noticeable performance degradation due to its limited transmission bandwidth, which is significantly lower than the host memory bandwidth. To address this, we introduce ReCXL, a CXL memory disaggregation system that utilizes near-memory processing for scalable, efficient recommendation model training. ReCXL features a unified, hardwareefficient NMP architecture that processes the entire embedding training within CXL memory, minimizing data transfers over the bandwidth-limited CXL and enhancing internal bandwidth. To further improve the performance, ReCXL incorporates softwarehardware co-optimizations, including sophisticated dependencyfree prefetching and fine-grained update scheduling, to maximize hardware utilization. Evaluation results show that ReCXL outperforms the CPU-GPU baseline and the naïve CXL memory by $7.1 \times \sim 10.6 \times(9.4 \times$ on average) and $12.7 \times \sim 31.3 \times(22.6 \times$ on average), respectively.

关键词： Training Degradation Scalability Prefetching Memory management Web and internet services Bandwidth

来源：评论

学校读者我要写书评

暂无评论

JPEG Compression-Resistant Generative Image Hiding Utilizing Cascaded Invertible Networks

引用

IEEE Transactions on Information Forensics and Security 2025年 20卷 6019-6032页

作者： Tiewei Qin Bingwen Feng Bingbing Zhou Jilian Zhang Zhihua Xia Jian Weng Wei Lu College of Cyber Security Jinan University Guangzhou China College of Cyber Security Engineering Research Center for Trustworthy AI Ministry of Education Jinan University Guangzhou China School of Computer Science and Engineering Ministry of Education Key Laboratory of Information Technology Guangdong Province Key Laboratory of Information Security Technology Sun Yat-sen University Guangzhou China

Generative steganography is renowned for its exceptional undetectability. However, prevalent generative methods often have insufficient capacity for concealing secret images. Furthermore, the sensitivity of commonly utilized generative models exacerbates the challenge of ensuring robustness against channel distortions such as JPEG compression. In this paper, we introduce a generative image hiding network that employs two invertible generators to transform secret images into stego images within a disparate image domain. Additionally, we seamlessly integrate an up-and-down sampling module (UDM) within these generators to facilitate efficient decoupling of the intermediate representations obtained by each generator. The UDM serves multiple purposes: preserving coherence between the intermediate representations, enhancing resilience against JPEG compression, and safeguarding the confidentiality of the concealed images. To address the complexity of mapping both uncompressed and compressed stego images to a unified intermediary representation, we implement two distinct flows for the forward and backward processes of the generator associated with the stego images. The experimental results show that our scheme offers concurrent advantages in terms of full-size image hiding ability, undetectability, confidentiality, and robustness.

关键词： Robustness Steganography Image coding Generators Translation Transform coding Training Gaussian distribution Transforms Standards

来源：评论

学校读者我要写书评

暂无评论

Towards Demystifying Android Adware: dataset and Payload Location

Towards Demystifying Android Adware: Dataset and Payload Loc...

引用

IEEE/ACM International Conference on Automated Software engineering - Workshops (ASE Workshops)

作者： Chao Wang Tianming Liu Yanjie Zhao Lin Zhang Xiaoning Du Li Li Haoyu Wang Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Monash University Clayton Australia Huazhong University of Science and Technology Wuhan China The National Computer Emergency Response Team/Coordination Center of China (CNCERT/CC) Beijing China Beihang University Beijing China

ISBN: (数字)9798400712494

ISBN: (纸本)9798331523169

Adware represents a pervasive threat in the mobile ecosystem, yet its inherent characteristics have been largely overlooked by previous research. This work takes a crucial step towards demystifying Android adware. We present a comprehensive, well-annotated Android adware dataset AdwareZoo, which comprises 15,996 adware samples across 118 distinct adware families collected from both security reports and app repositories, providing a robust foundation for in-depth analysis and future research. We identify adware family payloads by isolating packages from adware samples for VirusTotal rescanning. Our analysis unveils critical insights into the adware ecosystem, highlighting distinctive patterns in family naming conventions and exposing the unexpected classification of widely-used ad networks as adware. We identify diverse payload location strategies, with a notable finding that over 30% of adware families employ payloads beyond conventional Java/Kotlin code. Furthermore, we reveal several evasion techniques utilized by ad-ware, including package name obfuscation and dynamic payload loading. This research not only offers a robust foundation for understanding and combating adware but also highlights the pressing need for increased scrutiny of mobile advertising practices.

关键词： Prevention and mitigation Ecosystems Loading Pressing Regulation Mobile security Security Advertising Payloads Software engineering

来源：评论

学校读者我要写书评

暂无评论

Lightweight Pedestrian Detection through Guided Filtering and Deep Learning 10

Lightweight Pedestrian Detection through Guided Filtering an...

引用

10th IEEE Global Conference on Consumer Electronics, GCCE 2021

作者： Muchtar, Kahlil Saddami, Khairun Bintang, Akhyar Cenggoro, Tjeng Wawan Pardamean, Bens Lin, Chih-Yang Ernita, Tia Universitas Syiah Kuala Department of Electrical And Computer Engineering Aceh Indonesia Universitas Syiah Kuala Department of Electrical And Computer Engineering Aceh Indonesia Bina Nusantara University School of Computer Science Bina Nusantara University Bioinformatics And Data Science Research Center Computer Science Department Jakarta Indonesia Bina Nusantara University BINUS Graduate Program-Master of Computer Science Program Bina Nusantara University Bioinformatics And Data Science Research Center Computer Science Department Jakarta Indonesia Yuan-Ze University Department of Electrical And Engineering Taoyuan Taiwan

ISBN: (纸本)9781665436762

In this paper, we propose a novel approach to locate and detect moving pedestrians in a video. Our proposed method first locates the region of interest (ROI) using a background subtraction algorithm based on guided filtering. This novel background subtraction algorithm allows our method to also filter unexpected noises at the same time, which could benefit the performance of our proposed method. Subsequently, the pedestrians are detected using YOLOv3 within the provided ROI. Our experiments showed that the proposed method has a competitive performance in the CDNET2014 dataset with a fast-processing time. © 2021 IEEE.

关键词： Convolutional neural networks

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：