检索结果-内蒙古大学图书馆

Advancing knowledge management in machine-to-machine communication - A comparative analysis of stacked ensembles for IoT device classification mechanisms

引用

AIP Conference Proceedings 2024年第1期3214卷

作者： Ganesh S. Pise Sachin D. Babar Parikshit N. Mahalle Smt. Kashibai Navale College of Engineering Pune Assistant Professor in Pune Institute of Computer Technology Pune India Department of Computer Engineering Sinhgad Institute of Technology Lonavala Research Guide Smt. Kashibai Navale College of Engineering Pune India Department of Artificial Intelligent and Data Science Vishwakarma Institute of Information Technology Pune India

The Machine-to-Machine (M2M) connection in the context of the Internet of Things (IoT), with the main goal of improving information management through advanced classification methods. As the number of IoT devices has grown, strong methods for efficiently classifying them are needed to make contact smooth and make the best use of resources. This study compares two cutting-edge machine learning techniques called Stacked Ensembles to see which one is better at making IoT device classification more accurate and reliable. The paper research looks at different classification models within Stacked Ensembles and compares how well they work to more standard methods. The study system has a large collection with a lot of different IoT devices and different communication methods and network situations. The paper focused is to find the best Stacked Ensemble setups for accurate and efficient device classification in M2M communication by carefully testing and evaluating them. The study adds to the fields of machine learning and the Internet of Things, but it also looks at information management in M2M networks, which is a very important topic. We expect that system effectiveness, resource usage, and general network performance will all get better by using advanced sorting methods. It is hoped that the study results will help people create and use strong knowledge management strategies. This will make the M2M communication setting smarter and more flexible as the IoT world changes.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Exploratory data analysis of Indian Premier League (IPL)

引用

AIP Conference Proceedings 2023年第1期2773卷

作者： M. K. Manju Abin Oommen Philip M. U. Sreeja Department of Computer Science & Engineering Toc H Institute of Science & Technology Ernakulam Kerala India Assistant Professor Department of CSE-Cyber Security Indian Institute of Information Technology KottayamKerala India Assistant Professor Department of Information Technology Rajagiri School of Engineering & Technology Ernakulam Kerala India

Cricket is one of the games having the most number of followers and spectators in India. Among them, T20 League cricket is getting more attention. This paper have focused on performing an exploratory data analysis on Indian Premier League or IPL dataset utilizing the previous match details to draw hidden insights and patterns in data and further using it for the prediction of match outcomes. Indian Premier League or IPL results are always unpredictable, a large number of factors like venue, toss decision, player’s performance etc., determines the result of matches. Hence, on performing the analysis have drawn many important insights like whether home ground favors the winning of match, whether toss decision plays any role, who is the player of match of the season etc., were identified. Then, machine learning algorithms are applied on the relevant features for the prediction of matches. Finally, the accuracies of these algorithms are plotted to compare the performances to figure out the most accurate among them. The results illustrates that XGB Classifier showed the highest accuracy rate of 69.12%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Bayesian uncertainty estimation of learned variational MRI reconstruction

arXiv

引用

arXiv 2021年

作者： Narnhofer, Dominik Effland, Alexander Kobler, Erich Hammernik, Kerstin Knoll, Florian Pock, Thomas Institute of Computer Graphics and Vision Graz University of Technology Graz Austria Graz Austria Institute of Applied Mathematics University of Bonn Bonn Germany Computer Science Department Johannes Kepler University Linz Austria Technical University of Munich Munich Germany Imperial College London London United Kingdom Nyu School of Medicine NY United States

Recent deep learning approaches focus on improving quantitative scores of dedicated benchmarks, and therefore only reduce the observation-related (aleatoric) uncertainty. However, the model-immanent (epistemic) uncertainty is less frequently systematically analyzed. In this work, we introduce a Bayesian variational framework to quantify the epistemic uncertainty. To this end, we solve the linear inverse problem of undersampled MRI reconstruction in a variational setting. The associated energy functional is composed of a data fidelity term and the total deep variation (TDV) as a learned parametric regularizer. To estimate the epistemic uncertainty we draw the parameters of the TDV regularizer from a multivariate Gaussian distribution, whose mean and covariance matrix are learned in a stochastic optimal control problem. In several numerical experiments, we demonstrate that our approach yields competitive results for undersampled MRI reconstruction. Moreover, we can accurately quantify the pixelwise epistemic uncertainty, which can serve radiologists as an additional resource to visualize reconstruction *** Codes 68T45, 65K10, 65D19 Copyright © 2021, The Authors. All rights reserved.

关键词： Uncertainty analysis

来源：评论

学校读者我要写书评

暂无评论

Real-time GB pattern convolution neural network-based brain image classification

引用

AIP Conference Proceedings 2024年第1期3075卷

作者： Amarendra Reddy Panyala M. Baskar Research Scholar Department of Computer Science and Engineering School of Computing SRM Institute of Science and Technology Kattankulathur Chengalpattu Chennai Tamil Nadu 603 203 India Assistant Professor Department of Information Technology MLR Institute of Technology Hyderabad Telangana 500043 India Associate Professor Department of Computing Technologies School of Computing SRM Institute of Science and Technology Kattankulathur Chengalpattu Chennai Tamil Nadu 603 203 India

Medical image classification has been identified as a critical task in several medical solutions. Brain image classification has been identified as a challenging task that has been approached with different methods. The existing methods use different features like shape, texture, and gray to classify brain images. However, the methods need to improve performance in categorizing the brain image and detecting the presence of tumors. An efficient GB Pattern Convolution Neural Network (GBP-CNN) is presented to handle this issue. The method involves preprocessing the brain image given with Adaptive Feature Distribution Normalizer (AFDN) algorithm. The Grey Canvas Segmentation (GCS) technique was used to segment the normalized image. The feature vector is created by extracting the binary and grayscale patterns from the image that has been segmented. A convolution neural network is trained to recognize the features that were extracted. Two convolution layers in the CNN’s design are used to convolve the image’s features. Additionally, a pooling layer is being incorporated into the network’s design, which reduces the data to a single dimension. The neuron predicts support values for several attributes during the assessment stage. The approach then calculates the Class-Based Fitness value (CBFV) in order to categories the image against various tumour classes. The proposed GBP-CNN algorithm improves the performance of brain image classification with less time complexity.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Can GAN Generated Morphs Threaten Face Recognition Systems Equally as Landmark Based Morphs? - Vulnerability and Detection

Can GAN Generated Morphs Threaten Face Recognition Systems E...

引用

International Workshop on Biometrics and Forensics (IWBF)

作者： Sushma Venkatesh Haoyu Zhang Raghavendra Ramachandra Kiran Raja Naser Damer Christoph Busch Norwegian Biometrics Laboratory Norwegian University of Science and Technology (NTNU) Norway Fraunhofer Institute for Computer Graphics Research IGD Darmstadt Germany

ISBN: (数字)9781728162324

ISBN: (纸本)9781728162331

The primary objective of face morphing is to com-bine face images of different data subjects (e.g. an malicious actor and an accomplice) to generate a face image that can be equally verified for both contributing data subjects. In this paper, we propose a new framework for generating face morphs using a newer Generative Adversarial Network (GAN) - StyleGAN. In contrast to earlier works, we generate realistic morphs of both high-quality and high resolution of 1024 × 1024 pixels. With the newly created morphing dataset of 2500 morphed face images, we pose a critical question in this work. (i) Can GAN generated morphs threaten Face Recognition Systems (FRS) equally as Landmark based morphs? Seeking an answer, we benchmark the vulnerability of a Commercial-Off-The-Shelf FRS (COTS) and a deep learning-based FRS (ArcFace). This work also benchmarks the detection approaches for both GAN generated morphs against the landmark based morphs using established Morphing Attack Detection (MAD) schemes.

关键词： Biometrics Face Recognition Morphing At-tack Vulnerability image morphing morphs Facial Recognition Biometrics Vulnerability face recognition system Flexed Sidebent Rotated landmarks

来源：评论

学校读者我要写书评

暂无评论

Optical Wireless Network Architecture

Optical Wireless Network Architecture

引用

2022 27th OptoElectronics and Communications Conference (OECC) and 2022 International Conference on Photonics in Switching and Computing (PSC)

作者： Vincent W.S. Chan Joan and Irwin Jacobs Chair Professor Department of Electrical Engineering and Computer Science Claude E. Shannon Communication and Network Group Research Laboratory of Electronics Steve Schwarzman College of Computing AI and Decision System Sector Massachusetts Institute of Technology. President IEEE Communications Society 2020&#x2013 2021.

ISBN: (数字)9784885523366

ISBN: (纸本)9781665486064

Optical wireless network has the potential to serve space-space, space-terrestrial/aircraft, aircraft-aircraft, data centers and metropolitan area networks. This paper addresses architecture features necessary for these networks. Free space optical (FSO) networks have two dimensions that are not encountered in fiber networks and that is: (1) its ability to connect without pre-deployment of infrastructures and (2) the ability to reconfigure its connection topology by beam steering in time scales of mS-S to adapt to traffic loads, switching node states and atmospheric conditions. This paper presents a multi-layer approach to optical wireless networks and how the architecture can be tuned to applications.

关键词： Optical fibers Network topology Metropolitan area networks Wireless networks Optical switches computer architecture Telecommunication traffic

来源：评论

学校读者我要写书评

暂无评论

Governing AI-Driven Health Research: Are IRBs Up to the Task?

Ethics & human research

引用

Ethics & human research 2021年第2期43卷 35-42页

作者： Friesen, Phoebe Douglas-Jones, Rachel Marks, Mason Pierce, Robin Fletcher, Katherine Mishra, Abhishek Lorimer, Jessica Véliz, Carissa Hallowell, Nina Graham, Mackenzie Chan, Mei Sum Davies, Huw Sallamuddin, Taj Assistant professor in the Biomedical Ethics Unit and the Department of Social Studies of Medicine at McGill University Associate professor of anthropological approaches to data and infrastructure head of the Technologies in Practice research group the codirector of the ETHOS Lab at the IT University of Copenhagen Assistant professor of law at Gonzaga University and the Edmond J. Safra/Petrie-Flom Centers Joint Fellow-in-Residence at Harvard University Technology and Society at the Tilburg Law School at Tilburg University Coordinator of Cyber Security Oxford and the founding administrator of the Computer Science Department Research Ethics Committee in the Department of Computer Science at the University of Oxford DPhil candidate at the Uehiro Centre for Practical Ethics at the University of Oxford DPhil candidate on the NEUROSEC team in the Department of Psychiatry at the University of Oxford Associate professor in the Faculty of Philosophy at the Institute for Ethics in AI as well as a tutorial fellow at Hertford College at the University of Oxford Codirector of the EPSRC Centre for Doctoral Training in Health Data Science and a professor at the Ethox Centre and Wellcome Centre for Ethics and Humanities at the University of Oxford Senior research fellow in data ethics at the Wellcome Centre for Ethics and Humanities in the Nuffield Department of Population Health at the University of Oxford DPhil student in the Nuffield Department of Population Health at the University of Oxford and a research fellow in the Department of Applied Health Research at University College London Lecturer in education at the School of Education and Sport at the University of Edinburgh Data protection and information lawyer

Many are calling for concrete mechanisms of oversight for health research involving artificial intelligence (AI). In response, institutional review boards (IRBs) are being turned to as a familiar model of governance. Here, we examine the IRB model as a form of ethics oversight for health research that uses AI. We consider the model's origins, analyze the challenges IRBs are facing in the contexts of both industry and academia, and offer concrete recommendations for how these committees might be adapted in order to provide an effective mechanism of oversight for health-related AI research. © 2021 by The Hastings Center. All rights reserved.

关键词： AI research oversight artificial intelligence ethics committees health-related AI research institutional review boards research ethics

来源：评论

学校读者我要写书评

暂无评论

Abnormal event detection using unsupervised deep one class learning

引用

AIP Conference Proceedings 2024年第1期3075卷

作者： G. Balamurugan K. Kishore Anthuvan Saharaj V. Arulalan H. Aswini S. Mahalakshmi Assistant Professor Department of Computing Technologies Faculty of Engineering and Technology SRM Institute of Science and Technology Kattankulathur 603203 Chengalpattu Tamil Nadu India Department of Computer Science and Engineering IFET College of Engineering Villupuram Tamil Nadu India Department of Information Science and Engineering BMS Institute of Technology and Management Bengaluru Karnataka India

Intelligent video surveillance and transportation systems have become more important in the field of security in recent years for identifying abnormal events that happen along the side of the road. Recent developments in surveillance systems include the automatic detection of abnormal events in video surveillance. However, only one normal event is accessible for the learning process in the context of abnormal event detection. In this scenario, the idea addresses a novel unsupervised deep one class learning architecture. It can produce optical flow pictures from original movies in addition to generating concise spatio-temporal characteristics for abnormal event detection resolutions. To guarantee that the "deep-one" class learning is classified correctly, it is built using a customized loss function which is the combination of 3 terms: Reconstruction Loss (RL), Generation Loss (GL), and Compactness Loss (CL). On a relatively challenging dataset known as the UCSD anomalous detection dataset, the suggested technique achieved better results than the existing methods, the Satellite Smoke Scene Detection dataset, and the Cross View Geo localization dataset. The experimental results assure that the proposed work provides higher accuracy then the state of art techniques.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Novel Approach for Pose Invariant Face Recognition in Surveillance Videos

引用

Procedia computer science 2020年 167卷 890-899页

作者： Manju D Radha V Research Scholar Department of Computer Science Avinashilingam Institutre for Home Science and Higher Education for Women (Assistant Professor Depatment of Computing Coimbatore Institute of Technology) Coimbatore-641043 India Department of Computer Science Avinashilingam Institutre for Home Science and Higher Education for Women Coimbatore-641043 India

The face detection and face recognition methods are introduced to confirm the abnormal human activity in the video surveillance system. Face detection is carried out by Viola-Jones face detector. It is composed of three concepts namely integral image, AdaBoost and the cascade structure. After face detection, Histogram of Oriented Gradient(HOG) and Weighted Local Binary Patterns(WLBP) features are extracted and those are used in Orthogonal Locality Preserving Projection(OLPP) for face recognition. The detected faces may contain pose variation which dramatically degrades the OLPP based face recognition. So, pose-invariant OLLP-based face recognition is proposed where Histogram of Face Orientation(HFO) and Histogram of Face Direction(HFD), HOG and WLBP features are used in OLPP for efficient face recognition.

关键词： Face detection Face Recognition Viola-Jones face detector Histogram of Oriented Gradient Weighted Local Binary Patterns Orthogonal Locality Preserving Projection Histogram of Face Orientation Histogram of Face Direction

来源：评论

学校读者我要写书评

暂无评论

Intrusion Detection in Cloud Architecture Using Machine Learning

Intrusion Detection in Cloud Architecture Using Machine Lear...

引用

Advances in Computing, Communication Control and Networking (ICAC3N), International Conference on

作者： Govinda Rajulu. G R. Santhoshkumar D. Venkatesan Kalvikkarasi. S P. Santosh Kumar Patra Department of Computer Science and Design St. Martin’s Engineering College Department of Artificial Intelligence and Data Science St. Martin’s Engineering College Department of Artificial Intelligence and Machine Learning Department of CSE St. Martin’s Engineering College Professor in ECE Department Podhagai College of Engineering & Technology St. Martin’s Engineering College

The research of Intrusion Detection Systems is known to be among the most challenging aspects of Cloud Security. In the context of the cloud, security breaches such as denial of service, scanning, injection of malicious code, viruses, worms, and the breaking of passwords are becoming increasingly commonplace. In the event that these attacks are not stopped in a timely manner, the company's reputation may be put in jeopardy, and it may sustain financial harm. As a consequence of this, it is essential to safeguard the cloud against dangers of this kind. In this research, we provide solutions to defend cloud systems by incorporating some of the most successful methods of intrusion detection. Within IDS, our primary focus has been placed on two critical aspects: the effectiveness of the detection techniques and the pace of detection. In order to overcome these obstacles, we suggest utilising machine learning in conjunction with parallelization. Approaches based on machine learning gain information from the data itself, hence diminishing the significance of the human expert. In order to identify intrusions, statistical models, safe system approaches, neural networks, and a variety of other methods are utilised. The purpose of this study is to improve the accuracy of intrusion detection in cloud computing by presenting a new approach to intrusion detection that is based on existing intrusion detection systems and the various architectures that those systems employ.

关键词： Databases Cloud computing security Neural networks Intrusion detection computer architecture Passwords Decision trees

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：