检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Melotti, Gledson Premebida, Cristiano Bird, Jordan J. Faria, Diego R. Gonçalves, Nuno Federal Institute of Espirito Santo Brazil The Dep. of Electrical and Computer Engineering University of Coimbra-Portugal Portugal Department of Computer Science Nottingham Trent University United Kingdom School of Physics Engineering and Computer Science University of Hertfordshire United Kingdom Dep. of Electrical and Computer Engineering University of Coimbra-Portugal Portuguese Mint and Official Printing Office Lisbon Portugal

In state-of-the-art deep learning for object recognition, Softmax and Sigmoid layers are most commonly employed as the predictor outputs. Such layers often produce overconfidence predictions rather than proper probabilistic scores, which can thus harm the decision-making of 'critical' perception systems applied in autonomous driving and robotics. Given this, we propose a probabilistic approach based on distributions calculated out of the Logit layer scores of pre-trained networks which are then used to constitute new decision layers based on Maximum Likelihood (ML) and Maximum a-Posteriori (MAP) inference. We demonstrate that the hereafter called ML and MAP layers are more suitable for probabilistic interpretations than Softmax and Sigmoid-based predictions for object recognition. We explore distinct sensor modalities via RGB images and LiDARs (RV: range-view) data from the KITTI and Lyft Level-5 datasets, where our approach shows promising performance compared to the usual Softmax and Sigmoid layers, with the benefit of enabling interpretable probabilistic predictions. Another advantage of the approach introduced in this paper is that the so-called ML and MAP layers can be implemented in existing trained networks, that is, the approach benefits from the output of the Logit layer of pre-trained networks. Thus, there is no need to carry out a new training phase since the ML and MAP layers are used in the test/prediction phase. The Classification results are presented using reliability diagrams, while detection results are illustrated using precision-recall *** Codes 68T10 Copyright © 2022, The Authors. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Real-time Ventilation Detection for Feedback and Guidance During Newborn Resuscitation

Real-time Ventilation Detection for Feedback and Guidance Du...

引用

International Conference on Control, Decision and Information Technologies (CoDIT)

作者： Øyvind Meinich-Bache Hannah Håland Anita Yeconia Rafal Paprocki Solveig Haukås Haaland Øystein Gomo Thomas Haukland Siren Irene Rettedal Sara Brunner Esto Mduma Hege Ersdal Dep. of Electrical Engineering and Computer Science University of Stavanger Norway Strategic Research Laerdal Medical Stavanger Norway Haydom Lutheran Hospital Tanzania Stavanger University Hospital Norway Faculty of Health Sciences University of Stavanger Norway

ISBN: (数字)9798350373974

ISBN: (纸本)9798350373981

For a healthcare provider treating a non-breathing newborn baby, timely ventilation of the lungs is the most critical action to save the newborn’s life. However, the guidelines for newborn resuscitation are challenging to follow and a real-time feedback and guidance system may contribute to more optimal treatment. In this study we utilized deep neural networks for detecting ventilation in the audio signal extracted from video recordings of 25 newborn resuscitation episodes. The proposed ventilation detection system utilizes Log Mel Spectrograms for feature generation, audio augmentation for dataset expansion, and 2D Convolutional Neural Networks (CNNs) for ventilation classification. For the task of image classification, we compared two different pretrained backbones suited for real-time inference and a custom-built efficient CNN, called VD-CNN. We found that using MobilenNetV3Large as the feature extractor yielded the best results, achieving a F1-score of 97.21%. Our efficient VD-CNN, with a parameter count one fifth that of MobilenNetV3Large, still achieved a robust F1-score of 95.37%. To demonstrate that the proposed system can perform ventilation detection and provide immediate feedback during newborn resuscitation in real-time, we integrated the ventilation detection system into a newborn resuscitation station called Liveborn Station.

关键词： Pediatrics Computational modeling Tablet computers Medical services Ventilation Feature extraction Real-time systems Convolutional neural networks Video recording Spectrogram

来源：评论

学校读者我要写书评

暂无评论

Performance Monitoring and Controlling of Multicore Shared-Memory Parallel Processing Systems 3

Performance Monitoring and Controlling of Multicore Shared-M...

引用

3rd Information Technology to Enhance e-Learning and Other Application, IT-ELA 2022

作者： Haji, Lailan M Zeebaree, Subhi R. M. Ageed, Zainab Salih Ahmed, Omar M. Sadeeq, Mohammed A. M. Shukur, Hanan M. University of Zakho Faculty of Science Computer Science Dep. Duhok Iraq Technical College of Engineering Duhok Polytechnic University Energy Eng. Dept. Duhok Iraq College of Science Nawroz University Computer Science Dept. Duhok Iraq Zakho Technical Institute Duhok Polytechnic University Information Technology Dept. Duhok Iraq Technical College of Administration Duhok Polytechnic University ITM Dept. Duhok Iraq Al-Kitab University Computer Engineering Dept. Kirkuk Iraq

ISBN: (纸本)9798350334968

The field of research known as 'parallel processing' examines architectural and algorithmic methods for increasing the efficiency and other desirable qualities (such as cost-effectiveness and reliability) of computers by exploiting many forms of concurrency. The development of multi-core CPUs has opened the door to novel strategies for boosting system performance via parallelism. Increasing the number of concurrent threads greatly affects the time cost. While increased parallelism might reduce calculation time, the associated synchronization costs would likely be prohibitive for most applications. In this article, we'll go through the first half of the process, which involves gathering requirements and designing a prototype;the second half, which involves monitoring and managing a program that can run on a wide range of multicore system architectures, including those with (2, 4, and 8 CPUs). A shared-memory parallel processing method was proposed and built to show off the system's full potential. The implications of multi-core systems on overall program execution time and parallel processing in shared-memory systems provide the backbone of this investigation. © 2022 IEEE.

关键词： Cost effectiveness

来源：评论

学校读者我要写书评

暂无评论

Analyzing Data Efficiency and Performance of Machine Learning Algorithms for Assessing Low Back Pain Physical Rehabilitation Exercises

Analyzing Data Efficiency and Performance of Machine Learnin...

引用

European Conference on Mobile Robots (ECMR)

作者： Aleksa Marusic Louis Annabi Sao Mai Nguyen Adriana Tapus Autonomous Systems and Robotics Lab Computer Science and System Engineering (U2IS) ENSTA Paris Institut Polytechnique de Paris Palaiseau France Dep. Informatique IMT Atlantique

Physical rehabilitation focuses on the improvement of body functions, usually after injury or surgery. Patients undergoing rehabilitation often need to perform exercises at home without the presence of a physiotherapist. computer-aided assessment of physical rehabilitation can improve patients' performance and help in completing prescribed rehabilitation exercises. In this work, we focus on human motion analysis in the context of physical rehabilitation for Low Back Pain (LBP). As 2D and 3D human pose estimation from RGB images had made impressive improvements, we aim to compare the assessment of physical rehabilitation exercises using movement data acquired from RGB videos and human pose estimation from those. In this work, we provide an analysis of two types of algorithms on a Low Back Pain rehabilitation datasets. One is based on a Gaussian Mixture Model (GMM), with performance metrics based on the log-Likelihood values from GMM. Furthermore, with the recent development of Deep Learning and Graph Neural Networks, algorithms based on Spatio-Temporal Graph Convolutional Networks (STGCN) are taken as a novel approach. We compared the algorithms in terms of data efficiency and performance, with evaluation performed on two LBP rehabilitation datasets: KIMORE and Keraal. Our study confirms that Kinect, OpenPose, and BlazePose data yield similar evaluation scores, and shows that STGCN outperforms GMM in most configurations.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The search of the path MTU with QUIC

The search of the path MTU with QUIC

引用

2021 Workshop on the Evolution, Performance and Interoperability of QUIC, EPIQ 2021 - Part of CoNEXT 2021

作者： Völker, Timo Tüxen, Michael Rathgeb, Erwin P. FH Münster Uni. of Appl. Sciences Dep. of Electrical Engineering and Computer Science NRW Steinfurt Germany University of Duisburg-Essen Computer Networking Technology Group NRW Essen Germany

ISBN: (纸本)9781450391351

A data sender in an IP based network is only capable to efficiently use a network path if it knows the packet size limit of the path, i.e., the Path Maximum Transmission Unit (PMTU). The IETF recently specified a PMTU discovery framework for transport protocols like QUIC. This paper complements this specification by presenting a search algorithm. In addition, it defines several metrics and shows results of analyses for the algorithm with various PMTU candidate sequences using these metrics. We integrated the PMTU discovery with our algorithm into a QUIC simulation model. This paper describes the integration and presents measurements obtained by simulations. © 2021 ACM.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Intelligent Recognition of Immune Cells: Analysis and Research

Intelligent Recognition of Immune Cells: Analysis and Resear...

引用

IEEE International Conference on e-Business engineering (ICEBE)

作者： Chih-En Li Wei-Lun Liu Kun-Yi Lai Yu-Hsiang Chiang Xiaowei Yan Hao-Xiang Chen Hsu-Ching Li Wan-Shu Cheng Department of Electrical Engineering National Kaohsiung University of Science and Technology Kaohsiung Taiwan Institute for Systems Biology Seattle Washington U.S.A Dep. of Computer Science and Information Management Providence University Taichung Taiwan

Immunotherapy utilizes the potential of the patient's immune system to fight disease. T-lymphocytes have become the central focus of the immune system in the fight against cancer. One of the fundamental studies in immunotherapy is how to accurately identify various types of immune cells. Therefore, the study of immune-related cells will be an important reference for the treatment of COVID19 or other related diseases. In this paper, a series of experiments were conducted with COVID-19 patients as the starting point to design a strategy to identify the important subtypes of CD$4^{+}$T cells. In this paper, an intelligent machine learning algorithm is proposed according to the results of different experiments of linear and nonlinear dimension reduction algorithms, integrating the important characteristics of these two algorithms and improving the performance. Our experimental results show that the algorithm designed based on the front-end experiments can effectively distinguish the important lymphocytes. The proposed algorithm not only improves the performance, but also the dimension reduction procedure keeps the important features of both global and regional data. The experimental results of this paper will be beneficial for the subsequent analysis of the clustering in identifying important subtypes of CD$4^{+}$T cells. Most importantly, this wm significantly improve the procedure of manually integrating and labeling the recorded data after several tedious and monotonous analyses with external software.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Forecasting of Monkeypox Cases Using Optimized SARIMAX Based Model

Forecasting of Monkeypox Cases Using Optimized SARIMAX Based...

引用

Electronic engineering (ICEEM), International Conference on

作者： Mahmoud Elshabrawy Marwa M. Eid Abdelaziz A. Abdelhamid El-Sayed M. El-Kenawy Abdelhameed Ibrahim Dept. of Communications & Electronics Delta Higher Institute of Engineering and Technology Mansoura Egypt Faculty of Artificial Intelligence Delta University for Science and Technology Mansoura Egypt Dep. of Computer Science Faculty of Computer and Information Sciences Ain Shams University Cairo Egypt Computer Engineering and Control Systems Dept. Faculty of Engineering University Mansoura Egypt

This study presents a dipper-throated-based ant colony optimization (DTACO) with the Seasonal Auto-Regressive Integrated Moving Average with eXogenous factor (SARIMAX) model (DTACO+SARIMAX) to forecast monkeypox cases. The work optimizes the SARIMAX model using grid search cross-validation and fine-tunes its hyperparameters using DTACO to improve prediction accuracy. The suggested model's consistency and accuracy are considerable compared to previous studies. Comparisons with state-of-the-art models validate the proposed model's predictions. DTACO+SARIMAX can be used to control disease and monitor monkeypox. Healthcare organizations and governments can better manage and track the pandemic's course by offering accurate predictions, reducing public panic, and enabling effective pandemic planning. The Analysis of Variance (ANOVA) and Wilcoxon signed-rank tests are conducted on the proposed DTACO-SARIMAX model and compared models.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Blockchain Hybrid-model Scheme for Scalable Cross-domain Authorisation

引用

Blockchain: Research and Applications 2025年

作者： Munkenyi Mukhandi Jorge Granjal João P. Vilela CISUC Dep. of Informatics Engineering University of Coimbra Portugal CISUC Dep. of Informatics Engineering & CRACS / INESCTEC & Dep. of Computer Science Faculty of Sciences University of Porto Portugal

We introduce a novel blockchain-based inter-ledger authorization scheme, a unique solution designed to support delegated authorization management in cross-domain cloud environments. This innovative approach enables client applications, acting on behalf of a user, to request access to specific resources owned by a different organization. It benefits cross-domain multi-cloud applications, such as large-scale collaboration projects involving multiple cloud service providers. Multi-cloud presents authorization challenges because of complex access control operations in multiple distinct domains. OAuth2 is the state-of-the-art choice for delegated authorization. However, it falls short in handling such complex interactions with multiple authorization servers and resource servers, and this is our motivation. Compared to OAuth2, our approach overcomes the limitations of a centralized model and achieves coordinated distinct delegations among multiple entities without a third-party trusted component. Authorization servers are blockchain participants and designated access token issuers, ensuring minimum client data collection and promoting client privacy. Multiple smart contracts are dep.oyed in our multi-ledger blockchain environment to guarantee the provenance of the authorization operations and facilitate scalable cross-domain authorization. Our ‘hybrid inter-ledger model’, combines security techniques such as blockchain-based device authentication, hashed-time locks (HTCLs), and service discovery. The blockchain-based device authentication ensures secure and trusted interactions, HTCLs enable time-bound transactions, and service discovery simplifies finding and connecting to the required cloud services. Our experimental evaluation provides insights into the scalability of our approach, which achieves decentralized authorization in a multi-cloud environment with acceptable latencies compared to related works and shows stable throughput against concurrent authorization reque

关键词： OAuth2 multi-cloud decentralised coordinated authorisation multi-ledgers blockchain security smart contracts

来源：评论

学校读者我要写书评

暂无评论

ENHANCING SPARQL QUERY REWRITING FOR COMPLEX ONTOLOGY ALIGNMENTS

arXiv

引用

arXiv 2025年

作者： Ondo, Anicet Lepetit Capus, Laurence Bousso, Mamadou Dep. of Computer and Software Engineering Laval University QuebecQCG1V 0A6 Canada Dep. Computer Science Iba Der Thiam University Thies967 Senegal

SPARQL query rewriting is a fundamental mechanism for uniformly querying heterogeneous ontologies in the Linked Data Web. However, the complexity of ontology alignments, particularly rich correspondences (c: c), makes this process challenging. Existing approaches primarily focus on simple (s: s) and partially complex (s: c) alignments, thereby overlooking the challenges posed by more expressive alignments. Moreover, the intricate syntax of SPARQL presents a barrier for non-expert users seeking to fully exploit the knowledge encapsulated in ontologies. This article proposes an innovative approach for the automatic rewriting of SPARQL queries from a source ontology to a target ontology, based on a user's need expressed in natural language. It leverages the principles of equivalence transitivity as well as the advanced capabilities of large language models such as GPT-4. By integrating these elements, this approach stands out for its ability to efficiently handle complex alignments, particularly (c: c) correspondences, by fully exploiting their expressiveness. Additionally, it facilitates access to aligned ontologies for users unfamiliar with SPARQL, providing a flexible solution for querying heterogeneous data. © 2025, CC BY.

关键词： Query languages

来源：评论

学校读者我要写书评

暂无评论

Next Generation Image Watermarking via Combined DWT-SVD Technique 2

Next Generation Image Watermarking via Combined DWT-SVD Tech...

引用

2nd International Conference on Cyber Resilience, ICCR 2024

作者： Al-Na'amneh, Qais Almomani, Ammar Nasayreh, Ahmad Nahar, Khalid M.O. Gharaibeh, Hasan Al Mamlook, Rabia Emhamed Alauthman, Mohammad Applied Science Private University Department Of Cyber Security Amman Jordan School Of Computing Skyline University College P.O. Box 1797 Sharjah United Arab Emirates AlHuson University College AlBalqa Applied University I. T. Department Irbid Jordan Yarmouk University Department Of Computer Sciences Irbid211633 Jordan Yarmouk University Faculty Of Information Technology Computer Sciences Irbid211633 Jordan Trine University Dep. Of Business Administration IN United States University Of Zawia Dep.of Mechanical And Industrial Engineering Tripoli Libya University Of Petra Faculty Of Information Technology Department Of Information Security Amman Jordan

ISBN: (纸本)9798350394962

Personal computers and the Internet are used in different areas and are easier to use. Most data is easy to transmit and duplicate in digital format, and being tampered with and stolen easily leads to issues for content owners and service providers. The Paper describes a secure (tampering-resistant) method for watermarking images for protection and authentication and digital media like audio, video, and multimedia data, and a combination of singular value decomposition (SVD) and Discrete wavelet transform (DWT) for insertion watermark by MATLAB to increase accuracy, simplicity, and flexibility Readability, secure robustness, and imperceptibility the visibility of the image. The proposed algorithm consists of three main steps: Firstly, we decomposed the original image into four sub-bands and the original watermark. Secondly, embed the watermark in the LL sub-band by replacing the singular value for the watermark. Finally, embed a watermark in the other three sub-bands by adding LL values for a watermark in each sub-band in the original image. © 2024 IEEE.

关键词： Discrete wavelet transforms

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：