检索结果-内蒙古大学图书馆

Information Technology and Data Science (CITDS), IEEE Conference on

作者： Mohammed Nsaif Gergely Kovásznai Hasanein D. Rjeib Ali Malik Ruairí de Fréin Faculty of informatics University of Debrecen Hungary Faculty of Computer Science and Mathematics University of Kufa Iraq Department of Business Management Al-imam University College Balad Iraq Faculty of informatics Eszterházy Károly Catholic University Hungary Faculty of Engineering University of Kufa Iraq Institute of Information Technology University of Miskolc Hungary School of Electrical and Electronic Engineering Technological University Dublin Ireland

ISBN: (数字)9798350387889

ISBN: (纸本)9798350387896

Network traffic matrix prediction is used to estimate the patterns of future network flows before they are initiated. Traffic matrix prediction is needed by a wide range of network management functions such as network monitoring and it relies on historical data. In this paper, we address the task of multi-time step traffic matrix prediction using Recurrent Neural Networks (RNN). Our objective is to conduct a comparative study of different types of RNNs and to evaluate their ability to predict multi-time step Origin-Destination traffic matrices. Experiments show that RNNs are capable of predicting multiple steps of traffic matrices, however, the RMSE of the predictions increases as we move further away from the last true value. Our primary finding is that the RNN-GRU show has the best prediction ability in the very beginning steps with an RMSE of 0.048, while RNN-LSTM demonstrated higher capability with the last steps, having an RMSE value of 0.058.

关键词： Recurrent neural networks Power demand Telecommunication traffic Predictive models Data science Data models computer networks Numerical models Information technology Monitoring

来源：评论

学校读者我要写书评

暂无评论

Flicker Visibility With Different Spectra of White Light

引用

IEEE Transactions on Industry Applications 2025年

作者： Kukacka, Leos Hergesel, Jan Necasek, Jakub Bilek, Petr Vik, Michal Stiegler, Robert Pourarab, Morteza Meyer, Jan Drapela, Jiri Technical University of Liberec Faculty of Mechatronics Informatics and Interdisciplinary Studies Institute-of Mechatronics and Computer Engineering Liberec Czech Republic Technical University of Liberec Faculty of Textile Engineering Department of Material Engineering Czech Republic Technische Universität Dresden Institute of Electrical Power Systems and High Voltage Engineering Chair of Electrical Power Supply Dresden01069 Germany Brno University of Technology Faculty of Electrical Engineering and Communications Brno61600 Czech Republic

The standard flickermeter (voltage flickermeter) algorithm commonly used for the evaluation of flicker severity in current electromagnetic compatibility standards originates from the 1980 s. It was developed to mimic irritation of an average human observer by flickering incandescent lamp as a reference light source and optimized to voltage fluctuations caused by arc furnaces. However, the algorithm is questionable as the situation in the grid changed since the 1980 s;many modern devices are being connected to the grid, creating voltage distortion patterns which are not properly recognized by the voltage flickermeter. In addition, incandescent lamps have been largely replaced by discharge lamps and later by LEDs. Transitioning the algorithm from incandescent lamp light to LED light requires detailed revision of every part of the algorithm. This paper is concerned with verifying the frequency weighting function of the average human observer which is one of the bases of the voltage flickermeter, as well as of the derived light flickermeter. Flicker sensitivity of 34 human observers is measured with two different light sources (LED warm and neutral white, incandescent lamp) and compared with the frequency weighting function used in the current specification of the flickermeters in standards. Finally, an optimization of the weighting function is proposed based on the findings. © 1972-2012 IEEE.

关键词： Flickering

来源：评论

学校读者我要写书评

暂无评论

RerrFact: Reduced Evidence Retrieval Representations for Scientific Claim Verification

RerrFact: Reduced Evidence Retrieval Representations for Sci...

引用

2022 Workshop on Scientific Document Understanding, SDU 2022

作者： Rana, Ashish Khanna, Deepanshu Ghosal, Tirthankar Singh, Muskaan Singh, Harpreet Rana, Prashant Singh School of Business Informatics and Mathematics University of Mannheim Germany Department of Electronics & Communication Engineering Thapar Institute of Engineering & Technology India Institute of Formal and Applied Linguistics Faculty of Mathematics and Physics Charles University Czech Republic Department of Computer Science & Engineering Thapar Institute of Engineering & Technology India

Exponential growth in digital information outlets and the race to publish has made scientific misinformation more prevalent than ever. However, the task to fact-verify a given scientific claim is not straightforward even for researchers. Scientific claim verification requires in-depth knowledge and great labor from domain experts to substantiate supporting and refuting evidence from credible scientific sources. The SciFact dataset and corresponding task provide a benchmarking leaderboard to the community to develop automatic scientific claim verification systems via extracting and assimilating relevant evidence rationales from source abstracts. In this work, we propose a modular approach that sequentially carries out binary classification for every prediction subtask as in the SciFact leaderboard. Our simple classifier-based approach uses reduced abstract representations to retrieve relevant abstracts. These are further used to train the relevant rationale-selection model. Finally, we carry out two-step stance predictions that first differentiate non-relevant rationales and then identify supporting or refuting rationales for a given claim. Experimentally, our system RerrFact with no fine-tuning, simple design, and a fraction of model parameters fairs competitively on the leaderboard against large-scale, modular, and joint modeling approaches. © 2022 Copyright for this paper by its authors.

关键词： Abstracting

来源：评论

学校读者我要写书评

暂无评论

Application of deep learning and machine learning models to detect COVID-19 face masks - A review

引用

Sustainable Operations and computers 2021年 2卷 235-245页

作者： Mbunge, Elliot Simelane, Sakhile Fashoto, Stephen G Akinnuwesi, Boluwaji Metfula, Andile S Department of Computer Science Faculty of Science and Engineering University of Eswatini P Bag 4 Kwaluseni Swaziland Department of Information Technology Faculty of Accounting and Informatics Durban University of Technology P O Box 1334 Durban4000 South Africa

The continuous COVID-19 upsurge and emerging variants present unprecedented challenges in many health systems. Many regulatory authorities have instituted the mandatory use of face masks especially in public places where massive contact of people is frequent and inevitable, particularly inside public transport facilities, sports arenas, shopping malls and workplaces. However, compliance and adherence to proper wearing of face masks have been difficult due to various reasons including diversified mask types, different degrees of obstructions, various variations, balancing various model detection accuracy or errors and deployment requirements, angle of view, deployment of detection model on computers with limited processing power, low-resolution images, facial expression, and lack of real-world dataset. Therefore, this study aimed at providing a comprehensive review of artificial intelligence models that have been used to detect face masks. The study revealed that deep learning models such as the Inceptionv3 convolutional neural network achieved 99.9% accuracy in detecting COVID-19 face masks. We deducted that most of the datasets used to detect face masks are created artificially, do not represent the real-world environments which ultimately affect the precision accuracy of the model when deployed in the real world. Hence there is a need for sharing real-world COVID-19 face mask images for modelling deep learning techniques. The study also revealed that deeper and wider deep learning architectures with increased training parameters, such as inception-v4, Mask R-CNN, Faster R-CNN, YOLOv3, Xception, and DenseNet are not yet implemented to detect face masks. © 2021

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Data Augmentation Using Generative Adversarial Networks to Reduce Data Imbalance with Application in Car Damage Detection 15

Data Augmentation Using Generative Adversarial Networks to R...

引用

15th International Conference on Developments in eSystems engineering, DeSE 2023

作者： Mahyoub, Mohamed Natalia, Friska Sudirman, Sud Liatsis, Panos Jasim Al-Jumaily, Abdulmajeed Hammadi Tutor Reach United Kingdom Universitas Multimedia Nusantara Faculty of Engineering and Informatics Tangerang Indonesia School of Computer Science and Mathematics Liverpool John Moores University Liverpool United Kingdom Khalifa University Abu Dhabi United Arab Emirates Universiti Putra Malaysia Serdang Malaysia

ISBN: (纸本)9798350335149

Automatic car damage detection and assessment are very useful in alleviating the burden of manual inspection associated with car insurance claims. This will help filter out any frivolous claims that can take up time and money to process. This problem falls into the image classification category and there has been significant progress in this field using deep learning. However, deep learning models require a large number of images for training and oftentimes this is hampered because of the lack of datasets of suitable images. This research investigates data augmentation techniques using Generative Adversarial Networks to increase the size and improve the class balance of a dataset used for training deep learning models for car damage detection and classification. We compare the performance of such an approach with one that uses a conventional data augmentation technique and with another that does not use any data augmentation. Our experiment shows that this approach has a significant improvement compared to another that does not use data augmentation and has a slight improvement compared to one that uses conventional data augmentation. © 2023 IEEE.

关键词： Damage detection

来源：评论

学校读者我要写书评

暂无评论

Predicting Brain Multigraph Population From a Single Graph Template for Boosting One-Shot Classification

arXiv

引用

arXiv 2022年

作者： Pala, Furkan Rekik, Islem BASIRA Lab Faculty of Computer and Informatics Engineering Istanbul Technical University Istanbul Turkey

A central challenge in training one-shot learning models is the limited representativeness of the available shots of the data space. Particularly in the field of network neuroscience where the brain is represented as a graph, such models may lead to low performance when classifying brain states (e.g., typical vs. autistic). To cope with this, most of the existing works involve a data augmentation step to increase the size of the training set, its diversity and representativeness. Though effective, such augmentation methods are limited to generating samples with the same size as the input shots (e.g., generating brain connectivity matrices from a single shot matrix). To the best of our knowledge, the problem of generating brain multigraphs capturing multiple types of connectivity between pairs of nodes (i.e., anatomical regions) from a single brain graph remains unsolved. In this paper, we unprecedentedly propose a hybrid graph neural network (GNN) architecture, namely Multigraph Generator Network or briefly MultigraphGNet, comprising two subnetworks: (1) a many-to-one GNN which integrates an input population of brain multigraphs into a single template graph, namely a connectional brain temple (CBT), and (2) a reverse one-to-many U-Net network which takes the learned CBT in each training step and outputs the reconstructed input multigraph population. Both networks are trained in an end-to-end way using a cyclic loss. Experimental results demonstrate that our MultigraphGNet boosts the performance of an independent classifier when trained on the augmented brain multigraphs in comparison with training on a single CBT from each class. We hope that our framework can shed some light on the future research of multigraph augmentation from a single graph. Our MultigraphGNet source code is available at https://***/basiralab/MultigraphGNet. © 2022, CC BY-NC-ND.

关键词： Directed graphs

来源：评论

学校读者我要写书评

暂无评论

Semantic Segmentation and Depth Estimation of Urban Road Scene Images Using Multi-Task Networks 15

Semantic Segmentation and Depth Estimation of Urban Road Sce...

引用

15th International Conference on Developments in eSystems engineering, DeSE 2023

作者： Mahyoub, Mohamed Natalia, Friska Sudirman, Sud Al-Jumaily, Abdulmajeed Hammadi Jasim Liatsis, Panos Tutor Reach United Kingdom Universitas Multimedia Nusantara Faculty of Engineering and Informatics Tangerang Indonesia School of Computer Science and Mathematics Liverpool John Moores University Liverpool United Kingdom Universiti Putra Malaysia Serdang Malaysia Khalifa University Abu Dhabi United Arab Emirates

ISBN: (纸本)9798350335149

In autonomous driving, environment perception is an important step in understanding the driving scene. Objects in images captured through a vehicle camera can be detected and classified using semantic segmentation and depth estimation methods. Both these tasks are closely related to each other and this association helps in building a multi-Task neural network where a single network is used to generate both views from a given monocular image. This approach gives the flexibility to include multiple related tasks in a single network. It helps reduce multiple independent networks and improve the performance of all related tasks. The main aim of our research presented in this paper is to build a multi-Task deep learning network for simultaneous semantic segmentation and depth estimation from monocular images. Two decoder-focused U-N et-based multi-Task networks that use a pre-Trained Resnet-50 and DenseNet-121 which shared encoder and task-specific decoder networks with Attention Mechanisms are considered. We also employed multi-Task optimization strategies such as equal weighting and dynamic weight averaging during the training of the models. The corresponding models' performance is evaluated using mean IoU for semantic segmentation and Root Mean Square Error for depth estimation. From our experiments, we found that the performance of these multi-Task networks is on par with the corresponding single-Task networks. © 2023 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Analysis for Temperature Classification using Bioelectric Potential of Plant 6

Machine Learning Analysis for Temperature Classification usi...

引用

6th International Conference on Information Technology, Information Systems and Electrical engineering, ICITISEE 2022

作者： Tahyudin, Imam Akbar Awal Rozaq, Hasri Nambo, Hidetaka Amikom Purwokerto University Faculty of Computer Science Department of Information System Jl. Letjendpol Soemarto Purwanegara Banyumas53127 Indonesia Graduate School of Informatics Faculty of Computer Science Gazi University Yenimahalle Ankara Turkey Division of Electrical Engineering and Computer Science Graduate School of NST Kanazawa University Kakumamachi Ishikawa Kanazawa920-1192 Japan

ISBN: (纸本)9798350399615

Plants can respond to changes in their surroundings, such as temperature, humidity, and human behavior. This ability is due to photosynthesis and respiration in plants, resulting in low electrical signals. We focus on room temperature change by plant bioelectric potential detection. The temperature topic is interesting for the actual research because it is one of important factor in health aspect. This study aims to analysis of temperature of Bioelectric potential of plant using machine learning. This implementation identifies the plants' bioelectric potential in distinguishing three-room temperature categories: A, B, and C temperature. We conducted the experimental in room control. For the transformation process is using wavelet transform. Furthermore, the analysis process, we used the Decision Tree (DT), Support Vector Machine (SVM), Random Forest (RF), K-Nearest Neighborhood (K-NN), Naïve Bayes, and linear regression. Then, for the evaluation is using confusion Matrix. The result showed that the best level of transformation using Wavelet is 7thlevel for reducing the noise. Furthermore, the best accuracy of analysis process is using Decision tree which obtained 75%. © 2022 IEEE.

关键词： Bioelectric Electric Potential of Plant Machine Learning Temperature Wavelet Transform

来源：评论

学校读者我要写书评

暂无评论

Brain Tumor Segmentation in Fluid-Attenuated Inversion Recovery Brain MRI using Residual Network Deep Learning Architectures 15

Brain Tumor Segmentation in Fluid-Attenuated Inversion Recov...

引用

15th International Conference on Developments in eSystems engineering, DeSE 2023

作者： Mahyoub, Mohamed Natalia, Friska Sudirman, Sud Jasim Al-Jumaily, Abdulmajeed Hammadi Liatsis, Panos Tutor Reach United Kingdom Universitas Multimedia Nusantara Faculty of Engineering and Informatics Tangerang Indonesia School of Computer Science and Mathematics Liverpool John Moores University Liverpool United Kingdom Universiti Putra Malaysia Serdang Malaysia Khalifa University Abu Dhabi United Arab Emirates

ISBN: (纸本)9798350335149

Early and accurate detection of brain tumors is very important to save the patient's life. Brain tumors are generally diagnosed manually by a radiologist by analyzing the patient's brain MRI scans which is a time-consuming process. This led to our study of this research area for finding out a solution to automate the diagnosis to increase its speed and accuracy. In this study, we investigate the use of Residual Network deep learning architecture to diagnose and segment brain tumors. We proposed a two-step method involving a tumor detection stage, using ResNet50 architecture, and a tumor area segmentation stage using ResU-Net architecture. We adopt transfer learning on pre-trained models to help get the best performance out of the approach, as well as data augmentation to lessen the effect of data population imbalance and hyperparameter optimization to get the best set of training parameter values. Using a publicly available dataset as a testbed we show that our approach achieves 84.3 % performance outperforming the state-of-the-art using U-Net by 2% using the Dice Coefficient metric. © 2023 IEEE.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Machine Learning for Plastic Waste Detection: State-of-the-art, Challenges, and Solutions 3

Machine Learning for Plastic Waste Detection: State-of-the-a...

引用

3rd International Conference on Communications, Information, Electronic and Energy Systems, CIEES 2022

作者： Tamin, Owen Moung, Ervin Gubin Ahmad Dargham, Jamal Yahya, Farashazillah Omatu, Sigeru Angeline, Lorita Universiti Malaysia Sabah Faculty of Computing And Informatics Kota Kinabalu Malaysia Universiti Malaysia Sabah Faculty of Engineering Kota Kinabalu Malaysia Education Research Centre Higashi-Hiroshima739-0046 Japan Taylor's University School of Computer Science Faculty of Innovation And Technology Selangor Malaysia

ISBN: (数字)9781665491495

ISBN: (纸本)9781665491495

Machine learning has advanced rapidly in recent technologies of artificial intelligence. The abundant and cheap computation in machine learning has created more knowledge and reliability of this method. Therefore, more researchers have relied on machine learning to solve plastic waste pollution, which contributes to global greenhouse gas emissions. Datasets are fundamental requirements to build the foundation of the plastic waste detection system. This paper provides an overview of several state-of-the-art deep learning models, focusing on the dataset used for waste classification and identification. The performance of each deep learning model in classification accuracy is also discussed. The challenges of implementing deep learning in plastic waste detection are identified;(i) Data deficiency for training, (ii) Quality of the existing plastic waste dataset, and (iii) Color spaces. Lastly, the proposed solution to each challenge is presented. © 2022 IEEE.

关键词： Object detection

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：