检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Bowden, Daniel C. Fichtner, Andreas Nikas, Thomas Bogris, Adonis Simos, Christos Smolinski, Krystyna Koroni, Maria Lentas, Konstantinos Simos, Iraklis Melis, Nikolaos S. Institute of Geophysics ETH Zürich Zürich8092 Switzerland Dept. of Informatics and Telecommunications National and Kapodistrian University of Athens AthensGR-15784 Greece Dept. of Informatics and Computer Engineering University of West Attica Aghiou Spiridonos Egaleo 12243 Greece University of Thessaly Dept. of Physics Electronics Photonics Laboratory Lamia35100 Greece National Observatory of Athens Institute of Geodynamics Greece Department of Electrical and Electronics Engineering University of West Attica Aghiou Spiridonos Egaleo 12243 Greece

Distributed Acoustic Sensing (DAS) has become a popular method of observing seismic wavefields: backscattered pulses of light reveal strains or strain-rates at any location along a fiber-optic cable. In contrast, a few newer systems transmit light through a cable and collect integrated phase delays over the entire cable, such as the Microwave Frequency Fiber Interferometer (MFFI). These integrated systems can be deployed over significantly longer distances, may be used in conjunction with live telecommunications, and can be significantly cheaper. However, they provide only a single time series representing strain over the entire length of fiber. This work discusses theoretically how a distributed and integrated system can be quantitatively compared, and we note that the sensitivity depends strongly on points of curvature. Importantly, this work presents the first results of a quantitative, head-to-head comparison of a DAS and the integrated MFFI system using pre-existing telecommunications fibers in Athens, Greece. © 2022, CC BY.

关键词： Fiber optics

来源：评论

学校读者我要写书评

暂无评论

Prediction of Stroke Risk Within 7-Years Follow Up Using Machine Learning Models*

Prediction of Stroke Risk Within 7-Years Follow Up Using Mac...

引用

Data Science and engineering in Healthcare, Medicine and Biology, IEEE EMBS Special Topic Conference on

作者： Konstantina-Helen Tsarapatsani Antonis Sakellarios Vasilis D Tsakanikas Henrik Rudolf Hans J. Trampisch Vasileios C. Pezoulas George K. Matsopoulos Dimitrios I. Fotiadis Biomedical Research Institute Foundation for Research and Technology-Hellas (FORTH) Dept. of Materials Science and Engineering Unit of Medical Technology and Intelligent Information Systems University of Ioannina GR 45110 Ioannina Greece University Medical Center Rostock Institute for Biostatistics and Informatics in Medicine and Ageing Research Department of Medical Informatics Biometry and Epidemiology Ruhr University Bochum Bochum Germany School of Electrical and Computer Engineering National Technical University of Athens Athens Greece

A stroke, also known as brain attack, occurs when blood supply to your brain is interrupted. Primary prevention relies on prompt prediction of a stroke. While currently there are several clinical risk scores, machine learning (ML) models seems to be more suitable tools for accurate prediction of stroke events. Therefore, this work focuses on the prediction of stroke within 7 years follow-up in patients who have not suffered from a stroke or TIA event at baseline. LightGBM (LGBM), Extreme Grading Boosting (XGBoost), Support Vector Machine (SVM) and Decision Tree were employed in the getABI dataset, which includes 5,897 participants. The performance of models was calculated by Accuracy (ACC), Sensitivity (SENS), Specificity (SPE) and area under the receiver operating characteristic curve (AUC) of each model. According to the comparison analysis’s results, LGBM has been shown to be the most trustworthy algorithm, with accuracy 68 %. Moreover, sex, age, status of peripheral artery disease (PAD), history of myocardial infarction, angina pectoris, amputation and diabetes and pulse status of different arteries can be used as a simple and cost-effective way to predict *** Relevance: A fatal medical emergency, stroke may be anticipated using artificial intelligence, and the sooner it is predicted, the more cerebrovascular disease occurrences can be avoided.

关键词：

来源：评论

学校读者我要写书评

暂无评论

eLearning Readiness of Higher Education Institutions Students during Pandemic: Domain and Gender Perspectives 7

eLearning Readiness of Higher Education Institutions Student...

引用

7th IEEE International Conference on Smart Instrumentation, Measurement and Applications, ICSIMA 2021

作者： Kartiwi, Mira Gunawan, Teddy Surya Ahmad, Robiah International Islamic University Malaysia Information Systems Department Kuala Lumpur53100 Malaysia International Islamic University Malaysia Electrical and Computer Engineering Dept. Kuala Lumpur53100 Malaysia Universiti Teknologi Malaysia Razak Faculty of Technology Informatics Kuala Lumpur54100 Malaysia

ISBN: (纸本)9781728175225

In 2020, the pandemic has triggered a rapid paradigm shift and necessitated a prompt switch in teaching methods worldwide. This significant change has affected the educators to rethink and assess the notion of teaching and learning, as well as the impact on the students. While many have gained adequate exposure to eLearning, the prompt switch to remote learning has triggered a new set of challenges. The result of this study shows that although most students express their readiness for remote teaching and learning, the sudden shift to online mode prompted different concerns after the trial session started. Hence, the assessment of readiness may only offer a partial view of the eLearning conundrum. Furthermore, evaluation of students' experience during remote teaching and learning period shows an interesting pattern on the different perceptions of online teaching mode between male and female students and among the domain of the study. Finally, it highlights the potential support that educational institutions may provide to ease the transitions process. © 2021 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Using LSTM Neural Networks as Resource Utilization Predictors: The Case of Training Deep Learning Models on the Edge 1

引用

17th International Conference on Economics of Grids, Clouds, Systems, and Services, GECON 2020

作者： Violos, John Psomakelis, Evangelos Danopoulos, Dimitrios Tsanakas, Stylianos Varvarigou, Theodora School of Electrical and Computer Engineering National Technical University of Athens Zografou15771 Greece Dept. of Informatics and Telematcs Harokopio University of Athens Tavros Greece

ISBN: (数字)9783030630584

ISBN: (纸本)9783030630577

Cloud and Fog technologies are steadily gaining momentum and popularity in the research and industry circles. Both communities are wondering about the resource usage. The present work aims to predict the resource usage of a machine learning application in an edge environment, utilizing Raspberry Pies. It investigates various experimental setups and machine learning methods that are acting as benchmarks, allowing us to compare the accuracy of each setup. We propose a prediction model that leverages the time series characteristics of resource utilization employing an LSTM Recurrent Neural Network (LSTM-RNN). To conclude to a close to optimal LSTM-RNN architecture we use a genetic algorithm. For the experimental evaluation we used a real dataset constructed by training a well known model in Raspberry Pies3. The results encourage us for the applicability of our method. © 2020, Springer Nature Switzerland AG.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Techno-economic analysis of cognitive radio models in 5G networks 17

Techno-economic analysis of cognitive radio models in 5G net...

引用

17th International Conference on Mobile Systems and Pervasive Computing, MobiSPC 2020

作者： Bouras, Christos Kollia, Anastasia Papazois, Andreas Computer Technology Institute and Press Diophantus PatrasP.C. 26504 Greece Computer Engineering and Informatics Dept. University of Patras PatrasP.C. 26504 Greece

The first commercial products of 5G will be released within 2020 and therefore, it becomes an absolute necessity to research whether the key enabling technologies are advantageous for the operators to invest in. One of the most fundamental technologies Cognitive Radio (CR), since there is not much research in the field. This paper develops a techno-economic framework for the CR technology and is contrasted with an already existing model for Software Defined Networks (SDN). A Sensitivity Analysis (SA) indicates the cost parameters that are the most expensive ones and should be reconsidered for the model's wide adoption and viability. © 2020 The Authors.

关键词： Cognitive radio

来源：评论

学校读者我要写书评

暂无评论

GPU-Based Texture Analysis approach for Mammograms Institute of Biomedical informatics

GPU-Based Texture Analysis approach for Mammograms Institute...

引用

2020 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2020

作者： Hung, Che-Lun Lin, Chun-Yuan Institute of Biomedical Informatics National Yang Ming University Taipei Taiwan Chang Gung University Dept. of Computer Science and Information Engineering Taoyuan Taiwan

ISBN: (纸本)9781728162157

Mammograms are always used to detect signs of breast cancer. Texture-analysis techniques were applied to determine imaging biomarkers consisting of mean, contrast, correlation, energy and homogeneity features of parametric maps, and they can be utilized to retravel specific features of symptoms from medical images produced by X-ray, magnetic resonance imaging, computed tomography, and so forth. Gray level run-length matrix is the one of the texture extraction methods which has been successfully used to facilitate medical image analysis. However, it is computation-intensive method. We implemented it on GPU to accelerating extraction process for mammograms. The proposed method achieves significant speedup over CPU-based implementation. © 2020 IEEE.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Accelerating deep neural networks for efficient scene understanding in automotive cyber-physical systems

arXiv

引用

arXiv 2021年

作者： Nousias, Stavros Pikoulis, Erion Vasilis Mavrokefalidis, Christos Lalos, Aris S. Industrial Systems Institute Athena Research Center Patras Science Park Greece Computer Engineering Informatics Dept. University of Patras Greece

Automotive Cyber-Physical Systems (ACPS) have attracted a significant amount of interest in the past few decades, while one of the most critical operations in these systems is the perception of the environment. Deep learning and, especially, the use of Deep Neural Networks (DNNs) provides impressive results in analyzing and understanding complex and dynamic scenes from visual data. The prediction horizons for those perception systems are very short and inference must often be performed in real time, stressing the need of transforming the original large pre-trained networks into new smaller models, by utilizing Model Compression and Acceleration (MCA) techniques. Our goal in this work is to investigate best practices for appropriately applying novel weight sharing techniques, optimizing the available variables and the training procedures towards the significant acceleration of widely adopted DNNs. Extensive evaluation studies carried out using various state-of-the-art DNN models in object detection and tracking experiments, provide details about the type of errors that manifest after the application of weight sharing techniques, resulting in significant acceleration gains with negligible accuracy losses. © 2021, CC BY.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Elastic scale-free networks model based on the mediaton-driven attachment rule 3

Elastic scale-free networks model based on the mediaton-driv...

引用

3rd IEEE International Conference on Data Stream Mining and Processing, DSMP 2020

作者： Shergin, Vadim Chala, Larysa Udovenko, Serhii Pogurskaya, Mariya Kharkiv National University of Radio Electronics Artificial Intelligence Dept. Kharkiv Ukraine Simon Kuznets Kharkiv National University of Economics Informatics and Computer Engineering Dept Kharkiv Ukraine

ISBN: (纸本)9781728132143

The problem of modeling scale-free networks is considered. Mediation-driven attachment rule with nonconstant number of added links is proposed. Applying the copy-factor as the control parameter instead of traditionally used number of incoming links makes it possible to generate networks model, which combines the key benefits of mediation- driven attachment, such as indirect using the nodes degree, and elasticity, such as different relative growth rates for links and nodes. The properties of proposed networks model were studied analytically and confirmed by simulation results. © 2020 IEEE.

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

Context-aware Rate Adaptation for Predictive Flying Networks using Contextual Bandits

arXiv

引用

arXiv 2025年

作者： Queiros, Ruben Kaneko, Megumi Fontes, Helder Campos, Rui INESC TEC Faculty of Engineering University of Porto Porto Portugal National Institute of Informatics Dept. of Computer Science The University of Tokyo Tokyo Japan

The increasing complexity of wireless technologies, such as Wi-Fi, presents significant challenges for Rate Adaptation (RA) due to the large configuration space of transmission parameters. While extensive research has been conducted on RA for low-mobility networks, existing solutions fail to adapt in flying networks, where high mobility and dynamic wireless conditions introduce additional uncertainty. We propose Linear Upper Confidence Bound for RA (LinRA), a novel Contextual Bandit-based approach that leverages real-time link context to optimize transmission rates. Designed for predictive flying networks, where future trajectories are known, LinRA proactively adapts to obstacles affecting channel quality. Simulation results demonstrate that LinRA converges 5.2× faster than state-of-the-art benchmarks and improves throughput by 80% in Non Line-of-Sight (NLoS) conditions, matching the performance of ideal algorithms. With low time complexity, LinRA is a scalable and efficient RA solution for predictive flying networks. © 2025, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Load Shedding Automation System on Smart Meter Using Fuzzy Logic Method

Load Shedding Automation System on Smart Meter Using Fuzzy L...

引用

International Conference on Advanced Mechatronics, Intelligent Manufacture, and Industrial Automation (ICAMIMIA)

作者： Imam Wahyudi Farid Ciptian Weried Priananda Divan Andika Yuhansyah Siska Arifiani Ridho Rahman Hariadi Ardyono Priyadi Mauridhi Hery Purnomo Dept. Electrical Automation Engineering Dept. Electrical Engineering Institut Teknologi Sepuluh Nopember Surabaya Indonesia Dept. Electrical Automation Engineering Institut Teknologi Sepuluh Nopember Surabaya Indonesia Dept. Informatics Engineering Institut Teknologi Sepuluh Nopember Surabaya Indonesia Dept. Electrical Engineering Institut Teknologi Sepuluh Nopember Surabaya Indonesia Dept. Computer Engineering Institut Teknologi Sepuluh Nopember Surabaya Indonesia

ISBN: (纸本)9781665499705

The need for electrical energy for the household sector has become a basic need. However, there are still people who complain about expensive electricity bills. In addition, the use of electricity is not recommended to exceed the power capacity which can cause a short circuit. Therefore, a tool is needed, namely a Smart Meter that can monitor the use of electrical energy and can perform load shedding automatically to reduce the occurrence of short circuits. The load shedding automation system uses one of the methods of artificial intelligence technology, namely by using Mamdani's Fuzzy Logic so that it can recognize patterns, classify/identify, predict, and optimize the use of electrical energy. Load shedding is carried out based on priority loads and non-priority loads. From testing the load shedding automation system which was carried out 5x with 6x load combination trials, it resulted that in the 1st to 4th experiments, Relay_Hidup3 output was obtained. To carry out the load shedding process, the average delay time is 2,302 seconds

关键词： Fuzzy logic Automation Mechatronics Load shedding Smart meters Delays Pattern recognition

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：