检索结果-内蒙古大学图书馆

Orthogonal projection for anomaly detection in networking datasets

Journal of Ambient Intelligence and Humanized computing 2023年第6期14卷 7957-7966页

作者： Cortes-Polo, David Jimenez, Luis I. Paoletti, Mercedes E. Calle-Cancho, Jesus Rico-Gallego, Juan A. Department of Signal Theory and Communication University Rey Juan Carlos Cam. del Molino 5 Madrid Fuenlabrada28942 Spain Intelligent Systems Group Department of Computer Science University of Valladolid P.O de Belén 15 Valladolid47011 Spain Hyperspectral Computing Laboratory Department of Technology of Computers and Communication University of Extremadura Av. de la Universidad s/n Caceres10003 Spain Calle Sola 1 Extremadura Trujillo10200 Spain Computer and Telematics Systems Engineering University of Extremadura Av. de la Universidad s/n Caceres10003 Spain

In recent years, the impressive growth of new wireless technologies, together with the appearance of new requirements in applications and services, is progressively changing the use of networks. Due to the high mobility required, the network must adapt to the infrastructure to meet the demands of the users. As a result, service providers currently have to over-provision network capacity, which is costly. In addition, considering efficient resource planning in advance involves a lot of labor-intensive efforts. Consequently, network usage analysis is a very useful tool that allows network administrators to find patterns and anomalies. Whilst pattern detection provides administrators the ability to define the infrastructure, anomaly detection provides rich and valuable information for certain applications, for example, to avoid network saturation in urban areas during peak hours. This article proposes a new methodology based on orthogonal projections over Call Detail Records (CDR) for anomaly detection to help in the dynamic management of the network in an urban area. The method is evaluated in a real scenario provided by an Italian telecommunications operator, considering different locations in the Milan metropolitan area, differentiated by the geographic resolution of the data, reaching F1 scores above 0.8. In addition, a new ground truth is presented, hoping it will become a reference data set for the community, in the form of a set of locations that have been corroborated for use in evaluating anomaly detection techniques. © 2023, The Author(s).

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Overcoming the Passivity Bounds in communications systems with Spacetime Modulations 19

Overcoming the Passivity Bounds in Communications Systems wi...

引用

19th European Conference on Antennas and Propagation, EuCAP 2025

作者： Moreno-Rodríguez, Salvador Alex-Amor, Antonio Pérez-Escribano, Mario Valenzuela-Valdés, Juan F. Padilla, Pablo Molero, Carlos Research Centre for Information and Communication Technologies (CITIC-UGR) University of Granada Department of Signal Theory Telematics and Communications Granada Spain University of Pennsylvania Department of Electrical and Systems Engineering Philadelphia 19104 PA United States Telecommunication Research Institute (TELMA) Universidad de Malaga E.T.S. Ingeniería de Telecomunicación Málaga 29010 Spain

ISBN: (纸本)9788831299107

In this paper, we exploit the extra degrees of freedom associated with including time as a design variable to create communication scenarios beyond the physical bounds of passive structures. We particularize the results to a time-modulated diffractive one-dimensional grating. By tuning the temporal modulation, we show that two different scenarios can lead to the same output angles but with different output frequencies or incidence angles. These results illustrate the potential of these metastructures as diffractive beamformers and frequency mixers. © 2025 European Association on Antennas and Propagation.

关键词： beamforming electromagnetics frequency conversion metamaterials spacetime modulation

来源：评论

学校读者我要写书评

暂无评论

Single Reference Segmentation to Estimate T-Wave Alternans

Single Reference Segmentation to Estimate T-Wave Alternans

引用

Computers in Cardiology (CinC)

作者： E Sánchez-Carballo F M Melgarejo-Meseguer J L Rojo-Álvarez A García-Alberola Y Rudy Department of Signal Theory and Communications Telematics and Computing Systems Universidad Rey Juan Carlos Madrid Spain Arrhythmia Unit Hospital Universitario Virgen de la Arrixaca Murcia Spain Cardiac Bioelectricity and Arrhythmia Center Washington University in St. Louis USA

T-Wave Alternans (TWA) are an indicator of sudden cardiac death risk, and they measure the differences between consecutive T-waves in Electrocardiogram (ECG) studies. In this work, we used ECG Imaging (ECGI) data to scrutinize the spatial distribution of alternans along the torso and epicardium. ECGI signals were obtained from the torso of eight patients suffering from Long QT syndrome and from three control subjects, and epicardial signals were estimated through the inverse problem of ECG. We introduced a new method for segmenting T-waves, called the Single Reference Segmentation (SRS), and we analyzed its performance by estimating TWA and comparing it to the atomic segmentation method, consisting of performing the alignment of each signal in isolation. Our results showed that SRS improves the quality of TWA estimations, which could provide clinically useful representations of the spatial-temporal distribution of TWA using ECGI data.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Accuracy Estimation for Brain-Computer Interfaces based on Auditory Attention Decoding

TechRxiv

引用

TechRxiv 2023年

作者： Lopez-Gordo, Miguel A. Geirnaert, Simon Bertrand, Alexander The University of Granada Department of Signal Theory Telematics and Communications Spain Spain STADIUS Center for Dynamical Systems Signal Processing and Data Analytics Belgium Leuven.AI – KU Leuven Institute for AI Belgium KU Leuven Department of Neurosciences Research Group ExpORL Belgium

Auditory attention decoding (AAD) algorithms process brain data such as electroencephalography (EEG) in order to decode to which of multiple competing sound sources a person attends. Example use cases are neuro-steered hearing aids or brain-computer interfaces (BCI) for patients with severe motor or cognitive impairments. Recently, it has been shown that it is possible to train such AAD decoders in an unsupervised setting, where there is no ground truth available regarding which of the sound sources is attended. However, in the absence of such ground-truth labels, it is difficult to quantify the accuracy of the decoders, in particular when working with patients who can neither communicate nor show any evidence of collaboration. In this paper, we use principles of digital communications to estimate the AAD accuracy during a competing talker listening task in a completely unsupervised manner. We show that our proposed unsupervised estimation technique can accurately determine the accuracy of the decoder in a transparent-for-the-user way, for different amounts of training data, decision window lengths, and amounts of estimation data. Furthermore, since different applications demand different targeted accuracies, our approach can estimate the required minimal amount of training required for any given target accuracy. In neuro-steered hearing aids, our approach could support time-adaptive decoding, dynamic gain control, and neurofeedback training. In BCIs, it could support a robust communication paradigm for caregivers and professionals to reach and gain insights into people who cannot communicate by any means. © 2023, CC BY-SA.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Spatial Characterization of Indoor Radio Channel in the D-Band at 165 GHz

Spatial Characterization of Indoor Radio Channel in the D-Ba...

引用

European Conference on Antennas and Propagation, EuCAP

作者： Juan E. Galeote-Cazorla Ginés Martínez-García Alejandro Ramírez-Arroyo Ana Vázquez Alejos Juan F. Valenzuela-Valdés Department of Signal Theory Telematics and Communications Research Centre for Information and Communication Technologies (CITIC-UGR) University of Granada Granada Spain Department of Electronic Systems Aalborg University (AAU) Aalborg Denmark Escola de Enxeñaría de Telecomunicación atlanTTic Universidade de Vigo Vigo Spain

ISBN: (数字)9788831299107

ISBN: (纸本)9798350366327

This paper presents an experimental study of the indoor radio channel characteristics at 165 GHz in the D-band. Using wideband measurements based on sliding correlation technique (swept time delay cross-correlation, STDCC) with a pseudo-random binary sequence (PRBS) of length 2 23 , we analyze key parameters such as the power delay profile, delay spread, and fading effects as the receiver moves along a linear path. The results indicate significant multipath propagation, with increasing delay spread corresponding to distance. Additionally, signal quality degradation metrics, including Error Vector Magnitude (EVM) and Modulation Error Ratio (MER) are evaluated. The obtained results are consistent with an indoor scenario dominated by a LOS component, with no significant presence of multipath contributions.

关键词： Fading channels Power measurement Indoor radio communication Modulation Receivers Propagation losses Vectors Time measurement Delays Wideband

来源：评论

学校读者我要写书评

暂无评论

CyberTOMP: A novel systematic framework to manage asset-focused cybersecurity from tactical and operational levels

TechRxiv

引用

TechRxiv 2022年

作者： Domínguez-Dorado, Manuel Carmona-Murillo, Javier Polo, David Cortés Rodríguez Pérez, Francisco J. Department of Information Systems and Digital Toolkit. Public Business Entity Red.es. Madrid28020 Spain Department of Computing and Telematics Engineering Universidad de Extremadura Cáceres10003 Spain Department of Signal Theory and Communications and Telematics Systems and Computing Rey Juan Carlos University Móstoles Madrid28933 Spain

Currently different reference models are used to manage cybersecurity, although practically none are applicable "as is" to lower levels as they do not detail specific procedural aspects for them. However, they urge organizations to develop a methodological foundation to manage cybersecurity at those levels. Although they allow organizations to adhere to a recognized standard at the strategic level, this advantage vanishes when organizations must define specific low-level procedures, allowing the appearance of inconsistency at tactical and operational levels between departments of the same organization or between organizations. The design of these elements with the required holism and homogeneity is difficult, and this is why generic processes focused on getting certified regarding a standard are usually originated, but they are insufficient to obtain effective cybersecurity because they are not focused on dealing with real cyber threats. Because of the great responsibility of lower levels to achieve effective cybersecurity, this lack of methodological definition makes it difficult to adapt cybersecurity to the highly dynamic cyber context with the required holism and strategic alignment. Our proposal provides CyberTOMP, a process for managing cybersecurity at lower levels, as well as a set of methodological elements that support it. The novelty of these contributions is that they complement the strategic standard selected by the organization, providing it with a set of procedural elements ready to be used out of the box, contributing those aspects required by high-level frameworks to manage cybersecurity at lower levels, for which there is no alternative with a managerial approach. © 2022, CC BY-SA.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

A Data-Driven Approach for Digital Hair Removal in Dermoscopy Images Using Encoder-Decoder and Generative Adversarial Network-Based Models

SSRN

引用

SSRN 2024年

作者： Gómez-Martínez, Vanesa Chushig-Muzo, David Lara-Abelanda, Francisco Jesus Veierød, Marit B. Godtliebsen, Fred Granja, Conceição Soguero-Ruiz, Cristina Department of Signal Theory and Communications Telematics and Computing Systems Rey Juan Carlos University Madrid Spain Oslo Centre for Biostatistics and Epidemiology Department of Biostatistics Institute of Basic Medical Sciences University of Oslo Norway Department of Mathematics and Statistics UiT The Arctic University of Norway Norway Norwegian Centre for E-health Research University Hospital of North Norway Tromsø9019 Norway

Skin lesions present a growing challenge in public health, posing significant burdens on individuals and healthcare systems. Dermoscopy has emerged as a valuable tool for dermatologists, providing improved visualization for skin lesion diagnosis. However, hair in dermoscopy images often obscures crucial texture and color information, hindering accurate diagnosis. To address this challenge, we propose a two-stage data-driven methodology for digital hair removal. Our approach employs encoder-decoder architectures for hair segmentation and the Aggregated Contextual-Transformation-generative adversarial network model for image inpainting, aiming to preserve crucial texture and color information after hair removal. The proposed methodology was assessed across two public datasets: a skin lesion hair mask dataset with fine-grained annotations for hair segmentation and the skin_hair dataset for image inpainting. Our method demonstrated improvements over state-of-the-art models, achieving an inpainting quality of 0.99 in the structural similarity index and 1.00 in the image quality index. Furthermore, we evaluated the performance of our approach in a real-world scenario of skin lesion classification, particularly in melanoma identification. Using our methods, we extracted hairless images from three publicly available datasets (Seven-Point Checklist Dermatology Dataset (Derm7t), International Skin Imaging Collaboration 2020 (ISIC-2020), and PH2) and fed them into the convolutional neural network-based models to identify melanoma. Our approach achieved the best area under the receiver operating characteristic curve values, obtaining 0.75, 0.87, and 0.91 for the Derm7pt, ISIC-2020, and PH2 datasets, respectively. Results demonstrated the effectiveness of our approach in removing hair while preserving diagnostic information. © 2024, The Authors. All rights reserved.

关键词： Dermatology

来源：评论

学校读者我要写书评

暂无评论

A Study of FR2 Radio Propagation with Focus on Mobility Management in an Industrial Scenario

A Study of FR2 Radio Propagation with Focus on Mobility Mana...

引用

European Conference on Antennas and Propagation, EuCAP

作者： Alejandro Ramírez-Arroyo Melisa López Ignacio Rodríguez Troels B. Sørensen Samantha Caporal del Barrio Juan F. Valenzuela-Valdés Preben Mogensen Department of Signal Theory Telematics and Communications University of Granada (CITIC-UGR) Granada Spain Department of Electronic Systems Aalborg University (AAU) Aalborg Denmark Department of Electrical Engineering University of Oviedo (UNIOVI) Gijón Spain Nokia Aalborg Denmark

This work presents the analysis of a measurement campaign performed in a realistic two-hall industrial environment for FR2 band. In order to provide secure, reliable and high available Machine-to-Machine communications in the mmWave band for Industrial Internet of Things mobile applications, a study of the physical propagation channel must be carried out. The analysis shows the high variability of the propagation channel depending on the Line-of-Sight or Non Line-of-Sight condition, with path loss exponents ranging from 2.10 to 4.56. The mobility analysis demonstrates the high probability of beam switching if a threshold is not defined. By imposing this threshold, there is a decrease in the complexity of mobility management in exchange for a reduction in received power at the end user.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Transient Analysis of Space-Time Frequency-Dispersive Metal Slabs

Transient Analysis of Space-Time Frequency-Dispersive Metal ...

引用

International Congress on Advanced Electromagnetic Materials in Microwaves and Optics (METAMATERIALS)

作者： Pablo H. Zapata-Cano Salvador Moreno-Rodríguez Stamatios Amanatiadis Antonio Alex-Amor Zaharias D. Zaharis Carlos Molero School of Electrical and Computer Engineering Aristotle University of Thessaloniki Thessaloniki Greece Department of Signal Theory Telematics and Communications Research Centre for Information and Communication Technologies (CITIC-UGR) Universidad de Granada Granada Spain Department of Electrical and Systems Engineering Philadelphia University of Pennsylvania Pennsylvania United States

ISBN: (数字)9798350373493

ISBN: (纸本)9798350373509

In this paper, we analyze the scattering of an incident plane wave on a space-time metal slab in the presence of dispersion. Frequency dispersion is taken into account here by means of the Drude model. Analytical results, obtained via first-principle calculations, are in good agreement with in-house finite-difference time-domain (FDTD) computations.

关键词： Transient response Time-frequency analysis Metals Scattering Time-domain analysis Slabs Transient analysis Dispersion Physics Finite difference methods

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning Framework for the Automatic Classification of Microseisms at Cotopaxi Volcano 1

引用

7th IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2024

作者： Lara-Cueva, Román Iglesias, Iván Rosero, Alejandro Benítez, Diego Pérez-Pérez, Noel Rojo-Álvarez, José Luis Departamento de Eléctrica Electrónica y Telecomunicaciones Universidad de Las Fuerzas Armadas ESPE Sangolquí171103 Ecuador Colegio de Ciencias e Ingenierías "El Politécnico" Universidad San Francisco de Quito USFQ Quito170157 Ecuador Department of Signal Theory and Communications Telematics and Computing Systems Universidad Rey Juan Carlos Madrid28933 Spain

ISBN: (数字)9783031888540

ISBN: (纸本)9783031888533

This paper presents a comprehensive framework for an automated classification system of Long Period (LP) and Volcano Tectonic (VT) seismic events from the Cotopaxi volcano, employing two prominent Deep Learning models: Stacked Autoencoders and Deep Neural Networks. The dataset was provided by the Instituto Geofísico de la Escuela Politécnica Nacional (IGEPN), which consists of 1,044 LP events and 101 VT events. To enhance the model’s performance, data augmentation techniques were applied, generating synthetic microseismic data using a Conditional Generative Adversarial Network (CGAN), ultimately expanding the dataset to 10,000 microseisms, comprising both real and synthetic samples. In the feature extraction stage, we calculated the Power Spectral Density (PSD) using Welch’s method and a 512-point Fast Fourier Transform (FFT), resulting in 257 frequency-based features. Additionally, wavelet coefficients were obtained via Discrete Wavelet Transform (DWT) using the Symlet wavelet with six levels of decomposition. PSD was also computed on these wavelet coefficients, producing 257 additional frequency-scale features. The enriched feature set was used to train the Deep Learning models, with performance evaluated using standard classification metrics. The Stacked Autoencoder model outperformed others, achieving an accuracy of 99.73% and a balanced error rate (BER) of 0.0027, corresponding to just 3 errors per 1,000 classified microseisms. These results substantially exceed the geophysical accuracy requirement of a BER below 0.01. This paper demonstrates the efficacy of Deep Learning models in distinguishing between LP and VT events, offering new opportunities for enhancing volcanic monitoring and hazard assessment strategies. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Discrete Fourier 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：