☆ 4.7 Article

VisGIN: Visibility Graph Neural Network on one-dimensional data for biometric authentication

EXPERT SYSTEMS WITH APPLICATIONS (2024)

相关参考文献

注意：仅列出部分参考文献，下载原文获取全部文献信息。

Editorial Material Cardiac & Cardiovascular Systems

Explainable AI for ECG-based prediction of cardiac resynchronization therapy outcomes: learning from machine learning

Zachi Attia et al.

EUROPEAN HEART JOURNAL (2023)

添加到收藏夹

Article Automation & Control Systems

Model-driven deep unrolling: Towards interpretable deep learning against noise attacks for intelligent fault diagnosis

Zhibin Zhao et al.

Summary: Intelligent fault diagnosis (IFD) has made significant progress with the help of deep learning (DL)-based methods. However, the black box nature of DL-based methods and the negative impact of noise on IFD based on vibration signals remain challenges. In this paper, a model-driven deep unrolling method is proposed to address these issues, offering ante-hoc interpretability and robustness against noise attacks. The proposed algorithm, LGSC-Net, is unfolded based on the multi-layer sparse coding (ML-SC) model and its relationship with the convolutional neural network (CNN) is thoroughly discussed. Experimental results on aero-engine gear fault detection validate the effectiveness of the proposed model, and its interpretability is also discussed.

ISA TRANSACTIONS (2022)

添加到收藏夹

Article Computer Science, Information Systems

ECG-Based Biometrics Using a Deep Network Based on Independent Component Analysis

Jae-Neung Lee et al.

Summary: The study introduces a deep network based on ICA called ICANet1, which is later improved into ICANet2. ICANet2 uses the ICA algorithm to address the issue of decreased performance when data is modified. While it performs lower than deep learning, it is expected to excel in recognition speed, especially for mobile devices.

IEEE ACCESS (2022)

添加到收藏夹

Article Engineering, Multidisciplinary

AvgNet: Adaptive Visibility Graph Neural Network and Its Application in Modulation Classification

Qi Xuan et al.

Summary: This article introduces an Adaptive Visibility Graph (AVG) algorithm that can map time series into graphs. It also proposes an end-to-end classification framework called AvgNet. The research shows that AvgNet outperforms other deep learning methods in the task of radio signal modulation classification.

IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING (2022)

添加到收藏夹

Article Engineering, Electrical & Electronic

An ECG Biometric System Using Hierarchical LSTM With Attention Mechanism

Debasish Jyotishi et al.

Summary: This paper introduces a novel attention-based hierarchical long short-term memory (HLSTM) model for learning biometric representation corresponding to each individual from ECG signals. The model can effectively capture the temporal variation of ECG signals in different abstractions and focus on valuable biometric information, improving performance compared to existing methods.

IEEE SENSORS JOURNAL (2022)

添加到收藏夹

Article Chemistry, Multidisciplinary

Personal Identification Using an Ensemble Approach of 1D-LSTM and 2D-CNN with Electrocardiogram Signals

Jin-A Lee et al.

Summary: This paper proposes a personal identification technique based on electrocardiograms (ECGs) using an ensemble of long short-term memory (LSTM) and convolutional neural network (CNN), achieving higher performance in noise removal and feature extraction.

APPLIED SCIENCES-BASEL (2022)

添加到收藏夹

Article Engineering, Biomedical

BAED: A secured biometric authentication system using ECG signal based on deep learning techniques

Jaya Prakash Allam et al.

Summary: Biometric authentication technology has become increasingly common, requiring systems that are simple, flexible, efficient, and secure. ECGs are a suitable biometric trait but designing ECG-based systems is challenging. A novel biometric authentication scheme called BAED, based on ECG detection, is proposed and achieves better performance through deep learning algorithms.

BIOCYBERNETICS AND BIOMEDICAL ENGINEERING (2022)

添加到收藏夹

Review Engineering, Mechanical

Visibility graph for time series prediction and image classification: a review

Tao Wen et al.

Summary: The analysis of time series and images is significant in various fields. Visibility graph algorithms are used to map time series and images into different types of complex networks in order to explore their topological structure and information. By using local random walk algorithms and information fusion methods, time series can be forecasted, and images can be classified using machine learning models. The visibility graph algorithm outperforms existing algorithms in time series prediction and image classification, making complex networks an important tool for understanding the characteristics of time series and images.

NONLINEAR DYNAMICS (2022)

添加到收藏夹

Article Mathematics, Applied

Texture classification based on image (natural and horizontal) visibility graph constructing methods

Laifan Pei et al.

Summary: In this study, a texture classification algorithm named TCIVG was designed based on a newly proposed image visibility graph network constructing method. Experimental results on the Brodatz texture image database showed high classification accuracy for both artificial and natural texture images. The results outperformed some existing literature studies based on the same image database.

CHAOS (2021)

添加到收藏夹

Article Mathematics

XCM: An Explainable Convolutional Neural Network for Multivariate Time Series Classification

Kevin Fauvel et al.

Summary: This paper introduces XCM, a new compact convolutional neural network for MTS classification, which not only achieves good generalization performance on both large and small datasets, but also provides faithful explanations by precisely identifying important input data variables and timestamps.

MATHEMATICS (2021)

添加到收藏夹

Article Physics, Multidisciplinary

Using Convolutional Neural Network and a Single Heartbeat for ECG Biometric Recognition

Dalal A. AlDuwaile et al.

Summary: This paper explores the use of a short segment of an ECG signal for biometric recognition, achieving better accuracy and acceptability by enhancing entropy through a small CNN. It also investigates the impact of different segment lengths on performance. Results show that the time-frequency domain representation of a short segment of an ECG signal can improve accuracy and acceptability of this modality.

ENTROPY (2021)

添加到收藏夹

Article Health Care Sciences & Services

PQRST wave detection on ECG signals

Putri Madona et al.

Summary: By detecting abnormalities in the PQRST interval on ECG signals, it can serve as a preliminary diagnosis of heart health. The study results indicate that the feature extraction method used has a high accuracy in detecting the heart health status of the subjects.

GACETA SANITARIA (2021)

添加到收藏夹

Article Telecommunications

Lightweight authentication protocol for e-health clouds in IoT-based applications through 5G technology

Minahil et al.

Summary: Modern information technology is increasingly being utilized in storing and distributing healthcare data to reduce costs and improve medical facilities. While the emergence of e-Health clouds offers novel opportunities for easy and remote access to medical data, it also presents new risks and challenges in terms of ensuring integrity, security, and confidentiality. Authentication, particularly through factors like smart cards, passwords, and biometrics, is crucial in protecting susceptible e-Health data from illegal access. Many ECC-based authentication protocols have been proposed for e-Health clouds, but most suffer from security flaws and high computational overheads. Introducing a novel protocol that addresses major attack vectors and evaluating it through security analysis shows it to be more efficient, robust, and secure than existing protocols.

DIGITAL COMMUNICATIONS AND NETWORKS (2021)

添加到收藏夹

Article Telecommunications

An efficient hash-based authenticated key agreement scheme for multi-server architecture resilient to key compromise impersonation

Inam ul Haq et al.

Summary: Considering the low power and computational capacities of mobile devices, researchers have proposed hash-based multi-server authentication schemes for secure online communication. Existing schemes have security vulnerabilities, prompting the proposal of an improved scheme, which was verified using the AVISPA tool, showing higher efficiency.

DIGITAL COMMUNICATIONS AND NETWORKS (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Toward improving ECG biometric identification using cascaded convolutional neural networks

Yazhao Li et al.

NEUROCOMPUTING (2020)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Robust ECG biometrics using GNMF and sparse representation

Rui Li et al.

PATTERN RECOGNITION LETTERS (2020)

添加到收藏夹

Article Computer Science, Artificial Intelligence

InceptionTime: Finding AlexNet for time series classification

Hassan Ismail Fawaz et al.

DATA MINING AND KNOWLEDGE DISCOVERY (2020)

添加到收藏夹

Review Imaging Science & Photographic Technology

A Survey on Anti-Spoofing Methods for Facial Recognition with RGB Cameras of Generic Consumer Devices

Zuheng Ming et al.

JOURNAL OF IMAGING (2020)

添加到收藏夹

Article Robotics

CNNAI: A Convolution Neural Network-Based Latent Fingerprint Matching Using the Combination of Nearest Neighbor Arrangement Indexing

Uttam U. Deshpande et al.

FRONTIERS IN ROBOTICS AND AI (2020)

添加到收藏夹

Article Computer Science, Information Systems

An Efficient Network Method for Time Series Forecasting Based on the DC Algorithm and Visibility Relation

Junyin Zhao et al.

IEEE ACCESS (2020)

添加到收藏夹

Article Computer Science, Information Systems

A Score-Level Fusion of Fingerprint Matching With Fingerprint Liveness Detection

Yongliang Zhang et al.

IEEE ACCESS (2020)

添加到收藏夹

Article Computer Science, Information Systems

ECG Biometric Authentication: A Comparative Analysis

Mohit Ingale et al.

IEEE ACCESS (2020)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Deep-ECG: Convolutional Neural Networks for ECG biometric recognition

Ruggero Donida Labati et al.

PATTERN RECOGNITION LETTERS (2019)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Multivariate LSTM-FCNs for time series classification

Fazle Karim et al.

NEURAL NETWORKS (2019)

添加到收藏夹

Article Computer Science, Information Systems

An Enhanced Machine Learning-Based Biometric Authentication System Using RR-Interval Framed Electrocardiograms

Song-Kyoo Kim et al.

IEEE ACCESS (2019)

添加到收藏夹

Article Telecommunications

A data reduction scheme for active authentication of legitimate smartphone owner using informative apps ranking

Abdulaziz Alzubaidi et al.

DIGITAL COMMUNICATIONS AND NETWORKS (2019)

添加到收藏夹

Article Computer Science, Information Systems

User Identification System Using 2D Resized Spectrogram Features of ECG

Gyu-Ho Choi et al.

IEEE ACCESS (2019)

添加到收藏夹

Article Computer Science, Information Systems

A Deep Bidirectional GRU Network Model for Biometric Electrocardiogram Classification Based on Recurrent Neural Networks

Htet Myet Lynn et al.

IEEE ACCESS (2019)

添加到收藏夹

Article Computer Science, Information Systems

ECG Authentication Method Based on Parallel Multi-Scale One-Dimensional Residual Network With Center and Margin Loss

Yifan Chu et al.

IEEE ACCESS (2019)

添加到收藏夹

Article Biology

A novel wavelet sequence based on deep bidirectional LSTM network model for ECG signal classification

Ozal Yildirim

COMPUTERS IN BIOLOGY AND MEDICINE (2018)

添加到收藏夹

Article Automation & Control Systems

Feature Selection for Nonstationary Data: Application to Human Recognition Using Medical Biometrics

Majid Komeili et al.

IEEE TRANSACTIONS ON CYBERNETICS (2018)

添加到收藏夹

Article Computer Science, Information Systems

LSTM Fully Convolutional Networks for Time Series Classification

Fazle Karim et al.

IEEE ACCESS (2018)

添加到收藏夹

Article Telecommunications

An improved and secure multiserver authentication scheme based on biometrics and smartcard

Ashish Kumar et al.

DIGITAL COMMUNICATIONS AND NETWORKS (2018)

添加到收藏夹

Article Multidisciplinary Sciences

Beat-ID: Towards a computationally low-cost single heartbeat biometric identity check system based on electrocardiogram wave morphology

Joana S. Paiva et al.

PLOS ONE (2017)

添加到收藏夹

Article Chemistry, Analytical

Towards a Continuous Biometric System Based on ECG Signals Acquired on the Steering Wheel

Joao Ribeiro Pinto et al.

SENSORS (2017)

添加到收藏夹

Article Chemistry, Analytical

Toward Improving Electrocardiogram (ECG) Biometric Verification using Mobile Sensors: A Two-Stage Classifier Approach

Robin Tan et al.

SENSORS (2017)

添加到收藏夹

Article Computer Science, Information Systems

HeartID: A Multiresolution Convolutional Neural Network for ECG-Based Biometric Human Identification in Smart Health Applications

Qingxue Zhang et al.

IEEE ACCESS (2017)

添加到收藏夹

Article Computer Science, Information Systems

Biometric Authentication Using Noisy Electrocardiograms Acquired by Mobile Sensors

Hyun-Soo Choi et al.

IEEE ACCESS (2016)

添加到收藏夹

Article Computer Science, Theory & Methods

On Evaluating ECG Biometric Systems: Session-Dependence and Body Posture

Saeid Wahabi et al.

IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY (2014)

添加到收藏夹

Article Computer Science, Theory & Methods

ECG Biometric Recognition: A Comparative Analysis

Ikenna Odinaka et al.

IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY (2012)

添加到收藏夹

Article Computer Science, Theory & Methods

Electrocardiogram (ECG) Biometric Authentication Using Pulse Active Ratio (PAR)

Sairul I. Safie et al.

IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY (2011)

添加到收藏夹

Article Physics, Fluids & Plasmas

Horizontal visibility graphs: Exact results for random time series

B. Luque et al.

PHYSICAL REVIEW E (2009)

添加到收藏夹

Article Engineering, Electrical & Electronic

ECG analysis: A new approach in human identification

L Biel et al.

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT (2001)

添加到收藏夹

© Peeref 2019-2024. All rights reserved.