Toward improving person identification using the ElectroCardioGram (ECG) signal based on non-fiducial features

Hamza, Sihem; Ayed, Yassine Ben

doi:10.1007/s11042-022-12244-0

Cited by 3 publications

(2 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Its applications span across numerous fields such as access control, financial authentication, security, forensics, and the public sector. Personal identification utilizing vital signs encompasses methods using ECGs [17][18][19][20][21][22][23][24] and PPG [25]. ECG is a non-invasive method that employs simple skinattached electrodes to measure signals.…”

Section: A Methodologymentioning

confidence: 99%

Enhancing Privacy-Preserving Personal Identification Through Federated Learning With Multimodal Vital Signs Data

Hwang,

Shi,

Lee

2023

IEEE Access

View full text Add to dashboard Cite

Personal identification can be achieved through various multimodal vital sign measurement methodologies in human physiology, such as electrocardiogram (ECG) and radar signals. However, this process inevitably brings privacy protection issues into light during data collection and analysis. Additionally, potential discomfort may be associated with the physical contact during these measurements. To mitigate these issues, our study explores the utilization of federated learning (FL) for privacy protection and non-contact sensors, such as radar, to alleviate contact-related discomfort. Our objective was to establish the viability of privacy-secured personal identification (PI) models that utilize FL. Furthermore, we scrutinized the performance of FL-based PI models that incorporate non-contact radar signals. We compared the performance levels of five conventional machine learning (ML) models with that of five FL-based models by utilizing ECG and radar signals. The experimental outcomes indicated that ECG-based models had superior accuracy overall, with the FL-CNN-BLSTM model yielding an accuracy of 97.3%. Models based on radar signals displayed slightly lower accuracy, with the FL-CNN-BLSTM model delivering an accuracy of 81.9%. These results confirmed the effectiveness of FL-based PI models employing radar signals. Our research therefore augments the evolution of privacy-guarded PI processes utilizing radar signals and FL and lays a robust groundwork for upcoming studies in this field.

show abstract

Section: A Methodologymentioning

confidence: 99%

Enhancing Privacy-Preserving Personal Identification Through Federated Learning With Multimodal Vital Signs Data

Hwang,

Shi,

Lee

2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Therefore, when TNO training samples is large, TNO hidden nodes is also large, and the implementation of the network is very complex, and the network is solved from the HL to the OL. Galerkin method can reduce TNO HL parts to solve this problem [13,14].…”

Section: Radial Basis Function Neural Network (Rbfnn)mentioning

confidence: 99%

Person Recognition Optimization Method Relying on Radial Basis Function Network

2021

View full text Add to dashboard Cite

Artificial NN is an intelligent model for information processing by simulating the organization and mechanism of the nervous system of the brain. Thanks to its strong self-learning ability, artificial NN can liberate people's labor force to a large extent, so it has been widely studied and alied. The theoretical study of artificial NN can effectively explain the alication principle and potential problems of NN, so that it can be effectively improved and developed. Therefore, the main purpose of this paper is to study the optimization method of person recognition (PR) based on RBF network. In this paper, the damping coefficients of RBF networks with uniform center distribution are studied. This stochastic learning method is an important sulement to how to determine the center and limiting factor of the RBF of the NN, and can also improve the training efficiency of the network. The main research results of this paper are developed by analyzing the convergence of stochastic RBFNN and constructing corresponding models and algorithms. Compared with other algorithms, the results show that the ARBFNN algorithm can make the RBFNN obtain a smaller training error, improve the generalization ability of the network, and have the ability to deal with large data sets and fast convergence. Recognition is more convenient and quicker.

show abstract

Dual-feature and multi-scale fusion using U2-net deep learning model for ECG biometric recognition

Huang

Yang

2023

IFS

View full text Add to dashboard Cite

Aiming at the challenges that the traditional photoplethysmography (PPG) biometrics is not robust and precision of recognition, this paper proposes a dual-feature and multi-scale fusion using U2-net deep learning model (DMFUDM). First, to obtain complementary information of different features, we extract the local and global features of one-dimensional multi-resolution local binary patterns (1DMRLBP) and multi-scale differential feature (MSDF). Then, to extract robust discriminant feature information from the 1DMRLBP and MSDF features, a novel two-branch U2-net framework is constructed. In addition, a multi-scale extraction module is designed to capture the transition information. It consists of multiple convolution layers with different receptive fields for capturing multi-scale transition information. At last, a two-level attention module is used to adaptively capture valuable information for ECG biometrics. DMFUDM can obtain the average subject recognition rates of 99.76%, 98.31%, 98.97% and 98.87% on four databases, respectively, and experiment results show that it performs competitively with state-of-the-art methods on all four databases.

show abstract

Toward improving person identification using the ElectroCardioGram (ECG) signal based on non-fiducial features

Cited by 3 publications

References 28 publications

Enhancing Privacy-Preserving Personal Identification Through Federated Learning With Multimodal Vital Signs Data

Enhancing Privacy-Preserving Personal Identification Through Federated Learning With Multimodal Vital Signs Data

Person Recognition Optimization Method Relying on Radial Basis Function Network

Dual-feature and multi-scale fusion using U2-net deep learning model for ECG biometric recognition

Contact Info

Product

Resources

About