Biometric Authentication Using Noisy Electrocardiograms Acquired by Mobile Sensors

Choi, Hyun-Soo; Lee, Byunghan; Yoon, Sungroh

doi:10.1109/access.2016.2548519

Cited by 93 publications

(48 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The evaluation of individual identification is based on the notion of the numbers of correct classification (CC) and wrong classification (WC). Based on the individual identification results, the accuracy has been defined as follows [46,47]:…”

Section: Discussionmentioning

confidence: 99%

Multilinear EigenECGs and FisherECGs for Individual Identification from Information Obtained by an Electrocardiogram Sensor

et al. 2018

View full text Add to dashboard Cite

In this study, we present a third-order tensor-based multilinear eigenECG (MEECG) and multilinear Fisher ECG (MFECG) for individual identification based on the information obtained by an electrocardiogram (ECG) sensor. MEECG and MFECG are based on multilinear principal component analysis (MPCA) and multilinear linear discriminant analysis (MLDA) in the field of multilinear subspace learning (MSL), respectively. MSL directly extracts features without the vectorization of input data, while MSL extracts features without vectorizing the input data while maintaining most of the correlations shown in the original structure. In contrast with unsupervised linear subspace learning (LSL) techniques such as PCA (Principal Component Analysis) and LDA (Linear Discriminant Analysis), it is less susceptible to small-data problems because it learns more compact and potentially useful representations, and it can efficiently handle large tensors. Here, the third-order tensor is formed by reordering the one-dimensional ECG signal into a two-dimensional matrix, considering the time frame. The MSL consists of four steps. The first step is preprocessing, in which input samples are centered. The second step is initialization, in which eigen decomposition is performed and the most significant eigenvectors are selected. The third step is local optimization, in which input data is applied by eigenvectors from the second step, and new eigenvectors are calculated using the applied input data. The final step is projection, in which the resultant feature tensors after projection are obtained. The experiments are performed on two databases for performance evaluation. The Physikalisch-Technische Bundesanstalt (PTB)-ECG is a well-known database, and Chosun University (CU)-ECG is directly built for this study using the developed ECG sensor. The experimental results revealed that the tensor-based MEECG and MFECG showed good identification performance in comparison to PCA and LDA of LSL.

show abstract

Section: Discussionmentioning

confidence: 99%

Multilinear EigenECGs and FisherECGs for Individual Identification from Information Obtained by an Electrocardiogram Sensor

et al. 2018

View full text Add to dashboard Cite

show abstract

“…We used the accuracy as a performance measure of the ECG biometrics. The correct classification (CC) was divided by the total classification, i.e., the sum of the CC and WC (wrong classification) to obtain the accuracy [41] as shown in Equation (7).…”

Section: Databasementioning

confidence: 99%

Pre-Configured Deep Convolutional Neural Networks with Various Time-Frequency Representations for Biometrics from ECG Signals

Byeon

Kwak

2019

Applied Sciences

View full text Add to dashboard Cite

We evaluated electrocardiogram (ECG) biometrics using pre-configured models of convolutional neural networks (CNNs) with various time-frequency representations. Biometrics technology records a person’s physical or behavioral characteristics in a digital signal via a sensor and analyzes it to identify the person. An ECG signal is obtained by detecting and amplifying a minute electrical signal flowing on the skin using a noninvasive electrode when the heart muscle depolarizes at each heartbeat. In biometrics, the ECG is especially advantageous in security applications because the heart is located within the body and moves while the subject is alive. However, a few body states generate noisy biometrics. The analysis of signals in the frequency domain has a robust effect on the noise. As the ECG is noise-sensitive, various studies have applied time-frequency transformations that are robust to noise, with CNNs achieving a good performance in image classification. Studies have applied time-frequency representations of the 1D ECG signals to 2D CNNs using transforms like MFCC (mel frequency cepstrum coefficient), spectrogram, log spectrogram, mel spectrogram, and scalogram. CNNs have various pre-configured models such as VGGNet, GoogLeNet, ResNet, and DenseNet. Combinations of the time-frequency representations and pre-configured CNN models have not been investigated. In this study, we employed the PTB (Physikalisch-Technische Bundesanstalt)-ECG and CU (Chosun University)-ECG databases. The MFCC accuracies were 0.45%, 2.60%, 3.90%, and 0.25% higher than the spectrogram, log spectrogram, mel spectrogram, and scalogram accuracies, respectively. The Xception accuracies were 3.91%, 0.84%, and 1.14% higher than the VGGNet-19, ResNet-101, and DenseNet-201 accuracies, respectively.

show abstract

“…Lastly, let us highlight that wearable sensors capturing physiological data are used for applications beyond healthcare as such. For example, a biometric authentication system using electrocardiograms provided by a single mobile chip has been proposed [43]. The authentication follows the next scheme: (1) get the electrocardiograms from the mobile sensor, (2) apply a canceling noise filter to the data, (3) extract the features of the heartbeats, and (4) authenticate the user.…”

Section: Wearable Sensors In Healthcarementioning

confidence: 99%

Body Area Networks in Healthcare: A Brief State of the Art

et al. 2019

View full text Add to dashboard Cite

A body area network (BAN) comprises a set of devices that sense their surroundings, activate and communicate with each other when an event is detected in its environment. Although BAN technology was developed more than 20 years ago, in recent years, its popularity has greatly increased. The reason is the availability of smaller and more powerful devices, more efficient communication protocols and improved duration of portable batteries. BANs are applied in many fields, healthcare being one of the most important through gathering information about patients and their surroundings. A continuous stream of information may help physicians with making well-informed decisions about a patient's treatment. Based on recent literature, the authors review BAN architectures, network topologies, energy sources, sensor types, applications, as well as their main challenges. In addition, the paper focuses on the principal requirements of safety, security, and sustainability. In addition, future research and improvements are discussed.

show abstract

Biometric Authentication Using Noisy Electrocardiograms Acquired by Mobile Sensors

Cited by 93 publications

References 37 publications

Multilinear EigenECGs and FisherECGs for Individual Identification from Information Obtained by an Electrocardiogram Sensor

Multilinear EigenECGs and FisherECGs for Individual Identification from Information Obtained by an Electrocardiogram Sensor

Pre-Configured Deep Convolutional Neural Networks with Various Time-Frequency Representations for Biometrics from ECG Signals

Body Area Networks in Healthcare: A Brief State of the Art

Contact Info

Product

Resources

About