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

Abstract

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.

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

“…In this paper, we evaluate ECG biometrics using pre-configured models of the CNN with various time-frequency representations. The PTB-ECG [39,40] and CU (Chosun University)-ECG [18] databases were used in this study. PTB-ECG is a popular, open access ECG dataset, while CU-ECG was directly constructed for this study.…”

“…The ECG acquisition equipment was developed using Keysight, MSO9104, Atmega8, and non-invasive electrodes for constructing the CU-ECG database. Figure 9 shows the environment for acquiring the CU-ECG signals [18]. developed using Keysight, MSO9104, Atmega8, and non-invasive electrodes for constructing the CU-ECG database.…”

“…developed using Keysight, MSO9104, Atmega8, and non-invasive electrodes for constructing the CU-ECG database. Figure 9 shows the environment for acquiring the CU-ECG signals [18].…”

“…However, a few body states generate noisy biometrics. The geometry of the body temporarily changes when the subject receives an external impact due to movement, which changes the physical forces on the heart to generate a noisy ECG signal [17,18].…”

Intelligent Deep Models Based on Scalograms of Electrocardiogram Signals for Biometrics

“…The characteristics used in biometric study include face [ 7 ], iris [ 8 ], gait [ 9 ], sweat pore [ 10 ], finger-vein [ 11 ], palmprint, palmvein [ 12 ], voice [ 13 ], handwritten signature [ 14 ], and electrocardiogram (ECG) [ 15 ]. The disadvantages of each characteristic include the face having restrictions on glasses, mask, and makeup, and the original face for recognition should be recovered.…”