Biometric identification of cardiosynchronous waveforms utilizing person specific continuous and discrete wavelet transform features

Abstract

In this paper we explore how a Radio Frequency Impedance Interrogation (RFII) signal may be used as a biometric feature. This could allow the identification of subjects in operational and potentially hostile environments. Features extracted from the continuous and discrete wavelet decompositions of the signal are investigated for biometric identification. In the former case, the most discriminative features in the wavelet space were extracted using a Fisher ratio metric. Comparisons in the wavelet space were done using the Euclidean distance measure. In the latter case, the signal was decomposed at various levels using different wavelet bases, in order to extract both low frequency and high frequency components. Comparisons at each decomposition level were performed using the same distance measure as before. The data set used consists of four subjects, each with a 15 minute RFII recording. The various data samples for our experiments, corresponding to a single heart beat duration, were extracted from these recordings. We achieve identification rates of up to 99% using the CWT approach and rates of up to 100% using the DWT approach. While the small size of the dataset limits the interpretation of these results, further work with larger datasets is expected to develop better algorithms for subject identification.

A study on pre-filter design for improving accuracy in heart rate estimation from backside using discrete wavelet transform with mm-wave radar

“…Meanwhile, DWT is superior to EMD-based timedomain signal processing in terms of processing time. Therefore, we have been also considering utilizing discrete wavelet transform (DWT) to estimate heart-rate [7,8]. DWT is a signal processing method in the frequency domain.…”

On the Intersection of Signal Processing and Machine Learning: A Use Case-Driven Analysis Approach

“…1) Transformation coefficients as input features: In these approaches, the generated transform energy coefficients, representing signals' energy distribution across timefrequency instants, are used directly as input features for the ML model [198], [199], [211], [216], [219], [220], [231], [240]. Feature selection techniques are commonly used here to select the most distinctive representations, which helps reduce redundancy and relaxes computational requirements for training and inference.…”

“…Common decomposition approaches include wavelet-based decomposition and adaptive mode decomposition (ADM) methods. In wavelet-base decomposition methods [44], [240], [247]- [267], discrete wavelet transform (DWT), stationary wavelet transform (SWT), and wavelet packet transform (WPT) are commonly used to decompose the signal into elementary modes of high and low-frequency components using digital filter banks. The performance of wavelet decomposition is highly dependent on the base wavelet function and the level of decomposition.…”

Hybrid Deep Learning and Discrete Wavelet Transform-Based ECG Biometric Recognition for Arrhythmic Patients and Healthy Controls

“…This approach achieved high accuracies in identifying multiple heartbeats: 98.87% on raw electrocardiogram (ECG) data from ECG-ID (two-recording) [ 4 ], 92.30% on ECG-ID (All-recording) and 96.82% on MIT-BIH-AHA [ 5 ] databases. This study [ 15 ] is based on information extracted from four distinct 15-minute-long RFII recordings, each related to a different subject. The above system achieved recognition rates of up to 99.9% using the CWT approach and rate increases of up to 100% using the DWT approach.…”