article · International Journal of Communication Systems
Human identification presents an important challenge across security and access control settings. Biometric recognition using physiological signals provides a potential solution. A human identification system based on photoplethysmography (PPG) signals processes data through three stages: acquisition, pre-processing, and feature extraction combined with classification. During pre-processing, one-dimensional signals undergo noise removal, conversion into two-dimensional images, and spectrogram computation. A convolutional neural network containing convolutional and pooling layers extracts features from these visual representations, and a classifier subsequently identifies individuals. When evaluated without noise, the algorithm attains an identification accuracy of 99.5% using spectrogram representations and 89.8% using two-dimensional image representations. Tests involving additive white Gaussian noise and different denoising techniques show that wavelet denoising delivers the strongest performance compared with Savitzky-Golay and Kalman filtering approaches.
Robust personal identification is critical for securing physical facilities and digital systems against unauthorised access. By demonstrating that optical vital sign data can reliably authenticate individuals via deep learning, this research highlights how physiological biosignals could serve as alternatives or supplements to conventional biometrics like fingerprints and iris scans, provided suitable signal denoising methods are used.
The method targets cybersecurity and access control applications, which are relevant to security vendors and digital identity developers. Given that the validation relies on simulation results and synthetic additive white Gaussian noise rather than operational trials, the technology is at an applied and tested research stage, requiring real-world sensor validation and hardware testing before it can reach market viability.
AI-generated from the published abstract. Always read the original work before citing.
Abstract Human identification is considered as a serious challenge for several applications such as cybersecurity and access control. Recently, the trend of human identification has been directed to human biometrics, which can be used to recognize persons based on some physiological or behavioral characteristics that they own, such as fingerprint, iris, and biosignals. There are several types of human biosignals including electroencephalography (EEG), electrocardiography (ECG), and photoplethysmography (PPG) signals. This paper presents a human identification system based on PPG signals. The proposed system consists of three main phases: signal acquisition, signal pre‐processing, and feature extraction/classification. The pre‐processing phase involves denoising of the acquired signal, transformation of the 1D signal sequence into a 2D image, and computation of the spectrogram. Feature extraction is carried out on the images obtained from the pre‐processing phase. Features are extracted from the images based on convolutional neural networks (CNNs). The proposed CNN model consists of a sequence of convolutional (CNV) and pooling layers. Finally, the obtained feature maps are fed to the classifier to discriminate human identities. The proposed identification algorithm is applied on signals with and without an additive white Gaussian noise (AWGN). The simulation results reveal that the proposed algorithm achieves an accuracy of 99.5% with the spectrogram representation and 89.8% with the 2D image representation, in the absence of noise. In addition, the paper gives a discussion of the efficiency of denoising techniques such as wavelet denoising, Savitzky–Golay and Kalman filtering, when involved with the proposed algorithm. The simulation results prove that the wavelet dencoising technique has a best performance among the discussed noise reduction techniques.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1002/dac.4685
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
