Cancelable ECG biometric based on combination of deep transfer learning with DNA and amino acid approaches for human authentication

Sakr, Ahmed S.; Pławiak, Paweł; Tadeusiewicz, Ryszard; Hammad, Mohamed

doi:10.1016/j.ins.2021.11.066

Cited by 19 publications

(6 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…VGG-16 is composed of 16 layers, namely 13 convolutional layers and three fully connected (FC) layers. Sakr et al [93] proposed a cancellable ECG method to protect ECG features used for human authentication. The authors first applied image processing techniques to pre-process the input ECG signal, and then used the VGG-16 pre-training model-based deep learning approach as a feature extraction tool to extract informative and powerful ECG features.…”

Section: Convolutional Neural Networkmentioning

confidence: 99%

Feature extraction and learning approaches for cancellable biometrics: A survey

Yang,

Wang,

et al. 2024

CAAI Trans on Intel Tech

View full text Add to dashboard Cite

Biometric recognition is a widely used technology for user authentication. In the application of this technology, biometric security and recognition accuracy are two important issues that should be considered. In terms of biometric security, cancellable biometrics is an effective technique for protecting biometric data. Regarding recognition accuracy, feature representation plays a significant role in the performance and reliability of cancellable biometric systems. How to design good feature representations for cancellable biometrics is a challenging topic that has attracted a great deal of attention from the computer vision community, especially from researchers of cancellable biometrics. Feature extraction and learning in cancellable biometrics is to find suitable feature representations with a view to achieving satisfactory recognition performance, while the privacy of biometric data is protected. This survey informs the progress, trend and challenges of feature extraction and learning for cancellable biometrics, thus shedding light on the latest developments and future research of this area.

show abstract

Section: Convolutional Neural Networkmentioning

confidence: 99%

Feature extraction and learning approaches for cancellable biometrics: A survey

Yang,

Wang,

et al. 2024

CAAI Trans on Intel Tech

View full text Add to dashboard Cite

show abstract

“…Taking the advantage of the ECG-based authentication, we have a proposed ECG-based authentication scheme for 6LoWPAN-based IoT. The paper proposes a biometric template protection technique for human authentication [40]. The author proposed a novel cancelable ECG approach to save the original template using amino acids and DNA.…”

Section: Related Workmentioning

confidence: 99%

ECG-based Machine-to-Machine Authentication for 6LoWPAN-based IoT

Thungon,

Medhi,

Hussain

2023

Preprint

View full text Add to dashboard Cite

In Internet of Things (IoT), millions of devices communicate sensitive information with each other. Ensuring secure data generation and communication between the devices is critical and challenging. Automatic and secure authentication of users to access such critical services is a challenge. In this paper, we propose an ECG-based lightweight biometric-based authentication scheme based on Bio-CNN. The proposed scheme uses CNN architecture with suitable convolutional filters to properly analyze an ECG signal. We implement a hashing concept with the CNN features to make our system more secure. To examine the suitability of the proposed Bio-CNN-based scheme in an IoT device, we have tested all our experiments on a Raspberry Pi. Finally, the experiment results prove that the proposed method outperforms different CNN architectures and various state-of-the-art authentication techniques in terms of accuracy, precision, recall, etc., enhancing the overall performance.

show abstract

“…Thanks to the developments in the field of machine learning, computer aided diagnosis (CAD) systems are widely used in the healthcare field 5,6 . Deep learning, which has become popular in recent years as a sub‐branch of machine learning, is being used effectively in this field 7–9 . Successful solutions have been offered for classification problems using deep models developed by many researchers on medical images 10–15 .…”

Section: Introductionmentioning

confidence: 99%

“…5,6 Deep learning, which has become popular in recent years as a subbranch of machine learning, is being used effectively in this field. [7][8][9] Successful solutions have been offered for classification problems using deep models developed by many researchers on medical images. [10][11][12][13][14][15] Studies on biomedical data not only use images but also text processing which are very popular.…”

Section: Introductionmentioning

confidence: 99%

A hybrid deep neural network‐based automated diagnosis system using x‐ray images and clinical findings

Aydoğan

2023

Int J Imaging Syst Tech

View full text Add to dashboard Cite

Image-based computer-aided diagnosis systems are frequently utilized to detect vital disorders. These systems consist of methods based on machine learning and work on data obtained from imaging technologies such as x-rays, magnetic resonance imaging, and computed tomography. In addition to image data, clinical findings usually consist of text data that have a critical role in diagnosing diseases. In this study, an effective classification approach that can automatically detect diseases using a deep learning algorithm is proposed. A clinically usable deep machine-learning model is presented with an approach based on the hybrid use of image processing and text processing methods.Although image-processing techniques are used frequently in the literature by using images, text processing techniques are not often used in this field. The proposed method was evaluated on a dataset consisting of x-ray images of subjects with and without Covid-19 disease and their clinical notes. When the dataset was classified using image processing and text processing techniques accuracy values were obtained as 90.9% and 92.0% respectively. With the hybrid approach proposed in this study, the classification performance was increased and an accuracy value of 93.5% was obtained.

show abstract

Cancelable ECG biometric based on combination of deep transfer learning with DNA and amino acid approaches for human authentication

Cited by 19 publications

References 38 publications

Feature extraction and learning approaches for cancellable biometrics: A survey

Feature extraction and learning approaches for cancellable biometrics: A survey

ECG-based Machine-to-Machine Authentication for 6LoWPAN-based IoT

A hybrid deep neural network‐based automated diagnosis system using x‐ray images and clinical findings

Contact Info

Product

Resources

About