A novel feature extraction method in ECG biometrics

Hamdi, Takoua; Slimane, Anis Ben; Khalifa, Anouar Ben

doi:10.1109/ipas.2014.7043304

Cited by 16 publications

(6 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Furthermore, mean, standard deviation, range, interquartile range (IQR), percentiles of energy, slope and angles of P-QRS-T waves [13], PR intervals, and R amplitudes are extracted.…”

Section: Feature Engineeringmentioning

confidence: 99%

Detection of Atrial Fibrillation in ECG Hand-held Devices Using a Random Forest Classifier

Zabihi

Rad

Katsaggelos

et al. 2017

Computing in Cardiology Conference (CinC)

115

View full text Add to dashboard Cite

show abstract

“…Furthermore, mean, standard deviation, range, interquartile range (IQR), percentiles of energy, slope and angles of P-QRS-T waves [13], PR intervals, and R amplitudes are extracted.…”

Section: Feature Engineeringmentioning

confidence: 99%

Detection of Atrial Fibrillation in ECG Hand-held Devices Using a Random Forest Classifier

Zabihi

Rad

Katsaggelos

et al. 2017

Computing in Cardiology Conference (CinC)

115

View full text Add to dashboard Cite

show abstract

“…Furthermore, MLP has better generalization ability on noisy data, [14]. Research on ECG Biometric started with the pioneering work of Biel et al [15] who purposed the use of amplitude, distance of waves as features to identify a subject. He also proves that a single channel ECG contains enough discriminant information for recognition.…”

Section: Related Workmentioning

confidence: 99%

Electrocardiogram Identification: Use a Simple Set of Features in QRS Complex to Identify Individuals

TuerxunWaili

Nor

Rahman

et al. 2016

Recent Advances in Information and Communication Technology 2016

View full text Add to dashboard Cite

This paper presents a Multilayer Perception Neural Network developed to identify human subjects using electrocardiogram (ECG) signals. We use the amplitude values of Q, R and S as a features for our experiments. In this study, a total of 87 dataset were collected among 14 subjects from the Physikalisch-Technische Bundesanstalt (PTB) database. Out of the 14 subjects, Q-R-S feature points were taken from different day and time sessions to perform classification with MLP. Out of this data, 66 % is used as training dataset while the remaining 34 % is used for testing. Our method yields 96 % accuracy and demonstrates that the use of three fiducial points is sufficient to identify a subject despite the common practice of taking more feature points.

show abstract

“…MA provided the best result (97.93%). Teodoro et al worked with more users and produced a more acceptable result than the previous works where accuracy even moved up to 100% (PTB) [2] or 96.44% (Private DB) [3] but with less users.…”

Section: Literature Reviewmentioning

confidence: 94%

Runtime Optimization of Identification Event in ECG Based Biometric Authentication

Neehal

Karim

Banik

et al. 2019

2019 International Conference on Electrical, Computer and Communication Engineering (ECCE)

View full text Add to dashboard Cite

Biometric Authentication has become a very popular method for different state-of-the-art security architectures. Albeit the ubiquitous acceptance and constant development in trivial biometric authentication methods such as fingerprint, palm-print, retinal scan etc., the possibility of producing highly competitive performance from somewhat less-popular methods still remains. Electrocardiogram (ECG) based biometric authentication is such a method, which, despite its limited appearance in earlier research works, are currently being observed as equivalently high-performing as other trivial popular methods. In this paper, we have proposed a model to optimize the runtime of identification event in ECG based biometric authentication and we have achieved a maximum of 79.26% time reduction with 100% accuracy.Where w1 = 0.2, w2 = 0.5 and w3 = 0.3 was chosen as optimal weight values via trial and error.

show abstract

A novel feature extraction method in ECG biometrics

Cited by 16 publications

References 12 publications

Detection of Atrial Fibrillation in ECG Hand-held Devices Using a Random Forest Classifier

Detection of Atrial Fibrillation in ECG Hand-held Devices Using a Random Forest Classifier

Electrocardiogram Identification: Use a Simple Set of Features in QRS Complex to Identify Individuals

Runtime Optimization of Identification Event in ECG Based Biometric Authentication

Contact Info

Product

Resources

About