Evolution, Current Challenges, and Future Possibilities in ECG Biometrics

Pinto, João Ribeiro; Cardoso, Jaime S.; Lourenço, André

doi:10.1109/access.2018.2849870

Cited by 139 publications

(86 citation statements)

References 121 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…DNNs use multiple layers to explore more complex nonlinear, patterns and learn meaningful relationships within the data [51], and they learn and construct inherent features from each successive hidden layer of neurons, by minimizing or even removing the need for feature engineering. This last factor resulted in DL often outperforming ML techniques [50], revolutionizing this field with outstanding results and robustness to input noise and variability in diverse tasks [53]. Therefore, some authors point that DL could be seen as a specific case of BD solution, since the implementation of BD techniques, such as the parallelization in GPUs, has made this computationally demanding solution viable.…”

Section: Deep Learning Fundamentals and Elementsmentioning

confidence: 99%

“…Early ANN algorithms tried to model the functionality of a biological brain with a structure that was made of three layers (input, hidden, and output). Each layer consisted of several artificial neurons based on activation functions which linked them to each other and linked to the next layer through weighted connections [53,56]. Thereby, the axon is played by the output, the dendrites are played by the inputs, the nucleus is played by the activation function, and the synapses are played by the weights [50].…”

Section: Deep Learning Fundamentals and Elementsmentioning

confidence: 99%

“…Thereby, the axon is played by the output, the dendrites are played by the inputs, the nucleus is played by the activation function, and the synapses are played by the weights [50]. ANNs are especially useful in nonlinear, classification problems [53]. After the 1960s, research in ANNs slowed down due to the low capability, their shallow structure, and the limited computational capacity of computers [19].…”

Section: Deep Learning Fundamentals and Elementsmentioning

confidence: 99%

“…These signals are an invaluable data source which can be used to disease detection [50]. One of these physiological signals is the ECG, which is generated from the contraction and the recovery of the heart [53], and it is extensively used for diagnosing several heart diseases and conditions, like myocardial infarction, arrhythmias, hypertrophic cardiomyopathy, or dilated cardiomyopathy, among many others [177].…”

Section: Applications In Ecg Processingmentioning

confidence: 99%

“…However, these kinds of solutions are not effective for high-dimensional, more complex, real-world noisy signals, and these systems can suffer from an unreliable accuracy [22]. DL has been suggested to likely achieve a more effective analysis of ECG signals because its proven significant and remarkable improvements in robustness to noise and variability in several pattern recognition applications help real-time classification of very complex signals, though this scenario also raises new challenges, like regarding data availability [53,179]. Apart from health monitoring and medical diagnosis, the use of ECG as a biometric trait for identification or authentication has gained momentum [180].…”

Section: Applications In Ecg Processingmentioning

confidence: 99%

See 4 more Smart Citations

Deep Learning and Big Data in Healthcare: A Double Review for Critical Beginners

et al. 2019

View full text Add to dashboard Cite

In the last few years, there has been a growing expectation created about the analysis of large amounts of data often available in organizations, which has been both scrutinized by the academic world and successfully exploited by industry. Nowadays, two of the most common terms heard in scientific circles are Big Data and Deep Learning. In this double review, we aim to shed some light on the current state of these different, yet somehow related branches of Data Science, in order to understand the current state and future evolution within the healthcare area. We start by giving a simple description of the technical elements of Big Data technologies, as well as an overview of the elements of Deep Learning techniques, according to their usual description in scientific literature. Then, we pay attention to the application fields that can be said to have delivered relevant real-world success stories, with emphasis on examples from large technology companies and financial institutions, among others. The academic effort that has been put into bringing these technologies to the healthcare sector are then summarized and analyzed from a twofold view as follows: first, the landscape of application examples is globally scrutinized according to the varying nature of medical data, including the data forms in electronic health recordings, medical time signals, and medical images; second, a specific application field is given special attention, in particular the electrocardiographic signal analysis, where a number of works have been published in the last two years. A set of toy application examples are provided with the publicly-available MIMIC dataset, aiming to help the beginners start with some principled, basic, and structured material and available code. Critical discussion is provided for current and forthcoming challenges on the use of both sets of techniques in our future healthcare.

show abstract

Section: Deep Learning Fundamentals and Elementsmentioning

confidence: 99%

Section: Deep Learning Fundamentals and Elementsmentioning

confidence: 99%

Section: Deep Learning Fundamentals and Elementsmentioning

confidence: 99%

Section: Applications In Ecg Processingmentioning

confidence: 99%

Section: Applications In Ecg Processingmentioning

confidence: 99%

See 3 more Smart Citations

Deep Learning and Big Data in Healthcare: A Double Review for Critical Beginners

et al. 2019

View full text Add to dashboard Cite

show abstract

A Survey of ECG Classification for Arrhythmia Diagnoses Using SVM

Ayushi

Bhatt

Shah³

2019

Intelligent Communication Technologies and Virtual Mobile Networks

View full text Add to dashboard Cite

Don’t You Forget About Me: A Study on Long-Term Performance in ECG Biometrics

Lopes

Pinto

Cardoso

2019

Pattern Recognition and Image Analysis

Self Cite

View full text Add to dashboard Cite

The performance of biometric systems is known to decay over time, eventually rendering them ineffective. Focused on ECG-based biometrics, this work aimed to study the permanence of these signals for biometric identification in state-of-the-art methods, and measure the effect of template update on their long-term performance. Ensuring realistic testing settings, four literature methods based on autocorrelation, autoencoders, and discrete wavelet and cosine transforms, were evaluated with or without template update, using Holter signals from THEW's E-HOL 24h database. The results reveal ECG signals are unreliable for long-term biometric applications, and template update techniques offer considerable improvements over the state-of-the-art results. Nevertheless, further efforts are required to ensure long-term effectiveness in real applications.

show abstract

Evolution, Current Challenges, and Future Possibilities in ECG Biometrics

Cited by 139 publications

References 121 publications

Deep Learning and Big Data in Healthcare: A Double Review for Critical Beginners

Deep Learning and Big Data in Healthcare: A Double Review for Critical Beginners

A Survey of ECG Classification for Arrhythmia Diagnoses Using SVM

Don’t You Forget About Me: A Study on Long-Term Performance in ECG Biometrics

Contact Info

Product

Resources

About