Associate Professor Dr Dzati Athiar Ramli
School of Electrical and Electronical Engineering
Universiti Sains Malaysia
Malaysia

 

Dzati Athiar Ramli is currently an Associate Professor at the School of Electrical & Electronic Engineering, Universiti Sains Malaysia (USM) and her current administration post is as a Quality and Commercialization Programme Chairman. She is also a member of Intelligent Biometrics Research Group (IBG), USM. She was previously the visiting lecturer at the Department of Computer Science, University of Surrey, United Kingdom.

She received her Bachelor of Applied Science (Computer Aided Geometrical Design) and Master of Science (Mathematics) from the School of Mathematical Sciences, USM. She then obtained a Ph.D. degree in Electrical, Electronic and Systems Engineering from UKM. Her areas of interest are digital signal processing and artificial intelligence with applications to speech, palmprint and  electrocardiogram (ECG) biometrics and blind source separation (BSS) as well as in healthcare informatics for stroke monitoring and foetal ECG signal separation. She is also the principal investigator of several projects funded by USM and Ministry of Higher Education (MoHE) grants as well as a co-researcher for the ASEAN IVO International Grant and has published her research findings in local and international proceedings and journals.

 

Unlock Your World With Your Heartbeat: Evolution and Recent Trend of Electrocardiogram Biometrics

Biometric recognition provides automated security for identity recognition based on physiological or behavioural characteristics. It becomes one of the hottest topics in technologies nowadays as it offers an essential improvement over usernames and passwords. Emerging innovations to a mobile device, portable, wearable and other innovations are bringing biometrics to mainstream marketplaces. So far, various biometrics have been implemented in a real application for instance; face, speech, iris, signature and fingerprint. However, a security breach is one of the limitations of common biometrics. Recently, electrocardiogram (ECG) signal which is one of the most prominent biomedical signals for heart abnormality detection has been studied for the use of secure identity recognition. ECG has extremely discriminative characteristics in the biometric field and has recently received significant interest as a promising biometric trait. This innovation attracts intention among researchers owing to ECG signal is difficult to counterfeit through latent patterns as it is intrinsically originated from a critical heart activity. ECG signal analysis for biometric recognition can combine several steps, such as pre-processing, feature extraction, feature selection, feature transformation, and classification which is a very challenging task. Moreover, the selected success measures and proper structure of the ECG signal database play significant roles in biometric system analysis, considering that publicly available databases are essential to the research community to evaluate the performance of their proposed algorithms.  To date, ECG technology has emerged as a new viable alternative approach in a biometric scenario. In this talk, we highlight the recent advances in ECG biometric technology, its challenges and feasible future research opportunities.