(For USM Staff/Student Only)

EngLib USM > Ω School of Electrical & Electronic Engineering >

Hybrid heartbeat detection kit as biometrics and heart monitoring (id-care)/Hooi Man Yeap

Hybrid heartbeat detection kit as biometrics and heart monitoring (id-care)_Hooi Man Yeap_E3_2014_NI
Keselamatan berautomatik adalah salah satu tumpuan utama pada zaman moden dengan pengesahan yang selamat boleh dipercayai adalah dalam permintaan yang tinggi. Namum begitu, kaedah pengesahan tradisional seperti kata laluan dan kad pintar sudah ketinggalan zaman kerana ia boleh hilang, dicuri dan dikongsi. Dalam projek ini, sistem biometrik berasaskan isyarat denyutan jantung yang juga dikenali sebagai isyarat elektrokardiografi (ECG) telah dicadangkan. Denyutan jantung dipilih sebagai modaliti kerana isyarat ECG seseorang tidak boleh dipalsukan. Berbanding dengan cap jari, ia boleh tertipu dengan jari palsu, muka boleh diekstrak menggunakan foto pengguna dan suara boleh ditiru dengan mudah. Selain itu, isyarat ECG adalah mencerminkan pergerakan mekanikal jantung dan sistem kardiovaskular. Ciri-ciri ini mengandungi maklumat fisiologi dan patologi. Ciri-ciri ini menjadikan mereka sebagai teknologi pengesahan yang mantap dan juga untuk pengesanan denyutan jantung tidak normal. Berdasarkan kelebihan-kelebihan ini, kami mencadangkan kit pengesanan denyutan jantung hibrid yang boleh berfungsi sebagai sistem pengesahan biometrik dan sistem pemantauan jantung. Dalam projek ini, ubahan wavelet algoritma digunakan sebagai teknik pengekstrakan ciri manakala bagi proses klasifikasi Sokongan Mesin Vektor (SVM) digunakan. Sistem ini telah dilaksanakan di atas papan platform Intel. Produk akhir telah berjaya dibangunkan sebagai gelang dapat dipakai digunakan untuk kawalan akses dan pemantauan jantung. Keputusan ujikaji menunjukkan ketepatan 97.5% telah dicapai, dengan ini menunjukkan bahawa isyarat ECG boleh menjadi em-em yang dipercayai untuk sistem biometrik. ______________________________________________________________________________________ Automated security is one of the major concerns of modern time where secure and reliable authentication is in great demand. However, traditional authentication methods such as password and smart card are now outdated due to they can be lost, stolen and shared. In this project, biometrics system based on heartbeat signals which is also known as electrocardiographic (ECG) signals is proposed. Heartbeat is chosen as modality due to an individual’s ECG signals cannot be faked. Compared to fingerprint, it can be fooled with fake fingers, face can be extracted using user’s photo and voice can be imitated conveniently. Besides, ECG signals are reflection of the mechanical movement of the heart and cardiovascular system. These features contain physiological and pathological information. Unique physiological characteristics and clinical properties make them a promising authentication technology and also as heartbeat abnormality detection. Due to these advantages, we propose a hybrid heartbeat detection kit which can function as biometric authentication system as well as heart monitoring system. In this project, wavelet transform algorithm is used as feature extraction technique while for the classification process Support Vector Machine (SVM) is employed. Consequently, this developed system is then implemented as a prototype on an Intel platform board. The end product has successfully developed as a wearable bracelet of ECG detection kit used for personal system log in or access control and heart monitoring. Experimental results showed that 97.5% accuracy has been achieved, thus this shows that ECG signals can be a promising features for biometric system.
Contributor(s):
Hooi Man Yeap - Author
Primary Item Type:
Final Year Project
Language:
English
Subject Keywords:
hybrid heartbeat ; wearable bracelet ; cardiovascular
First presented to the public:
6/1/2014
Original Publication Date:
1/16/2020
Previously Published By:
Universiti Sains Malaysia
Place Of Publication:
School of Electrical & Electronic Engineering
Citation:
Extents:
Number of Pages - 146
License Grantor / Date Granted:
  / ( View License )
Date Deposited
2020-01-16 16:16:38.919
Submitter:
Nor Hayati Ismail

All Versions

Thumbnail Name Version Created Date
Hybrid heartbeat detection kit as biometrics and heart monitoring (id-care)/Hooi Man Yeap1 2020-01-16 16:16:38.919