|
PCA- Based Feature Extraction and LDA algorithm for Preterm Birth Monitoring
|
|
|
1 *Muhammad Naufal Mansor, 2 Sazali Yaacob, 3 Hariharan Muthusamy, 4 Shafriza Nisha
Basah, 5 Shahrul Hi-fi Syam bin Ahmad Jamil, 6 Mohd Lutfi Mohd Khidir, 7 Muhammad
Nazri Rejab, 8 Ku Mohd Yusri Ku Ibrahim, 9 Addzrull Hi-fi Syam bin Ahmad Jamil, 10
Jamaluddin Ahmad , 11 Ahmad Kadri Junoh
1,2,3,4,11 Intelligent Signal Processing Group (ISP), University Malaysia Perlis, no 70 &71,
Blok B, Jalan Kangar- Alor setar, 02000, Kangar, Perlis, Malaysia., apairia@yahoo.com,
sazali22@yahoo.com, wavelet.hari@gmail.com, shafriza@gmail.com, kadri@unimap.edu.my
5,6,7,8,9 Fakulti Kejuruteraan Elekterik, Politeknik Tuanku Syed Sirajuddin, Km. 25, Lebuhraya
Kuala Perlis Changlun, Ulu Pauh, 02600, Arau, Perlis., syahrull30@yahoo.com,
mdlutfi@gmail.com, nazri_554@yahoo.com, kmyusri82@gmail.com,
azrulhifisyam@yahoo.com
10Pediatric Department, Hospital Tuanku Fauziah, Jalan Kolam,01000, Kangar,
drjamaluddin@pls.moh.gov.my
|
|
|
|
Abstract
.Most pregnancies last around 40 weeks. Babies born between 37 and 42 completed weeks of pregnancy are called full term. Premature birth is a serious health problem. Premature babies are at increased risk for newborn health complications, such as breathing problems, and even death. Most premature babies require care in a newborn intensive care unit (NICU). A preemie usually needs frequent office care – to screen vision or hearing problems and assess baby development – involving multiple medical disciplines which require accurate coordination. Thus, we proposed a monitoring system to classify the behavior of a preemie using intelligent vision system. The focus is on predicting preemie behavior based on preemie motion, face and skin analysis. Our preliminary experimental results show a promising performance of the initial part of the system involving preemie face, skin detection and LDA algorithm.
|
|
|
|
Keywords
:
Preterm Birtt; Image Processing; PCA; LDA
|
|
|
|
URL: http://dx.doi.org/10.7321/jscse.v1.n1.5
|
|
|
|
|