Somsri Daochai

White Blood Cell Classification based on the Combination of Eigen Cell and Parametric Feature Detection

Numbers of white blood cells in different classes help doctors to diagnose patients. A technique for automating the differential count of white blood cell is presented. The proposed system takes an input, color image of stained peripheral blood smears. The process in general involves segmentation, feature extraction and classification. In this paper, features extracted from the segmented cell are motivated by the concept of the well-known eigen face which is performed on the pre-classified which blood cell based on parametric feature detection. The derived eigen value and eigen vector contributes to the important feature in the classification process. The results presented here are based on trials conducted with normal cells. For training the classifiers, a library set of 50 patterns is used. The tested data consists of 50 samples and produced correct classification rate close to 92 %

Analysis and Compiarison of a customi ze Infant Incubator Cambier Sap Using Fnite Eemient Method

The infant incubator is an essential medical device for a new born whose weight is lower than a standard level or early birth. In general, many parameters such as air temperature, air circulation, humidity, oxygenation, noise level and sterilization must be controlled strictly all over an operation range. In this paper, we presented an analysis of heat transfer and air flow circulation in chamber hood by comparing between 2 different design chambers as a semi-hexagonal hood and a dome hood. COMSOL Multiphysic3.3, a three dimensional simulation program was used in our experiment which basing on fluid dynamics and convective heat transfer equation. The simulation was performed under normal room circumstance at 25. The results show that a thermal distribution and air circulation of dome hood are quite better than semi-hexagonal hood noticeably.