Mohammad Javadi

Publications

2 A Serial Hierarchical Support Vector Machine and 2D Feature Sets Act for Brain DTI Segmentation

Authors: Mohammad Javadi

Abstract:

Serial hierarchical support vector machine (SHSVM) is proposed to discriminate three brain tissues which are white matter (WM), gray matter (GM), and cerebrospinal fluid (CSF). SHSVM has novel classification approach by repeating the hierarchical classification on data set iteratively. It used Radial Basis Function (rbf) Kernel with different tuning to obtain accurate results. Also as the second approach, segmentation performed with DAGSVM method. In this article eight univariate features from the raw DTI data are extracted and all the possible 2D feature sets are examined within the segmentation process. SHSVM succeed to obtain DSI values higher than 0.95 accuracy for all the three tissues, which are higher than DAGSVM results.

Keywords: SVM, hierarchical, DTI, Brain segmentation

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1517
1 Improving Power Plant Efficiency using Water Droplet Injection in Air Condensers

Authors: M. Moghiman, Mohammad Javadi, A. Golshani, Amir Mahdi Ghasemi, Morteza Anbarsooz

Abstract:

Observations show that power plant efficiency decreases in hot summer days. Water droplet injection in air condensers is suggested in order to decrease the inlet air temperature. Nozzle arrangement, injected water flow rate and droplets diameter effects on evaporation rate and the resulting air temperature are investigated using numerical simulation. Decreasing the diameter of injected droplets and increasing the number of injecting nozzles, decreases the outlet air temperature. Also a more uniform air temperature can be obtained using more injecting nozzles. Numerical results are in good agreement with analytical results.

Keywords: Power, evaporation, air condenser, droplet injection

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1307