Expectation-maximization algorithm

are two modules: feature extraction process and classification. First, the shape features are extracted using techniques like Scale invariant feature transform (SIFT), Harris corner detection and Zernike moments. Second, the supervised learning algorithms like Deep neural network (DNN) and Extreme learning machine (ELM) are used to classify the brain tumor images. Experiments are performed using 1000 brain tumor images. In the performance evaluation, sensitivity, specificity, accuracy, error…

treats the segmentation as a registration process. Some researchers used atlases not only to impose spatial constraint but also provide probabilistic information about the tissue model. They proposed a probabilistic tissue model and used expectation-maximization [23] to segment brain tumor by modifying an atlas with patient specific information about tumor location from different MRI a modalities [24][25]. The advantage is that it has ability to segment an image with no well-defined relation…

Literature Review Ⅰ. HOTSPOT MAPPING Hotspot can be defined as aggregations of raw crime data that identify geographic locations of highest incident concentration (Ratcliffe and McCullagh, 1999; Chainey and Ratcliffe, 2005). Hotspots have been formally recognized in the literature as early as 1751 when Henry Fielding suggested focusing on areas of high crime to deter offenders. A notable example of policing with hotspot is the study by Sherman et al., (1989), which found that over 50.4% of all…