The study aims to create an application using openCV that can identify and calculate the vegetation part of a satellite image. The study utilized the two out of seven Landsat-8 band images over a part of Metro Manila in Philippines acquired on Feb. 13, 2016. These band images are Bands 4 and 5 which are normally used to compute the vegetation index of a satellite image. The algorithm calculates the relative area of the vegetation using Normalized Difference Vegetation Index or NDVI formula. The output of the NDVI creates a single-band dataset that only shows greenery. Values close to zero represent rock and bare soil and negative values represent water, snow and clouds. Taking ratio or difference of two bands makes the vegetation growth signal differentiated from the background signal. Water has an NDVI value less than 0, bare soils between 0 and 0.1, and vegetation over 0.1. Increase in the positive NDVI value means greener the vegetation. The sample satellite image is Manila with Landsat-8 operational land imager (OLI) images. The study aims to test the NDVI formula in extracting vegetation index of Manila region which can be used to monitor the urban and classification of a certain region.

Academic Analytics is extracting hidden patterns from educational databases. The main goal of this area is to extract hidden patterns from student academic performances and behaviors. One of the main topics in academic analytics is to study the academic performance of freshman students. Students enrolled in first year are the most vulnerable to low student retention in higher education institution. Research studies from different Higher Educational Institutions already indicated that early identification of students with academic difficulty is very crucial in the development of intervention programs. As such, early identification of potential leavers and successful intervention program(s) are the keys for improving student retention. The study will utilize the available enrollment and admission data. Feature selection technique will be used to determine significant attributes. The study aims to produce predictive and cluster model in which can early identify students who are in need of academic help and program interventions. The extracted predictive and cluster models will be evaluated using confusion matrix and be integrated in the decision support application.

Analyzing cardiovascular activity of patients using ECG clinical paper printouts requires prior knowledge and practice. This research used spatial-oriented image processing methods for analyzing ECG readings by retrieving only the essential features, and not all ECG data, to assist physicians in diagnosis. Different values such as Atrial (rate/min) and Ventricular (rate/min), QRS interval (sec), QT interval (sec), QTc (sec), and PR interval (sec) were successfully extracted with indication as to whether the values are within the accepted normal values, given the patient’s gender and age. Performance of the system was tested based on accuracy, RMSE and normalized RMSE. The methodology achieved average accuracy as high as 95.424 % while the PR interval feature extraction achieved a relatively low average accuracy of 87.196%.