Recent works
A small Android App to help a client organize multiple tasks, based on time and location. Assuming that there are multiple dedicated workers to perform the tasks defined by the clients, the workers are assigned the defined tasks based on their distance from the task location, the estimated time for the worker to get to that location, task duration and desired task finishing time. Thus the clients get a possible schedule of their tasks along with the workers assigned to do it. For the initial version, a naive scheduling algorithm based on distance and time duration is implemented and Google Map API is used.
In this work, the effectiveness of supervised machine learning methods to classify species with DNA Barcode is presented. The analysis of results on considered datasets shows that the classification performances of the selected methods (e.g., Simple Logistic Function, Random Forest, PART, Instance based k-Nearest Neighbor, Attribute based Classifier and Bagging) are at a comparable level, and even superior in some cases, to the well-established DNA Barcode classification methods - BLAST, BLOG, DNA-BAR, PAR, Nj and NN.
Undergraduate works
Machine Learning
Pattern Recognition
Artificial Intelligence
Others