Saturday, June 15, 2013

Implementation of PSO Algorithm in Robot(Lejos Nxt)


Many research in robotics area to find path using different bio-inspired algorithms are conducted recently. Despite many researches are limited to the simulation result. This project tries to verify the robustness of Particle Swarm Optimization (PSO) algorithm in the real-world implementation. PSO optimizes a problem by having a population of candidate solutions, and moving these particles around in the search-space according to simple mathematical formula over the particle's position and velocity. In this project we are implementing PSO algorithm with some modification in robotics. We conducted many experiments with different number of robots and different number of destination too. The result verifies that PSO is technically sound for real-world problems of path finding even in the presence of obstacles.

Friday, May 3, 2013

Line Following Robot with obstacle avoidance (Lejos NXT)


The robot has to traverse an arena to reach a destination area. The destination lies towards the southern region of the arena. There is a path in the arena which leads to the destination. The path is black in colour over a white surface. This path ends in a red coloured region which is the destination. The trajectory of this path is variable (such as straight, zig-zag, circular etc.). There are obstacles of different shapes and sizes along the path. While traversing, the robot has to avoid any collision with those obstacles and keep following the path. If a yellow coloured strip is found on the path by the robot that would mean there is a junction point ahead wherein two or more paths diverge. The robot has to decide which way to go to reach the destination.

Algorithms

We use three different algorithm to implement our program that we are going to discus one by one but here it is the overall algorithm containing all the algorithm in one.

until destination reached

Friday, April 26, 2013

Implementation of C4.5 Algorithm using Hadoop Map Reduce Paradigm


C4.5 is a commonly used in decision tree algorithm in data mining for classification. The existing C4.5 algorithm implementation is running in serial way. We are implementing this algorithm using Hadoop MapReduce framework which can run parallel in multiple system. In this project we are comparing our result with Weka's result where C4.5 is serially implemented with different data source of different size.


Algorithm:

CurrentNode is assumed for splitting.
Map(key, value)
{

Thursday, February 21, 2013

Job openings in Feofus Solutions

Feofus Solutions is looking for Java Developer / Tester for Trivandrum office

Required Position: Java Developer / Tester

Job Description:
· Must be profound in Java, J2EE, spring, Hibernate and VAADIN
· Good to have Liferay, Adobe Flex and Java script experience.
· Candidates with good DB knowledge and Jasper reports will be preferred.
· Must have good communication skills, must be energetic
· Must be Fluent in English Language Writing and Speaking.

Notice period : 20 days or less

Interested candidate can mail their resume to pooja.s@feofus.com