Ramesh Nadavati — Projects

SAE Baja Team: University of Michigan; Flint.                                                                                         --2016

Design and Developed the computer controlled systems in the Baja car which is going to participate in multiple competitions in the years 2016-17. Lead a team of 4 people.

Table Functions in Oracle and their performances| Guide: Dr. Mani           -- Winter 2015

Examined the performance of table functions (TF) in oracle. Gave presentation on advantage of pipelined and parallel methods in oracle. I wrote programming code using SQL, MYSQL, and PLSQL to test TF in oracle. Data processing using “pipelined and parallel TF” was faster than data processing with “un pipelined and un parallel TF”, achieved 90% accuracy and faster performance.

Creating connection between Java and Database |Guide: Dr. Mani                -- Winter 2016

I wrote programming code in Java and I have created tables in DBMS. Also, I wrote programming code to set server o/p and to create connection to my database account. I executed the task and successfully achieved as much as 86% of accuracy. The outputs were out in Eclipse software.

Machine learning concepts in recognition of Face and Iris |Research |Guide: Dr. M. Farmer                                                                                                                                                               -- Fall 2015

Worked on machine learning concepts related to Biometric recognition, for this project reviewed and discussed more than 30 articles and understood some important concepts. The final report was submitted, including four supervised Machine Learning algorithms like ‘support vector machine’, ’Fuzzy expert system’, ‘Gaussian mixture model’, ‘Artificial Neural Network’ in biometrics research. Finally examined the dataset and have obtained the accuracy as much as 73%.

Texture Synthesis by Non-Parametric Sampling                                                           --Spring 2015

Modelled texture as a Markov Random Field where the texture synthesis process grows a new image outward from an initial point, one pixel at a mean time. Achieved the performance accuracy of 83%.

Your Face Tells Everything: An Analysis of Human Emotions with internet and without internet                                                                                                                                    --Winter 2016

From this study, I tried to analysis and provide the proof of usage of emoticons according to the age factor. To compute the results, I have collected the data from 63 users around the globe. The final results were intermediate, but 3^rd age group people were largely using emoticons for different things/meanings.