Resume
- 1. SUSMIT MOHAN JOSHI E-mail : sj6454@g.rit.edu Mobile : +1-585-309-5571 Objective: 1.To acquire an internship/ Co-op for spring 2016, as a software engineer. 2. Looking for a Full-Time opportunity after May 2016, as a software engineer. ACADEMIC DETAILS: EXAMINATION / DEGREE BOARD / UNIVERSITY YEAR OF PASSING MARKS / GRADE MS in Computer Engineering Rochester Institute of Technology, Rochester, New York, USA May 2016 (Expected) GPA: 3.33/4 Bachelors (Electronics and Telecommunication) University of Mumbai, Mumbai, INDIA 2014 WES GPA: 3.8/4 Undergrad Courses: Digital Signal Processing, Microprocessors and Microcontrollers, Wireless Networks, Image Processing, Mobile Communication Grad Courses: Computer Vision, Machine Learning, Artificial Intelligence Explorations, High Performance Architecture (CUDA C). SKILLS: Languages: C++ (Intermediate), Java (Beginner), Matlab, Embedded C (Beginner), Python, CUDA C Tools: OpenCV, Matlab, Canopy, Visual Studio Embedded Programming Software: Arduino IDE, µvision Keil Software. EXPERIENCE: Experience: Rochester Institute of Technology, Rochester, NY, USA. Designation: Grader (Analytical Topics) ACADEMIC PROJECTS: Facial Expression Recognition using Viola-Jones, PCA and Support Vector Machines (Using Matlab): Used the Cohn -Kanade data set of facial expression for implementation of the model. 6-basic expressions, i.e, Anger, Sad, Disgust, Happy, Fear, Surprise were classified. Histogram of Local Binary Patterns was used as features. PCA was used for dimensionality reduction and Support Vector Machines for classification. Achieved an accuracy > 90% for cross-validation over the data set. Emotion Intensity Recognition using Viola - Jones and Support Vector Machines (Using Matlab) : Used the Cohn-Kanade data set of facial expressions for implementation of the model. Each expression (6 basic expressions) were divided into three levels of intensity, i.e Peak, Mild and Neutral, making it a 13 class problem The emotion intensity of the subject was to be determined (i.e: Peak, Mild and Neutral) Histogram of Local Binary Patterns was used as features. PCA was used for dimensionality reduction and Support Vector Machines for classification. Achieved an average accuracy of 85 % for cross-validation over the data set. Face Recognition using (PCA / Modular PCA) as features and Support Vector Machines for Classification (Using Matlab) Multi-Class Support Vector Machines along with Polylinear Kernel were used for classification. PCA and Modular PCA were used for feature extraction For PCA as feature, an accuracy of 82.5% in case of the ORL database and an accuracy of 88.89% in case of the Yale database of faces was obtained. For MPCA as feature, an accuracy of 84.68 % in case of the ORL database and an accuracy of 93.89 % in case of the Yale database of faces was obtained. 40 Classes were classified in case of ORL dataset while 15 in case of Yale dataset. Object Recognition using Histogram of Oriented Gradients, Principal Component Analysis and Support Vector Machines (Using Matlab) Histogram of Oriented Gradients (HOG) works very well as a feature for object recognition. 5 classes( i.e Cars, Helicopters, Buses, Butterflies, Motorcycles) were used for classification from the Cal-tech 101 dataset Average Cross-Validation Accuracy obtained was 85 % Principal Component Analysis and SVM’s resulted in an accuracy of 90% Motion Controlled Robotic arm: A SCARA type of a robotic arm was built using high torque servo motors. Arduino UNO was used as a processing device and accelerometers were used as motion sensing devices. Got good experience of using an accelerometer and various concepts regarding it. Fundamentals of mechanics were essential to design the Robotic Arm. Received the best project award for this project. PUBLICATIONS: Motion Controlled Robotic Arm: A ‘SCARA’ type of a Robotic arm was implemented and was controlled by using Accelerometers as Motion Sensing devices. Project was published in the International Journal of Electronics and Communication Engineering (IJECE), in 2013. ISSE (Print):2278-9901; ISSN (Online):2278-991X: Vol-2, Issue-5, Nov-2013-Impact Factor (JCC) (2013): 2.5893. TRAINING: Completed Internship/course at Technophilia Systems Private Limited from 29th August, 2013-10th September, 2013. Learnt the concepts of ARM CORTEX-M3 Microcontroller using Embedded C and conducted hands on experiments on interfacing of different peripherals and I/O devices. AWARDS: Best Project award from the Department of Electronics and Telecommunication in the year 2012, for the project Motion Controlled Robotic Arm.