Machine learning engineer

Himani Bedekar

361-***-**** ***.*******@*****.*** https://www.linkedin.com/in/himani-bedekar/ Des Moines, IA

SUMMARY

A passionate thesis (Machine Learning) electrical engineer with experience in research, development, execution, validation of test plans and projects using wide areas of Artificial Intelligence, Machine Learning and Deep Learning including various Internet of Things(IoT).

EDUCATION

Master of Science – Electrical Engineering. Texas A&M University-Kingsville, TX May 2018 (GPA: 3.7/4)

Bachelor of Science – Electronics and Communication Engineering. Gujarat Technological University- Gujarat, India June 2016 (CGPA: 8.68/10)

TECHNICAL SKILLS & TRAINING

Programming Languages: Modern C++, Python 3, HTML, R, SQL, Scala, Scalding, Spark, Hadoop

Software/Tools: MATLAB & Simulink, Caffe, GitHub, TensorFlow, Theano, Torch, Tableau, Visual Studio, Office 365

Hardware/Lab Equipment: ARM Cortex development board, Oscilloscope, Logic Analyzer, I2C, Surface Mount Components, Emulation

Operating Systems: Windows XP / Vista / 7 / 8 / 10, Mac OS, Linux, UNIX, Solaris, Android, VxWorks

Networking: TCP/IP, FTP, CAN, Bluetooth, WI-FI, 4G LTE, WLAN, V2X, 3GPP, CDMA, OFDM, 802.11n, 802.11a

WORK EXPERIENCE (More Details: https://www.linkedin.com/in/himani-bedekar/)

Graduate Teaching Assistant, Texas A&M University-Kingsville, TX (EE/CS) 01/2018-04/2018

Guided and tutored students on implementation of various machine learning algorithms using python libraries like Scikit-learn, NumPy, SciPy, pandas and matplotlib in their course work and practical tests

Graded both graduate and undergraduate student assignments in Neural Networks and Data science

Graduate Research Assistant, Texas A&M University-Kingsville, TX (EE/CS) 01/2017-11/2017

Actively involved in research related to various types of Distributed Neural Networks (CNN, RNN, LSTM) and summarized relevant IEEE articles, journals and conference papers

Experienced with multi-threaded design and parallel/distributed computing.

Project Trainee, NCVT, Gujarat, India 06/2015-05/2016

Experienced with implementing numerical methods and data visualization.

Experienced with relevant SaaS providers (Watson, AWS, keras, etc.)

Worked for various projects related to machine learning, Deep learning and NN toolbox using MATLAB. Worked on analysis of GPU development and programming with optimized neural network based model

COURSEWORK

Neural Network, Deep Learning, Advanced Computer Architecture, Digital Communication, Machine Learning with C++, TensorFlow for Machine Learning, Digital Signal Processing, Image Processing, Machine Learning-Hands on with python & R in Data Science, Deep Learning: Artificial Neural Network, Object-Oriented Concepts and Programming, Simulation and Design Tools, Digital Logic Design, Circuits and Networks, Wireless Communication, Computer Communication Network, Broadband Network, RF communication, Satellite Communication, Embedded Systems

VOLUNTEER EXPERIENCE

Team Member, AI Group, Texas A&M University-Kingsville, TX- Worked in a small group to perform validation of custom machine learning applications. Also developed and executed test plans for complex machine learning algorithms

ACADEMIC RESEARCH PROJECTS (More Details: https://www.linkedin.com/in/himani-bedekar/)

Cognitive IoT for Medical Analysis- Thesis based on Machine Learning

Developed the Disease prediction system with the help of machine learning algorithms such as Support vector machine(SVM) and feedforward backpropagation multilayer neural network(NN) gaining high accuracy with very less mean square error(MSE) performed on two medical datasets. Obtained the results in python and R programming.

Project Duration Prediction( Software Project Management)– Model building in Matlab

Compared Linear Regression(LR) and Gaussian Process(GP) machine learning algorithms in terms of correlation coefficients for the successful software project predictions from the data. Gaussian process proved to be a good fit for the performance of the designed model.

Blind Image Blur Estimation- Via Deep Learning

Implemented a learning-based method using a pre-trained deep neural network(DNN) and a general regression neural network(GRNN) on a number of real images. First successfully classified the blur type and then estimated its category taking advantages of both classification and regression.

Network Routing- With Artificial Neural Network in TensorFlow

Proposed the design of the artificial neural network for the routing in the sensor network using TensorFlow.

Realized the more faster operation by replacing the routing table with trained ANN.

Image Segmentation and Preprocessing- Unsupervised Machine Learning Approach

Followed the preprocessing on images and analyzed K-means clustering ML algorithm for segmentation of those images. Also Performed the Brain tumor Segmentation using k-means clustering in MATLAB.

ACCOMPLISHMENTS

10th Annual Javelina Research Symposium-Research work presentation, Texas A&M University-Kingsville

14th Annual Tamus Pathways Research Symposium-2nd Place Award Winner (Among Master’s EE/CS Projects)

Contact this candidate