1. GuruMaheswara
Morthala
Machine/Deep Learning Engineer
PROFILE • ABOUT ME
Expertized in working majorly on Model Based Design [MBD] using
MATLAB tools called Simulink, State flow,Embedded Coder for ADAS
features named as SCC,FCA & Failsafe applications.
Good knowledge on Industry modeling guidlines- MAAB, MISRA2012.
Commandable knowledge on Machine & Deep learning concepts.
Strong Technical and communication skills with 4+ years of experience
combined with a dedication to contribute company's growth in turn ensuring
personal growth .
EDUCATION
EEE, Bachelor Of Engineering / Bachelor
Of Technology
RGMCET
JNTU-Anantapur – Marks 7.5 [CGPA]
Nandyal, Andhra Pradesh
Completed
May 2014
MPC, Intermediate
Sri Chaitanya Junior college
Intermediate – Marks 84%
Guntur, Andhra Pradesh
Completed
April 2010
SSC, High School
Subhodaya High School
SSC – Marks 89%
Ongole, Andhra Pradesh
Completed
April 2008
WORK EXPERIENCE
Ford Motor Company
Senior Software Engineer
Chennai, Tamil Nadu
January 2019
- Current
Experience in Functional Saftey Monitor Model design based on
Requirement specifications.
FSM is mainly focus on ISO26262 modeling Guidlines and standards.
Very familiar with MC/DC coverage .
Hyundai Mobis
Research Engineer
Hyderabad, Telangana
January 2016
- December 2018
Experience in ADAS features modeling by using MATLAB &
Simulink ,Validate by MIL, SIL testing approaches . Experience with Static
code Analysis methods- Polyspace
PROJECTS
Project Functional Safety Monitor- Highway Assist
[ADAS]
Period: January 2019 - Current
Company Name: Ford Motor Company
TRAINING & CERTIFICATIONS
Data Science with Python
SIMPLILEARN, 2019
Advanced Machine Learning
SIMPLILEARN, 2019
Deep Learning with Tensor Flow
SIMPLILEARN, completed by 2019
Embedded Systems
Vector India, 2015
AWARDS & HONORS
Engineer of Month:
Recognized by Team head,
contributed towards developing
complex modules of FSM-HA
Innovation:
As I am very new to Machine
learning, I proposed an efficient
solution which ML algorithm will give
more promising results considering
different available classification ML
algorithms.
SKILLS
MBD Tools:
MATLAB
Simulink
State flow
Simulink V&V
Embedded Coder
Simdiff
ODIN
BTC
Hyderabad, Telangana
+91.9573407096
gurumahesh.mgm@g
mail.com
https://www.linkedin.c
om/in/gurumaheswara-
reddy-bb4b70124/
2. Software Used: MATLAB, BTC Tool for Test case
implementation
Role: Senior Software Engineer
Technologies: ADAS- Advanced Driving Assistance Systems
Team Size: 1
Model Design based on Requirement Specifications.
FSM focuses on ISO26262 modeling Guidelines.
Experience on MC/DC coverage.
Experience on HPC for large data validations on Models.
Project SCC [Smart Cruise Control] & FCA [Forward
Collision Avoidance]- [ADAS]
Period: January 2016 - January 2018
Role: Research Engineer
Technologies: ADAS- Advanced driver Assistance Systems
Company Name: Hyundai Mobis
Team Size: 3
Software Used: MATLAB,Simulink,Visual Studio,ODIN
Experience in Model Based Development from Requirement Specifications.
Experience in Failsafe Algorithm implementations from Requirement
Specifications.
Creating ARXML interfaces from Requirement Specifications.
Fixed-Point Scaling.
Manual and Automatic test case generation in Simulink.
Auto-Code generation -Embedded Coder.
Debugging the MATLAB functions & S-functions using visual studio.
Static Code Analysis - Polyspace 2015b,2017b.
Experience in Managing Configurations on Project-Level.
Experience in Project-Management tools (SVN-Tortoise, Git-hub, JIRA).
Project Time Optimization: Mercedes-Benz Spends
On The Test Bench
Period: August 2019 - November 2019
Technologies: Machine Learning
Skils And Tools: Python,Numpy,Pandas,Sklearn,matplotlib,graph
viz
Software Used: Anaconda
EDA - Useful in early stage. Used Scatter plots to find relation of
features on Target (Test-Time)
Dimensionality Reduction: Feature Engineering is useful in finding
relative features towards sophisticated model design. used PCA, LDA
Cross validation methods are used to validate model performances
(cv=5,5-folds).
considered Mean Square Error (MAE) as performance evaluation
metrics over RMSE (observed very sensitive to outliers in data)
Linear Regression (Taring: 0.72, Testing: 0.58) - evident to overfitting
Regularization: Ridge (Training: 0.73, Testing: 0.60) -Still some
overfitting
Lasso (Taring: 0.78, Testing: 0.75) - Bias and variance trade-off
Decision Trees (Taring: 0.79, Testing: 0.76) - Used Grid search for
optimal hyper parameter tuning.
Ensemble Methods: Random Forest (Training:0.85, testing: 0.82)
DESCRIPTION
Reduce the time a Mercedes-Benz spends on the test bench.
Problem Statement Scenario:
Optimizing the speed of Benz testing system for many possible feature
combinations is complex and time-consuming without a powerful algorithmic
approach.
Concepts:
MBD
Software V cycle
Testing Concepts:
MIL, SIL
Configuration Tools:
SVN Tortoise
Git-hub, JIRA
Machine Learning Tools:
PYTHON
Jupiter Note book
Machine Learning Packages:
Sklearn
NumPy
Pandas
Matplotlib
seaborn
Concepts:
Supervised, Unsupervised Learning
Regression & Classification
Ensemble Learning, Boosting
Methods
Clustering Methods
Time series concepts
Recommended systems
COMPUTER PROFICIENCY
MS-Windows
MATLAB
Visual Studio
Python- Anaconda
BTC
ODIN
LANGUAGES
English
Hindi
Telugu
German
PERSONAL INTERESTS
Automotive Follower
Good Learner
Good Cooking
Travel new places
Cricket, Dance
PERSONAL INFORMATION
Birthday
June 30, 1993
Gender
Male
Marital Status
Single
Father’s Name
Mr. NARAYANA REDDY
3. Boosting methods: Ada-boost (Training: 0.86, Testing: 0.84)
Gradient boost (Training: 0.86, Testing: 0.83)
XG-boost (Training: 0.88, Testing: 0.86)
DECLARATION
GuruMaheswara Morthala Chennai, Tamil Nadu
November 11, 2019
I, GuruMaheswara Morthala, hereby declare that the information contained
herein is true and correct to the best of my knowledge and belief.
Nationality
India