Data Scientist Machine Learning

MONA JANNESAR

Green Card holder — Data Scientist with Expertise in Complex Systems Analysis

+1-667-***-**** + Cary, NC ï mona-jannesar # ****.********@*****.*** Google Scholar OBJECTIVE

Data scientist with a Ph.D. in Physics and a Master’s in progress in Data Analytics (Georgia Tech), specializing in time-series forecasting, stochastic modeling, and large-scale data systems. Over 10 years of experience solving complex real-world problems through data-driven solutions in academic and applied settings. Passionate about building data products, automation, and scalable modeling tools to drive impact. SKILLS

Statistical Modeling: Forecasting, Stochastic Processes, Markov Models, Langevin Dynamics Machine Learning: Regression, Clustering, Ensemble Models, Deep Learning, Neural Networks Big Data & Cloud: Azure, Docker, AWS, Google Cloud Programming Languages: Python, R, Matlab, C, LaTeX Libraries: Pandas, NumPy, Scikit-learn, SciPy, NetworkX, OpenCV, Seaborn, Matplotlib Technical Skills: SQL, Tableau, GitHub

Frameworks: TensorFlow, PyTorch, Keras

Domain Knowledge: Time Series Forecasting, Statistical Computing, Finance Communication: Effectively communicating findings, writing reports, and presenting results EXPERIENCE

AI Training Specialist (Contractor), Outlier May 2023 – Present

• Project: AI training in mathematics, physics, and scientific domains

• Objective: Created and evaluated complex and domain-specific prompts in mathematics, physics, and science to challenge AI understanding and highlight gaps in the model’s knowledge.

• Achievements:

– Assessed AI-generated responses for accuracy, logical consistency, and relevance, providing detailed feedback for model retraining and improvement.

– Applied expertise in physics and mathematics to design AI training scenarios that involve advanced scientific concepts, making the AI capable of solving domain-specific problems. Visiting Scholar, Laboratory for Computational Sensing and Robotics (LCSR), Johns Hopkins University May 2021 - May 2022

• Project: Needle Shape Sensing by Image Segmentation

• Objective: Engineered an advanced system for detecting needle shapes in stereo images using deep learning techniques for targeted healthcare applications.

• Achievements:

– Spearheaded the development and implementation of 2D U-Net architecture for needle segmentation, achiev- ing significant accuracy improvements.

– Contributed to advancements in healthcare imaging technology, enhancing patient outcomes. Visiting Researcher, Center For Complex Networks & Social Data Science June 2018 - Jan 2020

• Project: Analyzing Information Flow Between Stock Indices

• Objective: Conducted comprehensive analysis of information flow between stock indices over 22 years.

• Achievements:

– Implemented advanced data cleaning techniques and time series analysis.

– Utilized Transfer Entropy to compute Adjacency Matrix, revealing intricate information flow relevant to healthcare analytics. Generated actionable insights for investment strategies and risk management. Doctoral Researcher, Shahid Beheshti University, Department of Physics Sept 2012 - May 2018

• Project: Scaling Analysis and Modeling of Nano-Friction Dynamics

• Objective: Analyzed and modeled stochastic behavior of nano-friction, advancing the understanding of complex systems in healthcare applications.

• Achievements:

– Applied scaling analysis to study the stochastic behavior of nano-friction fluctuations, which has applications in healthcare, particularly in enhancing medical imaging and diagnostic techniques.

– Developed innovative methodologies for extracting governing equations, advancing the understanding of stochastic systems.

• Project: Statistical Modeling of Surface Roughness Effects on Thin Film Electrical Properties

• Objective: Developed innovative methods to estimate thin layer thickness and analyze capacitance variations in thin insulating films, focusing on the influence of surface roughness and coupling on electrical properties.

• Achievements:

– Innovated an inverse approach to estimate thin layer thickness by analyzing the relationship between surface morphology and electrical conductivity. This reliable technique enhances material scientists’ and engineers’ understanding of material properties, enabling more precise manufacturing processes.

– Developed a model to assess how surface roughness affects capacitance. I found that capacitors with coupled rough surfaces showed significant capacitance variations based on the type of coupling. This offers valuable insights for optimizing capacitor design in microelectronics, especially where surface roughness significantly influences electrical properties.

EDUCATION

Master of Science in Data Analytics, Georgia Institute of Technology, Atlanta, USA (Started Jan 2024) Ph.D. in Statistical Physics, Shahid Beheshti University, Tehran, Iran (Sept 2012 - May 2018) PUBLICATIONS

• A Langevin equation that governs the irregular stick-slip nano-scale friction, Scientific Reports, (2019)

• Multiscaling behavior of atomic-scale friction, Phys. Rev. E, (2017)

• Surface coupling effects on the capacitance of thin insulating films, Journal of Applied Physics, (2015)

• Thin film thickness measurement by the conductivity theory in the framework of Born approximation, Thin Solid Films, (2014)

SELECT ONLINE COURSE CERTIFICATES

• Supervised Machine Learning: Regression and Classification

• Python for Data Science and Machine Learning Bootcamp

• The Complete SQL Bootcamp 2020: Go from Zero to Hero

• Python for Computer Vision with OpenCV and Deep Learning PROJECTS

• Advanced Deep Learning Techniques for Healthcare Imaging: Led the implementation of deep learning models for precise medical image segmentation.

• Healthcare Data Analysis Projects: Conducted analysis and visualization of healthcare data to improve patient outcomes and provide actionable insights.

Contact this candidate