Cristovão Freitas Iglesias Junior

• Research Associate
• Ph.D. in Computer Science (Machine Learning), University of Ottawa
  
• Member of CARG Health-Devices

Contact

cristovao.casagrande@gmail.com
cfrei096@uottawa.ca

Bio

I am a ML Engineer with a robust background in software engineering. My experience spans across various projects, from molecular dynamics simulations to digital twins development. Currently, I completed a Ph.D. in Computer Science (Machine Learning) at the University of Ottawa. With over 10 years of experience in ML, I bring expertise in deep learning, Bayesian modeling, federated learning, and data fusion for time series analysis, regression, classification, forecasting and clustering tasks. I excel in both independent and collaborative environments, effectively bridging technical and business domains by translating complex technical concepts into actionable insights. My strengths lie in innovative problem-solving, optimizing data pipelines and algorithms with advanced statistical techniques, and maintaining a commitment to continuous learning and staying at the forefront of emerging analytics technologies.

Research Interests

• Data Science & Machine Learning: deep learning, Bayesian modeling, NLP, LLM, data fusion, scientific machine learning, nonlinear Kalman filters, time-series analysis, uncertainty quantification and federated learning
• Programming & Development: Python, SQL (PostgreSQL, MySQL), R, Julia, Ruby on Rails, Docker, AWS Stack, TensorFlow, PyTorch, JAVA, C++.

List of Papers (Google Scholar )

• RITA: Automatic Framework for Designing of Resilient IoT Applications (LAFUSION 2024)
  • Code
  • Skills: Python, LLM, Fine-tuning
• Two Students: Enabling Uncertainty Quantification in Federated Learning Clients (BDU – NeurIPS 2024)
  • Code
  • Skills: Python, Julia, Federated Learning
• Limitations of Joint and Dual Nonlinear Kalman Estimators in Low-Cost Bioprocess Monitoring (LatinX-ICML 2024)
  • Code
  • Skills: Julia, Global Optimization, Nonlinear Kalman Estimators, Bayesian Inference
• Batch Bayesian Auto-Tuning for Nonlinear Kalman Estimators (under review for Nature Scientific Reports 2024)
  • Code
  • Skills: Julia, Global Optimization, Genetic Algorithm, Bayesian Optimization, Bayesian Inference
• Hybrid Nonlinear Kalman Estimators for Low-Cost Bioprocess Monitoring (under review)
  • Code
  • Skills: Julia, Optimization, Bayesian Inference, Filters, Deep Learning
• How Not to Make the Joint Extended Kalman Filter Fail with Unstructured Mechanistic Models (Sensors Journal – 2024)
  • Code
  • Skills: Julia, Optimization, Bayesian Inference
• Automated Extraction of IoT Critical Objects from IoT Storylines, Requirements and User Stories via NLP (SDS – 2023)
  • Code
  • Skills: NLP, Python, TensorFlow, PyTorch, BERT, Transformers, ElMo

• An Architectural Design Decision Model for Resilient IoT Application (arXiv Preprint – 2023)

• DEMDE: Decision Making Design based on Bayesian Network for Personalized Monitoring System (FUSION – 2023)
  • Code
  • Skills: Bayesian Network

• rAAV Manufacturing: The Challenges of Soft Sensing during Upstream Processing (Bioengineering Journal – 2023)

• A Real-Time Respiration Monitoring and Classification System Using a Depth Camera and Radars (Frontiers – 2022)
  • Skills: Python, Classification, Data Fusion
• Monitoring the Recombinant Adeno-Associated Virus Production Using Extended Kalman Filter (Processes Journal – 2022)
  • Code
  • Skills: Julia, Bayesian Inference for Optimization, EKF, NODE
• Handling Massive Proportion of Missing Labels in Multivariate Long-Term Time Series Forecasting (IC-MSQUARE 2021)
  • Code
  • Skills: Python, TensorFlow, LSTM, Deep Learning

• A Domain Model for Personalized Monitoring System Based on Context-Aware Data Fusion (FUSION – 2019)

• Agile Software Development Learning Through Open Hardware Project (WBMA – 2015)

Visit his webpage for a deeper dive or to have a chat!