Scholars@Duke
Javier Pastorino

Javier Pastorino

Assistant Professor of the Practice in the Department of Electrical and Computer Engineering
Electrical and Computer Engineering
javier.pastorino@duke.edu
Hudson Hall 211, 100 Science D, Durham, NC 27708

Selected Publications

Data adequacy bias impact in a data-blinded semi-supervised GAN for privacy-Aware COVID-19 chest X-ray classification

Conference Proceedings of the 13th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics, BCB 2022 · August 7, 2022 Supervised machine learning models are, by definition, data-sighted, requiring to view all or most parts of the training dataset which are labeled. This paradigm presents two bottlenecks which are intertwined: risk of exposing sensitive data samples to the ... Full text Cite

Determination of optimal set of spatio-Temporal features for predicting burn probability in the state of California, USA

Conference Proceedings of the 2022 ACMSE Conference - ACMSE 2022: The Annual ACM Southeast Conference · April 18, 2022 Wildfires play a critical role in determining ecosystem structure and function and pose serious risks to human life, property and ecosystem services. Burn probability (BP) models the likelihood that a location could burn. Simulation models are typically us ... Full text Cite

Data-Blind ML: Building privacy-aware machine learning models without direct data access

Conference Proceedings - 2021 IEEE 4th International Conference on Artificial Intelligence and Knowledge Engineering, AIKE 2021 · January 1, 2021 Traditional Machine Learning (ML) pipeline development requires the ML practitioner to directly access the data to analyze, clean and preprocess it, in order to develop an ML model, train it and evaluate its performance. When the data owner has no infrastr ... Full text Cite

Hey ML, what can you do for me?

Conference Proceedings - 2020 IEEE 3rd International Conference on Artificial Intelligence and Knowledge Engineering, AIKE 2020 · December 1, 2020 Machine learning (ML) algorithms are data-driven and given a goal task and a prior experience dataset relevant to the task, one can attempt to solve the task using ML seeking to achieve high accuracy. There is usually a big gap in the understanding between ... Full text Cite

TexAnASD: Text Analytics for ASD Risk Gene Predictions

Conference Proceedings - 2019 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2019 · November 1, 2019 Autism Spectrum Disorder (ASD) is an extreme neurodevelopmental disease affecting 1 in every 59 children in the United States, and approximately 1% of US population. The clinical traits of the disorder include noticeable deficits in social interactions, la ... Full text Cite