Mr. Carlos Rodrigo Paredes Ocranza | Affective Computing | Machine Learning Research Award

Zhejiang University of Science and Technology | China

Mr. Carlos Rodrigo Paredes Ocaranza is an emerging researcher in artificial intelligence with a strong focus on EEG-based emotion recognition, affective computing, and brain–computer interface (BCI) analytics. His work challenges conventional assumptions in neurotechnology by demonstrating that traditional machine learning pipelines, when paired with domain-specific feature engineering, outperform state-of-the-art deep learning models such as EEGNet for consumer-grade EEG devices. His research introduces advanced domain adaptation methods—such as anatomical channel mapping, CORAL, and TCA—that collectively achieve remarkable gains in cross-dataset generalization, including a reported 69-fold improvement in robustness. He has conducted large-scale validation experiments across hundreds of independent evaluations to ensure statistical reliability and real-world applicability. His contributions highlight significant computational advantages, including faster model training, reduced inference time, and lower memory requirements, advancing the feasibility of accessible BCI systems for mental-health monitoring and multimodal emotion-decoding research. His citation profile is currently emerging, with one indexed publication in Scopus and expanding coverage as new profiles on Google Scholar and ORCID are being established. His scholarly documents, publication records, and citation metrics continue to grow as his research outputs undergo indexing in major academic databases. His work reflects a dedication to developing practical, interpretable, and resource-efficient neuro-AI systems that can be deployed beyond laboratory environments, strengthening the intersection between cognitive science, statistical learning, and computational affective modeling.

Publication Profile

ORCID

Featured Publication

Paredes Ocaranza, C. R., Paredes Ocaranza, E. D., & Yun, B. (2025). Traditional machine learning outperforms EEGNet for consumer-grade EEG emotion recognition: A comprehensive evaluation with cross-dataset validation. Sensors, 25(23), 7262.