Mr. Carlos Rodrigo Paredes Ocranza | Affective Computing | Artificial Intelligence Research Awards 

Mr. Carlos Rodrigo Paredes Ocranza | Affective Computing | Zhejiang University of science and Technology | China

Mr. Carlos Rodrigo Paredes Ocranza is a researcher and practitioner whose background spans applied statistics, machine learning, affective computing, and interdisciplinary creative arts. He holds a Master’s in Applied Statistics specialized in Artificial Intelligence from Zhejiang University of Science and Technology, Hangzhou, China, and has also studied at Universidad Autónoma Metropolitana, Mexico City. His academic training includes advanced courses and professional training in stochastic processes, multivariate statistical analysis, big data, graph theory, machine learning, as well as applied mathematics, statistical theory, and academic research essay writing. Over time, Carlos has acquired a diverse skill set: in programming (Python, SPSS Studio, GitHub, Visual Studio, HTML, JSON), in ML frameworks such as TensorFlow, Keras, and Scikit-learn, as well as in digital creation skills including drawing, painting, photo editing, digital illustration, and audio/music production (guitar, bass, drums, composition, singing, recording). He is also adept at using social-media suites, word processors, and comfortable with on-camera presence and communication, reflecting “excellent verbal and written communication skills.” On the professional side, Carlos has experience managing projects from inception to completion, demonstrating strong analytical and problem-solving abilities, adaptability to new situations, and solid teamwork skills. His research interests lie in affective computing and brain-computer interface (BCI) applications especially using consumer-grade EEG (or fNIRS) biosignal data for emotion recognition and other real-world problems. This interdisciplinary approach aims to optimize and adapt BCI technologies for practical use outside lab settings. His recent publication in shows that traditional machine-learning methods can outperform a standard deep-learning architecture (EEGNet) for emotion recognition using consumer-grade EEG sensors, arguing for feature engineering and domain-specific adaptations when working with noisy, low-cost EEG data.

Selected Publications

Paredes Ocaranza, C. R., Yun, B., & Paredes Ocaranza, E. D. (2025). Traditional Machine Learning Outperforms EEGNet for Consumer-Grade EEG Emotion Recognition: A Comprehensive Evaluation with Cross-Dataset Validation