I am a PhD researcher and software engineer specializing in machine learning, computer vision, and multimodal data fusion, with a strong focus on human behavior analysis and real-time intelligent systems. My doctoral research centers on the automated processing of structured, visual, and sensory data for the modeling and prediction of human behavior. In particular, my work emphasizes object detection, pose estimation, and aggression prediction through the design and implementation of real-time behavior recognition systems. These systems leverage machine learning and deep learning architectures to analyze human posture, movement, and contextual cues, with applications in sensitive clinical environments such as dementia monitoring and psychiatric care. A key methodological component of my research is multimodal data fusion, integrating visual, audio, and clinical data streams to enhance prediction robustness and behavioral understanding. By combining early- and late-fusion strategies with advanced feature extraction and classification models, my work aims to improve the accuracy, interpretability, and real-world applicability of intelligent behavioral analysis systems, supporting personalized treatment strategies and proactive intervention. In parallel with my academic work, I have extensive industry experience as a full-stack software engineer, contributing to large-scale, data-driven platforms and production-level systems.