My research activities follow a progressive trajectory structured into three periods, each corresponding to a key stage of my academic and scientific career. The first period began with my research master's internship carried out at the Laboratory of Electronics, Telecommunications and Applied Computer Science (LETIA) of the University of Abomey-Calavi.
The second period corresponds to the preparation of my PhD, jointly conducted between the Computer Science, Signal and Image Laboratory of the Côte d'Opale (LISIC) and the Laboratory of Research in Computer Science and Applications (LRSIA), and devoted to the detection, tracking and recognition of moving insects using hyperspectral imaging, with applications to pest monitoring.
The third period covers my research as a Temporary Teaching and Research Assistant: first at LISIC (2025-2026), in continuity with my doctoral work and with new work on crop classification under temporal shift from Sentinel-1 and Sentinel-2 imagery; then, since September 2026, at LIUM (Le Mans Université), on human activity recognition from video.
Keywords : Machine learning · Computer networks · Traffic classification · Feature selection
This research work, carried out during my research master's degree, focuses on the design of robust and interpretable Internet traffic classification models capable of handling real-world and partially missing data using machine learning techniques.
Read more : Internet Traffic Classification Using Machine Learning Methods
Keywords : Hyperspectral imaging · Butterfly recognition · Multi-target tracking · Pest insects · Hyperspectral video · Precision agriculture
This research activity corresponds to my PhD work, focusing on the design of a complete pipeline for detecting, tracking and recognizing moving agricultural pests from hyperspectral imagery, with applications to crop monitoring.
Read more : Detection, Tracking and Recognition of Agricultural Pests Using Hyperspectral Imaging
Keywords : Remote sensing · Sentinel-1 / Sentinel-2 · Multimodal fusion · Distribution shift · Convolutional neural networks · Precision agriculture
This work, carried out at LISIC during my ATER position at ULCO, addresses crop classification from multispectral and radar satellite imagery, and the robustness of models when spectral signatures vary from one year to the next.
Read more : Crop Classification under Temporal Shift through Sentinel-1 / Sentinel-2 Fusion