Research
My research interests span the areas of machine learning, semantic multimedia, multimodal learning, audio signal processing, and vision-language understanding, along with their applications in health, social systems, and IoT systems.
Early detection of respiratory diseases related to COVID-19 using speech and cough analysis software, with integration into telehealth services. The project focused on machine learning-based audio analysis for health-related applications.
Design and development of a fusion-based framework for surveillance applications in wireless multimedia sensor networks. The project investigated visual and auditory data fusion for energy-efficient object recognition and intelligent sensing.
Semantic content extraction, storage, and querying of visual, audio, and text data in videos. The project combined multimedia content understanding with semantic representation, indexing, object-oriented database modeling, and user-oriented semantic querying.
Extension of a fuzzy object-oriented database model for multimedia applications. The work introduced a multimedia-specific conceptual database model, a fuzzy index structure for efficient access to video objects, and a knowledge-based system with an inference engine and knowledge base.
Ph.D. research on structural and semantic analysis of audio content for content-based querying and browsing. The work focused on representing audio content using MPEG-7-compliant descriptors, constructing similarity matrices, and applying image-processing-based techniques for similarity analysis.
Design and implementation of an MPEG-7-based audio database for structured audio description and retrieval. The work focused on low-level audio feature extraction, MPEG-7 metadata representation, and content-based audio querying.
Industrial project on the development of a real-time digital signal processing, classification, and demodulation system. The implemented algorithms included phase difference tracking between receiver/transmitter sampling clocks and digital clock synchronization on the TMS320C6701 DSP platform.
Supervision
Selected MSc and PhD students supervised or co-supervised.