AI and ML application

Computer Vision focuses on enabling machines to interpret and understand visual information derived from images and video data. Detection and segmentation techniques represent key components of computer vision systems, allowing the identification, localization, and structural analysis of objects within visual scenes. The publications listed in this section reflect my work on designing and applying deep learning-based vision models across various computer vision tasks. These studies emphasize algorithmic development, model optimization, and practical implementation of intelligent visual analysis methods.

GeoAI and Remote Sensing integrate artificial intelligence with geospatial and environmental data, enabling large-scale analysis, modeling, and prediction of complex natural processes. These approaches combine machine learning, deep learning, and geostatistical techniques to interpret satellite observations and spatial measurements. The publications listed in this section reflect my work on AI-driven environmental modeling, risk assessment, and monitoring methodologies. The studies emphasize predictive modeling, spatial analysis, and hybrid AI–geostatistical frameworks for understanding environmental dynamics.

Industrial, Manufacturing, and Engineering AI focuses on the application of artificial intelligence techniques to technical systems, production processes, and engineered environments. These approaches leverage machine learning and deep learning models to support automation, anomaly detection, predictive analysis, and system optimization. The publications listed in this section reflect my work on developing AI-driven solutions for intelligent industrial and engineering systems. The studies emphasize practical implementation, model design, and data-driven analysis within complex technical infrastructures.

Large Language Models (LLMs), Multi-Agent Systems, and Generative AI represent a class of AI technologies focused on reasoning, knowledge representation, autonomous interaction, and content generation. These approaches enable systems capable of language understanding, decision-making, collaborative problem solving, and adaptive behavior. The publications listed in this section reflect my work on LLM-driven simulations, multi-agent architectures, and AI-assisted generative systems. The studies emphasize system design, emergent behavior modeling, and practical integration of generative AI methodologies.

Unmanned Aerial Vehicles (UAVs), robotic systems, and path planning techniques represent an important area of AI research focused on autonomous navigation, perception, and intelligent control. These approaches combine machine learning, computer vision, and optimization algorithms to enable adaptive and data-driven decision-making in dynamic environments. The publications listed in this section reflect my work on UAV control, intelligent navigation strategies, and AI-supported spatial analysis. The studies emphasize system design, algorithmic development, and practical implementation of autonomous and semi-autonomous platforms.

Active Learning is a machine learning paradigm designed to improve model performance while minimizing the need for extensive labeled datasets. These approaches enable models to selectively identify the most informative samples for annotation, thereby optimizing the learning process. The publications listed in this section reflect my work on developing and applying active learning strategies across different machine learning contexts. The studies emphasize algorithmic design, data efficiency, and intelligent sampling techniques for model training and optimization.

Interdisciplinary research area where artificial intelligence methods are applied to biological, chemical, and molecular data analysis. These approaches enable intelligent modeling, pattern recognition, and computational support for complex scientific investigations. The publications listed in this section reflect my work on integrating AI techniques with bioinformatics, molecular modeling, and data-driven scientific analysis. The studies emphasize methodological development, intelligent data interpretation, and AI-assisted research frameworks.

Optical Character Recognition (OCR) focuses on enabling computational systems to automatically detect, interpret, and digitize textual information from images and scanned documents. These technologies combine pattern recognition, computer vision, and machine learning techniques to transform visual text into structured digital data. The publications listed in this section reflect my work on the development and application of OCR methodologies, particularly for Cyrillic script recognition. The studies emphasize algorithmic design, character recognition accuracy, and intelligent text processing approaches.