Prof. Agnieszka Wosiak
Lodz University of Technology
Poland
agnieszka.wosiak@p.lodz.pl

Prof. Małgorzata Przybyła-Kasperek
University of Silesia in Katowice
Poland
malgorzata.przybyla-kasperek@us.edu.pl

Prof. Wiesław Paja
University of Rzeszów
Poland
wpaja@ur.edu.pl

Data Science, with its core components of machine learning, outlier detection, and distributed computing techniques, is at the forefront of scientific advancements, playing a transformative role in sectors such as medicine, healthcare, economics, and industry. These applications yield substantial benefits and drive significant technological advancements. This session explores the frontiers of data science and its transformative power across diverse domains, with a primary focus on healthcare, economy and industry. Enhanced disease diagnosis and prognosis, personalized treatment strategies, health monitoring through advanced wearable technology, predictive analytics for patient outcomes in medicine and healthcare, sophisticated risk assessment models, real-time fraud detection analytics, comprehensive customer behavior analysis in the financial domain, accurate energy consumption forecasting, seamless integration of renewable energy sources in the energy sector, as well as predictive maintenance advanced process optimization, AI-driven automation, and real-time safety and environmental monitoring using IoT devices for industry are among the many we can mention. This session aims to bring together researchers, data scientists specialists, experts and professionals from different domains to promote cross-disciplinary collaboration and knowledge sharing. Participants will gain insights into the latest developments, best practices, and real-world applications of data science across these diverse sectors.

The scope of the session includes, but is not limited to, the following topics:

• Advanced machine learning applications in healthcare and industry.
• Applications of outlier analysis.
• Distributed learning strategies for scalable computations.
• Outlier detection based on distance, density, depth, deviation.
• Outlier Detection in Categorical, Text, Mixed Attribute Data, and Stream Data.
• Approaches for handling outlier detection in big data environments.
• Ensemble methods to enhance prediction accuracy across various applications.
• Feature learning, selection, and transformation for enhanced models and efficiency in applications.
• Frequent Pattern Mining.
• Massive data analysis in medicine, finance, energy, and industry applications.
• Explainable models based on ontologies and AI techniques.
• Integration of signals from diverse sensors for a comprehensive understanding.
• Fusion of heterogeneous data types for a holistic perspective in applications.