Ph. D. Project
Title:
AI-Driven Dynamic Integration of Heterogeneous Data for Semantic Cluster Formalization in Human-Centric Intelligent Enterprise
Systems
Dates:
2025/11/01 - 2028/10/31
Student:
Supervisor(s):
Other supervisor(s):
TORRES Diego (diego.torres@lifia.info.unlp.edu.ar)
Description:
The logistics industry faces increasing challenges in integrating heterogeneous data from various Enterprise Resource Planning (ERP)
systems, Manufacturing Execution Systems (MES), and Customer Relationship Management (CRM) systems. These systems often
have unique structures, formats, and semantic interpretations, leading to data silos that hinder operational efficiency and informed
decision-making.
This PhD thesis focuses on developing an advanced Artificial Intelligence (AI)-driven framework to dynamically integrate
heterogeneous data sources and formalize semantic clusters for human-centric intelligent enterprise systems. By leveraging machine
learning, formal concept analysis (FCA), and semantic technologies, the research aims to harmonize disparate data formats and
address key challenges such as semantic heterogeneity, scalability, and semantic cluster formalization.
Objectives:
1. Semantic Heterogeneity: Develop methodologies to identify and resolve semantic inconsistencies across data sources, such as
variations in terminology, data representation, and contextual interpretations.
2. Scalability: Design an integration framework capable of handling large volumes of diverse data while maintaining performance,
supporting real-time updates, and enabling concurrent access.
3. Semantic Cluster Formalization: Propose innovative methods for identifying and formalizing clusters of semantically related
data elements, adapting dynamically to changes in data patterns.
Methodology:
The research will apply advanced AI techniques, including:
⬢ Machine learning for data transformation and integration.
⬢ Formal Concept Analysis (FCA) for semantic analysis and cluster formalization.
⬢ Ontology engineering to establish a coherent semantic foundation.
⬢ Dynamic data modeling to address evolving business requirements and market conditions.
The expected outcomes include:
⬢ A prototype integration framework capable of real-time heterogeneous data integration and semantic cluster analysis.
⬢ Enhanced methodologies for optimizing storage management and logistics operations.
⬢ Academic contributions in the form of publications and presentations.
The project will directly support MG-IB's R&D goals, offering practical tools to improve operational efficiency and customer
satisfaction while addressing broader challenges in the logistics sector.
systems, Manufacturing Execution Systems (MES), and Customer Relationship Management (CRM) systems. These systems often
have unique structures, formats, and semantic interpretations, leading to data silos that hinder operational efficiency and informed
decision-making.
This PhD thesis focuses on developing an advanced Artificial Intelligence (AI)-driven framework to dynamically integrate
heterogeneous data sources and formalize semantic clusters for human-centric intelligent enterprise systems. By leveraging machine
learning, formal concept analysis (FCA), and semantic technologies, the research aims to harmonize disparate data formats and
address key challenges such as semantic heterogeneity, scalability, and semantic cluster formalization.
Objectives:
1. Semantic Heterogeneity: Develop methodologies to identify and resolve semantic inconsistencies across data sources, such as
variations in terminology, data representation, and contextual interpretations.
2. Scalability: Design an integration framework capable of handling large volumes of diverse data while maintaining performance,
supporting real-time updates, and enabling concurrent access.
3. Semantic Cluster Formalization: Propose innovative methods for identifying and formalizing clusters of semantically related
data elements, adapting dynamically to changes in data patterns.
Methodology:
The research will apply advanced AI techniques, including:
⬢ Machine learning for data transformation and integration.
⬢ Formal Concept Analysis (FCA) for semantic analysis and cluster formalization.
⬢ Ontology engineering to establish a coherent semantic foundation.
⬢ Dynamic data modeling to address evolving business requirements and market conditions.
The expected outcomes include:
⬢ A prototype integration framework capable of real-time heterogeneous data integration and semantic cluster analysis.
⬢ Enhanced methodologies for optimizing storage management and logistics operations.
⬢ Academic contributions in the form of publications and presentations.
The project will directly support MG-IB's R&D goals, offering practical tools to improve operational efficiency and customer
satisfaction while addressing broader challenges in the logistics sector.
Keywords:
Artificial Intelligence, Semantic Clusters, Data Integration, FCA, Logistics, Ontology Engineering
Department(s):
| Modelling and Control of Industrial Systems |
Publications:
