Effects of Input Data Formalisation in Relational Concept Analysis for a Data Model with a Ternary Relation

Today pesticides, antimicrobials and other pest control products used in conventional agriculture are questioned and alternative solutions are searched out. Scientific literature and local knowledge describe a significant number of active plant-based products used as bio-pesticides. The Knomana (KNOwledge MANAgement on pesticide plants in Africa) project aims to gather data about these bio-pesticides and implement methods to support the exploration of knowledge by the potential users (farmers, advisers, researchers, retailers, etc.). Considering the needs expressed by the domain experts, Formal Concept Analysis (FCA) appears as a suitable approach, due do its inherent qualities for structuring and classifying data through conceptual structures that provide a relevant support for data exploration. The Knomana data model used during the data collection is an entity-relationship model including both binary and ternary relationships between entities of different categories. This leads us to investigate the use of Relational Concept Analysis (RCA), a variant of FCA on these data. We consider two different encodings of the initial data model into sets of object-attribute contexts (one for each entity category) and object-object contexts (relationships between entity categories) that can be used as an input for RCA. These two encodings are studied both quantitatively (by examining the produced conceptual structures size) and qualitatively, through a simple, yet real, scenario given by a domain expert facing a pest infestation.

[1]  Rudolf Wille,et al.  A Triadic Approach to Formal Concept Analysis , 1995, ICCS.

[2]  Giacomo Kahn,et al.  On-demand Relational Concept Analysis , 2018, ICFCA.

[3]  Marianne Huchard,et al.  ARES, Adding a class and REStructuring Inheritance Hierarchy , 1995, BDA.

[4]  Bernhard Ganter,et al.  Pattern Structures and Their Projections , 2001, ICCS.

[5]  Olivier Ridoux,et al.  Arbitrary Relations in Formal Concept Analysis and Logical Information Systems , 2005, ICCS.

[6]  Florence Le Ber,et al.  Régler le processus d'exploration dans l'analyse relationnelle de concepts - Le cas de données hydroécologiques , 2019, EGC.

[7]  Sébastien Ferré,et al.  How Hierarchies of Concept Graphs Can Facilitate the Interpretation of RCA Lattices? , 2018, CLA.

[8]  Jean Sallantin,et al.  Structural Machine Learning with Galois Lattice and Graphs , 1998, ICML.

[9]  George Voutsadakis,et al.  Polyadic Concept Analysis , 2002, Order.

[10]  Derrick G. Kourie,et al.  AddIntent: A New Incremental Algorithm for Constructing Concept Lattices , 2004, ICFCA.

[11]  Franz Baader,et al.  A Finite Basis for the Set of EL-Implications Holding in a Finite Model , 2008, ICFCA.

[12]  Amedeo Napoli,et al.  Relational concept analysis: mining concept lattices from multi-relational data , 2013, Annals of Mathematics and Artificial Intelligence.

[13]  Sébastien Ferré,et al.  A Proposal for Extending Formal Concept Analysis to Knowledge Graphs , 2015, ICFCA.

[14]  Clémentine Nebut,et al.  Sizing the Underlying Factorization Structure of a Class Model , 2013, 2013 17th IEEE International Enterprise Distributed Object Computing Conference.

[15]  Jens Kötters,et al.  Concept Lattices of a Relational Structure , 2013, ICCS.

[16]  Sergei O. Kuznetsov,et al.  On interestingness measures of formal concepts , 2016, Inf. Sci..

[17]  Nada Mimouni,et al.  A Conceptual Approach for Relational IR: Application to Legal Collections , 2015, ICFCA.

[18]  Florence Le Ber,et al.  Extracting Hierarchies of Closed Partially-Ordered Patterns Using Relational Concept Analysis , 2016, ICCS.

[19]  Bernhard Ganter,et al.  Formal Concept Analysis: Mathematical Foundations , 1998 .

[20]  StummeGerd,et al.  Computing iceberg concept lattices with TITANIC , 2002 .

[21]  Clémentine Nebut,et al.  Class Model Normalization - Outperforming Formal Concept Analysis Approaches with AOC-posets , 2015, CLA.