Conceptual Graphs Based Modeling of Semi-Structured Data

Abstract: Due to the fast growing of data in the digital world, not only in volume but also in its variety (structured, unstructured or hybrid), traditional RDBMS are complemented with a rich set of systems, known as NoSQL. One of the main categories of NoSQL databases are document stores which are speci cally designed to handle semi-structured data, for instance XML documents. In this paper, we present a modeling method for semi-structured data based on Conceptual Graphs and exemplify the method on an XML document. The expressive power of Conceptual Graphs makes them particularly suitable for conceptual modeling of semi-structured data.

Keywords: Conceptual Graphs, conceptual modeling, semi-structured data

Using analogical complexes to improve human reasoning and decision making in Electronic Health Record Systems

Abstract: A key ability of human reasoning is analogical reasoning. In this context, an important notion is that of analogical proportions that have been formalized and analyzed in the last decade. A bridging to Formal Concept Analysis (FCA) has been brought by introducing analogical complexes, i.e. formal concepts that share a maximal analogical relation enabling by this analogies between (formal) concepts. Electronic Health Record (EHR) systems are nowadays widespread and used in different scenarios. In this paper we consider the problem of improving EHR systems by using analogical complexes in an FCA based setting. Moreover, we present a study case of analogical complexes in a medical field. We analyze analogical proportions in Electronic Health Record Systems and prove that EHRs can be improved with an FCA grounded analogical reasoning component. This component offers methods for knowledge discovery and knowledge acquisition for medical experts based on patterns revealed by analogies. We also show that combining analogical reasoning with FCA brings a new perspective on the analyzed data that can improve the understanding of the subsequent knowledge structures and offering a valuable support for decision making.

Keywords: Formal Concept Analysis, Analogical Complexes, Electronic Health Record Systems

Symptoms investigation by means of Formal Concept Analysis for enhancing medical diagnoses

Abstract: Pattern extraction is one of the major topics in Knowledge Discovery. Out of numerous data mining techniques we propose to use a new approach: Formal Concept Analysis (FCA) together with Graph Databases with the implementation Neo4j. FCA is a prominent field of applied mathematics using maximal clusters of object-attribute relationships to discover and represent knowledge structures. The use of FCA gained much importance in many research domains in recent years. Despite the similarity of the graph representation between FCA and Neo4j, the structure and relations among the elements are represented differently and can offer a different perspective on the analysis. This paper gives more insight into how patterns can be extracted from medical data and interpreted by means of FCA and Neo4j in order to help medical staff improve the accuracy of diagnoses. We examine the factors related to patients' symptoms and diagnostics and then compare the results with the ones provided by a medical care center. We apply knowledge discovery techniques and conceptual landscapes paradigm in order to obtain an in-depth and high qualitative knowledge representation of medical data. By making use of the effectiveness and the graphical representation of conceptual hierarchies we extract valuable knowledge from medical data sets through which we solve the knowledge discovery, processing and representation task in Electronic Health Record systems.

Keywords: Formal Concept Analysis, Electronic Health Record, medical data, many-valued contexts, conceptual scaling, Triadic FCA, Neo4J

Investigating Educational Attractors and Life Tracks in e-Learning Environments Using Formal Concept Analysis

Abstract: E-learning platforms are widely used in modern education. While in the traditional education the instructor does not have a comprehensive insight on how his students are using the educational resources, the situation is different for online learning environments. Web usage logs comprise a variety of information regarding the visited pages.  These web-logs become a rich resource for data analysis. Understanding usage patterns from web-logs is widely used in order to improve web-based applications. In our research we are interested in distilling valuable knowledge on users behavior in online educational platforms using the knowledge discovery and processing methods of Formal Concept Analysis (FCA). This knowledge can then be used to understand how students are using the educational resources, to gain insight on their online behavior as well as how they use these resources over time. In this paper, we focus on the detection of behavioral patterns in web-based e-learning environments and on how users adhere to intended educational attractors. For this, we first use FCA to investigate so-called educational attractors and then distill users life tracks using Temporal Concept Analysis. We exemplify the developed methods on a locally developed e-learning platform called PULSE.

Keywords: Life tracks, Temporal Concept Analysis, Web logs analysis, Conceptual structures, User behavior, Attractors

An investigation of user behavior in educational platforms using Temporal Concept Analysis

Abstract: In this paper, we focus on the problem of investigating user behavior using conceptual structures distilled from weblogs of an educational e-platform. We define a set of so-called attractors as sets of scales in conceptual time systems and compute user life tracks in order to highlight different types of behaviors. These life tracks can give valuable feedback to the instructor how his students are using the online educational resources, analyzing their behavior and extracting as much knowledge as possible from the log access files. This might also be helpful to analyze the usability of the online educational content, eventually for improving the structure of the platform and to develop new educational instruments.

Keywords: Life tracks, Temporal Concept Analysis, Web logs analysis, Conceptual structures, User behavior, Attractors

A FCA Strategy for Improving Web-Based Learning Sites

Abstract: Nowadays, online educational systems show a rapid development due to the growth of the Internet, which offer unique opportunities to improve them based on users’ experiences. This paper presents advances of a Formal Concept Analysis (FCA) based strategy for improving web-based learning sites. We have used together Web Usage Mining and Formal Concept Analysis techniques in order to create a visual overview of exploring web-logs and discover knowledge in web logs. We have focused on visualizing triadic data in order to emphasize user dynamics through the educational systems. Switching from a triadic to a polyadic perspective we have detected repetitive browsing habits. From all the revealed behaviors we distill then users life tracks by using Temporal Concept Analysis.

Keywords: Web usage mining, Life track, Behavioral patterns, Online e-learning environment, Temporal Concept Analysis, Formal Concept Analysis, Triadic Formal Concept Analysis.

FCA Tools Bundle – a Tool that Enables Dyadic and Triadic Conceptual Navigation

Abstract: Formal Concept Analysis is a prominent field of applied mathematics handling collections of knowledge - formal concepts - which are derived from some basic data types, called formal contexts by using concept forming operators. One of the strengths of FCA is the elegant, intuitive and powerful graphical representation of landscapes of knowledge as concept lattices. Nevertheless, in case of triadic FCA (3FCA) for more than 20 years there was no automatic tool for graphical representation of triconcept sets. Moreover, the triangular representation of trilattices, used so far in 3FCA has several disadvantages. Besides the lack of clarity in representation, one major disadvantage is that not every trilattice has a triangular diagram representation. In this paper we focus on the problem of locally navigating in triconcept sets and propose a tool which implements this navigation paradigm. To the best of our knowledge this is the first tool which makes navigation in larger triconcepts sets possible, by flipping through a certain collection of concept lattices.

Keywords: FCA, Formal Concept Analysis, Context, Concepts, Dyadic Context, Triadic Context, Concept Finder, FCA Tools Bundle, Tools

Analysing the Effect of Changing the Educational Methods by Using FCA

Abstract: Formal Concept Analysis (FCA) developed in the last 30 years to a prominent field of Knowledge Discovery, Processing and Representation. Well-known for its intuitive representation of conceptual structures as order diagrams, FCA handles conceptual hierarchies which can be derived from various data sets. This makes FCA suitable for knowledge management tasks in many fields. We consider the problem of using FCA as a quality of education evaluation tool for the instructor. Students are using educational resources in an e-learning platform and the raw data set consists only of the subsequent recorded weblogs. After a preprocessing stage, various conceptual structures - among them behavioral patterns of e-learning resources usage - are distilled from the dataset using conceptual scaling and triadic FCA and are altogether offered as a decision support for the instructor. We prove the efficiency of using FCA in comparing students behavior through the educational process and highlight how new educational strategies correlate with their academic performance and the use of online learning ressources.

Keywords: Formal Concept Analysis, Knowledge Discovery, e-learning platform, triadic FCA, educational process

Is FCA suitable to improve Electronic Health Record Systems?

Abstract: Formal Concept Analysis (FCA) is a prominent field of applied mathematics using formal concepts - maximal clusters of object-attribute relationships - to discover, process, and represent knowledge in so-called conceptual hierarchies. Its efficient algorithms and expressive power makes FCA suitable to unify methodologies and to provide an in-depth insight on knowledge structures [1], [2]. Electronic Health Record (EHR) systems are nowadays widespread and used in different scenarios. In this paper we consider the problem of improving EHR systems with new, FCA grounded features. For this, we start with some particular medical data sets and discuss the improvement of some features of EHR systems by using FCA. Two main methods have been taken into consideration so far. First, we consider the medical data sets as many-valued contexts. By using conceptual scaling, we build `knowledge landscapes' [3] and show how these `landscapes' might be used in the framework of EHR. A complementary approach is based on Triadic FCA (3FCA) approach. We exemplify these methods on several medical datasets and discuss how conceptual landscapes can be used to improve not only the integrated view of patient data (as an EHR system specific feature), but also communication and support future research.

Keywords: Formal Concept Analysis, Electronic Health Record, medical data, many-valued contexts, conceptual scaling, Triadic FCA

Conceptual Navigation for Polyadic Formal Concept Analysis

Abstract: Formal Concept Analysis (FCA) is a mathematically inspired field of knowledge representation with wide applications in knowledge discovery and decision support. Polyadic FCA is an extension of classical FCA that instead of a binary uses an n-ary incidence relation to define formal concepts, i.e. data clusters in which all elements are interrelated. We consider a paradigm for navigating the space of concepts, based on so-called membership constraints. We present an implementation for the cases n ∈ {2, 3, 4} using an encoding into answer set programming (ASP) allowing us to exploit optimization strategies offered by ASP. For the case n = 3, we compare this implementation to a second strategy that uses exhaustive search in the concept set, which is precomputed by an existing tool. We evaluate the implementation strategies in terms of performance. Finally, we discuss the limitations of each approach and the possibility of generalizations to n-ary datasets.

Keywords: Formal Concept Analysis, Polyadic FCA, navigating the space of concepts, membership constraints, answer set programming