**2. Knowledge acquisition for the new GuideExpert acquaintance**

The GuideExpert system is an expert system developed to assist the designer of humancomputer interfaces during the phases of design and evaluation of interfaces. The system consists of five elements: user interface, inference engine, working memory, knowledge base and database. Figure 2 shows the architecture of the expert system. Through a series of questions and screens, the system selects a series of recommendations (called guidelines) of experts in the field of interfaces. The GuideExpert in its first version consisted of three hun‐ dred and twenty six guidelines of elicited interfaces projects from various authors and ex‐ perts in the field of interfaces. To search the knowledge base of the GuideExpert it was defined the meta-guidelines. They are concepts which embrace the guidelines according to the common characteristics and goals [6].

**Figure 2.** GuideExpert expert system

It is an approach to build domain ontologies and includes the notion of a library of reusable problem-solving methods (PSMs) that perform tasks. In PROTÉGÉ-II, PSM are decomposa‐ ble into subtasks. Other methods, sometimes called sub methods*,* can perform these sub‐ tasks. Primitive methods that cannot be decomposed further are called mechanisms. This decomposition is made to allow the reuse of knowledge, an essential part of the methodolo‐ gy. The choice of which method is suitable for the development of an intelligent system is essential, given the complexity of systems in the field of artificial intelligence (AI). It is im‐ portant to define a process that systematizes the life cycle, allowing a greater skill in eliciting and models description. In this work, it was elaborated a guide for knowledge acquisition based on ontologies [9] and applied to the extension of an expert system of recommenda‐

tions (guidelines) for designing human-computer interfaces.

86 Advances in Expert Systems

**Figure 1.** Stages of knowledge acquisition, design, implementation and evolution from MIKE.

which will be presented in the next section.

This expert system called GuideExpert was expanded to include recommendations about profiles of users with learning disorder (TA), attention deficit disorder / hyperactivity (ADD / H) and advices on cognitive learning styles (ECAS). The learning disorder is defined where individuals can not develop as expected in appropriate age scholl [22], on the other hand the deficit of attention disorder/ hyperactivity and impulsivity [1]. In turn, the cogni‐ tive learning styles represent a categorization of the cognition particularities with their re‐ spective skills [21]. There are several recommendations on how computer interfaces should be designed in order to attend, in a satisfactory way, users with learning disorders and dif‐ ferent cognitive styles, among other features. Thus, the aim of incorporating this knowledge to the GuideExpert base needed the establishment of a process for knowledge acquisition

In the second phase of the project, it was seen the need to incorporate in the system, the guidelines relative to the diversity of user profiles. We identified several recommendations, heuristic and knowledge about adults, children, handicapped users, users with deficits of at‐ tention and etc. In order to make the knowledge acquisition in this domain it was elaborated a guide based on Ontologies. Ontology is a formal and explicit specification of a shared con‐ ceptualization [9]. The ontologies are used to structure and share the knowledge. They can be seen as the highest level in a hierarchy of knowledge composed of vocabularies, thesauri, taxonomies, ontologies and frames. A taxonomy is to classify information in a hierarchy (tree) with the generalization relationship "kind-of" (parent-child) [4].

The existence of a taxonomy in GuideExpert system, formed by the meta-guidelines, moti‐ vated the ontology conceptualization for projects in human-computer interfaces. For the cre‐ ation of ontologies there are different methods belonging to the Ontological Engineering area. The goal of these methods is to provide tasks or steps to be followed in creating the ontology. Among the best known in litaratura we can mention: the method of Uschold [23], Horrocks [11], and Noy and McGuiness [14]. Uschold proposal called "Skeletal Methodolo‐ gy" uses scenarios to describe knowledge. Questions or types of questions are made primari‐ ly in order to specify the knowledge that is not being adequately addressed by the ontologies and that will be conceptualized through questions.

**2.** Consider the reusing of another ontologies: is whether ontology exists and refine or ex‐

Heuristics for User Interface Design in the Context of Cognitive Styles of Learning and Attention Deficit Disorder

http://dx.doi.org/10.5772/51455

89

**3.** Enumerate important terms of the ontology: is to define a list of the most common terms

**4.** Define the classes and class hierarchy: is to determine the consistency of the class-subclass hierarchy, ie it should be noted that a class has more or less subclasses There are several

**5.** Set the properties of the classes: it is to create some concepts in the hierarchy, and then

**6.** Set the values of properties (also called facets) is to describe the types of data (values ), allowed values, domain, scope, minimum and maximum number (cardinality) for property

**7.** Create instances: it consists in choosing the class for which you want to create instances

The method of Noy and McGuiness was adopted here in order to define concepts, proper‐ ties and relationships for the domain knowledge of Human Computer Interface. Thus, we

The method of Noy and McGuiness was adopted here in order to define concepts, proper‐ ties and relationships for the domain knowledge of Human Computer Interface. Thus, we

The Guidelines of the project of the GuideExpert were classified in a taxonomy consisting of 10 meta-guidelines, including: Feedback System, Data Protection, Documentation, interac‐ tion, presentation of data, Internationalization of interfaces, Colors, Terminology Interface,

From this taxonomy, the ontology was defined, following the steps of the methodology pro‐ posed by Noy and McGuinness [14]. At the stage of conceptualization of theontology for the system GuideExpert it was elicited domain, objective information, users, tasks and resour‐

**•** Definition of the main goal or purpose: create an ontology to guide the search for guide‐

**•** Definition of informations about the ones that should provide answers: related to the con‐

defined the classes and relationships of the knowledge of the system GuideExpert.

defined the classes and relationships of the knowledge of the system GuideExpert.

tend the model to new domain or task.

in the domain and the properties they possess:

**3.2** Which are the properties of these terms?

filling the property values for each instance.

Design, and Assisting people with disabilities.

lines (recommendations) of project interface;

cepts established on the metaguidelines.

**•** Domain definition: concepts of human-computer interfaces;

their properties.

values, and others.

**2.1. GuideExpert Ontology**

ces, namely:

**3.1** Which are the terms that are desired to be included?

strategies for defining the hierarchy: top-down, bottom-up or mixed.

The Ian Horrocks method, is composed of the following phases:


The Ian Horrocks method goes through the definition domain, the definition of classes, properties, etc. Another methods also start the creation of ontologies focusing on domains, classes and hierarchies, but though questionings. This is the case of the 101 method pro‐ posed by Natalya Noy and Mac Deborah McGuiness [14]. This method brings together rec‐ ommendations and experiences using the tool for editing ontologies, Protégé 2000 [17], the Ontolingua language [16] and the tool Chimaera [5]. This methodology focuses on the On‐ tology conceptualization phase, divided into seven steps, which involves: definition of the ontology classes, storage of the classes in the hierarchy, defining properties and definition of the instances.

The steps that comprise the methodology proposed by Noy and McGuinness are [14]:

**1.** Determine the scope of the ontology: to determine the domain and scope it is suggested the following questions:

**1.1** Which domain is desired to cover with the Ontology?

**1.2** With which purpose the Ontology will be used?

**1.3** For wich questions the Ontology mus provide answers?

**1.4** Who is going to use and maintain the ontology?

**2.** Consider the reusing of another ontologies: is whether ontology exists and refine or ex‐ tend the model to new domain or task.

**3.** Enumerate important terms of the ontology: is to define a list of the most common terms in the domain and the properties they possess:

**3.1** Which are the terms that are desired to be included?

**3.2** Which are the properties of these terms?

ation of ontologies there are different methods belonging to the Ontological Engineering area. The goal of these methods is to provide tasks or steps to be followed in creating the ontology. Among the best known in litaratura we can mention: the method of Uschold [23], Horrocks [11], and Noy and McGuiness [14]. Uschold proposal called "Skeletal Methodolo‐ gy" uses scenarios to describe knowledge. Questions or types of questions are made primari‐ ly in order to specify the knowledge that is not being adequately addressed by the

ontologies and that will be conceptualized through questions.

**•** Determine how the world (domain) must function

**•** Determine domain classes and properties

**•** Determine classes characteristics

**•** Add individual and relationships

**•** Care if the ontology already exists

**•** Verify if classes are coherent

**•** Specify an ontology

88 Advances in Expert Systems

the instances.

the following questions:

The Ian Horrocks method, is composed of the following phases:

**•** Determine domains and scopes (range) for this domain property

**•** Verify the consistency using a rationalization tool or inference motor

The Ian Horrocks method goes through the definition domain, the definition of classes, properties, etc. Another methods also start the creation of ontologies focusing on domains, classes and hierarchies, but though questionings. This is the case of the 101 method pro‐ posed by Natalya Noy and Mac Deborah McGuiness [14]. This method brings together rec‐ ommendations and experiences using the tool for editing ontologies, Protégé 2000 [17], the Ontolingua language [16] and the tool Chimaera [5]. This methodology focuses on the On‐ tology conceptualization phase, divided into seven steps, which involves: definition of the ontology classes, storage of the classes in the hierarchy, defining properties and definition of

The steps that comprise the methodology proposed by Noy and McGuinness are [14]:

**1.** Determine the scope of the ontology: to determine the domain and scope it is suggested

**•** Iterate the steps until end the ontology conceptualization

**1.1** Which domain is desired to cover with the Ontology?

**1.3** For wich questions the Ontology mus provide answers?

**1.2** With which purpose the Ontology will be used?

**1.4** Who is going to use and maintain the ontology?

**4.** Define the classes and class hierarchy: is to determine the consistency of the class-subclass hierarchy, ie it should be noted that a class has more or less subclasses There are several strategies for defining the hierarchy: top-down, bottom-up or mixed.

**5.** Set the properties of the classes: it is to create some concepts in the hierarchy, and then their properties.

**6.** Set the values of properties (also called facets) is to describe the types of data (values ), allowed values, domain, scope, minimum and maximum number (cardinality) for property values, and others.

**7.** Create instances: it consists in choosing the class for which you want to create instances filling the property values for each instance.

The method of Noy and McGuiness was adopted here in order to define concepts, proper‐ ties and relationships for the domain knowledge of Human Computer Interface. Thus, we defined the classes and relationships of the knowledge of the system GuideExpert.

The method of Noy and McGuiness was adopted here in order to define concepts, proper‐ ties and relationships for the domain knowledge of Human Computer Interface. Thus, we defined the classes and relationships of the knowledge of the system GuideExpert.

#### **2.1. GuideExpert Ontology**

The Guidelines of the project of the GuideExpert were classified in a taxonomy consisting of 10 meta-guidelines, including: Feedback System, Data Protection, Documentation, interac‐ tion, presentation of data, Internationalization of interfaces, Colors, Terminology Interface, Design, and Assisting people with disabilities.

From this taxonomy, the ontology was defined, following the steps of the methodology pro‐ posed by Noy and McGuinness [14]. At the stage of conceptualization of theontology for the system GuideExpert it was elicited domain, objective information, users, tasks and resour‐ ces, namely:


**•** Definitions of the users: the potencial users of the ontologies are the engineers of the inter‐ faces Human-Computer and learners of the development of interfaces projects.

Once elicited the ontology, it was used for the acquisition of knowledge about the guidelines for user profiles. For each of the ontology classes it were surveyed authors and experts in the field of interfaces. Thus, it was possible to expand the taxonomy with more concepts and relationships. The method of eliciting followed, based on the ontology, was the following

Heuristics for User Interface Design in the Context of Cognitive Styles of Learning and Attention Deficit Disorder

http://dx.doi.org/10.5772/51455

91

**4.** If a new knoweledge if found, describe the class and add it to the ontology.

**1.** Selecting of a class of the ontology of the GuideExpert.

**Figure 4.** Knowledge acquisition process based on ontologies used in GuideExpert.

Analog Analytical cognitive style, etc.

**learning and attention deficit disorder**

served during the interface design [12],[13],[20]:

It was incorporated into the knowledge base of the GuideExpert, one hundred thirty six spe‐ cific guidelines of the profile of users and special features such as: ADHD users, users with

**3. Heuristics for user interface design in the context of cognitive styles of**

The user population is not a system composed of only one type of user. In general, there is a

Speaking of users interacting with computers, we refer to the user's knowledge that should be taken into account in the design of an IHC. Below are some features that must be ob‐

mixture of multiple profiles of users who need to somehow get their needs met [15].

**2.** Elicit questions that can be answered by specialists.

**3.** Make the acquisition of this knoweledge.

(Figure 4):


Subsequently, based on the taxonomy, it was defined the classes and relationships. The main classes were expanded in most relationships and subclasses according to the recom‐ mendations of guidelines that exist in the system GuideExpert. Figure 3 shows the concept of class interaction with the relationships used (Table 1).


**Table 1.** relationships dictionary

Once elicited the ontology, it was used for the acquisition of knowledge about the guidelines for user profiles. For each of the ontology classes it were surveyed authors and experts in the field of interfaces. Thus, it was possible to expand the taxonomy with more concepts and relationships. The method of eliciting followed, based on the ontology, was the following (Figure 4):


**•** Definitions of the users: the potencial users of the ontologies are the engineers of the inter‐

**•** Definition of tasks: the main tasks held for the development of the ontologies consist in following the steps of the Noy and McGuiness methodology in this first step of the re‐

**•** Definition of the resources: the resources needed for the development of the ontology are the computational tool to model the ontology and the language to formalize it. These

Subsequently, based on the taxonomy, it was defined the classes and relationships. The main classes were expanded in most relationships and subclasses according to the recom‐ mendations of guidelines that exist in the system GuideExpert. Figure 3 shows the concept

faces Human-Computer and learners of the development of interfaces projects.

steps will be developed in the next steps of the project.

of class interaction with the relationships used (Table 1).

**Figure 3.** Diagram of the subclass interaction ontology.

Is-a Indicates that one class is subclass of another. s\_PartOf Indicates that one classe is part of another

hasValue Indicates that one class obtain values from another class.

defines Indicates that one class defines a determinate concept from another class discovers Indicates that a class discovers a determinate pattern by another class

**Relationship Meaning**

**Table 1.** relationships dictionary

search.

90 Advances in Expert Systems

**4.** If a new knoweledge if found, describe the class and add it to the ontology.

**Figure 4.** Knowledge acquisition process based on ontologies used in GuideExpert.

It was incorporated into the knowledge base of the GuideExpert, one hundred thirty six spe‐ cific guidelines of the profile of users and special features such as: ADHD users, users with Analog Analytical cognitive style, etc.
