Karel Mls

Application of Ambient Intelligence in Educational Institutions: Visions and Architectures

The ambient intelligence concept provides a vision of society of the future, where people will find themselves in an environment of intelligent and intuitively usable interfaces. The manuscript applies this definition to the specific environment of higher education in the context of the Czech Republic. The existence of the so-called Generation Y and characteristics of included individuals represent the main rationale of this paper. In particular sections of this paper, three visions that focus on intelligent assistance for graduation thesis preparation, smart lecture halls, and smart university campuses are described, and related architectures are depicted. Furthermore, results from a survey evaluating three main aspects-feasibility, willingness to use, and accessibility of technologies-of these visions are presented.

Interactive evolutionary optimization of fuzzy cognitive maps

Abstract Modeling dynamic systems with Fuzzy Cognitive Maps (FCMs) is characterized by the simplicity of the model representation and its execution. Furthermore, FCMs can easily incorporate human knowledge from the given domain. Despite the many advantages of FCMs, there are some drawbacks, too. The quality of knowledge obtained from the domain experts, and any differences and uncertainties in their opinions, has to be improved by different methods. We propose a new approach for handling incompleteness and natural uncertainty in expert evaluation of the connection matrix of a particular FCM. It is based on partial expert estimations and evolutionary algorithms in the role of an expert-driven optimization and outside of the FCM optimization (adaptation) research area known as Interactive Evolutionary Computing (IEC). In the present paper, a modification of IEC for the purposes of FCM optimization is presented, referred to as the IEO-FCM method, i.e., the Interactive Evolutionary Optimization of Fuzzy Cognitive Maps. Experimental results on two control problems suggest that the IEO-FCM method can improve the quality of an FCM even in situations without any measured data necessary for other known learning algorithms.

Agent-Based Simulation for Identifying the Key Advantages of Intelligent Environments for Inhabitants with Special Needs

In the paper, simulation of the interaction between an intelligent house containing smart sensors and its inhabitants is introduced. The simulation model is mainly focused on monitoring of different inhabitants’ needs and their health statuses. Different situations affecting inhabitant’s health status are simulated. The proposed simulation model has an ability to test different arrangements of sensors in the environment without the necessity of its real construction. The most critical situation—heart attack occurrence based on the selected attributes—is studied in a practical example. The monitoring and processing system can recognize a person who needs an urgent medical assistance. In this case, the Emergency Medical Responders (EMR) are called immediately. The simulation tool AnyLogic has been used and its usability for modeled cases seemed to be proven.

Decision Support Smartphone Application Based on Interval AHP Method

Multicriteria decision making based on Analytic Hierarchy Process in the health care mobile application is introduced and studied. The application focuses on processing data from internal sensors of a smart phone as well as external sensors in order to monitor current state of a person. Measured data are partly evaluated in the device in order to identify critical situations such as fall of the person, and then are also sent to a server for the deeper analysis. While using AHP method, pairwise comparison matrices have to be created by experts - in our case doctors. Each expert can have different preferences and thus the resulting matrix, created based on the opinions of several experts, may be inconsistent. The method presented in this paper is based on interval judgments and shows how to merge inconsistent and uncertain preference matrices from several experts to deliver a robust and sensitive model for online machine decision making.

Decision Support Biomedical Application Based on Consistent Optimization of Preference Matrices

In designing a medical application, big emphasis must be given on correct understanding of experts’ opinions. This article deals with the decision making support based on Analytic Hierarchy Process (AHP). Inconsistency measures of preference matrices and the problem of consistent optimization are studied. A new method for computing the optimal consistent approximation of a given preference matrix is described. Furthermore, algorithms for finding a consensus of several experts are discussed. The proposed methods are presented and explained on numerical examples.