IEEE Xplore

Human surrounding environment parameters are gathered regularly from electrical signals which are converted to digital signal using ADC converters and performing necessary data transformations. The gathered environment data can be estimated as a time series to apply standard statistical models. In this study, there are analyzed statistical models that help understand data and find consistent patterns-trends to make predictions depending on all previous data. Energy consumption data processing prediction methods were analyzed and presented. Dependency on time series analysis’ results when using task management with prediction parameters is the special feature of designed measurement system. Transition from one state to another includes not only estimates of the previous and current states, but also a prediction state.

The paper presents a research based on a vision of a multi-agent model working for the ambient comfort measurement and environment control system. Such means are used for developing the Smarter Eco-Social Laboratory (SrESL). The human Ambient Comfort Affect Reward (ACAR) index is proposed for development of the Reinforcement Learning Based Ambient Comfort Controller (RL-ACC) for experiments using equipment of SrESL. The ACAR index is recognized as dependent on human physiological parameters, such as the temperature, the electrocardiogram (ECG) and the electrodermal activity (EDA). The fuzzy logic is used to approximate the ACAR index function by defining two fuzzy inference systems: the Arousal-Valence System, and the Ambient Comfort Affect Reward (ACAR) System. The goal of the RL-ACC is to find such the environmental state characteristics that create an optimal comfort for people affected by this environment. The Radial Basis Neural Network is used as the main component of the RLACC to performing of two roles: the policy structure, known as the Actor, used to select actions, and the estimated value function, known as the Critic that criticizes the actions made by the Actor. The Actor which manages Critic processes was used as a value function approximation of the continuous learning tasks of the RL-ACC and presented in this paper.

At present, in various control systems the electronic devices with the built-in test equipment are applied. At exploitation of electronic devices, the inspection of their technical state is periodically carried out. For this purpose, the built-in test equipment is applied.At design stages and exploitation of control systems operation safeguarding their reliability are carried out. This requires the information on parameters, which characterize efficiency of use of the built-in test equipment. In the paper, the method of evaluation of definition probability by the built-in test equipment of state of nonserviceability of electronic devices is analyzed.

The paper analyzes the abilities for improving the distance learning system by means of developing collaboration components. Multi-layer architecture of the distance learning system and demand for integration of intelligent agents are also analyzed. The architecture solution of this type learning system is proposed by integration of scenarios and decision support components in the context analysis stage. The possibilities to integrate different levels of domain ontology into a content management system of selected architecture are discussed. The approach to developing the component-based knowledge management system in the e-learning environment is discussed in order to intellectualize processes such as collaboration support, adaptive presentation, interactive problem support, etc. The supposed collaborative architecture is developed with a view to integrate components by means of agents and their scenarios.