Ambient Intelligence System (AmIS) can be constructed using data collected from Internet of Things (IoT). In this paper, the IoT data collection problem is studied for AmIS with dynamic structure and dynamic behavior of participants (devices), where constraints on resources consumption and performance are essential. A novel technology is proposed, which includes the following steps: (1) definition of the data collection (DC) problem (considering the model of the observed system, DC conditions, etc.); (2) DC policy assignment; (3) construction of DC models; (4) evaluation and presentation of the data processing results. The proposed DC technology supports the development of data collecting subsystems in AmIS. Such subsystems provide data that reflect the changes in structure, state, situation, and behavior of participants in their IoT environment in time. Therefore, we show how this “cognitive” function of the DC process increases the intelligence level of IoT environment.

Introduction: Various interfering influences raise pressing problems of promptly restoring the flow of distorted frames,remembering about the background and dynamics of the event measurement laws. The traditional methods of recovering flows ofdistorted frames do not fully take into account the peculiarities of this process. Purpose: Exploring the possibilities of recurrent neuralnetworks with controlled elements for restoring frame flows. Results: It is proposed to evaluate the potential of a recurrent neuralnetwork with controlled elements by the number of successful options for restoring a distorted sequence of frames. Evaluation of thecapabilities of such neural networks according to the introduced indicator showed their strong dependence on the type of networkstructure and settings. Recurrent neural networks with spiral structures of layers work better. As the number of the turns in the helixgrows, the network capabilities also grow. Enhancing the capacity of a network to restore distorted frame flows is feasible if we replaceunipolar functions of the synapse weights by bipolar ones. A significant increase in the capabilities of the neural networks under studyis possible by controlling the neuron excitation thresholds in order to provide sequential rather than parallel elimination of variouserrors. In contrast to the conventional neural networks, recurrent neural networks with controlled elements can adapt to changes in№ 5, 2019 ИНФОРМАЦИОННОУПРАВЛЯЮЩИЕ СИСТЕМЫ 17ОБРАБОТКА ИНФОРМАЦИИ И УПРАВЛЕНИЕthe laws inherent in frame flows, and implement controlled associative signal processing. Experiments have shown that these neuralnetworks can use associative connections for taking into account deep current experience in signal processing, and be successfully usedfor restoring distorted frame flows.