Feramat Cybernetics (Czechia)

This paper deals with the state estimation of stochastic models with continuous dynamics. The aim is to incorporate spectral differentiation methods into the solution to the Fokker-Planck equation in grid-based state estimation routine, while taking into account the specifics of the field, such as probability density function (PDF) features, moving grid, zero boundary conditions, etc. The spectral methods, in general, achieve very fast convergence rate of $\mathcal{O}\left(c^{N}\right)(O{\lt}$ $c{\lt}1$) for analytical functions such as the probability density function, where N is the number of grid points. This is significantly better than the standard finite difference method (or midpoint rule used in discrete estimation) typically used in grid-based filter design with convergence rate $\mathcal{O}\left(\frac{1}{N^{2}}\right)$. As consequence, the proposed spectral method based filter provides better state estimation accuracy with lower number of grid points, and thus, with lower computational complexity.

In this paper, we propose an improved training protocol of U-Net architecture for the semantic segmentation of aerial images. We test our approach on the challenging FLAIR #2 dataset. We present an extensive ablation study on the influence of different approach components on the overall performance. The ablation study includes a comparison of different model backbones, image augmentations, learning rate schedulers, loss functions, and training procedures. We additionally propose a two-stage training procedure and evaluate different options for the model ensemble. Based on the results we design the final setup of the model training protocol. This final setup decreases the relative error by approximately 18% and achieves mIoU equal to 0.641, which is a new state-of-the-art result. Our code is available at: h ttps://github.com/strakaj/U-Net-for-remote-sensing.

Behavioural support has been shown to possess high efficacy in aiding smokers to stop smoking at a level at least similar to nicotine replacement therapies (NRT) while causing no adverse physiological effects. Furthermore, the effects of behavioural interventions and NRT appear to be roughly additive. The effectiveness of interventions appears to increase with the frequency of contact with an eHealth application, with daily contact showing higher efficacy compared to weekly sessions with a trained stopsmoking specialist. Previous automated counsellors based on a motivational interview approach, lapse preparation, and lapse management are rigid in their therapeutic path, with limited ability to reflect the needs and the specific situation of a given patient. AIMS: This report aims to describe a possible approach to developing a more engaging, patient-tailored automated counsellor based on recent advances in the natural language processing (NLP) field that should make

The paper describes a system for automatic evaluation of synthetic speech quality based on continuous detection of emotional states throughout the spoken sentence using a Gaussian mixture model (GMM) classification. The final evaluation decision is made by statistical analysis of the results of emotional class differences between the sentences of original male or female voices and the speech synthesized by various methods with different parameters, approaches to prosody manipulation, etc. The basic experiments confirm the functionality of the developed system producing results comparable with those obtained by the standard listening test method. Additional investigations have shown that a number of mixtures, types of speech features, and a speech database used for creation and training of GMMs have a relatively great influence on continuous emotional style detection and the final quality evaluation of the tested synthetic speech.

The word information is often used without carefully distinguishing between different meanings it has taken on during its history. Generally, it refers to a finding or findings concerning facts, events, things, people, thoughts or notions, that is, a certain reflection of real or abstract objects or processes. It usually consists of its syntactic (structure), semantic (meaning), and pragmatic (goal) components. Therefore information can be defined as data that has been

This paper discusses the issue of demand side management, in particular control of the output power of heat pumps based on the spot market electricity price. The main presumptions are the ability of controlled HVAC system to shift energy load on the customer's side and sufficient credibility of an energy price prognosis on the electricity provider's side. The paper first presents current situation in the Czech republic with electricity tariffs legislations, which have to be followed so that the proposed method is applicable in practice. It is shown that for successful implementation, it is required to have an energy load model, model of the accumulation as well as parameters of the heat pump. For the energy load model, statistical black box methods are used, while the other models are based on first principles. The models are together with the prediction of spot market price used within model predictive control framework resulting in cost savings higher than 10%.

Unexpected stimuli are a challenge to any machine learning algorithm. Here, we identify distinct types of unexpected events when general-level and specific-level classifiers give conflicting predictions. We define a formal framework for the representation and processing of incongruent events: Starting from the notion of label hierarchy, we show how partial order on labels can be deduced from such hierarchies. For each event, we compute its probability in different ways, based on adjacent levels in the label hierarchy. An incongruent event is an event where the probability computed based on some more specific level is much smaller than the probability computed based on some more general level, leading to conflicting predictions. Algorithms are derived to detect incongruent events from different types of hierarchies, different applications, and a variety of data types. We present promising results for the detection of novel visual and audio objects, and new patterns of motion in video. We also discuss the detection of Out-Of- Vocabulary words in speech recognition, and the detection of incongruent events in a multimodal audiovisual scenario.

Data mining is sometimes treating data consisting of items representing measurements of a single property taken in different time points. In this case data can be understood as a time series of one feature. It is no exception when the clue for evaluation of such data is related to their development trends as observed in several successive time points. From the qualitative point of view one can distinguish three basic types of behaviour between two neighbouring time points: the value of the feature is stable (remains the same), it grows or it falls. This paper is concerned with identification of typical qualitative development patterns as they appear in the windows of given length in the considered time-stamped data and their utilization for specification of interesting subgroups.