Linear fusion of estimates has been studied from the perspectives of known and unknown correlations of estimation errors. Whereas optimal linear combinations can be designed in the former case, a robust approach is usually chosen in the latter one. The loss of performance may ...

Condition monitoring is the process of signal measuring and processing to detect an early change in the system. In turbomachinery, blade state monitoring is an important task of this kind. It is important, especially in terms of the last stages of the low-pressure turbine. In&...

Decentralised estimation often sacrifices optimality for solution simplicity, while within the fusion under unknown correlation, a worst-case type of optimality is adopted. This paper studies the gap between the simple solution and the optimal one for special cases. Namely, symmetric configuratio...

This paper presents a cloud-based multi-modal human-robot interaction architecture. The architecture consists of parts running on the edge (mobile) platform and cluster services. Software on the mobile platform is represented primarily by a Robot Operating System, an MQTT broker and the clie...

The paper deals with the development of an experimental benchmark mechatronic system that was employed in control courses taught at our university. The first part introduces its mechanical design, installed instrumentation and software environment. Methodology of its use in terms of our ...

Online evaluation and prediction of turbine generator failures is a key factor for its successful long-term operation. Generator torque fluctuations, caused by, for example, non-stationary conditions in the power grid, affect the shaft torsional vibration as well as the vibration of&#...

The experimental study focuses on minimally invasive fixation techniques of linear sacral fractures and its results are utilised for development and validation of the related computational model. The model is extended for analysis of unstable pelvic ring injuries with spinopelvic dissociation...

This work focuses on the multiscale modeling of composites made of layers consisting of hybrid fabric reinforcement and polymer matrix. The fabric (HP-P167AC) is a plain-weave textile with carbon (3K, 200 tex) and aramid (Kevlar 49, 158 tex) tows each placed in single direction...

Building accurate knowledge of the identity, the geographic distribution and the evolution of species is essential for the sustainable development of humanity, as well as for biodiversity conservation. However, the difficulty of identifying plants, animals and fungi is hindering the aggregation&#...

The paper deals with the development of an experimental mechatronic system for battery management of drones called Droneport. It was developed as an automatic system with battery swapping and recharging feature set outside the drone, allowing a quick return to a mission. The first&...

Prosodic boundaries in speech are of great relevance to both speech synthesis and audio annotation. In this paper, we apply the wav2vec 2.0 framework to the task of detecting these boundaries in speech signal, using only acoustic information. We test the approach on a set ...

Czech is a very specific language due to its large differences between the formal and the colloquial form of speech. While the formal (written) form is used mainly in official documents, literature, and public speeches, the colloquial (spoken) form is used widely among people ...

In this paper, we investigate two research questions related to the phonetic representation of input text in Czech neural speech synthesis: 1) whether we can afford to reduce the phonetic alphabet, and 2) whether we can remove pauses from phonetic transcription and let the spe...

In this paper, we present a spoken dialog system used for collecting data for future research in the field of dementia prediction from speech. The dialog system was used to collect the speech data of patients with mild cognitive deficits. The core task solved by the ...

Pre-trained models used in the transfer-learning scenario are recently becoming very popular. Such models benefit from the availability of large sets of unlabeled data. Two kinds of such models include the Wav2Vec 2.0 speech recognizer and T5 text-to-text transformer. In this paper, we&...

Appropriate prosodic phrasing of the input text is crucial for natural speech synthesis outputs. The presented paper focuses on using a Text-to-Text Transfer Transformer for predicting phrase boundaries in text and inspects the possibility of enriching the input text with more detailed ...

The task of grammatical error correction is a widely studied field of natural language processing where the traditional rule-based approaches compete with the machine learning methods. The rule-based approach benefits mainly from a wide knowledge base available for a given language. On ...

We present our system for measuring the lexical semantic change between corpora pairs, developed for the RuShiftEval competition. We measure semantic changes in a list of test words between three different corpora (for each pair), pre-Soviet, Soviet, and post-Soviet, each from a differe...

The process of combining data and estimates is inherent in estimation problems. This paper focuses on the linear fusion under the assumption that only some elements of the cross-correlation matrix of the estimation errors are known. Configurations of the knowledge are discussed individu...

The Fast Fourier Transform is the unique tool enabling to engage the frequency domain analysis in detection and isolation of periodic disturbances in industrial processes containing rotating elements. Nevertheless, there exist particular problems where the time-domain examination of oscillations can&#...