In this paper, a new intent and entity recognition model for the subject area of air passenger service, labelled as IRERAIR-TWIN, is developed using the ‘no code’ question-answer development platform ‘TWIN’. The advantages of the no-code platform were analysed in terms of the ease of developing an application question-answer system and reducing the amount of work involved in developing an application model for a narrow subject area. The results show that the ‘TWIN’ system provides an intuitive web-based user interface and a simpler approach to develop the semantic module of a question-answer system capable of solving application problems for a narrow subject area that are not overly complex. However, this approach has limitations for deep semantic analysis tasks, especially in complex contextual inference and processing of large text fragments. The paper concludes by emphasising that future research will focus on using ChatGPT-based ‘low code’ platforms and large language models to further improve the intelligence of the IRERAIR-TWIN model. This extension aims to broaden the scope of the scenarios.

Keywords: question-answering systems, No-code, Low-code, Intent recognition, Named entity recognition, Data annotation, Feature engineering, Pre-trained model, software development,End-user development

This paper explores in detail the technological evolution and current state of question and answer (Q&A) systems. Using an example of an airline customer service task, a BERT-based model is developed that is capable of recognising user intentions and extracting named entities. The paper provides a detailed description of the dataset preparation, data analysis methods and data exploration techniques of the project. A description of the model and parameter settings during the model tuning process and the model training process is presented. The model developed in this project is named RNEEMAviCS-BERT, which achieved an intent recognition accuracy of 98.2% and named entity recognition accuracy of 83%. We have created a semantic analysis module for the question and answer system. The next stage of our work will be to integrate the dataset to complete the query-response and response generation components of the Q&A system.

Keywords: question-answering systems, ChatGPT, BERT, machine learning, neural networks, pre-trained models, intention recognition, named entity recognition, data analysis, model training

ZnO nanorod arrays have been synthesized on silicon wafers by chemical vapor deposition (CVD) technique with different  temperature modes, without metal catalyst.  With this method   vertically aligned ZnO nanostructures  were grown at the quite low temperatures.  Modification of the method allowed to place silicon substrates in areas with different  ratios of concentrations of the molecules in the vapor phase. Photoluminescence spectroscopy and electron microscopy studies have shown that morphologies and optical properties of nanorods depends on different ratios of concentrations of the molecules in the vapor phase.

Keywords: ZnO nanorods,chemical vapor deposition (CVD), photoluminescence

The arrays of ZnO nanorods were obtained on the sapphire substrates by means of pulsed laser deposition under the high pressure of argon. The conditions of synthesis were optimized, and their influence on the morphology of  ZnO nanostructures were revealed. It is shown that the concentration of oxygen vacancies in ZnO nanorods can be changed by regulation of the synthesis temperature from 850 to 915 °. This process can be controlled by the ratio of intensities of the photoluminescence emission in the visible and ultraviolet regions. So, it allows to create nanostructures for UV photodetectors or chemosensors depending on the temperature choice.

Keywords: ZnO nanorods, laser deposition, PLD, photoluminescence

The mathematical model of the potential distribution in the semiconductor surficial region in the presence of deep-lying levels in its forbidden zone which specified by multiple-charge impurity centers has been developed. The simulation results can be used for the width of the space charge region estimation, for the prognostication of the most probable mechanism of the charge carriers transfer in metal-semiconductor structure with multiple-charge deep-lying levels and also for the prognostication of the barrier capacitance value. It can be used in the development of solid-state electronic devices with improved values of some parameters.

Keywords: Poisson’s equation, multiple-charge impurity center, potential distribution, deep-lying levels

Structure of  surface acoustic waves(SAW) of CO sensor was developed. SAW sensor include transceiving IDT and catoptric IDT, which is loaded on the impedance of ZnO nanorods. Peak of reflection SAW from IDT clearly observed as result Fourier transformation of time function of pulsed response. IDT loaded on resistance paralleled ZnO nanorods, which depends on the concentration of CO.

Keywords: ZnO nanorods, device on SAW, CO sensor

Combined method which allows analyzing parameters of the nanoscale atomic and electronic structure of materials relying on three different methods (x-ray absorption spectroscopy (XAFS), x-ray diffraction (XRD) and Raman spectroscopy) was developed. The method was applied for the study of nickel oxide nanoparticles, which serve as an efficient catalyst for the artificial photosynthesis process. 

Keywords: solar energy, artificial photosynthesis, NiO, Raman, x-ray diffraction, XAFS

In the present work we have carried out studies of the processes of growth of zinc oxide nanorods by hydrothermal method on silicon substrates. As sublayer catalyst used growth caused by laser deposition of zinc oxide, various thicknesses. Studied selective growth of nanorods on the microstructure of thin-film sub-layers of zinc oxide obtained by laser deposition. The optimal conditions for the synthesis of: the concentration of Zn (NO3) 2 - 0.4 mol / l, hexamethylenetetramine - 0.4 mol / l, the concentration of NH3 · H2O - 0,01 mol / L -0.01, process time 4:00, the process temperature is 80 ° C. Sublayer thickness of zinc oxide, as shown by experiment, the growth of the rods has no noticeable effect. Oriented arrays of nanorods were obtained up to 500 nm and a diameter of 60-150 nm.
Keywords: zinc oxide nanorods and micro-oriented arrays of nanorods, hydrothermal synthesis method, selective growth, thin film underlayer.

Keywords: