Секция 5. Recent Developments in Radiophysics, Optics, Photonics, Optoinformatics and Information Technologies
Все специальности секций 1, 2 и 3
Detecting depression from text: A gender based comparative approach using Machine learning and BERT embeddings
NR TSU, TomskDepression is a grave medical issue experienced by numerous individuals globally, leading to a continuous decline in one's mood and significantly impacting their emotions. This article explores the use of machine learning and BERT embeddings for detecting depression from text data and gender variable. We compare the performance of different machine learning algorithms, including logistic regression, support vector machines, and random forests, on a benchmark dataset of DAIC_WOZ. We also experiment with BERT embeddings, a pre-trained language model that can encode the meaning of text, as input to these models. We found that including gender information as a feature significantly improves the performance of the models. Specifically, logistic regression and random forests show higher accuracy in detecting depression when gender information is included. These findings suggest that BERT embeddings and gender information can be effective tools for detecting depression from text and highlight the potential of machine learning for mental health research with consideration of gender differences. Our proposed approach outperforms the state-of-the-art methods and we show them by comparing the root mean squared error (RMSE) and mean absolute error (MAE).
V.D. Moskalenko, D.A. Frolova, D.A. Pidotova
Research of the gain of silicon photomultipliers in a temperature chamber at various voltages.
NR TSU, TomskThe results of the research of the gain for a series of silicon photomultipliers are presented. A model for research the characteristics of photodetectors in a temperature chamber was assembled. The amplification factors of the samples were determined at voltages 38 – 42 V and temperatures from -20 to +20 °C. The recommended operating conditions for photodetector samples were revealed.
Influence of an impurity introduced into a nonlinear ZnGeP2 crystal on its optical properties
NR TSU, TomskThe paper presents the results of studying the effects of post-growth treatments on the radiation resistance of ZGP single crystals. The effect of the defect structure and parameters of antireflection interference coatings on the optical breakdown threshold of ZGP.
UV radiation photodetectors based on Ga2O3/ZnGeP2 structures
NR TSU, TomskThe paper presents the results of studies of the electrical and photoelectric characteristics of the Ga2O3/ZnGeP2 structure. These structures exhibit the properties of ultraviolet radiation detectors and are capable of operating in the photovoltaic mode. Open-circuit voltages and short-circuit current under deep ultraviolet exposure were determined.
NR TSU, TomskThis report presents the advantages of the method used to create a hidden information transmission channel. Encrypting data has been the most popular approach for protecting information but this protection can be broken with enough computational power. An alternate approach that problem is a method that is often called data hiding or steganography.
A.S. Sokolov, O.I. Kukenov
Investigation of the Bimodal Character of RHEED Intensity Oscillations during Homoepitaxial Growth of Si/Si(100)
NR TSU, TomskInvestigation of the dependence of the nature of intensity oscillations and the nature of structure growth on the substrate surface on its temperature.
Generation and propagation of perfect vortex beams in artificial convective turbulence
NR TSU, TomskThe report considers the formation principles of perfect vortex beams. The results of the experiment on their propagation in an artificial convective turbulent medium are presented. The random walks of vortex beams are compared and it is shown that the amplitude of random deviations of propagation of a vortex beams does not depend on the topological charge.
Effect of ion implantation on the gas sensitive properties of ɛ-Ga2O3
NR TSU, TomskThe effect of Si+ ion implantation on the gas-sensitive properties of ɛ-Ga2O3 grown by halide vapor phase epitaxy has been studied. It has been established that samples irradiated with a dose of 8∙1014–8∙1015 cm-2 at an energy of 100 keV without post-implantation annealing, and samples irradiated with a dose of 8∙1015 cm-2 followed by post-implantation annealing, increase the response of α-Ga2O3 films to the action of H2 at low temperatures 100-200 ºС.
Promising organic compounds for use in organic light-emitting diodes
NR TSU, TomskResearch of chemical compounds from the family of dibenzosulfones synthesized at the Institute of Chemical Physics in Chernogolovka is presented. Spectral luminescent properties were studied in chloroform and ethanol solutions, TVO films at room temperature and a gradual decrease in temperature to the temperature of liquid nitrogen. From the positions of the maxima of the phosphorescence and fluorescence spectra, the magnitude of the delta E energy gap between S1 and T1 levels is determined. All molecules detect thermally activated delayed fluorescence (TADF) both in solutions and in films obtained by thermal vacuum deposition (TVO).
Efficiency evaluation of the creation of sodium laser guide stars for observatories of the Russian Federation
NR TSU, TomskAtmospheric conditions have a serious impact on the quality of ground-based astronomical observations. Random inhomogeneities of the refractive index due to turbulent motion in the atmosphere cause effects such as scintillation, jitter, and degradation of the optical images. Adaptive optics (AO) systems with a laser guide star (LGS), which is created in the mesosphere, are designed to eliminate these negative effects. LGS as a guide source is currently widely used in foreign large-aperture astronomical telescopes. In Russian observatories LGS is not used. Therefore, knowledge about the parameters of the sodium layer of the mesosphere is necessary. In this work the results of analytical and numerical calculations are reported. The estimation of sodium column density and height peak of sodium mesospheric layer for large Russian Observatories the telescopes of which can potentially be equipped with AO systems with LGS are presented also.
Modeling the detection of electromagnetic field sources using time reversal in Maxwell's equations
NR TSU, TomskThe paper presents the results of numerical model of the solution of the direct and inverse problem of the propagation of electromagnetic waves in an inhomogeneous medium. The numerical model is implemented by the finite difference time domain method. The reverse propagation of waves is realized by representing the measurement area as a radiation area with a reverse time course.
D.S. Dilla, E.V. Pustovalov
Science intensive analysis of amorphous alloys atomic structure
FEFU, VladivostokAmorphous materials lack the kind of crystalline structure that is common in solid materials. Today, researchers are looking for an alternative way to understand the atomic structure and physicochemical properties of amorphous alloys than the approach used for crystals. Atomic-scale simulations are a vital part of modern research into materials and the atomic structure of amorphous alloys. By understanding the properties and atomic structure of these materials, we can develop new materials and improve our understanding of how these materials behave. This article discusses a lesser-known perspective on the study of atomic structure and physicochemical properties of amorphous alloys in order to better understand the materials and their properties. It also outlines the event-driven dynamics algorithm's application in sequential and parallel programming to investigate the macroscale atomic structure and physicochemical characteristics of amorphous alloys. Further, a cluster analysis of computational experiment findings is also performed to explore the atomic structure and physicochemical properties of amorphous alloys. Finally, it exhibits the results of statistical analysis as well as the conclusions of science intense investigation of the atomic structure of amorphous alloys.
Effective Field Theories for Physics Beyond the Standard Model at ATLAS CERN
NR TSU, TomskThe overview of effective field theory in regards to electroweak interactions is given. The basis used for the research at ATLAS is outlined and the selection of each of the effective lagrangian operators is explained. The prospects of utilizing effective field theory for the description of anomalous gauge couplings are discussed. As an example, previous results of effective field theory application for the similar research in ATLAS collaboration are presented.
Fabricating flexible conductive structures by printing techniques and printable conductive materials
NR TSU, TomskThe printing techniques for fabricating flexible conductive structures are considered. The report presents an overview of printed conductive materials for fabricating flexible conductive structures. Synergistic effects are analyzed for the flexible conducting structures fabrication, which would provide a valuable reference for constructing flexible electronics.
NR TSU, TomskThe prospects for the use of memristors are analyzed. The report presents a classification and construction of memristors. The advantages and disadvantages of the memristor as one of the basic passive elements in radiophysics are considered.
NR TSU, TomskPopular science report. Basic theory of non-linear junction detection is introduced. Possible applications of non-linear junction detectors are described. Innovative approach to search for radio-controlled explosive devices is proposed.
NR TSU, TomskThis report presents an analysis of the current state and potential applications of quantum computers. The technology behind these devices is discussed, along with their unique capabilities and limitations. The advantages of quantum computing over classical computing, as well as the challenges that scientists and engineers face in developing this technology are considered.
Neural Networks and How It works
NR TSU, TomskThe report presents the history of the creation and application of Neural Networks. The basic concepts in the field of Neural Networks are given. The relevance of Neural Networks at the moment and the prospects for development in the future are analyzed.
Диплом I степени
Сабанова Ирина Олеговна за доклад «Modeling the detection of electromagnetic field sources using time reversal in Maxwell's equations» (НИ ТГУ, г. Томск)
Неда Фироз за доклад «Detecting depression from text: A gender based comparative approach using Machine learning and BERT embeddings» (НИ ТГУ, г. Томск)
Диплом II степени
Багреев Глеб Анатольевич за доклад «Effective Field Theories for Physics Beyond the Standard Model at ATLAS CERN» (НИ ТГУ, г. Томск)
Димов Максим Андреевич за доклад «Counter-terrorists win» (НИ ТГУ, г. Томск)
Диплом III степени
Олейник Марина Алексеевна за доклад «Steganography» (НИ ТГУ, г. Томск)
Абдулхамидов Шавкатбек Шухратбек угли за доклад «Quantum Computers» (НИ ТГУ, г. Томск)