Technology audit and production reserves

Development of a mathematical model of acoustic processes in the Opera Studio of the Kyiv Conservatory

Valeriia Havrylko — Wed, 04 Dec 2024 00:00:00 +0200

The object of this study is the acoustic characteristics of a concert hall, with a particular focus on the reverberation time, which significantly affects both the perception of sound by listeners and the performance of musicians.

The study emphasises the importance of mathematical modelling of acoustic processes in concert halls, especially in optimising reverberation time. In the context of modern materials and advanced acoustic design technologies, precise calculations and analyses are required to evaluate the impact of various elements on a room’s overall acoustics. Poor design or material selection can result in listener discomfort and reduced sound quality, highlighting the critical role of scientific methods in analysing and modelling acoustic processes under specific conditions.

The research utilised mathematical models developed in MATLAB^® software to calculate reverberation time based on different materials and their surface areas.

The key findings demonstrate that mathematical models can accurately simulate acoustic processes in a room, enabling predictions of acoustic characteristics based on defined parameters. The correlation between theoretical calculations and experimental data confirms that mathematical modelling is an effective tool for improving the acoustic quality of concert halls, considering the use of different materials.

The practical significance of the results lies in the ability to implement recommendations for optimising acoustic conditions in concert halls. The identified parameters can guide the design of spaces for musical events and enhance methods of acoustic design. Applying these findings in practice can improve sound quality, thereby increasing listener comfort and enhancing the overall perception of music.

Analysis of machine learning models for forecasting retail resources

Pavlo Teslenko, Serhii Barskyi — Fri, 22 Nov 2024 00:00:00 +0200

The object of research is the process of forecasting loosely structured data of retail artifacts by means of machine learning.

The paper analyzes data and models for forecasting retail resources. The analysis is carried out for a specific business situation and task, when a large corporation needs a fuller loading of its own warehouses with goods and resources that will be used in future periods for sale or in projects. The task is to reduce overall corporate costs by purchasing the necessary goods/resources in advance. The data required for forecasting, their sources and properties are defined. It is shown that the data will come from different sources, will have a different time interval, categorical component and logistic reference. RNN, LSTM, Random Forest, Gradient Boosting, XGBoost models and forecasting methods were chosen for such data. They were analyzed according to the criteria of data source, time interval, categorization of data, availability of a logistic component, flexibility of tools in working with heterogeneous data, requirements of tools for computing resources, interpretability of modeling results.

Data sources explain where the data for analysis comes from. Usually it is: stores, warehouses, logistics companies, projects and strategic plans of the corporation. The time interval characterizes the frequency and regularity of receiving data for analysis. The criterion "data categorization" characterizes how this type of data affects the quality of the analysis. The logistic parameters of the data also characterize the impact on the analysis. "Flexibility in working with heterogeneous data" shows the ability of the model to effectively work with data of different formats and sources. Requirements for computing resources determine their necessary power for training and operation of the model. Interpretability of a model characterizes its ability to explain how and why it makes specific decisions or predictions based on input data. The more complex the model, the more difficult it is to interpret. In the retail business, interpretability is important for explaining demand forecasts.

Based on the results of the analysis, the XGBoost model was recommended as the best for forecasting retail resources.

Improvement of the process of preparing cargo tanks of crude oil tankers for cargo operations

Mykhaylo Kolegaev, Igor Brazhnik — Thu, 05 Dec 2024 00:00:00 +0200

The object of research is the process of inerting the cargo tank of an oil tanker. Issues related to improving the process of preparing cargo tanks of oil tankers for cargo operations are considered. It is noted that the efficiency of oil tanker operation, in addition to transport operations, is determined by the technologies used during the preparation of the vessel for receiving new cargo. One of such technologies is the inerting cargo tanks, which precedes any cargo operations. The study was aimed at improving the inert flue gas system by using a new technology for supplying jets of inert gas to the cargo tanks of an oil tanker. The main task of the research is to establish the degree of influence of the gas flow parameters (formed by the inert flue gas generator) at the entrance to the cargo tank on the nature of the change in air concentration in the entire volume of the tank. The final result of solving this scientific and applied problem is determined to be a reduction in the inerting time of cargo spaces of oil tankers. During the experiments, the supply of inert gas to the cargo hold was provided according to three technological schemes. The first contained only one jet source with an opening angle of 60°, which was located at the central point of the cargo tank bottom. The second contained four sources of inert gas jets, which were located crosswise on the tank bottom. The nozzles were installed diagonally in the centers of four identical rectangular zones of the tank bottom. Their opening angle to create a conical jet torch was 30°. The number of sources of inert gas jets of the third scheme was five. At the beginning of the inert gas supply process, four sources were used, which were located at the corners of the tank with an opening angle of 30°. When the initial value of the oxygen concentration in the air was reduced by thirty percent, the inert gas was supplied only from the fifth – the central jet source. It used a nozzle that creates a 90° cone opening angle of the jet torch. With the start of operation of the central nozzle, all angular sources of inert gas jets were turned off. It has been proven that this scheme ensures an improvement in the inerting process of an oil tanker, which is reflected in a reduction in the time required for its implementation.

Assessment of the global artificial intelligence market in healthcare

Fri, 06 Dec 2024 00:00:00 +0200

Recently, there has been a significant increase in the use of artificial intelligence in healthcare, an increased trust of healthcare providers in artificial intelligence, and the interest of investors in the development of healthcare solutions based on artificial intelligence. The vast majority of providers of medical services and technologies, as well as of biomedical companies, are using artificial intelligence which confirms the great demand in the field of health care. The increased adoption of artificial intelligence techniques in medical applications has led to the focus of key market participants on new products and technical connections to expand commercial production.

The object of research is the world market of artificial intelligence in healthcare. Factors influencing the market positively and negatively have been identified. The general characteristics are given, as well as key points of the state and development of the market. The market is segmented by geographic regions, applications, therapeutic area support, market components, technologies, and usage. According to the segmentation of the world artificial intelligence market in health care by geographical regions, the largest market share belonged to the segment of the North American region (45 %); by application – to clinical trials segment (22.7 %); by the support of therapeutic areas – to radiology segment (75 %); by artificial intelligence components – to software segment (41 %); by technologies – to machine learning segment (33.1 %); by use – to medical imaging and diagnostics segment (27.1 %).

The main strategic trends and directions of further development of the market of artificial intelligence in health care are provided. The dynamics of the market in terms of growth factors, market opportunities, limitations, and challenges are considered. Important factors inhibiting the development of the artificial intelligence market in the field of health care are the lack of qualified specialists and ineffective cooperation between the public and private sectors.

Data on competitive tech giants and artificial intelligence healthcare powerhouses are provided.