neural networks

The main purpose of the article is to describe state-of-the-art approaches to speech separation and de- monstrate the structures and challenges of building and training such systems. Designing efficient optimized neural network model for speech recognition requires using encoder-decoder model structure with masks estimation flow. The fully-convolutinoal SuDoRM-Rf model demonst- rates the high efficiency with relatively small number of parameters and can be boosted with accelerators, that supports convolutional operations.

Methods and approaches to computational diagnosis of various pulmonary diseases via automated analysis of chest images performed with computed tomography were reviewed. Google Scholar database was searched with several queries focused on deep learning and machine learning chest computed tomography imagery analysis studies published during or after 2017. A collection of 39 papers was collected after screening the search results. The collection was split by publication date into two separate sets based on the date being prior to or after the start of the COVID-19 pandemic.

Розглядаються питання, пов’язані з розпізнаванням скінченних множин за допомогою двопорогових нейронних елементів. Показано, що задача навчання ДНЕ є NP-повною. Також наведено умови, виконання яких забезпечує двопороговість булевих функцій, які задаються за допомогою списків рішень.

We study finite set dichotomies on bithreshold neurons. We prove that training a BN is NP-complete task. We also give sufficient conditions ensuring that decision list represents a bithreshold function.

The article presents a modern aircraft detection system based on the analysis of sound signals, developed using neural networks and sound analysis algorithms. During the development of the system, the latest technologies were used, such as acoustic sensors, single-board microcomputers and external devices for processing and storing information received from the environment, which ensures fast and accurate detection of aircraft in the air.

Recently, deep learning technologies, namely Neural Networks [1], are attracting more and more attention from businesses and the scientific community, as they help optimize processes and find real solutions to problems much more efficiently and economically than many other approaches. In particular, Neural Networks are well suited for situations when you need to detect objects or look for similar patterns in videos and images, making them relevant in the field of information and measurement technologies in mechatronics and robotics.

With the rapid growth of wind energy production worldwide, the Wind Power Forecast (WPF) will play an increasingly important role in the operation of electricity systems and electricity markets. The article presents an overview of modern methods and tools for forecasting the generation of electricity by wind farms. Particular attention is paid to the intelligent approaches. The article considers the issues of preparation and use of data for such forecasts. It presents the example of a forecasting system based on neural networks, proposed by the authors of the paper.

The article is devoted to the problem of excessive traffic of base station cells. In order to reduce the
impact of this problem on the quality of services of mobile network operators, it is proposed to use
artificial intelligence (AI) technology to analyze and predict the load on the network. AI is great for
wireless environments, as it has a lot of data available for analysis and obtaining certain patterns.
The article proposes a model of machine learning and neural network architecture for forecasting
the load on 5G cells.

The problem of finding objects in images using modern computer vision algorithms has been considered. The description of the main types of algorithms and methods for finding objects based on the use of convolutional neural networks has been given. A comparative analysis and modeling of neural network algorithms to solve the problem of finding objects in images has been conducted. The results of testing neural network models with different architectures on data sets VOC2012 and COCO have been presented.

Data acquisition and processing in cyber-physical system for remote monitoring of the human functional state have been considered in the paper. The data processing steps, strategies for multi-step forecasting evaluation metrics and machine learning algorithms to be implemented have been analysed and described. What is important, this way it will be possible to track the condition of the sick and response to the health changes in advance.