real time

Проаналізовано особливості апаратної реалізації штучних нейронних мереж, вибрано принципи побудови, визначено шляхи підвищення ефективності використання обладнання, розроблено методи синтезу та базові структури нейрокомп’ютерних систем реального часу.

Features of hardware representation of artificial neural networks were analyzed, principles of construction were chosen, ways of efficiency increase of equipment use were determined, methods of synthesis and base structures of the neural computing, , real-time systems were developed.

As a result of the analytical review, it was established that the family of Yolo models is a promising area of search and recognition of objects. However, existing implementations do not support the ability to run the model on the iOS platform. To achieve these goals, a comprehensive scalable conversion system has been developed to improve the recognition accuracy of arbitrary models based on the Docker system. The method of improvement is to add a layer with the Mish activation function to the original model. The method of conversion is to quickly convert any Yolo model to CoreML format.

It is shown that for the pro­ces­sing of in­tensi­ve da­ta flows in in­dustry (ma­na­ge­ment of techno­lo­gi­cal pro­ces­ses and complex ob­jects), energy (op­ti­mi­za­ti­on of lo­ad in po­wer grids), mi­li­tary af­fa­irs (techni­cal vi­si­on, mo­bi­le ro­bot traf­fic control, cryptog­raphic da­ta pro­tec­ti­on), transport (traf­fic ma­na­ge­ment and en­gi­ne), me­di­ci­ne (di­se­ase di­ag­no­sis) and instru­men­ta­ti­on (pat­tern re­cog­ni­ti­on and control op­ti­mi­za­ti­on) the re­al-ti­me hardwa­re neu­ral net­works with high ef­fi­ci­ency of eq­uipment use sho­uld be appli­ed.

The features of the most common methods and systems for searching and recognizing objects in video are explored. The research shows the feasibility of building search and recognition tools for the iOS platform in real time. The method of functional adaptation of the algorithm of search and recognition of objects to features of video is offered, which consists in processing of video image by smoothing and minimization filters, which reduces the time of search and recognition of objects. The block diagram and algorithm of system functioning were designed.

It is determined that the main tasks for the monitoring of technological processes at an enterprise are the collection, storage, visualization, preliminary analytical and intellectual processing of technological data in real time. The requirements have been formed and the principles of developing a monitoring system for technological processes in the enterprise have been selected, the main ones are modularity, system integration, openness and compatibility.

Design principles of toolkit for characteristics investigation of the digital signal processors generated by Chameleon© C2HDL design tool and implemented to the FPGA of Altera DE1-SoC platform are considered. The structure and organization of toolkit and its components, including the digital signal processor synthesis and implementation in FPGA flow are described. The chain of DSP performance investigation which are generated by the Chameleon© C2HDL design tool using toolkit is formed.

Nowadays, industrial development creates new and more complex processes leading to emergence of specific conditions for use of sensors and therefore specific measurement tasks. These circumstances lead to new requirements both for the methods of measurement and for sensors that implement these methods. Developments in microelectronic technologies and materials science have led to a significant number of types of pressure sensors.

Nowadays the problem of quick-changing non-stationary values measurement is extremely actual in various modern technical systems (parameters control of engine combustion chamber, testing of aerospace complex products, scientific researches etc.). There are sufficiently effective ways of such measurement. However, increase in the speed of such methods is needed urgently. The attempt of finding the new approach to the problem of sensor output signal processing when measuring non-stationary values using the example of non-stationary pressure measurement by piezoresistive sensors is presented.

The requirements for the real-time hardware development have been formed. The principles of such development have been selected.  Consistent flow graphs for sorting algorithms by merging data sets have been created. The hardware for sorting data with the high efficiency of equipment usage has been synthesized.