Кафедра мікропроцесорних технологій і систем (МТС)
Постійний URI для цієї колекції
Перегляд
Останні подання
- ДокументІнтеграція нейронних мереж у медичні пристрої на основі STM32 для автоматичної діагностики та моніторингу пацієнтів(ХНУРЕ, 2023) Чумак, В. С.This article discusses the technical aspects of integrating neural networks into medical devices based on STM32 microcontrollers. The focus is on the selection and optimization of communication interfaces, the development of software for interacting with neural networks, and the implementation of machine learning algorithms. Technical analysis includes memory management, code optimization, and the use of development tools. Overcoming challenges associated with limited resources ensures the creation of intelligent medical devices with increased diagnostic accuracy and efficiency.
- ДокументДослідження можливості використання алгоритму Прюіт для обробки медичних зображень(ХНУРЕ, 2023) Дерюга, І. М.; Чумак, В. С.In the context of rapid advancements in medical technologies and the increasing utilization of digital technologies in the healthcare sector, addressing challenges in medical image processing becomes crucial. Computational methods for analyzing boundaries in images obtained from various scanning devices have garnered particular interest. This article explores the application of the Pruitt algorithm for detecting boundaries in medical images. The use of FPGA is proposed for implementing this algorithm to optimize productivity and real-time image processing speed. Experimental results underscore the importance of further research and refinement of medical image processing algorithms to achieve improved accuracy and efficiency in diagnostics.
- ДокументОгляд пристрою KRIA KV260 VISION AI для інтелектуального машинного бачення(ХНУРЕ, 2023) Столовий, І. В.; Білоцерківець, О. Г.Deep Learning (DL) has revolutionized research and development. A couple of problems are that DL requires a lot of power and can be slow. Programmable gate arrays (FPGAs) are excellent candidates for implementing DL algorithms and solutions because they are configurable and offer low latency and low power consumption. Additionally, the versatile FPGA architecture allows users to design application-specific hardware instead of using general-purpose hardware in the processor. An example of these solutions is the Xilinx Kria KV260 Vision AI (KV260) FPGA board. This board contains numerous accelerated programs for performing DL using live camera feed.
- ДокументВикористання ESP-EYE для пошуку речей з залученням AI та функції активації голосом(ХНУРЕ, 2023) Білоцерківець, О. Г.; Воргуль, О. В.The application of AI allows the ESP-EYE board to recognize objects and determine their placement in images, potentially allowing you to quickly and efficiently find the desired objects or things. In addition, with the voice activation function, ESP-EYE can respond to commands received through a summoned AI assistant or other voice interface. This system under investigation could find applications in a variety of areas, including home smart home, office automation, and other scenarios where object detection and voice activation can be useful.
- ДокументРеалізація цифрових фільтрів на мікроконтролерах STM32 з використанням кільцевих буферів(ХНУРЕ, 2023) Зубков, О. В.; Яковенко, О. С.The analysis of digital filters in electronics and their software implementation on general-purpose microcontrollers was completed in this work. A real-time digital filtering algorithm has been developed for STM32 microcontrollers with support for DSP instructions and the use of ring buffers. A study of the proposed algorithm performance was carried out using the example a digital low-pass filter with a finite impulse response implementation. A comparative analysis of performance measurement results and comparisons with the results of using the standard library proved the effectiveness of the proposed algorithm.