вбудовані системи

This paper presents a hybrid approach to traffic sign recognition that combines classical preprocessing techniques (color segmentation, contour detection, Haar Cascade, and HOG) with a lightweight Convolutional Neural Network (CNN) for classification. The proposed method reduces the amount of processed image data by a factor of 10–20, as only preselected regions of interest are passed to the neural network.

This paper examines the structure and functional capabilities of the programmable embedded system for adaptive acoustics parameter research – AMES (Acoustic Measurement Embedded System). The core implementation platform is the PSoC 5 LP programmable system-on-chip, which provides extensive software control over acoustic parameter measurement processes. A mixed-signal conversion method based on selective charge amplification is proposed, enhancing noise immunity and measurement accuracy.

The article analyzes the methods and tools for designing embedded Internet of Things (IoT) systems. The main stages of developing IoT systems are considered, the main design approaches are compared, and their advantages and limitations are identified. The analysis of hardware platforms, their characteristics, performance, energy efficiency, and applications in various fields is conducted. Considered Software tools and their effectiveness in developing IoT solutions.