This paper presents an inexpensive, high-precision, but at the same time, easy-to-maintain PIEEG board to convert a RaspberryPI to a Brain-computer interface. This shield allows measuring and processing eight real-time EEG(Electroencephalography) signals. We used the most popular programming languages-C, C++ and Python to read the signals, recorded by the device. The process of reading EEG signals was demonstrated as completely and clearly as possible. This device can be easily used for machine learning enthusiasts to create projects for controlling robots and mechanical limbs using the power of thought. We will post use cases on GitHub (https://github.com/Ildaron/EEGwithRaspberryPI) for controlling a robotic machine, unmanned aerial vehicle, and more just using the power of thought.
In recent years, neural networks showed unprecedented growth that ultimately influenced dozens of different industries, including signal processing for the electroencephalography (EEG) process. Electroencephalography, although it appeared in the first half of the 20th century, was not changed the physical principles of work to this day. But signal processing technology made significant progress in this area through the use of neural networks. But many different models of neural networks complicate the process of understanding the real situation in this area. This manuscript summarizes the current state of knowledge on this topic, summarizes and describes the most significant achievements in various fields of application of neural networks for processing EEG signals. We discussed in detail the results presented in recent research papers for various fields in which EEG signals have been involved. We also examined in detail the process of extracting features from EEG signals using neural networks. In conclusion, we have provided recommendations for the correct demonstration of research results in manuscripts on the subject of neural networks and EEG.
Prediction of metrological, botanical characteristics is extremely important for different directions in agriculture. The availability of these data allows us to adjust the process of growing crops, which has a huge impact on yield, speed of ripening and the presence of vitamins in the grown culture. Increasing yields due to changes in culture growing conditions without the use of gene mutations and herbicides are the most popular destination in the agriculture field. In this manuscript, a realisation of the neural network for the construct of an efficient autonomous farm was represented. The developed by farm creates the optimal conditions for growing a crop by controlling the following indicators: Illumination, PH of the ground, air temperature, the temperature of the ground, air humidity, CO2 concentration and humidity of the ground. Theoretical research and experimental research on the use of a neural network to predict vegetable growth were represented. The presented model can also be considered as a prototype device for testing various cultivated vegetables to identify the optimal characteristics for them growing.