Analysis of human psychophysiological state based on biomedical signals
Students Name: Stadnyk Andrii Olehovych
Qualification Level: magister
Speciality: Informatively-Instrumentation Technologies in Roboticotekhnic
Institute: Institute of Computer Technologies, Automation and Metrology
Mode of Study: full
Academic Year: 2020-2021 н.р.
Language of Defence: ukrainian
Abstract: The main theme of the work is the analysis of the psychophysical state of man on the basis of his biomedical signals. To solve this problem, it was decided to create an autonomous work to analyze the human condition by collecting and processing its medical records. Indicators such as heart rate, blood oxygen saturation, temperature, hand tremors, visual state of a person’s face, were used to establish not only the physical or psychological state of a person.Pulse, temperature, vibration and camera sensors have been adapted to perform the task in real time. This model has the potential to be used as a control system for health and well-being in businesses, public places, medicine and car assembly, as a precautionary measure in case the driver has symptoms of intoxication, drowsiness, or epileptic seizures. But during a pandemic, as a platform that reveals the main signs of most infectious diseases (fever, trembling hands and low oxygen levels in the body). The Arduino Nano computer computing platform was used to build this system, the main component of which is the ATmega328 microprocessor, adapted for use with a mock-up board. Also a microcomputer or a computer on a Raspberry pi 4 module for calculating data from the camera, the main component of which is a Quad core 64-bit ARM-Cortex A72 processor with a frequency of 1.5GHz. Digital optical pulse and arterial oxygen saturation sensor (saturation) - MAX30102. DS18B20 digital sensor for temperature control. Camera module for Raspberry Pi for image of human face. 3-axis digital accelerometer based on the ADXL345 chip to detect hand shake. OLED display with a diagonal of 0.96 "to show the measurement results on the board. All this is built into the case with the following parameters: 64x95x164mm, which allows to demonstrate the operation of this platform. To work with this microcontroller was written code in programming language C , and for the operation of a microcomputer in Python, to create a neural network, using Open CV libraries and other machine learning tools. The economic analysis is carried out and the economic substantiation of the expenses necessary for performance of research work is carried out. Key words: robot, robotics, sensor, measurement. Arduino, Raspberry Pi, Machine learning, Neural Networks, OpenCV, tensorflow.