Artem Kramov

Artem Kramov, Olexandr Bauzha

An implementation of the remote pulse monitoring system which allows observing of the patient's pulse in a real-time mode via browser is offered in this work. The result of the work is the development of the complex system, which contains the hardware components for the pulse measurement and the software component for the data processing and visualization in a web-interface. The web-interface provides the heart rate visualization in real-time mode and informs the appropriate person in case of deviation from pulse limits. The monitoring system can detect two disease types: tachycardia and bradycardia. A pulse sensor detects the heartbeat moment and functions like a plethysmograph. The microcontroller ATmega8 is used to read data from the sensor, to analyze information, and pass it to the next hardware block. Arduino Uno and Ethernet module ENC28J60 are used to transform the information about the heartbeat event to the web interface. Ethernet module ENC28J60 is connected to Arduino Uno using the SPI interface. The pair of Bluetooth modules HC-05 is used to connect ATmega8 and Arduino Uno with each other. The module HC-05 is connected to both microcontrollers using the UART interface. The WebSocket protocol is used to implement the real-time data demonstration in the web-interface. The web-interface is adapted to mobile devices therefore it can be viewed from smartphones and tablets. The complex can be used both by the qualified specialist for the remote monitoring of the patient's state and as a personal prophylactic

Artem Kramov

Different state-of-the-art methods of the detection of schizophrenia symptoms based on the estimation of text coherence have been analyzed. The analysis of a text at the level of phrases has been suggested. The method based on the graph of the consistency of phrases has been proposed to evaluate the semantic coherence and the cohesion of a text. The semantic coherence, cohesion, and other linguistic features (lexical diversity, lexical density) have been taken into account to form feature vectors for the training of a model-classifier. The training of the classifier has been performed on the set of English-language interviews. According to the retrieved results, the impact of each feature on the output of the model has been analyzed. The results obtained can indicate that the proposed method based on the graph of the consistency of phrases may be used in the different tasks of the detection of mental illness.