MOHSEN ANVARI

2- Custom Peripheral Driver Development for STM32F446RE: I2C, SPI, GPIO and USART

View GitHub Repository | README

This project uses the STM32F446RE microcontroller to interface with the DS1307 Tiny RTC module over I2C and display real-time data on a 16x2 LCD. It showcases my expertise in developing custom drivers for I2C, SPI, GPIO, and USART on the STM32F446RE. The project highlights how to handle real-time clock functionality using the DS1307 RTC and manage periodic updates via the SysTick timer.

Technologies: STM32F446RE Driver Development | I2C | SPI | GPIO | USART

4- Clock Alarm Application (UML HSM Project) 

View GitHub Repository | README

This project implements a clock alarm application using a hierarchical state machine (HSM) modeled with QM and programmed in C++ for an Arduino board. 

Technologies: HSM | UML | C++ | State-Driven Design | QM Modeling Tool | RTC

1- Real-Time Multi-Channel ECG Monitoring and Signal Processing Software 

This advanced LabVIEW-based application enables real-time acquisition and visualization of six-channel ECG signals via a serial port interface. The software automatically detects the active communication port, reads and formats incoming data, and displays synchronized ECG waveforms. Users can enhance signal clarity using a configurable moving average filter, adjusting the filter length dynamically to observe real-time effects. Additionally, it features a data logging capability, allowing seamless storage of ECG data for offline analysis. This solution is ideal for biomedical research and medical device prototyping, offering robust, real-time signal processing and customization options. 

3- Real-Time Single-Channel EEG Recording with Alpha Wave Detection and Frequency Analysis 

This LabVIEW-based software captures and displays single-channel EEG signals in real-time through a serial port interface, automatically detecting and configuring the communication port for seamless data acquisition. Users can apply a dynamic moving average filter, adjusting its length to enhance signal clarity while monitoring brain activity. A key feature of the software is its ability to perform alpha wave detection through guided mental tasks. It records EEG data for one minute during both cognitive activity (eyes open, thinking) and relaxation (eyes closed), computes the Fast Fourier Transform (FFT) of both signals and visualizes frequency-domain results for alpha wave identification. The software also includes data logging for later analysis, making it a robust tool for neuroscience research and biofeedback training. 

Patent: a non-invasive, cuff-less arterial blood pressure monitoring system using machine learning

Hypertension or high blood pressure (BP) is one of the most common worldwide diseases leading to heart attack or stroke. Continuous assessment of blood pressure levels is key to diagnosing hypertension. In this study, we designed and tested a dedicated cuff-less monitoring system that estimates BP levels without calibration. We obtained continuous measurements from 40 healthy subjects (30 males and 10 females) ranging from 20–30 years old. Our measurement protocol consisted of 15 minutes of simultaneous ECG and PPG within three sessions, i.e. rest, bicycle exercise, and recovery. From ECG and PPG signals, we obtained 34 candidate features from which up to 9 were selected to estimate systolic and diastolic BP levels. We validate our results with three regression models: linear regression, support vector machines (SVM) regression, and multilayer perceptron (MLP) to obtain the best results. The study provides a promising approach for modern cuff-less BP monitoring devices

pdf | Published Paper

English Language Proficiency: Certified by IELTS Academic 

pdf 

CV | E-Mail | LinkedIn | GitHub

 MOHSEN ANVARI