Find a project you can actually build
Working IoT, AI/ML and embedded builds with abstracts, component lists, documentation, and developer support — ready for your final-year submission.
Real-Time ECG Signal Acquisition and Anomaly Detection Using BioAmp EXG and Machine Learning
Cardiovascular diseases remain one of the leading causes of death globally, highlighting the urgent need for accessible, continuous, and intelligent health monitoring systems. This project proposes a real-time, low-cost electrocardiogram (ECG) monitoring and classification system using the BioAmp EXG Pill and machine learning techniques. The system is designed to capture biopotential signals non-invasively from the human body using surface electrodes placed on the chest and limbs. These signals are amplified, filtered, and digitized using a microcontroller (Arduino or ESP32), then transmitted to a host computer for processing. The signal processing pipeline involves noise removal, bandpass filtering, baseline drift correction, and R-peak detection to isolate individual heartbeats. From these beats, essential temporal and morphological features are extracted, including RR intervals, QRS duration, heart rate variability (HRV), and frequency-domain characteristics using Fast Fourier Transform (FFT). These features are used to train and validate supervised machine learning models such as Random Forest, Support Vector Machine (SVM), and K-Nearest Neighbors (KNN) for classifying normal sinus rhythm and various types of cardiac anomalies (e.g., arrhythmias). The experimental results demonstrate the system's capability to accurately differentiate between healthy and abnormal ECG patterns using publicly available datasets (e.g., MIT-BIH Arrhythmia Dataset) for model training and real-time data from the BioAmp EXG for testing. A simple Python-based GUI is also developed to display real-time ECG waveforms along with the classification results, enhancing the system's usability for patients and healthcare providers. The proposed system provides a compact, affordable, and effective solution for personal health monitoring and early detection of cardiovascular issues. It holds great potential for integration into wearable medical devices, remote patient monitoring, and telehealth platforms, making ECG-based diagnostic tools more accessible to rural and underserved populations.
smart agri with wild life and solenoid and npk sensor
Modern agriculture demands smart, scalable, and autonomous solutions to tackle challenges such as crop disease, wildlife intrusion, and inefficient irrigation. This project presents a Smart Agriculture System integrating IoT and Machine Learning (ML) to monitor environmental conditions, detect leaf diseases, and deter wildlife in real time. At the core, an ESP32 microcontroller collects data from a temperature sensor, soil moisture sensor, water level sensor, and other components. A solenoid valve, controlled through a relay, along with a water pump, automates irrigation based on soil conditions. For plant health, an ESP32-CAM, interfaced via a camera converter, captures leaf images which are processed using ML algorithms through a Flask-based web server to identify signs of disease. Wildlife detection is achieved through real-time video analysis, triggering a buzzer, LED light, or servo motor-based deterrent system to scare animals away. A toy-based setup with a container simulates the real-time farm environment, while an external adaptor powers the system for stability. The dashboard offers real-time monitoring, historical logs, and remote actuation features. This solution promotes precision agriculture, resource optimization, and crop protection through intelligent automation.