Author name: NewGen IEDC BNMIT

There are 3 stages of our project: POSE DETECTION: In this stage of the project, we confirm if the user is performing the pose or not using a deep learning model which is 95% accurate. The model treats pose detection as a classification problem and has two outputs i.e., the user is performing a selected pose and the user is not performing the selected pose. If the output is negative, the program does not proceed further and it has to start from the beginning. POSE ESTIMATION: A computer vision technique that predicts and tracks the location of a person or object. This is done by looking at the orientation and combination of the pose. Pose estimation for our project is done by using MediaPipe which outputs a set of 33 keypoints on the user. This is typically done by identifying, locating, and tracking a number of key points on a given person, these key points represent important joints like an elbow or knee. POSE CORRECTION : In this stage of the project we find the angles of the various joints involved by using keypoints and compare it with standard angles for the given pose. The accuracy before correction is calculated using the two i.e, deviation and standard angles. The area of correction is then identified and conveyed to the user and also corrections to be made to the pose is given quantitatively to the user. This system can be implemented on any embedded device or an android app to guide a person to go through the positions of a yoga exercise by estimating the position of limbs, compare it with a reference model and voice assistant tells the user about the correctness of the asana.

We all encounter small accidents and injuries in our daily lives. Often, people fall sick with the change in season, particularly elderly people. Is it feasible and necessary to run to a doctor every time for a simple flu or an injury? We would say ‘NO’. But some measures have to be taken to treat these basic injuries and flu and identify its severity. To deal with this problem, we have come up with an innovative solution of a bot which will help people to get all the first aid help they need and also get information about the probability of the diseases they might have. In this era, health monitoring devices are the need of the hour as there is an increase in diseases of different kinds. For certain diseases people have to visit the doctor as soon as possible and take treatment to stop it or slowdown from making more severe damage. Conventionally when people fall sick, they try to be the doctor themselves and ignore their issue by swallowing few tablets to get rid of the ailment for the time being. To help people to get timely and proper diagnosis and help them to take more care about their health, we propose the idea of a health aid device.

The preictal state is very useful for seizure prediction, as it starts few minutes before the seizure. The aim of this project is to predict epileptic seizure by detecting the start of preictal state’s sufficient time before the ictal state or onset of seizure starts. Early prediction helps patients, as medication can be done by the doctors to prevent the seizure. This project aims at providing cost-effective solution for predicting and monitoring Seizure Onset with Electroencephalogram data. The concept of Machine Learning is implemented fore predicting the onset of seizure before in hand. A neural network is implemented to predict the EEG signals received by the sensors. It has two hidden layers for prediction. This neural network has an accuracy up to 97%, which is good, effective neural network to predict an occurring seizure. The Arduino Mega 2560 is used for process the signals received by the sensors. EEG sensors, pulse sensor, and temperature sensor are used to measure EEG signals, heart rate and the body temperature of the patient. Analog signals are received by the sensors and given to Arduino Mega 2560 for digitization using built-in A-D converter. These digital signals are recorded for future use. They are now given to the neural network for prediction of the seizure of the patient. If there is a prediction of seizure, the patient can refrain themselves from doing any work that might cause harm to them such as swimming or driving. This system gives almost accurate results in predicting seizures and is patient specific results based on their history. The reports are analyzed to keep the patient safe and healthy.