About The Project
How The Model Works
In this mode, A Machine Learning model (Sensor Model) will give an evaluated score of the task using a file (contained the data/reading from seneors all over the house). For demo purpose, the model used a file on the server to make prediction. Our model use this data to train and test the model performance. In the evaluate phase, the model achieved 60% accuracy. The prediction is not an medical diagnosis, it just remind user to pay attention to health status.
The Algorithm
We use XGBoost model to implement the machine learning model. XGBoost is a decision-tree-based ensemble Machine Learning algorithm that uses a gradient boosting framework. In prediction problems involving unstructured data (images, text, etc.), artificial Neural Networks tend to outperform all other algorithms. However, when it comes to small-to-medium data, decision tree based algorithms are considered best-in-class right now.