Multivariate Time Series Classification for Human Activity Recognition with LSTM
Human Activity Recognition UCI Dataset, final score 0.97196
A Machine Learning approach to predict the activities of person.
Реализация методов обнаружения точек изменений и кластеризация для поиска подтипов активностей
This Human Activity Recogisition analyses human activity patterns using smartphone sensor data from the UCI Human Activity Recognition dataset. It involves outlier detection, correlation analysis, and structural graph analysis. DBSCAN clustering is applied, followed by LDA for dimensionality reduction, to visualise and interpret activity clusters
Add a description, image, and links to the human-activity-monitor topic page so that developers can more easily learn about it.
To associate your repository with the human-activity-monitor topic, visit your repo's landing page and select "manage topics."