Research seminar

Multi-sensor hygrothermal data correlation and clustering analysis based on unsupervised learning – An experimental study of Dalarna villa-wooden house in Sweden

Research Seminar in Complex Systems & Microdata Analysis
This event has already passed

but you still can read the text

Date: , kl 10:30 - 12:00
Location: Campus Borlänge
Locale: Dalarna University, Room 331
Presenter: Dr Peng

This presentation focuses on the use of 9 months of temperature and humidity data from five sensors in a wooden house in Dalarna for correlation of temperature, relative humidity and EMC parameters and their clustering analysis based on unsupervised learning.

The purpose of this study is to provide a prediction analysis for the housing environment by exploring the distribution and time series of indoor and outdoor temperature and humidity data. At the same time, the analysis of EMC data helps to assess the service life of building materials.