Abstract
More and more applications nowadays use spatio-temporal data for different purposes. In order to be processed and used efficiently, this unique type of data requires special handling. This paper summarizes methods and approaches for feature selection of spatio-temporal data and machine learning algorithms for spatio-temporal data engineering. Furthermore, it highlights relevant work in specific domains. The range of possible approaches for data processing is quite wide. However, in order to use these approaches with the spatio-temporal data in a meaningful and practical way, individual data processing steps need to be adapted. One of the most important steps is feature engineering.
Highlights
These days, spatio-temporal data are widely used and common
Before we can dive into the data processing part, it is important to take the preprocessing steps into account, especially the feature engineering part
All the methods for feature selection we described in 2 can be applied to spatio-temporal data
Summary
It is often required to process them using machine learning algorithms. Usually machine learning is based on loose feature records which have no relation with each other. If they do, only in one dimension, such as time. Before we can dive into the data processing part, it is important to take the preprocessing steps into account, especially the feature engineering part. New features are extracted from the existing ones during feature extraction This step can involve other data sources. 5, the most important data mining tasks are explored and some examples are given, how they can be implemented using which machine learning. We conclude this paper with a summary and an overview over future work
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have