LSPEnv: location-based service provider for environmental data

Abstract

Abstract. This paper presents an approach for forecasting environmental data for location based services. The environment becomes a very important issue and especially people with health problems need more information and support in their daily life. In this work we propose a system for making predictions for spatial-temporal variables using the Bayesian Network method as a machine learning. To handle the missing values in our data we use the Structural Expectation Maximization Algorithm. The architecture of our system is based on a three-tier architecture which assists the distribution of the evaluation process. The case study is based on real environmental data from the Swiss national network. The provided data represent different types of location, e.g. rural, urban, etc. and are taken in different time. The results can be presented on a mobile device, in Internet and to any mobile user.