Integrating Statistical Machine Learning in a Semantic Sensor Web for Proactive Monitoring and Control.

Autor: Adeleke JA; School of Mathematics, Statistics and Computer Science, University of KwaZulu-Natal, Westville Campus, University Road, Durban 3629, South Africa. judeleke@gmail.com.; CSIR Meraka Centre for Artificial Intelligence Research (CAIR), Meiring Naude Road, Brummeria, Pretoria 0001, South Africa. judeleke@gmail.com.; National Space Research and Development Agency, Obasanjo Space Centre, Airport Road, Abuja 900107, Nigeria. judeleke@gmail.com., Moodley D; CSIR Meraka Centre for Artificial Intelligence Research (CAIR), Meiring Naude Road, Brummeria, Pretoria 0001, South Africa. deshen@cs.uct.ac.za.; Department of Computer Science, University of Cape Town, 18 University Avenue, Rondebosch 7701, South Africa. deshen@cs.uct.ac.za., Rens G; School of Mathematics, Statistics and Computer Science, University of KwaZulu-Natal, Westville Campus, University Road, Durban 3629, South Africa. gavinrens@gmail.com.; CSIR Meraka Centre for Artificial Intelligence Research (CAIR), Meiring Naude Road, Brummeria, Pretoria 0001, South Africa. gavinrens@gmail.com., Adewumi AO; School of Mathematics, Statistics and Computer Science, University of KwaZulu-Natal, Westville Campus, University Road, Durban 3629, South Africa. adewumia@ukzn.ac.za.
Jazyk: angličtina
Zdroj: Sensors (Basel, Switzerland) [Sensors (Basel)] 2017 Apr 09; Vol. 17 (4). Date of Electronic Publication: 2017 Apr 09.
DOI: 10.3390/s17040807
Abstrakt: Proactive monitoring and control of our natural and built environments is important in various application scenarios. Semantic Sensor Web technologies have been well researched and used for environmental monitoring applications to expose sensor data for analysis in order to provide responsive actions in situations of interest. While these applications provide quick response to situations, to minimize their unwanted effects, research efforts are still necessary to provide techniques that can anticipate the future to support proactive control, such that unwanted situations can be averted altogether. This study integrates a statistical machine learning based predictive model in a Semantic Sensor Web using stream reasoning. The approach is evaluated in an indoor air quality monitoring case study. A sliding window approach that employs the Multilayer Perceptron model to predict short term PM 2 . 5 pollution situations is integrated into the proactive monitoring and control framework. Results show that the proposed approach can effectively predict short term PM 2 . 5 pollution situations: precision of up to 0.86 and sensitivity of up to 0.85 is achieved over half hour prediction horizons, making it possible for the system to warn occupants or even to autonomously avert the predicted pollution situations within the context of Semantic Sensor Web.
Databáze: MEDLINE