Otebolaku, AM and Lee, GM (2017) Towards Context Classification and Reasoning in IoT. In: Proceedings of the14th International Conference on Telecommunications (ConTEL) . pp. 145-154. (The 14th International Conference on Telecommunications, Zagreb, Croatia 28-30 June 2017, 28 June 2017 - 30 May 2017, Zagreb, Croatia).

Preview

Text Otebolaku_Lee_2017.pdf - Accepted Version Download (1MB) | Preview

Abstract

Internet of Things (IoT) is the future of ubiquitous and personalised intelligent service delivery. It consists of interconnected, addressable and communicating objects, which are embedded in our environments. To realize this new and promising generation of ubiquitous systems, the IoT's 'smart' objects should be supported with intelligent platforms for data acquisition, preprocessing, classification, modelling, reasoning and inference including context distribution. However, some current IoT systems lack these capabilities: they provide only the functionality for obtaining raw sensor data. In this paper, we propose a framework towards deriving high-level context information from streams of raw IoT sensor data, using artificial neural networks (ANN) as context recognition model. Before building the model, the data was preprocessed using weighted average low-pass filtering and a sliding window with overlapping algorithm. From the resulting windows, statistical features were extracted as vectors, which were used to train the ANN model. Evaluations of the proposed system show that it has between 87.3% and 98.1% accuracies.

Item Type:	Conference or Workshop Item (Paper)
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions:	Computer Science & Mathematics
Publisher:	IEEE
Date Deposited:	16 Jun 2017 10:27
Last Modified:	13 Apr 2022 15:15
URI:	https://researchonline.ljmu.ac.uk/id/eprint/6708

View Item