Title: Knowledge discovery of tourist subjective data in smartphone-based participatory sensing system by interactive growing hierarchical SOM and C4.5

Authors: Takumi Ichimura; Shin Kamada; Kosuke Kato

Addresses: Faculty of Management and Information Systems, Prefectural University of Hiroshima, 1-1-71, Ujina-Higashi, Minami-ku, Hiroshima 731-8558, Japan. ' Faculty of Management and Information Systems, Prefectural University of Hiroshima, 1-1-71, Ujina-Higashi, Minami-ku, Hiroshima 731-8558, Japan. ' Faculty of Applied Information Science, Hiroshima Institute of Technology, 2-1-1 Miyake, Saeki-ku, Hiroshima 731-5193, Japan

Abstract: A self organising map (SOM) is trained using unsupervised learning to produce a two-dimensional discretised representation of input space of the training cases. Growing hierarchical SOM is an architecture which grows both in a hierarchical way representing the structure of data distribution and in a horizontal way representing the size of each individual maps. The control method of the growing degree by pruning off the redundant branch of hierarchy in SOM has been proposed and the criteria were designed by the adjustment of parameter settings according to a quantisation error and the size of map. Moreover, the interface tool for the proposed method called the interactive GHSOM has been developed. The interactive GHSOM can determine the knowledge of classification from the hierarchy of structure. A smartphone-based tourist participatory sensing system has been developed in Android smartphone. The system can collect tourist subjective data which includes jpeg files with GPS, geographic location name, the evaluation, and comments written in natural language at sightseeing spot. In this paper, we classified the subjective data by interactive GHSOM and extracted the rules by C4.5. After the interactive GHSOM implementation, the structure of the extracted rules became a lucid expression.

Keywords: self organising map; growing hierarchical SOM; interactive GHSOM; mobile phones; cell phones; smartphones; participatory sensing; MPPS; classification; knowledge discovery; C4.5; tourist informatics; unsupervised learning; training; tourism; tourist data; subjective data; jpeg files; GPS; geographic location; natural language; sightseeing spots.

DOI: 10.1504/IJKWI.2012.050283

International Journal of Knowledge and Web Intelligence, 2012 Vol.3 No.2, pp.110 - 129

Published online: 04 Sep 2014 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article