Authors:
Orathai Sangpetch
1
;
Akkarit Sangpetch
1
;
Jittinat Nartnorakij
1
and
Narawan Vejprasitthikul
2
Affiliations:
1
Department of Computer Engineering, Faculty of Engineering, King Mongkut’s Institute of Technology Ladkrabang, 1 Soi Chalongkrung, Ladkrabang, Bangkok, Thailand, CMKL University, 1 Soi Chalongkrung, Ladkrabang, Bangkok and Thailand
;
2
Department of Computer Engineering, Faculty of Engineering, King Mongkut’s Institute of Technology Ladkrabang, 1 Soi Chalongkrung, Ladkrabang, Bangkok and Thailand
Keyword(s):
Data Exchange, API, Interoperability, Machine Learning, Visualization.
Abstract:
As data becomes vital to urban development of modern cities, Thailand has initiated a smart city project on pilot cities around the country. We have implemented an interoperable data platform for smart city to enable Internet of Things (IoT) data exchanges among organizations through APIs. One of the key success is that people can access and visual the data. However, data can have various attributes since standard has not completely established and adopted. Therefore, it is difficult to automate the process to achieve comprehensive visualization. Traditionally, we require developers to manually examine data streams to determine which data attribute should be presented. This process can be very time consuming. The visualization system must be manually updated whenever a source stream modifies its data attributes. This problem becomes an impediment to implement a scalable cloud-based visualization service. To mitigate this challenge, we propose an automated attribute inference approach
to automatically select key visualizable attribute from heterogeneous streams of data sources. We have experimented with different data attribute selection algorithms, namely an empirical rule-based system and the chosen machine learning algorithms. We implement and evaluate the proposed selection algorithms through our 3D visualization program in order to get the feedback from users.
(More)