Data analysis in the intelligent building environment

Kriksciuniene, D., Pitner, T., Kucera, A., & Sakalauskas, V. (2014). IJCSA, 11(1), 1-17.

This article addresses the problem of intelligent facility management by gathering and evaluating data from heterogeneous sources, such as automation sensors, weather services and schedule tables. Viscovery SOMine is used to condense the various room and weather data at Masaryk University Brno, Czech Republic, into meaningful clusters.

Understanding the relationship between scheduling problem structure and heuristic performance using knowledge discovery

Smith-Miles, K., James, R., Giffin, J., & Tu, Y. (2009). Learning and Intelligent Optimization, LION, 3.

The relationship between problem structure and optimal processing schedule on a single machine is analyzed. For this purpose, 75 000 generic instances, characterized by the number of jobs, individual processing times and due dates, are clustered with Viscovery SOMine and additionally analyzed with a decision tree.

Intelligent web traffic mining and analysis

Wang, X., Abraham, A., & Smith, K. A. (2005). Journal of Network and Computer Applications, 28(2), 147-165.

Viscovery SOMine is used to generate cluster information for pattern analysis in combination with a fuzzy inference system to capture the chaotic trend to provide short-term (hourly) and long-term (daily) Web-traffic trend predictions. Empirical results demonstrated that the approach is efficient for mining and predicting Web-server traffic and could be extended to other Web environments as well.

Analysis of performance metrics from a database management system using Kohonen’s self organizing maps

Fernandez, C. L., Jimenez, J. T., Martinez, M. R., & Gomez, C. C. (2003). WSEAS Transactions on Systems, 2(3), 629-634.

This article analyzes the performance of 10 000 different SQL statements in an experiment with Oracle 8.1.7 on a Windows NT system. The statements are clustered according to different performance metrics with Viscovery SOMine.

Improved web searching through neural network based index generation

Wang, X., Alahakoon, D., & Smith, K. A. (2003, June). In International Conference on Computational Science (pp. 151-158). Springer, Berlin, Heidelberg.

Self-organizing maps are used for clustering query logs to identify prominent groups of user query terms for further analysis. Such groups can provide meaningful information regarding web users’ search interests. Identified clusters can further be used for developing an adaptive indexing database for improving conventional search engine efficiency. The proposed hybrid model, which combines neural networks and indexing for web search applications, can provide better data filtering effectiveness and efficiently adapt to changes based on the web searchers’ interests or behavior patterns.