Post Processing Method that Acts on Two-dimensional Clusters of User Data to Produce Dead Bands and Improve Classification

David Adrian Sanders, Alexander Gegov

Abstract

A post processing method is described that acts on two-dimensional clusters of data produced from a data mining system. Dead bands are automatically created that further define the clusters. This was achieved by defining data within the dead bands as NOT belonging to either cluster. The three clusters produced were definitely YES, definitely NO and a new set of DON’T KNOW. The creation of the new set improved the accuracy of decisions made about the data remaining in YES and NO clusters. The introduction of the dead bands was achieved by either setting a radius during the learning process or by setting a straight line boundary. Each radius (or line) was calculated during the learning process by considering the twodimensional position of each of the users within each cluster of dimensions. A radius line (or straight line) was then introduced so that the 80% of users within a particular dimension who were nearest to the origin (or edge) were placed into a set. The other 20% were outside the radius line (or straight line) and not recorded as being part of the set. If the two lines did not overlap, then this sometimes created a dead-band that contained users with less certain results and that in turn increased the accuracy of the other sets. Two case studies are presented as examples of that improvement.

References

  1. Bergasa-Suso, J., Sanders, d., Tewkesbury, G., 2005. Intelligent browser-based systems to assist Internet users. IEEE T EDUC 48 (4), pp. 580-585.
  2. Chester, S., Tewkesbury, G., Sanders, D., et al 2006. New electronic multi-media assessment system. 2nd Int Conf on Web Info Sys and Tech, pp: 424 Year.
  3. Chester, S., Tewkesbury, G., Sanders, D., et al 2007. New electronic multi-media assessment system. Web Info Systems and Technologies 1, pp 414-420.
  4. Felder, R., Soloman, B., 2009. Index of Learning Styles Questionnaire [Online] Available: http://www.engr.ncsu.edu/learningstyles/ilsWeb.html.
  5. Litzinger, T., Lee, S., Wise, J., et al. 2007. A psychometric study of the Index of Learning Styles. J. Eng Ed vol. 96, no. 4, pp 309-319.
  6. Sanders, D. A., 1999. Perception in robotics IND ROBOT 26 (2), pp: 90-92.
  7. Sanders, D. A., 2007. Viewpoint - Force sensing IND ROBOT 34 (4), pp: 268.
  8. Sanders, D. A., 2008a. Controlling the direction of "walkie" type forklifts and pallet jacks on sloping ground. ASSEMBLY AUTOM 28 (4), pp 317-324.
  9. Sanders, D. A., 2008b. Progress in machine intelligence. IND ROBOT 35 (6), pp: 485-487.
  10. Sanders, D. A., 2008c. Environmental sensors and networks of sensor. SENSOR REV 28 (4), pp: 273- 274.
  11. Sanders, D. A., 2009a. Introducing AI into MEMS can lead us to brain-computer interfaces and super-human intelligence. ASSEMBLY AUTOM 29 (4), pp: 309- 312.
  12. Sanders, D. A., 2009b. Recognizing shipbuilding parts using artificial neural networks and Fourier descriptors. P I MECH ENG B-J ENG 223 (3), pp: 337-342.
  13. Sanders, D. A., Bergasa-Suso, J., 2010 Inferring Learning Style From the Way Students Interact With a Computer User Interface and the WWW. IEEE T EDUC 53(4), pp: 613-620.
  14. Sanders, D. A., Haynes, B. P., Tewkesbury, G. E., 1996. The addition of neural networks to the inner feedback path in order to improve on the use of pre-trained feed forward estimators. MATH COMPUT SIMULAT 41 (5-6), pp: 461-472.
  15. Sanders, D. A., Hudson, A. D., 1999. A specific blackboard expert system to simulate and automate the design of high recirculation airlift reactors MATH COMPUT SIMULAT 53 (1-2), pp: 41-65.
  16. Sanders, D., Stott, I., 1999. A new prototype intelligent mobility system to assist powered wheelchair users IND ROBOT 26 (6), pp: 466-475.
  17. Sanders, D., Tan, Y. C., Rogers, I., et al 2009. An expert system for automatic design-for-assembly. ASSEMBLY AUTOM 29 (4), Pages: 378-388.
  18. Sanders, D., Tewkesbury, G., 2009. A pointer device for TFT display screens that determines position by detecting colours on the display using a colour sensor and an Artificial Neural Network. DISPLAYS 30 (2), pp 84-96.
  19. Sanders, D., Urwin-Wright, S., Tewkesbury, G., et al 2005. Pointer device for thin-film transistor and cathode ray tube computer screens. ELECTRON LETT 41 (16), pp 894-896.
  20. Stott, I., Sanders, D., 2000. New powered wheelchair systems for the rehabilitation of some severely disabled users. INT J REHABIL RES 23 (3), pp 149- 153.
  21. Stott I., Sanders, D., Goodwin, M., 1997. A software algorithm for the intelligent mixing of inputs to a teleoperated vehicle. Euromicro Conference 95 in J SYST ARCHITECT 43 (1-5), pp 67-72.
  22. Tewkesbury, G. E., Sanders, D., 1999. A new simulation based robot command library applied to three robots J ROBOTIC SYST 16 (8), pp: 461-469.
Download


Paper Citation


in Harvard Style

Adrian Sanders D. and Gegov A. (2015). Post Processing Method that Acts on Two-dimensional Clusters of User Data to Produce Dead Bands and Improve Classification . In Proceedings of the 11th International Conference on Web Information Systems and Technologies - Volume 1: WEBIST, ISBN 978-989-758-106-9, pages 267-272. DOI: 10.5220/0005473202670272


in Bibtex Style

@conference{webist15,
author={David Adrian Sanders and Alexander Gegov},
title={Post Processing Method that Acts on Two-dimensional Clusters of User Data to Produce Dead Bands and Improve Classification},
booktitle={Proceedings of the 11th International Conference on Web Information Systems and Technologies - Volume 1: WEBIST,},
year={2015},
pages={267-272},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005473202670272},
isbn={978-989-758-106-9},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 11th International Conference on Web Information Systems and Technologies - Volume 1: WEBIST,
TI - Post Processing Method that Acts on Two-dimensional Clusters of User Data to Produce Dead Bands and Improve Classification
SN - 978-989-758-106-9
AU - Adrian Sanders D.
AU - Gegov A.
PY - 2015
SP - 267
EP - 272
DO - 10.5220/0005473202670272