minedICE: A Knowledge Discovery Platform for Neurophysiological Artificial Intelligence
In this paper we present the minedICE TM computer architecture and network comprised of neurological instruments and artificial intelligence (AI) agents. It’s called minedICE because data that is “mined” via IntraCortical Electroencephalography (ICE) located deep inside the human brain procures (mined) knowledge to a Decision Support System (DSS) that is read by a neurosurgeon located either at the bedside of the patient or at a geospatially remote location. The DSS system 1) alerts the neurosurgeon when a severe neurological event is occurring in the patient and 2) identifies the severe neurological event. The neurosurgeon may choose to provide feedback to the AI agent which controls the confidence level of the association rules and thereby teaches the learning component of minedICE.
Unable to display preview. Download preview PDF.
- 1.Lewis, R., Raś, Z.: Rules for Processing and Manipulating Scalar Music Theory. In: Proceedings of the International Conference on Multimedia and Ubiquitous Engineering, MUE 2007, April 26-28, pp. 819–824. IEEE Computer Society, Los Alamitos (2007)Google Scholar
- 3.Lewis, R., Kalita, J., Sarmah, S., Bhattacharyya, D.: Music Industry Scalar Analysis Using Unsupervised Fourier Feature Selection. In: Proceedings of IIS 2009, Recent Advances in Intelligent Information Systems, Krakow, Poland, June 15-18, pp. 562–571 (2009)Google Scholar
- 4.Lewis, R., Parks, B., Shmueli, D., White, A.M.: Deterministic Finite Automata in the Detection of Epileptogenesis in a Noisy Domain. In: Proceedings of the Joint Venture of the 18th International Conference Intelligent Information Systems (IIS) and the 25th International Conference on Artificial Intelligence, Siedlce, Poland, June 8-10, pp. 207–218 (2010)Google Scholar
- 5.Lewis, R., Parks, B., White, A.M.: Determination of Epileptic Seizure Onset From EEG Data Using Spectral Analysis and Discrete Finite Automata. In: Proceedings of the 2010 IEEE International Conference on Granular Computing, Silicon Valley, August 14-16, page will appear (2010)Google Scholar
- 6.Lewis, R., Parks, B., White, A.M.: Discrete Finite Automata and KDD for Mining EEG Spikes and Seizures. In: Proceedings of XVIIth International Conference on Systems Science, Warsaw, Poland, September 14-16 (2010) (will appear)Google Scholar
- 7.Lewis, R., White, A.M.: Multimodal Spectral Analysis and Discrete Finite Automata for Detecting Seizures. In: Proceedings of the IEEE/WIC/ACM International Joint Conference on Web Intelligence (WI 2010) and Intelligent Agent Technology, IAT 2010, Toronto, Canada, August 31-September 3 (2010) (will appear)Google Scholar
- 8.Lewis, R., White, A.M.: Seizure Detection Using Sequential and Coincident Power Spectra with Deterministic Finite Automata. In: Proceedings of the International Conference on Bioinformatics and Computational Biology (BIOCOMP), Las Vegas Nevada, July 12-15, vol. II, pp. 481–488 (2010)Google Scholar
- 9.Lewis, R.A., Wieczorkowska, A.: Categorization of Musical Instrument Sounds Based on Numerical Parameters. In:Conceptual Structures: Knowledge Architectures for Smart Applications, in Proceedings of RSEISP LNAI, 15th International Conference on Conceptual Structures, ICCS 2007, vol. 4604, pp. 784–792. Springer, Heidelberg (2007)Google Scholar
- 11.Wieczorkowska, A., Synak, P., Lewis, R., Raś, Z.: Creating Reliable Database for Experiments on Extracting Emotions from Music. In: Proceedings of the IIS 2005 Symposium on Intelligent Information Processing and Web Mining, Advances in Soft Computing, pp. 395–404. Springer, Gdansk (2005)Google Scholar