Constrained Tensor Decomposition via Guidance: Increased Inter and Intra-Group Reliability in fMRI Analyses
Recently, Davidson and his colleagues introduced a promising new approach to analyzing functional Magnetic Resonance Imaging (fMRI) that suggested a more appropriate analytic approach is one that views the spatial and temporal activation as a multi-way tensor . In this paper, we illustrate how the use of prior domain knowledge might be incorporated into the deconstruction of the tensor so as to increase analytical reliability. These results will be discussed in reference to implications towards military selection and classification.
KeywordsTensor decomposition Functional magnetic resonance imaging Reliability
This research is supported by Office of Naval Research grant NAVY 00014-09-1-0712. The opinions of the authors do not necessarily reflect those of the United States Navy or the University of California - Davis.
Peter B Walker and Sidney Fooshee are military service members. This work was prepared as part of their official duties. Title 17 U.S.C. 101 defines U.S. Government work as a work prepared by a military service member or employee of the U.S. Government as part of that person’s official duties.
- 1.Walker, P.B., Davidson, I.: Exploring new methodologies for the analysis of functional magnetic resonance imaging (fMRI) following closed-head injuries. In: Schmorrow, D.D., Fidopiastis, C.M. (eds.) FAC 2011. LNCS, vol. 6780, pp. 120–128. Springer, Heidelberg (2011)Google Scholar
- 2.Davidson, I., Gilpin, S., Carmichael, O., Walker, P.: Guided network discovery via constrained tensor analysis of fMRI data. In: KDD 2013 Proceedings of the 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 194–202. ACM, New York (2013)Google Scholar
- 4.Phillips, H.L., Walker, P.B., Kennedy, C.H., Carmichael, O., Davidson, I.N.: Guided learning algorithms: an application of constrained spectral partitioning to functional magnetic resonance imaging (fMRI). In: Schmorrow, D.D., Fidopiastis, C.M. (eds.) AC 2013. LNCS, vol. 8027, pp. 709–716. Springer, Heidelberg (2013)CrossRefGoogle Scholar
- 5.Olson, T.M., Walker, P.B., Phillips IV, H.L.: Assessment and selection of aviators in the US military. In: O’Connor, P.E., Cohn, J.V. (eds.) Human Performance Enhancement in High-Risk Environments: Insights, Developments, and Future Directions from Military Research: Insights, Developments, and Future Directions from Military Research, pp. 37–57. ABC-CLIO, Santa Barbara (2009)Google Scholar
- 7.Graner, J., Oakes, T. R., French, L. M., Riedy, G.: Functional MRI in the investigation of blast-related traumatic brain injury. Front. Neurol. 4 (2013)Google Scholar
- 10.Tan, P.N., Steinbach, M., Kumar, V.: Introduction to Data Mining, 1st edn. Addison-Wesley Longman Publishing Co. Inc., Redwood City (2005)Google Scholar