Issue No. 02 - Feb. (2013 vol. 35)
Fei Wang , IBM T.J. Watson Res. Center, Hawthorne, NY, USA
Noah Lee , Dept. of Biomed. Eng., Columbia Univ., New York, NY, USA
Jianying Hu , IBM T.J. Watson Res. Center, Hawthorne, NY, USA
Jimeng Sun , IBM T.J. Watson Res. Center, Hawthorne, NY, USA
S. Ebadollahi , IBM T.J. Watson Res. Center, Hawthorne, NY, USA
A. F. Laine , Dept. of Biomed. Eng., Columbia Univ., New York, NY, USA
This paper proposes a novel temporal knowledge representation and learning framework to perform large-scale temporal signature mining of longitudinal heterogeneous event data. The framework enables the representation, extraction, and mining of high-order latent event structure and relationships within single and multiple event sequences. The proposed knowledge representation maps the heterogeneous event sequences to a geometric image by encoding events as a structured spatial-temporal shape process. We present a doubly constrained convolutional sparse coding framework that learns interpretable and shift-invariant latent temporal event signatures. We show how to cope with the sparsity in the data as well as in the latent factor model by inducing a double sparsity constraint on the β-divergence to learn an overcomplete sparse latent factor model. A novel stochastic optimization scheme performs large-scale incremental learning of group-specific temporal event signatures. We validate the framework on synthetic data and on an electronic health record dataset.
Convolution, Sparse matrices, Knowledge representation, Data mining, Complexity theory, Approximation methods, Convergence
Fei Wang, N. Lee, Jianying Hu, Jimeng Sun, S. Ebadollahi and A. F. Laine, "A Framework for Mining Signatures from Event Sequences and Its Applications in Healthcare Data," in IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 35, no. 2, pp. 272-285, 2013.