MFPCA: Multiscale Functional Principal Component Analysis
Authors: Zhenhua Lin, Hongtu Zhu4320-4327
AAAI 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Both theoretically and numerically, we show that MFPCA can capture features on areas of low variance without estimating high-order principal components, leading to overall improvement of performance on dimension reduction for heteroscedastic functional data. The theoretical analysis is complemented by numerical simulation in Section 4. We illustrate the estimation of eigenfunctions φ and projection PΦ via n = 50 and n = 200 simulated samples from a Gaussian process on the interval [0, 1]... We apply multiscale FPCA to analyze the brain microstructure in the corpus callosum of healthy subjects and patients with multiple sclerosis (MS). |
| Researcher Affiliation | Academia | Zhenhua Lin University of California, Davis One Shields Avenue, Davis, CA 95616 linzh@ucdavis.edu Hongtu Zhu University of North Carolina at Chapel Hill Chapel Hill, NC 27599 htzhu@email.unc.edu |
| Pseudocode | Yes | Algorithm 1 (MFPCA). Suppose that X1, . . . , Xn are functional data on a common interval I, either given in the dense form or sparse form. |
| Open Source Code | No | The paper does not provide any explicit statements or links indicating that source code for the described methodology is publicly available. |
| Open Datasets | No | We illustrate the estimation of eigenfunctions φ and projection PΦ via n = 50 and n = 200 simulated samples from a Gaussian process on the interval [0, 1]... The DTI dataset we used in the following analysis was collected at Johns Hopkins University and the Kennedy Krieger Institute. It consists of data from n1 = 340 MS patients and n2 = 42 healthy subjects. |
| Dataset Splits | No | We randomly sample 42 subjects among all 342 MS patients without replacement, and combine those data with the data from the 42 healthy subjects to form a new dataset, which we then randomly divide into two equal halves. The classifier is trained on one half, while the correct classification rate is computed on the other half. This describes a train/test split, but no distinct validation set is mentioned for hyperparameter tuning or early stopping. |
| Hardware Specification | No | The paper does not provide specific details about the hardware used for the experiments, such as GPU/CPU models or memory. |
| Software Dependencies | No | The paper mentions using a 'random forest classifier' and 'Daubechies least asymmetric wavelets' but does not specify any software names with version numbers. |
| Experiment Setup | No | The paper describes aspects of the experimental procedure (e.g., random sampling for classification), but does not provide specific hyperparameter values for the models or other detailed system-level training settings. |