Robust nonlinear model identification methods using forward regression

In this correspondence new robust nonlinear model construction algorithms for a large class of linear-in-the-parameters models are introduced to enhance model robustness via combined parameter regularization and new robust structural selective criteria. In parallel to parameter regularization, we use two classes of robust model selection criteria based on either experimental design criteria that optimizes model adequacy, or the predicted residual sums of squares (PRESS) statistic that optimizes model generalization capability, respectively. Three robust identification algorithms are introduced, i.e., combined A- and D-optimality with regularized orthogonal least squares algorithm, respectively; and combined PRESS statistic with regularized orthogonal least squares algorithm. A common characteristic of these algorithms is that the inherent computation efficiency associated with the orthogonalization scheme in orthogonal least squares or regularized orthogonal least squares has been extended such that the new algorithms are computationally efficient. Numerical examples are included to demonstrate effectiveness of the algorithms.

Standardized evaluation of algorithms for computer-aided diagnosis of dementia based on structural MRI: The CADDementia challenge

Algorithms for computer-aided diagnosis of dementia based on structural MRI have demonstrated high performance in the literature, but are difficult to compare as different data sets and methodology were used for evaluation. In addition, it is unclear how the algorithms would perform on previously unseen data, and thus, how they would perform in clinical practice when there is no real opportunity to adapt the algorithm to the data at hand. To address these comparability, generalizability and clinical applicability issues, we organized a grand challenge that aimed to objectively compare algorithms based on a clinically representative multi-center data set. Using clinical practice as the starting point, the goal was to reproduce the clinical diagnosis. Therefore, we evaluated algorithms for multi-class classification of three diagnostic groups: patients with probable Alzheimer's disease, patients with mild cognitive impairment and healthy controls. The diagnosis based on clinical criteria was used as reference standard, as it was the best available reference despite its known limitations. For evaluation, a previously unseen test set was used consisting of 354 T1-weighted MRI scans with the diagnoses blinded. Fifteen research teams participated with a total of 29 algorithms. The algorithms were trained on a small training set (n = 30) and optionally on data from other sources (e.g., the Alzheimer's Disease Neuroimaging Initiative, the Australian Imaging Biomarkers and Lifestyle flagship study of aging). The best performing algorithm yielded an accuracy of 63.0% and an area under the receiver-operating-characteristic curve (AUC) of 78.8%. In general, the best performances were achieved using feature extraction based on voxel-based morphometry or a combination of features that included volume, cortical thickness, shape and intensity. The challenge is open for new submissions via the web-based framework: http://caddementia.grand-challenge.org.

Structural features of condensed tannins affect in vitro ruminal methane production and fermentation characteristics

An in vitro study was conducted to investigate the effects of condensed tannins (CT) structural properties, i.e. average polymer size (or mean degree of polymerization); percentage of cis flavan-3-ols and percentage of prodelphinidins in CT extracts on methane production (CH4) and fermentation characteristics. CT were extracted from eight plants in order to obtain different CT types: black currant leaves, goat willow leaves, goat willow twigs, pine bark, red currant leaves, sainfoin plants, weeping willow catkins and white clover flowers. They were analysed for CT content and CT composition by thiolytic degradation, followed by HPLC analysis. Grass silage was used as a control substrate. Condensed tannins were added to the substrate at a concentration of 40 g/kg, with or without polyethylene glycol (+ or −PEG 6000 treatment) to inactivate tannins, and then incubated for 72 h in mixed buffered rumen fluid from three different lactating dairy cows per run. Total cumulative gas production (GP) was measured by an automated gas production system. During the incubation, 12 gas samples (10 μl) were collected from each bottle headspace at 0, 2, 4, 6, 8, 12, 24, 30, 36, 48, 56 and 72 h of incubation and analyzed for CH4. A modified Michaelis–Menten model was fitted to the CH4 concentration patterns and model estimates were used to calculate total cumulative CH4 production (GPCH4). Total cumulative gas production and GPCH4 curves were fitted using biphasic and monophasic modified Michaelis-Menten models, respectively. Addition of PEG increased GP, GPCH4, and CH4 concentration compared to the −PEG treatment. All CT types reduced GPCH4 and CH4 concentration. All CT increased the half time of GP and GPCH4. Moreover, all CT decreased the maximum rate of fermentation for GPCH4 and rate of substrate degradation. The correlation between CT structure and GPCH4 and fermentation characteristics showed that the proportion of prodelphinidins within CT had the largest effect on fermentation characteristics, followed by average 27 polymer size and percentage of cis-flavan-3-ols.