FairDRO: Group fairness regularization via classwise robust optimization.

Existing group fairness-aware training methods fall into two categories: re-weighting underrepresented groups according to certain rules, or using regularization terms such as smoothed approximations of fairness metrics or surrogate statistical quantities. While each category has its own strength in applicability or performance when compared to each other, their successful performances are typically limited to specific cases. To that end, we propose a new approach called FairDRO, which takes advantage of both categories through a classwise group distributionally robust optimization (DRO) framework.

Interpretable deep learning-based hippocampal sclerosis classification.

Objective: To evaluate the performance of a deep learning model for hippocampal sclerosis classification on the clinical dataset and suggest plausible visual interpretation for the model prediction.

Methods: T2-weighted oblique coronal images of the brain MRI epilepsy protocol performed on patients were used. The training set included 320 participants with 160 no, 100 left and 60 right hippocampal sclerosis, and cross-validation was implemented.

Is the posterior cingulate cortex an on-off switch for tinnitus?: A comparison between hearing loss subjects with and without tinnitus.

As the human brain works in a Bayesian manner to minimize uncertainty toward external stimuli, the deafferented brain may generate tinnitus in an attempt to fill in missing auditory information, e.g. due to hearing loss.

Toward a unified framework for interpreting machine-learning models in neuroimaging.

Machine learning is a powerful tool for creating computational models relating brain function to behavior, and its use is becoming widespread in neuroscience. However, these models are complex and often hard to interpret, making it difficult to evaluate their neuroscientific validity and contribution to understanding the brain. For neuroimaging-based machine-learning models to be interpretable, they should (i) be comprehensible to humans, (ii) provide useful information about what mental or behavioral constructs are represented in particular brain pathways or regions, and (iii) demonstrate that they are based on relevant neurobiological signal, not artifacts or confounds.

Estimating PM2.5 concentration of the conterminous United States via interpretable convolutional neural networks.

We apply convolutional neural network (CNN) model for estimating daily 24-h averaged ground-level PM of the conterminous United States in 2011 by incorporating aerosol optical depth (AOD) data, meteorological fields, and land-use data. Unlike some of the recent supervised learning-based approaches, which only utilized the predictors from the location of which PM value is estimated, we naturally aggregate predictors from nearby locations such that the spatial correlation among the predictors can be exploited. We carefully evaluate the performance of our method via overall, temporally-separated, and spatially-separated cross-validations (CV) and show that our CNN achieves competitive estimation accuracy compared to the recently developed baselines.

Dynamic functional connectivity analysis reveals improved association between brain networks and eating behaviors compared to static analysis.

Uncontrollable eating behavior is highly associated with dysfunction in neurocognitive systems. We aimed to quantitatively link brain networks and eating behaviors based on dynamic functional connectivity analysis, which reflects temporal dynamics of brain networks. We used 62 resting-state functional magnetic resonance imaging data sets representing 31 healthy weight (HW) and 31 non-HW participants based on body mass index (BMI).

DUDE-Seq: Fast, flexible, and robust denoising for targeted amplicon sequencing.

We consider the correction of errors from nucleotide sequences produced by next-generation targeted amplicon sequencing. The next-generation sequencing (NGS) platforms can provide a great deal of sequencing data thanks to their high throughput, but the associated error rates often tend to be high. Denoising in high-throughput sequencing has thus become a crucial process for boosting the reliability of downstream analyses.

Micro-Doppler Based Classification of Human Aquatic Activities via Transfer Learning of Convolutional Neural Networks.

Accurate classification of human aquatic activities using radar has a variety of potential applications such as rescue operations and border patrols. Nevertheless, the classification of activities on using radar has not been extensively studied, unlike the case on dry ground, due to its unique challenge. Namely, not only is the radar cross section of a human on water small, but the micro-Doppler signatures are much noisier due to water drops and waves.