Search for: All records

Masked Autoencoder (MAE) is a notable method for self-supervised pretraining in visual representation learning. It operates by randomly masking image patches and reconstructing these masked patches using the unmasked ones. A key limitation of MAE lies in its disregard for the varying informativeness of different patches, as it uniformly selects patches to mask. To overcome this, some approaches propose masking based on patch informativeness. However, these methods often do not consider the specific requirements of downstream tasks, potentially leading to suboptimal representations for these tasks. In response, we introduce the Multi-level Optimized Mask Autoencoder (MLO-MAE), a novel framework that leverages end-to-end feedback from downstream tasks to learn an optimal masking strategy during pretraining. Our experimental findings highlight MLO-MAE's significant advancements in visual representation learning. Compared to existing methods, it demonstrates remarkable improvements across diverse datasets and tasks, showcasing its adaptability and efficiency. Our code is available at https://github.com/Alexiland/MLO-MAE 

Arachidonic acid (AA) metabolites have been associated with several diseases across various organ systems, including the cardiovascular, pulmonary, and renal systems. Lipid mediators generated from AA oxidation have been studied to control macrophages, T-cells, cytokines, and fibroblasts, and regulate inflammatory mediators that induce vascular remodeling and dysfunction. AA is metabolized by cyclooxygenase (COX), lipoxygenase (LOX), and cytochrome P450 (CYP) to generate anti-inflammatory, pro-inflammatory, and pro-resolutory oxidized lipids. As comorbid states such as diabetes, hypertension, and obesity become more prevalent in cardiovascular disease, studying the expression of AA pathway genes and their association with these diseases can provide unique pathophysiological insights. In addition, the AA pathway of oxidized lipids exhibits diverse functions across different organ systems, where a lipid can be both anti-inflammatory and pro-inflammatory depending on the location of metabolic activity. Therefore, we aimed to characterize the gene expression of these lipid enzymes and receptors throughout multi-organ diseases via a transcriptomic meta-analysis using the Gene Expression Omnibus (GEO) Database. In our study, we found that distinct AA pathways were expressed in various comorbid conditions, especially those with prominent inflammatory risk factors. Comorbidities, such as hypertension, diabetes, and obesity appeared to contribute to elevated expression of pro-inflammatory lipid mediator genes. Our results demonstrate that expression of inflammatory AA pathway genes may potentiate and attenuate disease; therefore, we suggest further exploration of these pathways as therapeutic targets to improve outcomes. 

Cyber-physical systems are starting to adopt neural network (NN) models for a variety of smart sensing applications. While several efforts seek better NN architectures for system performance improvement, few attempts have been made to study the deployment of these systems in the field. Proper deployment of these systems is critical to achieving ideal performance, but the current practice is largely empirical via trials and errors, lacking a measure of quality. Sensing quality should reflect the impact on the performance of NN models that drive machine perception tasks. However, traditional approaches either evaluate statistical difference that exists objectively, or model the quality subjectively via human perception. In this work, we propose an efficient sensing quality measure requiring limited data samples using smart voice sensing system as an example. We adopt recent techniques in uncertainty evaluation for NN to estimate audio sensing quality. Intuitively, a deployment at better sensing location should lead to less uncertainty in NN predictions. We design SQEE, Sensing Quality Evaluation at the Edge for NN models, which constructs a model ensemble through Monte-Carlo dropout and estimates posterior total uncertainty via average conditional entropy. We collected data from three indoor environments, with a total of 148 transmitting-receiving (t-r) locations experimented and more than 7,000 examples tested. SQEE achieves the best performance in terms of the top-1 ranking accuracy---whether the measure finds the best spot for deployment, in comparison with other uncertainty strategies. We implemented SQEE on a ReSpeaker to study SQEE's real-world efficacy. Experimental result shows that SQEE can effectively evaluate the data collected from each t-r location pair within 30 seconds and achieve an average top-3 ranking accuracy of over 94%. We further discuss generalization of our framework to other sensing schemes. 

Real-world applications often involve irregular time series, for which the time intervals between successive observations are non-uniform. Irregularity across multiple features in a multi-variate time series further results in a different subset of features at any given time (i.e., asynchronicity). Existing pre-training schemes for time-series, however, often assume regularity of time series and make no special treatment of irregularity. We argue that such irregularity offers insight about domain property of the data—for example, frequency of hospital visits may signal patient health condition—that can guide representation learning. In this work, we propose PrimeNet to learn a self-supervised representation for irregular multivariate time-series. Specifically, we design a timesensitive contrastive learning and data reconstruction task to pre-train a model. Irregular time-series exhibits considerable variations in sampling density over time. Hence, our triplet generation strategy follows the density of the original data points, preserving its native irregularity. Moreover, the sampling density variation over time makes data reconstruction difficult for different regions. Therefore, we design a data masking technique that always masks a constant time duration to accommodate reconstruction for regions of different sampling density. We learn with these tasks using unlabeled data to build a pre-trained model and fine-tune on a downstream task with limited labeled data, in contrast with existing fully supervised approach for irregular time-series, requiring large amounts of labeled data. Experiment results show that PrimeNet significantly outperforms state-of-the-art methods on naturally irregular and asynchronous data from Healthcare and IoT applications for several downstream tasks, including classification, interpolation, and regression. 

The frequency-dependent nature of hearing loss poses many challenges for hearing aid design. In order to compensate for a hearing aid user’s unique hearing loss pattern, an input signal often needs to be separated into frequency bands, or channels, through a process called sub-band decomposition. In this paper, we present a real-time filter bank for hearing aids. Our filter bank features 10 channels uniformly distributed on the logarithmic scale, located at the standard audiometric frequencies used for the characterization and fitting of hearing aids. We obtained filters with very narrow passbands in the lower frequencies by employing multi-rate signal processing. Our filter bank offers a 9.1× reduction in complexity as compared to conventional signal processing. We implemented our filter bank on Open Speech Platform, an open-source hearing aid, and confirmed real-time operation.