The data of interest are assumed to be represented as -dimensional real vectors, and these vectors are compressible in some linear basis B, implying that the signal can be reconstructed accurately using only a small number of basis-function coefficients associated with B. Compressive sensing is a framework whereby one does not measure one of the aforementioned -dimensional signals directly, but rather a set of related measurements, with the new measurements a linear combination of the original underlying -dimensional signal. The number of required compressive-sensing measurements is typically much smaller than , offering the potential to simplify the sensing system. Let denote the unknown underlying -dimensional signal, and a vector of compressive-sensing measurements, then one may approximate accurately by utilizing knowledge of the (under-determined) linear relationship between and , in addition to knowledge of the fact that is compressible in B. In this paper we employ a Bayesian formalism for estimating the underlying signal based on compressive-sensing measurements . The proposed framework has the following properties: i) in addition to estimating the underlying signal , "error bars" are also estimated, these giving a measure of confidence in the inverted signal; ii) using knowledge of the error bars, a principled means is provided for determining when a sufficient number of compressive-sensing measurements have been performed; iii) this setting lends itself naturally to a framework whereby the compressive sensing measurements are optimized adaptively and hence not determined randomly; and iv) the framework accounts for additive noise in the compressive-sensing measurements and provides an estimate of the noise variance. In this paper we present the underlying theory, an associated algorithm, example results, and provide comparisons to other compressive-sensing inversion algorithms in the literature.Index Terms-Adaptive compressive sensing, Bayesian model selection, compressive sensing (CS), experimental design, relevance vector machine (RVM), sparse Bayesian learning.

No abstract

Abstract-Recently developed methods for learning sparse classifiers are among the state-of-the-art in supervised learning. These methods learn classifiers that incorporate weighted sums of basis functions with sparsity-promoting priors encouraging the weight estimates to be either significantly large or exactly zero. From a learning-theoretic perspective, these methods control the capacity of the learned classifier by minimizing the number of basis functions used, resulting in better generalization. This paper presents three contributions related to learning sparse classifiers. First, we introduce a true multiclass formulation based on multinomial logistic regression. Second, by combining a bound optimization approach with a component-wise update procedure, we derive fast exact algorithms for learning sparse multiclass classifiers that scale favorably in both the number of training samples and the feature dimensionality, making them applicable even to large data sets in high-dimensional feature spaces. To the best of our knowledge, these are the first algorithms to perform exact multinomial logistic regression with a sparsity-promoting prior. Third, we show how nontrivial generalization bounds can be derived for our classifier in the binary case. Experimental results on standard benchmark data sets attest to the accuracy, sparsity, and efficiency of the proposed methods.

Summary Acute respiratory infections (ARI) are a common reason for seeking medical attention and the threat of pandemic influenza will likely add to these numbers. Using human viral challenge studies with live rhinovirus, respiratory syncytial virus, and influenza A, we developed peripheral blood gene expression signatures that distinguish individuals with symptomatic ARI from uninfected individuals with > 95% accuracy. We validated this “acute respiratory viral” signature - encompassing genes with a known role in host defense against viral infections - across each viral challenge. We also validated the signature in an independently acquired dataset for influenza A and classified infected individuals from healthy controls with 100% accuracy. In the same dataset, we could also distinguish viral from bacterial ARIs (93% accuracy). These results demonstrate that ARIs induce changes in human peripheral blood gene expression that can be used to diagnose a viral etiology of respiratory infection and triage symptomatic individuals.

Sepsis is a common cause of death, but outcomes in individual patients are difficult to predict. Elucidating the molecular processes that differ between sepsis patients who survive and those who die may permit more appropriate treatments to be deployed. We examined the clinical features, and the plasma metabolome and proteome of patients with and without community-acquired sepsis, upon their arrival at hospital emergency departments and 24 hours later. The metabolomes and proteomes of patients at hospital admittance who would die differed markedly from those who would survive. The different profiles of proteins and metabolites clustered into fatty acid transport and β-oxidation, gluconeogenesis and the citric acid cycle. They differed consistently among several sets of patients, and diverged more as death approached. In contrast, the metabolomes and proteomes of surviving patients with mild sepsis did not differ from survivors with severe sepsis or septic shock. An algorithm derived from clinical features together with measurements of seven metabolites predicted patient survival. This algorithm may help to guide the treatment of individual patients with sepsis.

No abstract

We use mechanical translation of a coded aperture for code division multiple access compression of video. We present experimental results for reconstruction at 148 frames per coded snapshot.

A Semantic Compositional Network (SCN) is developed for image captioning, in which semantic concepts (i.e., tags) are detected from the image, and the probability of each tag is used to compose the parameters in a long short-term memory (LSTM) network. The SCN extends each weight matrix of the LSTM to an ensemble of tag-dependent weight matrices. The degree to which each member of the ensemble is used to generate an image caption is tied to the image-dependent probability of the corresponding tag. In addition to captioning images, we also extend the SCN to generate captions for video clips. We qualitatively analyze semantic composition in SCNs, and quantitatively evaluate the algorithm on three benchmark datasets: COCO, Flickr30k, and Youtube2Text. Experimental results show that the proposed method significantly outperforms prior state-of-the-art approaches, across multiple evaluation metrics.