# Marco DuarteUniversity of Massachusetts Amherst | UMass Amherst · Department of Electrical and Computer Engineering

Marco Duarte

Ph.D. Electrical Engineering

## About

150

Publications

30,422

Reads

**How we measure 'reads'**

A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more

15,538

Citations

Citations since 2016

Introduction

All papers listed are available at my website, http://www.ecs.umass.edu/~mduarte

Additional affiliations

August 2011 - present

**University of Massachusetts Amherst**

September 2010 - August 2011

September 2009 - August 2010

## Publications

Publications (150)

Machine learning methods have been remarkably successful for a wide range of application areas in the extraction of essential information from data. An exciting and relatively recent development is the uptake of machine learning in the natural sciences, where the major goal is to obtain novel scientific insights and discoveries from observational o...

Self-taught learning is a technique that uses a large number of unlabeled data as source samples to improve the task performance on target samples. Compared with other transfer learning techniques, self-taught learning can be applied to a broader set of scenarios due to the loose restrictions on the source data. However, knowledge transferred from...

Few-shot learning is a technique to learn a model with a very small amount of labeled training data by transferring knowledge from relevant tasks. In this paper, a few-shot learning method for wearable sensor based human activity recognition, which is a technique that seeks high-level human activity knowledge from low-level sensor inputs, is propos...

Machine learning methods have been remarkably successful for a wide range of application areas in the extraction of essential information from data. An exciting and relatively recent development is the uptake of machine learning in the natural sciences, where the major goal is to obtain novel scientific insights and discoveries from observational o...

Few-shot learning is a technique to learn a model with a very small amount of labeled training data by transferring knowledge from relevant tasks. In this paper, we propose a few-shot learning method for wearable sensor based human activity recognition, a technique that seeks high-level human activity knowledge from low-level sensor inputs. Due to...

In this letter, Laplace distribution is used to model the prior for the direction of arrival (DoA) of sources. In order to incorporate the real and imaginary part of the received signal, we propose a method that pairwise estimates the hyperparameters for parts of the signal coefficients. In addition, we propose a multi-task algorithm to extend the...

Wideband communication is often expected to deal with a very wide spectrum, which in many environments of interest includes strong interferers. Thus receivers for the wideband communication systems often need to mitigate interferers to reduce the distortion caused by the amplifier nonlinearity and noise. Recently, a new architecture for communicati...

Wideband communication receivers often deal with the problems of detecting weak signals from distant sources received together with strong nearby interferers. When the techniques of random modulation are used in communication system receivers, one can design a spectrally shaped sequence that mitigates interferer bands while preserving message bands...

Self-taught learning is a technique that uses a large number of unlabeled data as source samples to improve the task performance on target samples. Compared with other transfer learning techniques, self-taught learning can be applied to a broader set of scenarios due to the loose restrictions on source data. However, knowledge transferred from sour...

Feature selection is a dimensionality reduction technique that selects a subset of representative features from high-dimensional data by eliminating irrelevant and redundant features. Recently, feature selection combined with sparse learning has attracted significant attention due to its outstanding performance compared with traditional feature sel...

Cognitive radio (CR) is a multiuser, wireless communication concept that allows for a dynamic and adaptive assignment of spectral resources. The coexistence of multiple users, often transmitting at significantly different power levels, makes CR receivers vulnerable to spectral leakage caused by components’ nonlinearities and time-truncation of the...

High spectral resolution brings hyperspectral images with large amounts of information, which makes these images more useful in many applications than images obtained from traditional multispectral scanners with low spectral resolution. However, the high data dimensionality of hyperspectral images increases the burden on data computation, storage,...

This paper proposes a new hyperspectral unmixing method for nonlinearly mixed hyperspectral data using a semantic representation in a semi-supervised fashion, assuming the availability of a spectral reference library. Existing semi-supervised unmixing algorithms select members from an endmember library that are present at each of the pixels; most s...

The high data dimensionality of hyperspectral images increases the burden on data computation, storage, and transmission ; fortunately, the high redundancy in the spectral domain allows for significant dimensionality reduction. Band selection provides a simple dimensionality reduction scheme by discarding bands that are highly redundant, therefore...

This paper proposes an out-of-sample extension framework for a global manifold learning algorithm (Isomap) that uses temporal information in out-of-sample points in order to make the embedding more robust to noise and artifacts. Given a set of noise-free training data and its embedding, the proposed framework extends the embedding for a noisy time...

We consider the problem of selecting an optimal mask for an image manifold, i.e., choosing a subset of the pixels of the image that preserves the manifold's geometric structure present in the original data. Such masking implements a form of compressive sensing through emerging imaging sensor platforms for which the power expense grows with the numb...

Hyperspectral signature classification is a quantitative analysis approach for hyperspectral imagery which performs detection and classification of the constituent materials at the pixel level in the scene. The classification procedure can be operated directly on hyperspectral data or performed by using some features extracted from the correspondin...

Sparse modeling has been widely and successfully used in many applications
such as computer vision, machine learning, and pattern recognition and,
accompanied with those applications, significant research has studied the
theoretical limits and algorithm design for convex relaxations in sparse
modeling. However, only little has been done for theoret...

In wideband communication one often aims to detect a weak signal received together with a strong interferer. One can design a spectrally shaped sequence to be convolved with the received signal featuring a bandpass for the message and a notch for the interferer. Unfortunately, when the sequence must be quantized, commonly used constrained optimizat...

This paper proposes an out-of-sample extension framework for a global manifold learning algorithm (Isomap) that uses temporal information in out-of-sample points in order to make the embedding more robust to noise and artifacts. Given a set of noise-free training data and its embedding, the proposed framework extends the embedding for a noisy time...

Feature design is a crucial step in many hyperspectral signal processing applications like hyperspectral signature
classification and unmixing, etc. In this paper, we describe a technique for automatically designing universal features of hyperspectral signatures. Universality is considered both in terms of the application to a multitude of classifi...

We study the compressed sensing (CS) signal estimation problem where an input signal is measured via a linear matrix multiplication under additive noise. While this setup usually assumes sparsity or compressibility in the input signal during recovery, the signal structure that can be leveraged is often not known a priori. In this paper, we consider...

Cross-correlation is a popular signal processing technique used in numerous
localization and tracking systems for obtaining reliable range information.
However, a practical efficient implementation has not yet been achieved on
resource constrained wireless sensor network platforms. In this paper, we
propose: SparseXcorr: cross-correlation via spars...

In recent years, compressive sensing (CS) has attracted significant attention
in parameter estimation tasks, including frequency estimation, time delay
estimation, and localization. In order to use CS in parameter estimation,
parametric dictionaries (PDs) collect observations for a sampling of the
parameter space and yield sparse representations fo...

We consider the application of non-homogeneous hidden Markov chain (NHMC) models to the problem of hyperspectral signature classification. It has been previously shown that the NHMC model enables the detection of several semantic structural features of hyperspectral signatures. However, there are some aspects of the spectral data that are not fully...

We propose a new spectral unmixing method using a semantic spectral representation, which is produced via non-homogeneous hidden Markov chain (NHMC) models applied to wavelet transforms of the spectra. Previous studies have shown that the representation is robust to spectral variability in the same materials because it can automatically detect the...

We study the compressed sensing (CS) signal estimation problem where a signal is measured via a linear matrix multiplication under additive noise. While this setup usually assumes sparsity or compressibility in the signal during estimation, additional signal structure that can be leveraged is often not known a priori. For signals with independent a...

We consider the problem of selecting an optimal mask for an image manifold, i.e., choosing a subset of the dimensions of the image space that preserves the manifold structure present in the original data. Such masking implements a form of compressed sensing that reduces power consumption in emerging imaging sensor platforms. Our goal is for the man...

Hyperspectral imaging is a powerful technology for remotely inferring the material properties of the objects in a scene of interest. Hyperspectral images consist of spatial maps of light intensity variation across a large number of spectral bands or wavelengths; alternatively, they can be thought of as a measurement of the spectrum of light transmi...

While manifolds have attracted significant attention from the image processing and computer vision communities, we are not aware of openly available tools for visualization of manifold-modeled data that allows for interactive navigation over the embedded dataset. We introduce the Manifold Analysis GUI (MAGI), a freely available toolbox for Matlab t...

Motivated by the compelling application of interference mitigation at wideband receivers in wireless communication and sensing systems, we consider the recovery of a frequency-sparse signal from samples of small magnitude. The standard ℓ1-norm minimization results in an inadequate signal-dependent recovery performance, and hence we introduce three...

We consider the use of non-homogeneous Markov chain (NHMC) models for wavelet transformations of hyperspectral signatures to generate features for signal processing purposes. Inspired by the use of hidden Markov trees for natural images, the NHMC model enables the characterization of absorption bands and other structural features of mineral spectra...

This paper makes several contributions toward the "underdetermined" setting
in linear models when the set of observations is given by a linear combination
of a small number of groups of columns of a dictionary, termed the
"block-sparse" case. First, it specifies conditions on the dictionary under
which most block submatrices of the dictionary are w...

In recent years, sparsity and compressive sensing have attracted
significant attention in parameter estimation tasks, including frequency
estimation, delay estimation, and localization. Parametric dictionaries
collect observations for a sampling of the parameter space and can yield
sparse representations for the signals of interest when the samplin...

The recently introduced theory of Compressive Sensing (CS) enables a new method for signal recovery from incomplete information (a reduced set of “compressive” linear measurements), based on the assumption that the signal is sparse in some dictionary. Such compressive measurement schemes are desirable in practice for reducing the costs of signal ac...

Compressive sensing (CS) is a new approach to simultaneous sensing and compression of sparse and compressible signals based on randomized dimensionality reduction. To recover a signal from its compressive measurements, standard CS algorithms seek the sparsest signal in some discrete basis or frame that agrees with the measurements. A great many app...

In compressive sensing, a small collection of linear projections of a sparse signal contains enough information to permit signal recovery. Distributed compressive sensing extends this framework by defining ensemble sparsity models, allowing a correlated ensemble of sparse signals to be jointly recovered from a collection of separately acquired comp...

Time delay estimation has long been an active area of research. In this work,
we show that compressive sensing with interpolation may be used to achieve good
estimation precision while lowering the sampling frequency. We propose an
Interpolating Band-Excluded Orthogonal Matching Pursuit algorithm that uses one
of two interpolation functions to esti...

We propose new compressive parameter estimation algorithms that make use of
polar interpolation to improve the estimator precision. Moreover, we evaluate
six algorithms for estimation of parameters in sparse translation-invariant
signals, exemplified with the time delay estimation problem. The evaluation is
based on three performance metrics: estim...

The Delsarte-Goethals frame (DGF) has been proposed for deterministic compressive sensing of sparse and compressible signals. Results in compressive sensing theory show that the DGF enables successful recovery of an overwhelming majority of sufficiently sparse signals. However, these results do not give a characterization of the sparse vectors for...

Existing approaches to compressive sensing of frequency-sparse signals
focuses on signal recovery rather than spectral estimation. Furthermore, the
recovery performance is limited by the coherence of the required sparsity
dictionaries and by the discretization of the frequency parameter space. In
this paper, we introduce a greedy recovery algorithm...

This paper describes our methods for repairing and restoring images of hidden paintings (paintings that have been painted over and are now covered by a new surface painting) that have been obtained via noninvasive X-ray fluorescence imaging of their canvases. This recently developed imaging technique measures the concentrations of various chemical...

Recent work has leveraged sparse signal models for parame-ter estimation purposes in applications including localization and bearing estimation. A dictionary whose elements corre-spond to observations for a sampling of the parameter space is used for sparse approximation of the received signals; the resulting sparse coefficient vector's support ide...

Compressive sensing (CS) allows for acquisition of sparse signals at sampling rates significantly lower than the Nyquist rate required for bandlimited signals. Recovery guarantees for CS are generally derived based on the assumption that measurement projections are selected independently at random. However, for many practical signal acquisition app...

Compressive sensing (CS) allows for acquisition of sparse signals at sampling
rates significantly lower than the Nyquist rate required for bandlimited
signals. Recovery guarantees for CS are generally derived based on the
assumption that measurement projections are selected independently at random.
However, for many practical signal acquisition app...

This paper is dedicated to the memory of Hyeokho Choi, our colleague, mentor, and friend. Compressive sensing is a signal acquisition framework based on the revelation that a small collection of linear projections of a sparse signal contains enough information for stable recovery. In this paper we introduce a new theory for distributed compressive...

The emergence of low-cost sensing architectures for diverse modalities has made it possible to deploy sensor networks that acquire large amounts of very high-dimensional data. To cope with such a data deluge, manifold models are often developed that provide a powerful theoretical and algorithmic framework for capturing the intrinsic structure of da...

We study the compressed sensing (CS) signal estimation problem where an input
is measured via a linear matrix multiplication under additive noise. While this
setup usually assumes sparsity or compressibility in the observed signal during
recovery, the signal structure that can be leveraged is often not known a
priori. In this paper, we consider uni...

Signal compression is an important tool for reducing communication costs and increasing the lifetime of wireless sensor network deployments. In this paper, we overview and classify an array of proposed compression methods, with an emphasis on illustrating the differences between the various approaches.

Compressed sensing (CS) is an exciting, rapidly growing, field that has attracted considerable attention in signal processing, statistics, and computer science, as well as the broader scientific community. Since its initial development only a few years ago, thousands of papers have appeared in this area, and hundreds of conferences, workshops, and...

We report on a number of extensions of our previously published pump-probe technique that resolves the two kinds of melanin in human skin including new flexibility, three-dimensional sectioning capabilities, and improved image processing results.

We study the compressed sensing (CS) estimation problem where an input is measured via a linear matrix multiplication under additive noise. While this setup usually assumes sparsity or compressibility in the observed signal during recovery, the signal structure that can be leveraged is often not known a priori. In this paper, we consider universal...

Compressive sensing (CS) is an emerging approach for the acquisition of signals having a sparse or compressible representation in some basis. While the CS literature has mostly focused on problems involving 1-D signals and 2-D images, many important applications involve multidimensional signals; the construction of sparsifying bases and measurement...

Compressed sensing (CS) is an emerging field that has attracted considerable
research interest over the past few years. Previous review articles in CS limit
their scope to standard discrete-to-discrete measurement architectures using
matrices of randomized nature and signal models based on standard sparsity. In
recent years, CS has worked its way i...

The Delsarte-Goethals frame has been proposed for deterministic compressive sensing of sparse and compressible signals. Its performance in compressive imaging applications falls short of that obtained for arbitrary sparse vectors. Prior work has proposed specially tailored signal recovery algorithms that partition the recovery of the input vector i...

The aim of compressed sensing is to recover attributes of sparse signals using very few measurements. Given an overall bit budget for quantization, this paper demonstrates that there is value to redundant measurement. The measurement matrices considered here are required to have the property that signal recovery is still possible even after droppin...

In compressive sensing, a small collection of linear projections of a sparse
signal contains enough information to permit signal recovery. Distributed
compressive sensing (DCS) extends this framework, allowing a correlated
ensemble of sparse signals to be jointly recovered from a collection of
separately acquired compressive measurements. In this p...

In compressive sensing, a small collection of linear projections of a
sparse signal contains enough information to permit signal recovery.
Distributed compressive sensing (DCS) extends this framework by defining
ensemble sparsity models, allowing a correlated ensemble of sparse
signals to be jointly recovered from a collection of separately acquire...

Many applications in cellular systems and sensor networks involve a random
subset of a large number of users asynchronously reporting activity to a base
station. This paper examines the problem of multiuser detection (MUD) in random
access channels for such applications. Traditional orthogonal signaling ignores
the random nature of user activity in...

This paper describes our work on the problem of reconstructing the original visual appearance of underpaintings (paintings that have been painted over and are now covered by a new surface painting) from noninvasive X-ray fluorescence imaging data of their canvases. This recently-developed imaging technique yields data revealing the concentrations o...

This paper considers on-off random access channels where users transmit either a one or a zero to a base station. Such channels represent an abstraction of control channels used for scheduling requests in third-generation cellular systems and uplinks in wireless sensor networks deployed for target detection. This paper introduces a novel convex-opt...

Compressive sensing (CS) is a new approach to simultaneous sensing and compression for sparse and compressible signals. While the discrete Fourier transform has been widely used for CS of frequency-sparse signals, it provides optimal sparse representations only for signals with components at integral frequencies. There exist redundant frames that p...

The emergence of low-cost sensing architectures for diverse modalities has made it possible to deploy sensor networks that capture a single event from a large number of vantage points and using multiple modalities. In many scenarios, these networks acquire large amounts of very high-dimensional data. For example, even a relatively small network of...

Two-photon calcium imaging is an emerging experimental technique that enables the study of information processing within neural
circuits in vivo. While the spatial resolution of this technique permits the calcium activity of individual cells within the field of view
to be monitored, inferring the precise times at which a neuron emits a spike is ch...

Compressive sensing (CS) is an alternative to Shannon/Nyquist sampling for the acquisition of sparse or compressible signals that can be well approximated by just K Â¿ N elements from an N -dimensional basis. Instead of taking periodic samples, CS measures inner products with M < N random vectors and then recovers the signal via a sparsity-seeking...

Compressive sensing (CS) is an emerging approach for acquisition of signals having a sparse or compressible representation in some basis. While CS literature has mostly focused on problems involving 1-D and 2-D signals, many important applications involve signals that are multidimensional. We propose the use of Kronecker product matrices in CS for...

This paper develops a new class of algorithms for signal recovery in the distributed compressive sensing (DCS) framework. DCS exploits both intra-signal and inter-signal correlations through the concept of joint sparsity to further reduce the number of measurements required for recovery. DCS is well-suited for sensor network applications due to its...

A recent revisionist theory claims that as early as 1430 European artists secretly invented optical projectors and used them as aids during the execution of their paintings. Key artworks adduced in support of this theory are a pair of portraits of Cardinal Niccolo Albergati by Jan van Eyck: a silverpoint study (1431) and a formal oil work (1432). W...