Fusion of Algorithms for Compressed Sensing

Ambat, Sooraj K.; Chatterjee, Saikat; Hari, K.V.S.

doi:10.1109/tsp.2013.2259821

Cited by 30 publications

(15 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Bearing vibration signals are sparse vectors in the frequency domain, and the fast Fourier transform (FFT) is one of the most commonly used transforms, mainly because of its efficient structure. In this study, the Fourier transform matrix is selected to be the orthogonal basis matrix [15].…”

Section: Vibration Signal Recovery Based On Compressed Sensingmentioning

confidence: 99%

Rolling bearing fault diagnosis under fluctuant conditions based on compressed sensing

Yuan

2016

Struct. Control Health Monit.

View full text Add to dashboard Cite

Bearings are widely used in industries and construction for shaft supporting or seismic isolation. In recent years, their fault diagnosis, especially under variable, or fluctuant conditions, has received increasing attention. Sufficient monitoring data are usually required for bearing diagnosis. However, sufficient data cannot be guaranteed in some engineering cases with limitations of the transmission channel bandwidth or onboard/onsite computational capabilities. Fortunately, the emerging compressed sensing technique, which provides an effective solution to data compression and processing, has the ability to transform traditional monitoring data to the compressed information domain for a highly effective diagnosis under fluctuant conditions. This study proposes a bearing fault diagnosis method under fluctuant conditions based on compressed sensing theory. First, a random matrix is constructed as the measurement matrix and is employed to compress the original signal into the compressed information domain. Then, reconstruction-evaluation based fault diagnosis method is conducted with compressed signals. Moreover, the compressed signals used for fault diagnosis are reconstructed on the remote side. The experimental results provide evidence that the proposed method can effectively reduce the data volume required for bearing diagnosis and maintain an accuracy similar to current approaches, and the reconstructed signals can be used for other fault diagnosis methods.

show abstract

Section: Vibration Signal Recovery Based On Compressed Sensingmentioning

confidence: 99%

Rolling bearing fault diagnosis under fluctuant conditions based on compressed sensing

Yuan

2016

Struct. Control Health Monit.

View full text Add to dashboard Cite

show abstract

“…At the end of (kþ1)th iteration, we need to retain only K potential atoms fromT k andT k þ 1 . Recently Ambat et al [32][33][34][35][36] proposed fusion schemes based on leastsquares to efficiently identify the true atoms from the union of the estimated support-sets. We use this fusion strategy here to select K potential atoms fromT k and T k þ 1 .…”

Section: Definitionmentioning

confidence: 99%

An iterative framework for sparse signal reconstruction algorithms

Ambat

Hari

2015

Signal Processing

Self Cite

View full text Add to dashboard Cite

“…Instead of worst case approaches, average case analysis approaches such as replica method tools from statistical physics field [39] have been used for convex optimization based CS algorithms [40], [41], [42], but there is no precedence to use them for analyzing GP algorithms due to analytical intractability. Further, in worst case analysis tools, RIP is found to offer more analytical tractability than mutual-coherence and is recently in more use, such as analysis of OMP [43], model based CS [44] and fusion framework where several CS algorithms are used jointly [45], [46]. Therefore we decide to use RIP to analyze DIPP.…”

Section: Introductionmentioning

confidence: 99%

Design and Analysis of a Greedy Pursuit for Distributed Compressed Sensing

Sundman

Chatterjee

Skoglund

2016

IEEE Trans. Signal Process.

Self Cite

View full text Add to dashboard Cite

Abstract-We consider a distributed compressed sensing scenario where many sensors measure correlated sparse signals and the sensors are connected through a network. Correlation between sparse signals is modeled by a partial common support-set. For such a scenario, the main objective of this paper is to develop a greedy pursuit algorithm. We develop a distributed parallel pursuit (DIPP) algorithm based on exchange of information about estimated support-sets at sensors. The exchange of information helps to improve estimation of the partial common support-set, that in turn helps to gradually improve estimation of supportsets in all sensors, leading to a better quality reconstruction performance. We provide restricted isometry property (RIP) based theoretical analysis on the algorithm's convergence and reconstruction performance. Under certain theoretical requirements on the quality of information exchange over network and RIP parameters of sensor nodes, we show that the DIPP algorithm converges to a performance level that depends on a scaled additive measurement noise power (convergence in theory) where the scaling coefficient is a function of RIP parameters and information processing quality parameters. Using simulations, we show practical reconstruction performance of DIPP vis-avis amount of undersampling, signal-to-measurement-noise ratios and network-connectivity conditions.

show abstract

Fusion of Algorithms for Compressed Sensing

Cited by 30 publications

References 20 publications

Rolling bearing fault diagnosis under fluctuant conditions based on compressed sensing

Rolling bearing fault diagnosis under fluctuant conditions based on compressed sensing

An iterative framework for sparse signal reconstruction algorithms

Design and Analysis of a Greedy Pursuit for Distributed Compressed Sensing

Contact Info

Product

Resources

About