Abstract
Compressed signal processing (CSP) is a branch of compressive sensing (CS), which gives a direction to solve a class of signal processing problems directly from the compressive measurements of a signal. CSP utilizes the information preserved in the compressive measurements of a signal to solve certain inference problems like: classification, detection, and estimation, without reconstructing the original signal. It further simplifies the signal processing compared to conventional CS by omitting their complex reconstruction stage. This, in turn, reduces the implementation complexity of signal processing systems. This paper investigates the performance of CSP for classification application. After extracting the features from compressive measurements, these features or the data instances are used for classification purpose. Through experimental analysis, it has been found that as the CS undersampling factor is increased, the overlapping among the data instances predominates. This results in a complex decision boundary, which in turn degrades the classification accuracy at higher undersampling factors. To overcome the above issue, this paper proposes the use of a machine learning method known as overlap aware learning along with CSP. This generates a smoother decision boundary and hence improves the classification accuracy at higher undersampling factors. The simulation results show the trend of improved classification accuracy using the proposed method. An analysis of the proposed method has been done on different datasets and based on run-time complexity and complexity vs gain analysis to verify the effectiveness of proposed method.
Highlights
Compressive sensing (CS) is a signal acquisition technique, which works on the random sensing principle
In the initial part of simulations, the compressive measurements have been obtained from the raw vibration dataset and the features have been extracted from these measurements
SCOPE Compressed signal processing (CSP) is an emerging aspect of CS, in which work has been done on solving some signal processing problems directly from compressive measurements
Summary
Compressive sensing (CS) is a signal acquisition technique, which works on the random sensing principle. This seemed to be possible due to the fact that the compressive measurements preserve the signal structure, which allows reconstruction In this regard, the way-out has been proposed in [9]–[11], to solve the signal processing problems like: classification, detection, and estimation, directly from compressive measurements. The way-out has been proposed in [9]–[11], to solve the signal processing problems like: classification, detection, and estimation, directly from compressive measurements The major challenge that needs to be addressed for the power-constrained environment is that the inference problem for the system must be solved from minimum number of measurements in order to minimize the power consumption This can be feasible if the system performs satisfactorily even with highly undersampled input signal [12]–[17]. To highlight the achieved gain an analysis has been presented between increased accuracy and the differential run-time complexity
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
