Compressed Signal Classification Using Informed Instance Selection. Issue 2 (4th March 2021)

• Record Type: Journal Article
• Authors: Rani, Meenu; Dhok, S. B.; Deshmukh, R. B.; Kumar, Punit
• Is Part Of: IETE technical review. Volume 38:Issue 2(2021)
• Page Start: 206
• Page End: 220
• Publication Date: 2021-03-04
• Subjects: Compressive sensing -- Compressed signal processing -- Feature extraction -- Random demodulator -- Active learning -- Classification; Telecommunication -- Periodicals; Electronics -- Periodicals; Electronics; Telecommunication; Periodicals; 621.38
• DOI: 10.1080/02564602.2019.1708818
• Languages: English
• ISSNs: 0256-4602

Abstract

ABSTRACT: Compressive sensing (CS) eases signal acquisition by relaxing the barrier of Nyquist rate. It randomly samples the signal at a rate proportional to the signal sparsity. This compresses the signal at the time of sensing. This superiority of CS is hindered by the complex reconstruction algorithms. The way-out is proposed by an advanced area of CS, in which signal processing is directly done on compressive measurements, avoiding reconstruction. This area is known as compressed signal processing (CSP). It saves power and time and also reduces the computational complexity drastically. CSP is best suited to real-time condition monitoring scenarios where devices are power constrained. These devices generate massive amount of unlabeled data, labeling of which is done manually to train a classifier for condition monitoring. This is quite laborious and time-consuming task. To overcome this burden, use of informed instance selection scheme of active learning (AL) is proposed in this paper. Using this technique, the classifier can be trained even if the data have only few labeled instances. Thus, combining CSP with AL improves the performance of condition monitoring systems to a great extent. The simulation results show that the significant improvement can be obtained using the proposed method.