https://scholars.lib.ntu.edu.tw/handle/123456789/611217
Title: | Low-Complexity On-Demand Reconstruction for Compressively Sensed Problematic Signals | Authors: | AN-YEU(ANDY) WU | Keywords: | compressed learning; Compressed sensing; hardware sharing; on-demand reconstruction; sparse transform | Issue Date: | 2020 | Journal Volume: | 68 | Start page/Pages: | 4094-4107 | Source: | IEEE Transactions on Signal Processing | Abstract: | Compressed Sensing (CS) is a revolutionary technology for realizing low-power sensor nodes through sub-Nyquist sampling, and the CS reconstruction engines have been widely studied to fulfill the energy efficiency for real-time processing. However, in most cases, we only want to analyze the problematic signals which account for a very low percentage. Therefore, large efforts will be wasted if we recover uninterested signals. On the other hand, in order to identify the high-risk signals, additional hardware and computation overhead are required for classification other than CS reconstruction. In this paper, to achieve low-complexity on-demand CS reconstruction, we propose a two-stage classification-aided reconstruction (TS-CAR) framework. The compressed signals can be classified with a sparse coding based classifier, which provides the hardware sharing potential with reconstruction. Furthermore, to accelerate the reconstruction speed, a cross-domain sparse transform is applied from classification to reconstruction. TS-CAR is implemented in electrocardiography based atrial fibrillation (AF) detection. The average computational cost of TS-CAR is 2.25× fewer compared to traditional frameworks when AF percentage is among 10% to 50%. Finally, we implement TS-CAR in TSMC 40 nm technology. The post-layout results show that the proposed intelligent CS reconstruction engine can provide a competitive area- and energy-efficiency compared to state-of-the-art CS and machine learning engines. © 1991-2012 IEEE. |
URI: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85089303594&doi=10.1109%2fTSP.2020.3006766&partnerID=40&md5=02cb607776f5fe7f966a53f8f7e4551c https://scholars.lib.ntu.edu.tw/handle/123456789/611217 |
ISSN: | 1053587X | Other Identifiers: | ITPRE | DOI: | 10.1109/TSP.2020.3006766 | SDG/Keyword: | Compressed sensing; Energy efficiency; Engines; Learning systems; Sensor nodes; Signal reconstruction; Atrial fibrillation; Compressive sensing; Computation overheads; Computational costs; Realtime processing; Reconstruction speed; Revolutionary technology; Sub-Nyquist sampling; Biomedical signal processing |
Appears in Collections: | 電機工程學系 |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.