Compressed Sensing Verses Auto-Encoder: On the Perspective of Signal Compression and Restoration
- Resource Type
- Periodical
- Authors
- Jeong, J.; Ozger, M.; Lee, W.
- Source
- IEEE Access Access, IEEE. 12:41967-41979 2024
- Subject
- Aerospace
Bioengineering
Communication, Networking and Broadcast Technologies
Components, Circuits, Devices and Systems
Computing and Processing
Engineered Materials, Dielectrics and Plasmas
Engineering Profession
Fields, Waves and Electromagnetics
General Topics for Engineers
Geoscience
Nuclear Engineering
Photonics and Electrooptics
Power, Energy and Industry Applications
Robotics and Control Systems
Signal Processing and Analysis
Transportation
Sensors
Artificial neural networks
Training
Sparse matrices
Compressed sensing
Sparks
Signal processing algorithms
Encoding
Mean square error methods
auto-encoder
signal processing
compression
restoration
- Language
- ISSN
- 2169-3536
This paper presents a comparison between compressed sensing (CS) and auto-encoder (AE) for compression and restoration of signals. The study used K-sparse vectors and generated an under-determined system, which is a system of linear equations with fewer equations than unknowns. By using CS and AE under various specific conditions, the accuracy of the signal restoration is compared with mean squared error (MSE). The experimental methodology includes comparing and analyzing the signal recovery performance by altering the algorithm and various parameters. The result represents the performance and accuracy of signal compression and restoration obtained using both techniques. It also provides a comprehensive analysis of CS and AE methods. The importance of this research and the possibility of practical application in various fields are discussed. Overall, this study provides insights into the comparison of CS and AE techniques in the field of sparse signal compression and restoration.