Unsupervised Noise Reduction for Nanochannel Measurement Using Noise2Noise Deep Learning

Takaai, Takayuki; Tsutsui, Makusu

doi:10.1007/978-3-030-75015-2_5

Cited by 1 publication

(1 citation statement)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Qingchun Li et al [11] proposed a single noise audio denoising framework (SNA-DF) based on N2N for processing single noise audio denoising, and used the deep and complex U-net model to realize the denoising processing. Shirong Koh et al [12] proposed the WaveN2N model to deal with the noise of acoustic signals in underwater areas without prior knowledge and clean signals from real data; Takayuki Takaai et al [13] applied the Noise2Noise method to current waveform signals obtained from multi-stage narrow nanochannels, which are characterized by high noise and complex measurement principles. The CAE model and U-net model are used, respectively, and the final noise reduction effect is better than the traditional signal processing methods, such as frequency filter, wavelet transform, and Kalman filter, which can retain the signal details more accurately.…”

Section: Introductionmentioning

confidence: 99%

Unsupervised Noise Reductions for Gravitational Reference Sensors or Accelerometers Based on the Noise2Noise Method

Yang

Zhang

et al. 2023

Sensors

View full text Add to dashboard Cite

Onboard electrostatic suspension inertial sensors are important applications for gravity satellites and space gravitational-wave detection missions, and it is important to suppress noise in the measurement signal. Due to the complex coupling between the working space environment and the satellite platform, the process of noise generation is extremely complex, and traditional noise modeling and subtraction methods have certain limitations. With the development of deep learning, applying it to high-precision inertial sensors to improve the signal-to-noise ratio is a practically meaningful task. Since there is a single noise sample and unknown true value in the measured data in orbit, odd–even sub-samplers and periodic sub-samplers are designed to process general signals and periodic signals, and adds reconstruction layers consisting of fully connected layers to the model. Experimental analysis and comparison are conducted based on simulation data, GRACE-FO acceleration data, and Taiji-1 acceleration data. The results show that the deep learning method is superior to traditional data smoothing processing solutions.

show abstract

Section: Introductionmentioning

confidence: 99%