Logarithmic Analogue-to-Digital Converters

Guilherme, Jorge; Vital, J.C.

doi:10.1007/978-1-4757-3724-0_7

Cited by 4 publications

(1 citation statement)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, a B-mode image is obtained by envelope detection and logarithmic compression of the beamformed output. 4) Training: Because of the non-uniform distribution of ultrasound data, we initialize the ADCs with a logarithmic quantization rule (exponentially spaced), which is known to result in a higher quantization resolution in the low-intensity ranges [43]. Training is based on a signed-mean-squaredlogarithmic-error loss function, defined as L(ŝ, s) = 1 2 log 10 (ŝ + ) − log 10 (s + ) where ŝ and s denote the predicted and target frames, respectively, and (•) ± denote the positive and negative signal components.…”

Section: Case Study: Ultrasound Beamformingmentioning

confidence: 99%

Learning Task-Based Analog-to-Digital Conversion for MIMO Receivers

Shlezinger

Sloun

Huijben

et al. 2020

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

Analog-to-digital converters (ADCs) allow physical signals to be processed using digital hardware. Their conversion consists of two stages: Sampling, which maps a continuous-time signal into discrete-time, and quantization, i.e., representing the continuous-amplitude quantities using a finite number of bits. ADCs typically implement generic uniform conversion mappings that are ignorant of the task for which the signal is acquired, and can be costly when operating in high rates and fine resolutions. In this work we design task-oriented ADCs which learn from data how to map an analog signal into a digital representation such that the system task can be efficiently carried out. We propose a model for sampling and quantization that facilitates the learning of non-uniform mappings from data. Based on this learnable ADC mapping, we present a mechanism for optimizing a hybrid acquisition system comprised of analog combining, tunable ADCs with fixed rates, and digital processing, by jointly learning its components end-to-end. Then, we show how one can exploit the representation of hybrid acquisition systems as deep network to optimize the sampling rate and quantization rate given the task by utilizing Bayesian meta-learning techniques. We evaluate the proposed deep task-based ADC in two case studies: the first considers symbol detection in multi-antenna digital receivers, where multiple analog signals are simultaneously acquired in order to recover a set of discrete information symbols. The second application is the beamforming of analog channel data acquired in ultrasound imaging. Our numerical results demonstrate that the proposed approach achieves performance which is comparable to operating with high sampling rates and fine resolution quantization, while operating with reduced overall bit rate. For instance, we demonstrate that deep task-based ADCs enable accurate reconstruction of ultrasound images while using 12.5% of the overall number of bits used by conventional ADCs to achieve similar performance.

show abstract

Section: Case Study: Ultrasound Beamformingmentioning

confidence: 99%