• Home
  • Search
  • Towards high-performance deep learning architecture and hardware accelerator design for robust analysis in diffuse correlation spectroscopy
  • Cite Icon2
  • https://doi.org/10.1016/j.cmpb.2024.108471Copy DOI Icon

Towards high-performance deep learning architecture and hardware accelerator design for robust analysis in diffuse correlation spectroscopy

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

This study proposes a compact deep learning (DL) architecture and a highly parallelized computing hardware platform to reconstruct the blood flow index (BFi) in diffuse correlation spectroscopy (DCS). We leveraged a rigorous analytical model to generate autocorrelation functions (ACFs) to train the DL network. We assessed the accuracy of the proposed DL using simulated and milk phantom data. Compared to convolutional neural networks (CNN), our lightweight DL architecture achieves 66.7% and 18.5% improvement in MSE for BFi and the coherence factor β, using synthetic data evaluation. The accuracy of rBFi over different algorithms was also investigated. We further simplified the DL computing primitives using subtraction for feature extraction, considering further hardware implementation. We extensively explored computing parallelism and fixed-point quantization within the DL architecture. With the DL model's compact size, we employed unrolling and pipelining optimizations for computation-intensive for-loops in the DL model while storing all learned parameters in on-chip BRAMs. We also achieved pixel-wise parallelism, enabling simultaneous, real-time processing of 10 and 15 autocorrelation functions on Zynq-7000 and Zynq-UltraScale+ field programmable gate array (FPGA), respectively. Unlike existing FPGA accelerators that produce BFi and the β from autocorrelation functions on standalone hardware, our approach is an encapsulated, end-to-end on-chip conversion process from intensity photon data to the temporal intensity ACF and subsequently reconstructing BFi and β. This hardware platform achieves an on-chip solution to replace post-processing and miniaturize modern DCS systems that use single-photon cameras. We also comprehensively compared the computational efficiency of our FPGA accelerator to CPU and GPU solutions.

Similar Papers
  • PDF
  • Research Article
  • Citations31

Comparative Study of Popular Deep Learning Models for Machining Roughness Classification Using Sound and Force Signals.

  • Nov 29, 2021
  • Micromachines
  • Binayak Bhandari
  • Dissertation
  • Citations1

FPGA acceleration of continual learning at the edge

  • Jan 01, 2021
  • Gane Pathirannahelage Duvindu Piyasena
  • Research Article
  • Citations111

A deep learning analysis on question classification task using Word2vec representations

  • Jan 21, 2020
  • Neural Computing and Applications
  • Seyhmus Yilmaz +1
  • Book Chapter
  • Citations1

Deep Learning and Applications

  • Jan 01, 2017
  • Zhu Han +2
  • Research Article
  • Citations9

Evaluating deep transfer learning for whole-brain cognitive decoding

  • Jul 13, 2023
  • Journal of the Franklin Institute
  • Armin W Thomas +3
  • PDF
  • Research Article
  • Citations19

A hybrid CNN and ensemble model for COVID-19 lung infection detection on chest CT scans.

  • Mar 09, 2023
  • PLOS ONE
  • Ahmed A Akl +3
  • Dissertation

Baking physics into deep learning for modeling scientific problems

  • Jan 01, 2021
  • Chengping Rao
  • Research Article

STEERING ANGLE DETECTION IN AUTONOMOUS CARS USING DEEP LEARNING

  • Jan 01, 2024
  • International Journal Of Trendy Research In Engineering And Technology
  • Aishwarya N +4
  • PDF
  • Research Article
  • Citations2

Enhanced Sequence-to-Sequence Deep Transfer Learning for Day-Ahead Electricity Load Forecasting

  • May 20, 2024
  • Electronics
  • Vasileios Laitsos +4
  • Research Article
  • Citations3

Early diagnosis of mild cognitive impairment and Alzheimer's disease using multimodal feature-based deep learning models in a Chinese elderly population.

  • Sep 01, 2025
  • Asian journal of psychiatry
  • Chu Wang +6
  • Conference Article

Comparative study of deep learning architectures and vision transformers for lemon leaf disease classification

  • Mar 24, 2026
  • Muhammad Salimy Ahsan +3
  • Research Article
  • Citations1

Optimizing deep learning models from multi-objective perspective via Bayesian optimization

  • Apr 01, 2025
  • IAES International Journal of Artificial Intelligence (IJ-AI)
  • Abdul Rahman Mohamad Rom +2
  • Research Article
  • Citations33

Deep Learning Models for Time-History Prediction of Vehicle-Induced Bridge Responses: A Comparative Study

  • Aug 06, 2022
  • International Journal of Structural Stability and Dynamics
  • Huile Li +3
  • Research Article
  • Citations14

AUQantO: Actionable Uncertainty Quantification Optimization in deep learning architectures for medical image classification

  • Jul 25, 2023
  • Applied Soft Computing
  • Zakaria Senousy +2
  • Research Article

Real-Time Human Motion Behaviour Recognition Using Deep Learning Models

  • Jan 20, 2025
  • Indian Engineering Journal
  • Prashant Awasthi
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.