no code implementations • 29 Apr 2022 • Liangrui Pan, Hetian Wang, Lian Wang, Boya Ji, Mingting Liu, Mitchai Chongcheawchamnan, Jin Yuan, Shaoliang Peng
The study proposes a typical transformer image classification framework by integrating noise reduction convolutional autoencoder and feature cross fusion learning (NRCA-FCFL) to classify osteosarcoma histological images.
no code implementations • 22 Aug 2021 • Liangrui Pan, Boya Ji, Peng Xi, Xiaoqi Wang, Mitchai Chongcheawchamnan, Shaoliang Peng
Diabetic retinopathy(DR) is the main cause of blindness in diabetic patients.
no code implementations • 5 Apr 2021 • Liangrui Pan, Peng Zhang, Chalongrat Daengngam, Mitchai Chongcheawchamnan
This review summarizes the work of Raman spectroscopy in identifying the composition of substances and reviews the preprocessing process of Raman spectroscopy, the analysis methods and applications of artificial intelligence.
no code implementations • 29 Oct 2020 • Liangrui Pan, Pronthep Pipitsunthonsan, Chalongrat Daengngam, Mitchai Chongcheawchamnan
The scheme first transforms the noisy Raman spectrum to a two-dimensional scale map using CWT.
no code implementations • 9 Sep 2020 • Liangrui Pan, Pronthep Pipitsunthonsan, Chalongrat Daengngam, Sittiporn Channumsin, Suwat Sreesawet, Mitchai Chongcheawchamnan
The optimum back-end classifier was obtained by testing the ML and DCNN models with several noisy Raman spectrums (10-30 dB noise power).