Efficient Convolution Neural Network Software Implementation and DS Preprocessing for AIRBiS

AIRBiS progress meeting†

↑

Background†

With the Coronavirus disease (COVID-19) disrupting large part of the world, the number of patients has grown progressively. For dealing with this serious emergency, accurate diagnosis and fast reporting are two significant mechanisms.

↑

Research Goal†

  1. Search and collect X-ray image datasets containing non-infected (normal) and infected (COVID-19) data given many open sources
  2. Perform pre-processing tasks, e.g. as follows:
    1. denoising
    2. resizing
    3. data augmentation
    4. segmentation
    5. we should also come up with other issues and corresponding strategies
  3. CNN implementation and evaluation
    1. A CNN-based architecture will be adopted for the binary classification task. Once the model learns the feature representation of the input images, a classifier can thus output the diagnosis result, i.e., normal or infected. Framework and language: TensorFlow (Keras), Python
    2. Using the diagnosis (classification) results to evaluate the performance of the CNN (e.g., detection accuracy)
AIRBiS-SW.png
↑

Research Schedule†

DateTask
☑️June 1 - July 15, 2020Making prototype CNN
☑️July 15 - Aug 15, 2020Preprocessing the Dataset
☑️Aug 15 - Aug 31, 2020Argumentation the Dataset
☑️Sep 1 - Oct 31, 2020Evaluation Dataset
☑️Nov 1 - Nov 16, 2020Evaluation CNN
☑️Nov 16 - Nov 25, 2020Writing a paper
☑️Nov 26 - Nov 30, 2020Writing a progress report
☑️Deadline for 1st Draft: 11th Dec 2020Preparing draft for International ACM conference
( Dec 13 - Dec 23, 2020: Winter Vacation )
Dec 24 - Jan 1st, 2021 -> after ACMExperiments with different CNN optimizers
☑️7th January, 2021[ACM] Acceptance/Rejection Notification
☑️Jan 7 - Jan 26Preparing a presentation
☑️Jan 7 - Jan 31Research of Real-time augmentation
☑️Jan 7 - Jan 31Writing additional contents to paper
☑️27-30 January, 2021[ACM] Conference
☑️Feb 1st weekCorrecting Final draft
☑️Feb 19Submitted the final Draft
☑️( Feb 3rd week - Apr 30, 2021: Job Hunting )
April 30, 2021 -Reading papers for HW optimization
May 17, 2021The AIRBiS meeting: Creating an annual schedule
May 17, 2021 -Starting the implemention of optimization of HW
May 20 - June 5, 2021Deal with the accuracy problem of the new dataset with Mr.Wang.
June 7 - June 25Improve the accuracy by changing the augmentation methods
June 28 - July 30Changing input image size, segmentation
Aug 1 - Aug 30Evaluation of AIRBiS software part
Sep 1 - Sep 30Writing Introduction of the master thesis
Oct 1st weekReading the paper of UI, especially how to use SQL
Oct 2nd weekReview and functional design of functions required for UI
Oct 18, 2021Submission of the theme for master's thesis
Oct 3-4 weeksImplementing the patients Database
Nov 1st -Connecting UI-Hardware
Dec 6, 2021Submission the thesis drafts to the referees
Jan 28, 2022Submission Final MT
Feb 10, 2022Presentation of MT

MEMO:

Schedule last Updated on: 29/09/2021
↑

Research Progress†

↑

References†

トップ   新規 一覧 検索 最終更新   ヘルプ   最終更新のRSS