Week 2

Task list:

IoT:

• Sensor node bin file name needs to be changed. Check into the config to see how it can be changed (Low priority)
• Server not sending data to the cloud from S3-router node. (Low priority)
• For Sensor nodes, we should only define MESH-ID and Password and no wifi information. (Low priority)
• Need to have a mechanism to capture and log all esp errors that can potentially come from esp_functions by capturing the return esp_error_t. (Medium priority)
• Explore how to increase measurement size based on the flash memory increment. (Low priority)
• Power up the EZSBC node
• Redo the project documentation, (High priority)
  • USB-to-HTTP node
  • Test wave generation doc
  • Refactor the existing documentation
  • Update the project ReadMe's

CCTV:

• Create a plan for the next steps in filling the gaps of CCTV pipeline

Planned items for CCTV

CCTV image processing

Find the CCTV workflow diagram here

• Convert the cctv_SD1_label_images notebook as is to use yml passed in as an attribute from commandline.

  • Move the large label list variables into the DB as tables.

• Migrate the Prepare_CCTV_training_CSV colab notebook to gqc-utility-notebooks as a standard module.

  • Figure out how FB and VB splitting is done.
    • VB code needs to be reimplemented to pick the videos randomly.
  • Clean up and only keep the code for SD1
  • Should read from the DB
  • Should we write to the DB? (It is generating multiple csv files as output. Need to plan how it is done)

• Document everything!

• all_conditions table should have a column indicating the source DB name which contained the metadata.

• UTILITY specific notebooks, py modules and click modules based on that.

• Commit SD1 PACP code file that Vannary sent me - Here is the link https://drive.google.com/file/d/15mW1g5S2KHtWlmXIxOxkWUz4rvBXtfgH/view?usp=sharing

  • Need to include this file under utility specific metadata in the repository, since it's a standard file for SD1 utility.
  • When we start the script running through CCTV Usage, it needs to be inserted into the DB in the first step.
  • Need to include the steps in the workflow (as text and in Mermaid diagram) about including Supplementary data (PACP_Code)

• [Low Priority] Boiler plate for Database

  • Discuss on how to handle creating single column tables for each variable in initialize_variables function in 'SD1_label_images.py'
  • Each utility has a database like this specifically

• Update in the CCTV workflow page, probably as warning, that metadata extraction notebook for creating 'all_conditions.csv' only runs on windows (windows access db) and that it gives warnings when it's not able to find tables to run SQL queries on.

CCTV_apps

1. Create a mermaid diagram for the cctv apps and data sources.
2. CSV files should be loaded from the csv folder itself through a drop down.
3. Test symlinks in the MSI machine to mount images into public folder.
   1. Does not work if the original folder is located outside public
4. Look into the column names of the csv.

compute-msi

• Run a two-stage model
• Training frames needs to be extracted from zip files and put in the train directory. See if this can be streamlined.
• Solve progress-bar being printed issue.
  • Opened an issue in fastai
• Need to define the next steps

Vannary's suggestions:

• What to do with k=4 cross-validation sets? Initially, I trained all four and then averaged their F1 and F2 scores for cross-validation. However, Sudhir and Deven suggested choosing one because it was computation-intensive, and the results of the four runs were similar. You should do a k=4 cross-validation run on the new dataset to see if there is a significant discrepancy in the F1 and F2 scores. Sudhir: Not at this point
• Selecting the Videos for setting aside for testing in VB approach. You can pick the videos according to pipe materials or do it randomly. The important part is to ensure that the sum of the test number is around 20% of the total number of images. Here is an example that I did for COV: Sudhir: Randomly

Improvement suggestions

1. Improvement of frame labeling:
   1. annotated defective frames
   2. CCTV AI for workforce training