X Team| Chasers of the Lost Data

Project Details

The Challenge | Chasers of the Lost Data

Help find ways to improve the performance of machine learning and predictive models by filling in gaps in the datasets prior to model training. This entails finding methods to computationally recover or approximate data that is missing due to sensor issues or signal noise that compromises experimental data collection. This work is inspired by data collection during additive manufacturing (AM) processes where sensors capture build characteristics in-situ, but it has applications across many NASA domains.

Blank Sweeper

Filling out blank data in incomplete form.

X Team

Problem Statement

Find a way using machine learning algorithm to fill in gaps in datasets prior to model training in order to improve the completeness of data obtained by the sensors

Initial Approaches

Use Python, an open sourced programming language, to fulfill machine learning which assist us to form the correlations among the given data. (We should simply describe which method we’ve used ) In addition, we've made an Graphical User Interface (GUI), abstracting the code in order to simplify the operation, which make it more convenient for user. User selects the type of data, the program will choose an appropriate method(solution) , and apply it to find the missing data more effectively and efficiently.

GitHub

https://github.com/beicoles/blank_sweeper

Resources Used

Data :

Fireball And Bolide Reports

https://catalog.data.gov/dataset/fireball-and-bolide-reports

Programming :
  • Language

Python 3.6, Java 1.8.0_231

  • Package Environment

Anaconda3

  • Libraries used

pandas, numpy, dateutil, sklearn, impyute

  • IDE

Notebooks - Jupyter Notebooks

  • Future steps

More filling algorithms

Team Member

Tzu-Cheng, Hsueh

Yu-Yu, Hsiao

Chi-Jhih, Li

You-Sheng, Tsao

Shih-Yang, Ko