Scribd
Upload
12 views

P_V3_Description_Synthetic Data Generation Using Generative AI_18.10.2024

Uploaded by

Samruddh Kandagal
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
12 views

P_V3_Description_Synthetic Data Generation Using Generative AI_18.10.2024

Uploaded by

Samruddh Kandagal
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 4

Language: Python Date: 18/10/2024

Synthetic Data Generation Using Generative AI based on LLM

Model

DESCRIPTION:

1. In this project based on Webpage Flask model for Synthetic Data

Generation Using Generative AI.

2. Input: The dataset, Synthetic Data Healthcare /Query Dataset is

implemented as input. The input dataset is taken from dataset repository.

3. Pre-processing: The collected input data’s are subjected to pre-processing.

In the Pre-processing step,

NLP Pre-processing

Data Augmentation

4. Generation: In this step selected Data AI Generation New data using LLM

Algorithm.

5. Data splitting: In this step, the pre-processed data’s are split into train set

and test set for decision

Train data is used for evaluate the model (80%).

Test data is used for predict the model (20%).

egc 1
Language: Python Date: 18/10/2024
6. Test and Validation : In this step, we can implement the algorithms model

such as,

LLM API Model

7. Output/objective: The objective is to classify or predict for generated for

new health care Synthetic Data using LLM model based on dataset

attributes by using the classification algorithms.

8. Comparison: In this step, we can compare the both machine algorithms

results and will display which algorithm is efficient.

9. Performance Estimation: In this step, we can analyse some performance

metrics such

Accuracy (Improved Acc –above 90)

Confusion Metrics

Classification Report

Train and test Accuracy

Train and test Loss

egc 2
Language: Python Date: 18/10/2024

FLOW OF PROCESS

egc 3
Language: Python Date: 18/10/2024
Note:

All the process is going to be done as per the description given above.

The dataset will be provided by us.

Not a real time project.

No GUI is provided.

Language: Python

Front End: Flask (HTML and CSS)

Back End: Anaconda Navigator – Spyder Console

egc 4

You might also like