https://github.com/thoratstuti/to-predict-the-mood-level-based-on-score-generated-by-the-depression-scale
Designing a system that will detect various tendencies in a particular individual using his facial expressions and text based data analysis. Then classifying him as neutral or negative.
https://github.com/thoratstuti/to-predict-the-mood-level-based-on-score-generated-by-the-depression-scale
Last synced: 3 months ago
JSON representation
Designing a system that will detect various tendencies in a particular individual using his facial expressions and text based data analysis. Then classifying him as neutral or negative.
- Host: GitHub
- URL: https://github.com/thoratstuti/to-predict-the-mood-level-based-on-score-generated-by-the-depression-scale
- Owner: thoratstuti
- Created: 2024-08-16T08:17:26.000Z (10 months ago)
- Default Branch: main
- Last Pushed: 2024-08-16T08:24:54.000Z (10 months ago)
- Last Synced: 2025-01-14T07:50:56.863Z (5 months ago)
- Size: 124 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# To-Predict-the-mood-level-based-on-score-generated-by-the-depression-scale
Designing a system that will detect various tendencies in a particular individual using his facial expressions and text based data analysis. Then classifying him as neutral or negative.
Objectives
1.To Predict the mood level based on score generated by the depression scale.
2.To successfully implement the test model based on training set as supervised
learning approach.
3.To generate accurate results based on the given inputs.
• A framework architecture is proposed for the automatic depression scale prediction that includes the frame segment level feature extraction, dynamic feature
generation, feature dimension reduction and regression techniques.
• The various features, including deep features, are extracted on the frame-level
that captured better facial expression information
• A new feature (FDHH) is generated by observing the dynamic variation patterns
across the frame-level features.
• Then the advanced regressive techniques are used for regression.