Skip to content

A step towards e-learning/online learning enhancement

Notifications You must be signed in to change notification settings

mayureshagashe2105/Effilearn

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

12 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Effilearn

A step towards e-learning/online learning enhancement

Streamlit

Understanding the Problem Statement

Due to this unforeseen COVID-19 pandemic learning sector has undergone substantial changes. Many untrivial methods like online schooling and self-paced video lecture courses are now leading the era of newly found online learning methodologies. Despite the effectiveness of these methods, there are a lot of challenges to be addressed to exploit the capability of online learning to its fullest.

This product specifically aims to solve the issue of unwanted background noise in the self-paced pre-recorded lectures.

Why this issue?

Many online learning platforms/universities/organizations are nowadays offering self-paced pre-recorded video lectures as a part of their curriculum. However, it does not imply that every university/organization can afford highly sophisticated architecture like an auditorium, and recording rooms to record these video lectures in a noise-free environment. In such cases, the faculties are forced to record their lectures either from their homes or maybe locations like staff offices, staff rooms, cabins, etc. So the faculties do not have any sort of control over the background noise and is inevtable. This introduction of background noise in the lectures deteriorate the overall quality of the lectures.

Goals To Achieve

  • Enabling faculties to record the video lectures from the comfort of their homes.
  • Improving the quality of pre-recorded video lectures with ML/AI solutions.

Services we provide

1. De-noised Video Lectures:

Our Noise Suppressor model extracts the audio from uploaded video and performs noise-suppression on that audio and clips it back to the original video. Thereby yielding De-Noised Video Lectures.

2. Secured Portal with Facial Recognition:

By using Siamese nets and performing one-shot learning, only authenticated authorities will be able to add/modify video lectures.

3. Automated Online Attendance:

By using Siamese nets and performing one-shot learning, attendance of registered students will be taken automatically.

4. Dashboard MONITORING:

image

Prototype Insights

Bridge Minimalist Video Collage

TechStack Used

TensorFlow Keras NumPy Pandas Flask React JavaScript Python OpenCV Streamlit