VGU RESEARCH REPOSITORY
Please use this identifier to cite or link to this item:
https://epub.vgu.edu.vn/handle/dlibvgu/1276
Title: | The application of liquid time-constant networks in learning handwashing process | Authors: | Huynh Duc Khai | Keywords: | Liquid time-constant;Handwashing process;Recurrent neural network;Deep learning application | Issue Date: | 2021 | Abstract: | This thesis will introduce the core idea for making software that is able to detect whether a person has a qualified hand washing process or not by taking advantage of modern technology: Deep Learning. More specifically, by applying a new variation of Recurrent Neural Network (RNN) - the Liquid Time-constant (LTC) Network - the software now can have more accurate in classifying an entire handwashing process compared to vanilla RNN algorithm of its - the famous Long Short Term Memory (LSTM) networks. In this paper, I take one step further by creating multiple LTC networks, combine them into a decision forest and add one more layer outside to determine which recorded video is a qualified hand washing process. Although LTC improves effectiveness, we still need more consideration to compare it to more recent advanced variations of neuron networks to understand more about its strength and weakness. |
URI(1): | http://epub.vgu.edu.vn/handle/dlibvgu/1276 |
Appears in Collections: | Computer Science (CS) |
Files in This Item:
File | Description | Size | Format | Existing users please Login |
---|---|---|---|---|
The application of liquid time-constant networks in learning handwashing process.pdf | 5.26 MB | Adobe PDF |
Page view(s)
121
checked on Apr 24, 2024
Download(s)
39
checked on Apr 24, 2024
Google ScholarTM
Check
Items are protected by © Copyright of Vietnamese - German University Library