arem-deeplearning-activityrecognition

This repository contains the code and resources for the Activity Recognition System based on Multisensor Data Fusion (AReM) project, completed as part of the deep learning course (CS7389H) at the Department of Computer Science, Texas State University.

https://github.com/habibirani/arem-deeplearning-activityrecognition

Science Score: 44.0%

This score indicates how likely this project is to be science-related based on various indicators:

✓
CITATION.cff file
Found CITATION.cff file
✓
codemeta.json file
Found codemeta.json file
✓
.zenodo.json file
Found .zenodo.json file
○
DOI references
○
Academic publication links
○
Academic email domains
○
Institutional organization owner
○
JOSS paper metadata
○
Scientific vocabulary similarity
Low similarity (10.6%) to scientific vocabulary

Last synced: 10 months ago · JSON representation ·

Repository

Basic Info

Host: GitHub
Owner: habibirani
Language: Jupyter Notebook
Default Branch: main
Homepage:
Size: 3.8 MB

Statistics

Stars: 3
Watchers: 1
Forks: 0
Open Issues: 0
Releases: 0

Created about 2 years ago · Last pushed about 2 years ago

Metadata Files

Readme Citation

README.md

AReM-DeepLearning-ActivityRecognition

Dataset

The dataset used in this project is titled "Activity Recognition system based on Multisensor data fusion (AReM)" and is sourced from the UCI Machine Learning Repository. It comprises sensor data collected from wearable devices for activity recognition tasks. Initially, the project identified data leakage in the dataset. To address this issue, preprocessing techniques were employed along with data augmentation methods such as adding noise to generalize the data.

Installation

To set up the project, you need to have Python and PyTorch installed. Clone the repository and install the required packages:

```bash git clone https://github.com/Habibirani/AReM-DeepLearning-ActivityRecognitiont.git cd AReM-DeepLearning-ActivityRecognition conda env create -f environment.yml

```

Models Trained

Three different deep learning models were trained for activity recognition:

Long Short-Term Memory (LSTM)
Convolutional Neural Network (CNN)
Transformer

All codes for both the original dataset and the augmented dataset are available in the 'scripts' directory.

Contributing

Pull requests are welcome. For major changes, please open an issue first to discuss what you would like to change.

Please make sure to update tests as appropriate.

Owner

Name: Habib Irani
Login: habibirani
Kind: user
Location: Tehran

Website: habibirani.ir
Twitter: Habibirani
Repositories: 2
Profile: https://github.com/habibirani

Citation (CITATION.cff)


# See GiHub's Doc on citation files: https://docs.github.com/en/repositories/managing-your-repositorys-settings-and-features/customizing-your-repository/about-citation-files

# This CITATION.cff file was generated with cffinit.
# Visit https://bit.ly/cffinit to generate yours today!


cff-version: 1.0.0
title: >-
  AReM-DeepLearning-ActivityRecognition
message: >-
  If you find this project or code useful, please consider citing it as below!
type: software
authors:
  - given-names: Habib
    family-names: Irani
    email: habibirani@txstate.edu
    affiliation: Computer Science Department, Texas State University 
    orcid: 'https://orcid.org/0000-0002-8117-0778 '

GitHub Events

Total

Watch event: 3

Last Year

Watch event: 3

Dependencies

environment.yml conda

matplotlib 3.4.3
numpy 1.21.2
pandas 1.3.3
python 3.9.*
pytorch 2.2.2
scikit-learn 0.24.2
scipy 1.7.3
seaborn 0.11.2
tensorflow 2.6.0
torch 1.10.0
tsai 0.2.21

ecosyste.ms

Data

Tools

Indexes

Applications

Experiments

Open Source Science