rl-based-adaptive-classifier

Deep Reinforcement Learning based adaptive time-series binary classifier.

https://github.com/mshuqair/rl-based-adaptive-classifier

Science Score: 57.0%

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
    Found 4 DOI reference(s) in README
  • Academic publication links
  • Academic email domains
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (9.4%) to scientific vocabulary

Keywords

classification deep-reinforcement-learning keras parkinsons-disease python reinforcement-learning
Last synced: 4 months ago · JSON representation ·

Repository

Deep Reinforcement Learning based adaptive time-series binary classifier.

Basic Info
  • Host: GitHub
  • Owner: mshuqair
  • Language: Python
  • Default Branch: main
  • Homepage:
  • Size: 1.04 MB
Statistics
  • Stars: 3
  • Watchers: 1
  • Forks: 1
  • Open Issues: 0
  • Releases: 0
Topics
classification deep-reinforcement-learning keras parkinsons-disease python reinforcement-learning
Created almost 3 years ago · Last pushed 8 months ago
Metadata Files
Readme Citation

README.md

Deep Reinforcement-Learning-Based Adaptive Classifier

This unique approach uses Reinforcement Learning (RL) to discern shifts in data stream distributions during state transitions. Training an RL agent to recognize these transitions makes it adept at identifying transitions in new data. Instead of static models, our agent interacts with the data's dynamics and makes optimal classification decisions. This RL-driven framework prioritizes understanding changes in data distribution, making it robust against inter and intra-data variations.

Figure 1. The proposed reinforcement-learning-based adaptive classification framework.

Figure 2. The model prediction for Walking vs. Non-walking (1 vs. 2) in one participant of the MHEALTH dataset.

Updates

More updates regarding the description are coming soon. Code updates: - Update the model train and test to improve readability and reproducibility - Updated to Python 3.10.11 - Updated to TensorFlow 2.10.0 - Various updates to plotting functions

Deep Reinforcement Learning Adaptive Classification of PD Medication State

  • The preliminary results of this project were published at the IEEE ICDM 2022 Conference. Incremental Learning in Time-series Data using Reinforcement Learning: https://doi.org/10.1109/ICDMW58026.2022.00115
  • The IEEE Journal of Biomedical and Health Informatics has recently published an extensive extension of this work. Reinforcement Learning-Based Adaptive Classification for Medication State Monitoring in Parkinson's Disease: https://doi.org/10.1109/JBHI.2024.3423708
  • Please cite the papers if you find this work useful

Code Requirements and Compatability

The code was run and tested using the following: - Python 3.10.11 - tensorflow 2.10.1 - keras 2.10.0 - matplotlib 3.10.1 - numpy 1.26.3 - pandas 2.2.3 - scikit-learn 1.6.1

Conclusions

Owner

  • Name: Mustafa
  • Login: mshuqair
  • Kind: user
  • Company: Florida Atlantic University

PhD candidate and researcher focusing on machine learning, reinforcement learning and learning systems.

Citation (CITATION.cff)

message: "If you use this software, please cite it as below."
authors:
- family-names: "Shuqair"
  given-names: "Mustafa"
  orcid: "https://orcid.org/0000-0002-9134-5447"
title: "Reinforcement Learning Based Adaptive Binary Classifier"
version: 1.2
date-released: 2023-01-18
url: "https://github.com/mshuqair/RL-based-adaptive-classifier"

GitHub Events

Total
  • Watch event: 1
  • Push event: 5
Last Year
  • Watch event: 1
  • Push event: 5

Issues and Pull Requests

Last synced: about 1 year ago

All Time
  • Total issues: 0
  • Total pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Total issue authors: 0
  • Total pull request authors: 0
  • Average comments per issue: 0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
Past Year
  • Issues: 0
  • Pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Issue authors: 0
  • Pull request authors: 0
  • Average comments per issue: 0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
Top Authors
Issue Authors
Pull Request Authors
Top Labels
Issue Labels
Pull Request Labels