Dynamic Fusion of LSTM Predictions Using Reinforcement Learning-Based GOWLA for Human Activity Recognition

Human Activity Recognition (HAR) contributes significantly to vital areas in healthcare, IoT, and smart monitoring applications. Generally, the current models rely on deep learning and traditional machine learning techniques such as LSTM and SVM. However, these methods face considerable challenges,...

Full description

Saved in:
Bibliographic Details
Main Authors: Hayder K. Fatlawi, Attila Kiss
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11036747/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850166542435614720
author Hayder K. Fatlawi
Attila Kiss
author_facet Hayder K. Fatlawi
Attila Kiss
author_sort Hayder K. Fatlawi
collection DOAJ
description Human Activity Recognition (HAR) contributes significantly to vital areas in healthcare, IoT, and smart monitoring applications. Generally, the current models rely on deep learning and traditional machine learning techniques such as LSTM and SVM. However, these methods face considerable challenges, such as imbalanced data distribution, weak adaptation of weights to temporal changes, and a decline in classification performance in rare activities. In this paper, we propose a new method based on dynamic reinforcement learning to update GOWLA weights, which is entitled Dynamic RL-GOWLA. In this method, the LSTM outputs are combined using Weighted Logarithmic Averaging with a reinforcement learning agent for dynamically updating the weights based on the model’s performance in each training iteration. Experiments on WISDM database show that the proposed method outperforms traditional models such as LSTM, SVM, Bayesian Classifier, RNN, and CNN, achieving a F1-score of 96.58%. This approach improves the adaptability of models to imbalanced data, making it a promising solution for tasks that require accurate classification of dynamic human activities.
format Article
id doaj-art-ab85ebaf36f4484db59be58ae9e9c8b9
institution OA Journals
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-ab85ebaf36f4484db59be58ae9e9c8b92025-08-20T02:21:25ZengIEEEIEEE Access2169-35362025-01-011310477910479010.1109/ACCESS.2025.357992611036747Dynamic Fusion of LSTM Predictions Using Reinforcement Learning-Based GOWLA for Human Activity RecognitionHayder K. Fatlawi0https://orcid.org/0000-0001-7243-8181Attila Kiss1https://orcid.org/0000-0001-8174-6194Center of Information Technology Research and Development, University of Kufa, Najaf, IraqDepartment of Information Systems, Eötvös Loránd University, Budapest, HungaryHuman Activity Recognition (HAR) contributes significantly to vital areas in healthcare, IoT, and smart monitoring applications. Generally, the current models rely on deep learning and traditional machine learning techniques such as LSTM and SVM. However, these methods face considerable challenges, such as imbalanced data distribution, weak adaptation of weights to temporal changes, and a decline in classification performance in rare activities. In this paper, we propose a new method based on dynamic reinforcement learning to update GOWLA weights, which is entitled Dynamic RL-GOWLA. In this method, the LSTM outputs are combined using Weighted Logarithmic Averaging with a reinforcement learning agent for dynamically updating the weights based on the model’s performance in each training iteration. Experiments on WISDM database show that the proposed method outperforms traditional models such as LSTM, SVM, Bayesian Classifier, RNN, and CNN, achieving a F1-score of 96.58%. This approach improves the adaptability of models to imbalanced data, making it a promising solution for tasks that require accurate classification of dynamic human activities.https://ieeexplore.ieee.org/document/11036747/Human activity recognitionreinforcement learningdeep learningordered weighted averaging
spellingShingle Hayder K. Fatlawi
Attila Kiss
Dynamic Fusion of LSTM Predictions Using Reinforcement Learning-Based GOWLA for Human Activity Recognition
IEEE Access
Human activity recognition
reinforcement learning
deep learning
ordered weighted averaging
title Dynamic Fusion of LSTM Predictions Using Reinforcement Learning-Based GOWLA for Human Activity Recognition
title_full Dynamic Fusion of LSTM Predictions Using Reinforcement Learning-Based GOWLA for Human Activity Recognition
title_fullStr Dynamic Fusion of LSTM Predictions Using Reinforcement Learning-Based GOWLA for Human Activity Recognition
title_full_unstemmed Dynamic Fusion of LSTM Predictions Using Reinforcement Learning-Based GOWLA for Human Activity Recognition
title_short Dynamic Fusion of LSTM Predictions Using Reinforcement Learning-Based GOWLA for Human Activity Recognition
title_sort dynamic fusion of lstm predictions using reinforcement learning based gowla for human activity recognition
topic Human activity recognition
reinforcement learning
deep learning
ordered weighted averaging
url https://ieeexplore.ieee.org/document/11036747/
work_keys_str_mv AT hayderkfatlawi dynamicfusionoflstmpredictionsusingreinforcementlearningbasedgowlaforhumanactivityrecognition
AT attilakiss dynamicfusionoflstmpredictionsusingreinforcementlearningbasedgowlaforhumanactivityrecognition