A Novel Hybrid Deep Learning Model for Human Activity Recognition Based on Transitional Activities

Irfan, Saad; Anjum, Nadeem; Masood, Nayyer; Khattak, Ahmad Saeed; Ramzan, Naeem

doi:10.3390/s21248227

Cited by 14 publications

(6 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several studies have proposed effective systems for recognizing transition states in human action. For instance, real-time ML-based methods have been employed for automatic segmentation and recognition of continuous human daily action by integrating change point detection algorithms with smart home action recognition [37], [38]. Among them, an online change point detection strategy was introduced [36] that segmented continuous multivariate timeseries smartphone sensor data and applied it to a transitionaware action recognition framework based on the hypothesis and verification principle.…”

Section: Transition-aware Action Recognitionsmentioning

confidence: 99%

Smarter Aging: Developing a Foundational Elderly Activity Monitoring System With AI and GUI Interface

Htet,

Zin,

Tin

et al. 2024

IEEE Access

View full text Add to dashboard Cite

The global rise in the elderly population, which presents challenges to healthcare systems owing to labor shortages in caregiving facilities, necessitates innovative solutions for elderly care services. Smart aging technologies such as robotic companions and digital home gadgets, offer a solution to these challenges by improving the elderly's quality of life and assisting caregivers. However, limitations in data privacy, real-time processing, and reliability often hinder the effectiveness of the existing technologies. Among these, privacy concerns are a major barrier to ensuring user trust and ethical implementation. Therefore, this study proposes a more effective approach for smart aging through elderly activity monitoring that prioritizes data privacy. The proposed system utilizes stereo depth cameras to monitor the activities of the elderly. Data were collected from real-world environments with the participation of six elderly individuals from a care center and hospital. This system focuses on recognizing common daily actions of the elderly including sitting, standing, lying down, and seated in a wheelchair. Additionally, it recognizes transition states (in-between actions such as changing from sitting to standing) that are crucial for assessing balance issues. By integrating motion information with a deep-learning architecture, the system achieved a high accuracy of 99.42% in recognizing daily actions in real-time. This high accuracy was maintained even with minimal data from new environments through transfer learning, and the adaptability of this model ensured its potential for real-world applications. For intuitive interaction between the caregivers and the system, a user-friendly graphical interface (GUI) was also designed in the proposed approach.

show abstract

Section: Transition-aware Action Recognitionsmentioning

confidence: 99%

Smarter Aging: Developing a Foundational Elderly Activity Monitoring System With AI and GUI Interface

Htet,

Zin,

Tin

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The results of hybrid deep learning model consists of CNN, LSTM ,and BiLSTM in [56] exhibited the accuracies of 98.38% on the Human Activity dataset with transition and basic activities and 96.11% on the HAPT dataset. In [57] article, a hybrid deep CNN-LSTM with Self-Attention model using Wearable Sensors for the classification of daily activities and get accuracy 93.11% and 98.76% for UCI-HAR and MHEALTH datasets.…”

Section: Hybrid Deep Learning-based Model Harmentioning

confidence: 99%

Leveraging LDA Feature Extraction to Augment Human Activity Recognition Accuracy

Vazan,

Sharifi,

Farahani

et al. 2024

Preprint

View full text Add to dashboard Cite

This research introduces a hybrid feature extraction approach that combines Linear Discriminant Analysis (LDA) and Multilayer Perceptron (MLP) methods to address the challenges of reducing feature vector dimensionality and accurately classifying smartphone-based human activities. Moreover, to refine activity classification accuracy, Support Vector Machine (SVM) optimization with Stochastic Gradient Descent (SGD) is employed. LDA, a statistical tool, is leveraged to derive a new feature space for data projection, enhancing class separation and test feature label prediction. The proposed approach, named LMSS, was evaluated using the UCI-HAR dataset and compared with state-of-the-art models. The results demonstrate that the proposed approach outperformed the best-performing method over this dataset. It achieved an accuracy rate of 99.52%, precision of 99.55%, recall of 99.53%, and an F1-score of 99.54%, highlighting the effectiveness of the proposed method in accurately classifying the data.

show abstract

“…Previous research on human activity recognition (HAR) using artificial intelligence (AI) and machine learning (ML) has focused primarily on accurately predicting classes of known, human-labeled activities for each observation of network device telemetry data for specific human subjects. These models have typically been trained on labeled activities from specific subjects, and as such generally have subject dependency recognition constraints and their accuracy in identifying activities depends in large part on the feature selection process (1), (10), and (11). These studies have indicated that there are potentially several machine learning and deep learning algorithms that can be applied with varying degrees of success to achieve some degree of reliability for multinomial HAR classification accuracies.…”

Section: Statement Of the Problemmentioning

confidence: 99%

Gradient Descent Machine Learning with Equivalency Testing for Non-Subject Dependent Applications in Human Activity Recognition

Woolman

Pickard

2022

EAI Endorsed Trans Context Aware Syst App

View full text Add to dashboard Cite

INTRODUCTION: A solution to subject-independent HAR prediction through machine learning classification algorithms using statistical equivalency for comparative analysis between independent groups with non-subject training dependencies.OBJECTIVES: To indicate that the multinomial predictive classification model that was trained and optimized on the one-subject control group is at least partially extensible to multiple independent experiment groups for at least one activity class.METHODS: Gradient boosted machine multinomial classification algorithm is trained on a single individual with the classifier trained on all activity classes as a multinomial classification problem.RESULTS: Levene-Wellek-Welch (LWW) Statistic calculated as 0.021, with a Critical Value for LWW of 0.026, using an alpha of 0.05.CONCLUSION: Confirmed falsifiability that incorporates reproducible methods into the quasi-experiment design applied to the field of machine learning for human activity recognition.

show abstract

A Novel Hybrid Deep Learning Model for Human Activity Recognition Based on Transitional Activities

Cited by 14 publications

References 49 publications

Smarter Aging: Developing a Foundational Elderly Activity Monitoring System With AI and GUI Interface

Smarter Aging: Developing a Foundational Elderly Activity Monitoring System With AI and GUI Interface

Leveraging LDA Feature Extraction to Augment Human Activity Recognition Accuracy

Gradient Descent Machine Learning with Equivalency Testing for Non-Subject Dependent Applications in Human Activity Recognition

Contact Info

Product

Resources

About