Hybrid Deep Learning Methods for Human Activity Recognition and Localization in Outdoor Environments

Activity recognition and localization in outdoor environments involve identifying and tracking human movements using sensor data, computer vision, or deep learning techniques. This process is crucial for applications such as smart surveillance, autonomous systems, healthcare monitoring, and human–co...

Full description

Saved in:
Bibliographic Details
Main Authors: Yirga Yayeh Munaye, Metadel Addis, Yenework Belayneh, Atinkut Molla, Wasyihun Admass
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Algorithms
Subjects:
Online Access:https://www.mdpi.com/1999-4893/18/4/235
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850183667124535296
author Yirga Yayeh Munaye
Metadel Addis
Yenework Belayneh
Atinkut Molla
Wasyihun Admass
author_facet Yirga Yayeh Munaye
Metadel Addis
Yenework Belayneh
Atinkut Molla
Wasyihun Admass
author_sort Yirga Yayeh Munaye
collection DOAJ
description Activity recognition and localization in outdoor environments involve identifying and tracking human movements using sensor data, computer vision, or deep learning techniques. This process is crucial for applications such as smart surveillance, autonomous systems, healthcare monitoring, and human–computer interaction. However, several challenges arise in outdoor settings, including varying lighting conditions, occlusions caused by obstacles, environmental noise, and the complexity of differentiating between similar activities. This study presents a hybrid deep learning approach that integrates human activity recognition and localization in outdoor environments using Wi-Fi signal data. The study focuses on applying the hybrid long short-term memory–bi-gated recurrent unit (LSTM-BIGRU) architecture, designed to enhance the accuracy of activity recognition and location estimation. Moreover, experiments were conducted using a real-world dataset collected with the PicoScene Wi-Fi sensing device, which captures both magnitude and phase information. The results demonstrated a significant improvement in accuracy for both activity recognition and localization tasks. To mitigate data scarcity, this study utilized the conditional tabular generative adversarial network (CTGAN) to generate synthetic channel state information (CSI) data. Additionally, carrier frequency offset (CFO) and cyclic shift delay (CSD) preprocessing techniques were implemented to mitigate phase fluctuations. The experiments were conducted in a line-of-sight (LoS) outdoor environment, where CSI data were collected using the PicoScene Wi-Fi sensor platform across four different activities at outdoor locations. Finally, a comparative analysis of the experimental results highlights the superior performance of the proposed hybrid LSTM-BIGRU model, achieving 99.81% and 98.93% accuracy for activity recognition and location prediction, respectively.
format Article
id doaj-art-c126412a4df14a7d9208343bb789a5bf
institution OA Journals
issn 1999-4893
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Algorithms
spelling doaj-art-c126412a4df14a7d9208343bb789a5bf2025-08-20T02:17:19ZengMDPI AGAlgorithms1999-48932025-04-0118423510.3390/a18040235Hybrid Deep Learning Methods for Human Activity Recognition and Localization in Outdoor EnvironmentsYirga Yayeh Munaye0Metadel Addis1Yenework Belayneh2Atinkut Molla3Wasyihun Admass4Department of Information Technology, Injibara University, Injibara 40, EthiopiaDepartment of Computer Science, Dire Dawa University, Dire Dawa 1362, EthiopiaDepartment of Information Technology, Injibara University, Injibara 40, EthiopiaDepartment of Information Technology, Injibara University, Injibara 40, EthiopiaSchool of Software Engineering, University of Science and Technology of China, Suzhou 215123, ChinaActivity recognition and localization in outdoor environments involve identifying and tracking human movements using sensor data, computer vision, or deep learning techniques. This process is crucial for applications such as smart surveillance, autonomous systems, healthcare monitoring, and human–computer interaction. However, several challenges arise in outdoor settings, including varying lighting conditions, occlusions caused by obstacles, environmental noise, and the complexity of differentiating between similar activities. This study presents a hybrid deep learning approach that integrates human activity recognition and localization in outdoor environments using Wi-Fi signal data. The study focuses on applying the hybrid long short-term memory–bi-gated recurrent unit (LSTM-BIGRU) architecture, designed to enhance the accuracy of activity recognition and location estimation. Moreover, experiments were conducted using a real-world dataset collected with the PicoScene Wi-Fi sensing device, which captures both magnitude and phase information. The results demonstrated a significant improvement in accuracy for both activity recognition and localization tasks. To mitigate data scarcity, this study utilized the conditional tabular generative adversarial network (CTGAN) to generate synthetic channel state information (CSI) data. Additionally, carrier frequency offset (CFO) and cyclic shift delay (CSD) preprocessing techniques were implemented to mitigate phase fluctuations. The experiments were conducted in a line-of-sight (LoS) outdoor environment, where CSI data were collected using the PicoScene Wi-Fi sensor platform across four different activities at outdoor locations. Finally, a comparative analysis of the experimental results highlights the superior performance of the proposed hybrid LSTM-BIGRU model, achieving 99.81% and 98.93% accuracy for activity recognition and location prediction, respectively.https://www.mdpi.com/1999-4893/18/4/235outdoor environmenthuman activitydeep learningWi-Fi signals
spellingShingle Yirga Yayeh Munaye
Metadel Addis
Yenework Belayneh
Atinkut Molla
Wasyihun Admass
Hybrid Deep Learning Methods for Human Activity Recognition and Localization in Outdoor Environments
Algorithms
outdoor environment
human activity
deep learning
Wi-Fi signals
title Hybrid Deep Learning Methods for Human Activity Recognition and Localization in Outdoor Environments
title_full Hybrid Deep Learning Methods for Human Activity Recognition and Localization in Outdoor Environments
title_fullStr Hybrid Deep Learning Methods for Human Activity Recognition and Localization in Outdoor Environments
title_full_unstemmed Hybrid Deep Learning Methods for Human Activity Recognition and Localization in Outdoor Environments
title_short Hybrid Deep Learning Methods for Human Activity Recognition and Localization in Outdoor Environments
title_sort hybrid deep learning methods for human activity recognition and localization in outdoor environments
topic outdoor environment
human activity
deep learning
Wi-Fi signals
url https://www.mdpi.com/1999-4893/18/4/235
work_keys_str_mv AT yirgayayehmunaye hybriddeeplearningmethodsforhumanactivityrecognitionandlocalizationinoutdoorenvironments
AT metadeladdis hybriddeeplearningmethodsforhumanactivityrecognitionandlocalizationinoutdoorenvironments
AT yeneworkbelayneh hybriddeeplearningmethodsforhumanactivityrecognitionandlocalizationinoutdoorenvironments
AT atinkutmolla hybriddeeplearningmethodsforhumanactivityrecognitionandlocalizationinoutdoorenvironments
AT wasyihunadmass hybriddeeplearningmethodsforhumanactivityrecognitionandlocalizationinoutdoorenvironments