Gesture Recognition Achieved by Utilizing LoRa Signals and Deep Learning

This study proposes a novel gesture recognition system based on LoRa technology, integrating advanced signal preprocessing, adaptive segmentation algorithms, and an improved SS-ResNet50 deep learning model. Through the combination of residual learning and dynamic convolution techniques, the SS-ResNe...

Full description

Saved in:
Bibliographic Details
Main Authors: Peihao Zhang, Baofeng Zhao
Format: Article
Language:English
Published: MDPI AG 2025-02-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/5/1446
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850030222351532032
author Peihao Zhang
Baofeng Zhao
author_facet Peihao Zhang
Baofeng Zhao
author_sort Peihao Zhang
collection DOAJ
description This study proposes a novel gesture recognition system based on LoRa technology, integrating advanced signal preprocessing, adaptive segmentation algorithms, and an improved SS-ResNet50 deep learning model. Through the combination of residual learning and dynamic convolution techniques, the SS-ResNet50 model significantly enhances the extraction capability of multi-scale gesture features, thereby augmenting the classification accuracy. To counter environmental noise and static interferences, an adaptive segmentation approach based on sliding window variance analysis is introduced in the research. This method effectively increases data diversity while preserving the specific components of gestures. Experimental outcomes indicate that the system exhibits strong robustness in cross-scenario and cross-device tests, with an average recognition accuracy of over 95% for six gestures. The system’s low power consumption, long-distance communication, and strong anti-interference capabilities offer broad prospects for its application in complex environments, particularly in resource-constrained scenarios such as underground mine gesture monitoring and remote control in dynamic environments and other practical applications. This study demonstrates the feasibility of gesture recognition systems based on LoRa technology and provides a new solution for low-power, long-distance non-contact gesture recognition.
format Article
id doaj-art-b60e8ba7ef2a4b0889f1bf744c49390e
institution DOAJ
issn 1424-8220
language English
publishDate 2025-02-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-b60e8ba7ef2a4b0889f1bf744c49390e2025-08-20T02:59:16ZengMDPI AGSensors1424-82202025-02-01255144610.3390/s25051446Gesture Recognition Achieved by Utilizing LoRa Signals and Deep LearningPeihao Zhang0Baofeng Zhao1Taiyuan University of Technology, Taiyuan 030024, ChinaTaiyuan University of Technology, Taiyuan 030024, ChinaThis study proposes a novel gesture recognition system based on LoRa technology, integrating advanced signal preprocessing, adaptive segmentation algorithms, and an improved SS-ResNet50 deep learning model. Through the combination of residual learning and dynamic convolution techniques, the SS-ResNet50 model significantly enhances the extraction capability of multi-scale gesture features, thereby augmenting the classification accuracy. To counter environmental noise and static interferences, an adaptive segmentation approach based on sliding window variance analysis is introduced in the research. This method effectively increases data diversity while preserving the specific components of gestures. Experimental outcomes indicate that the system exhibits strong robustness in cross-scenario and cross-device tests, with an average recognition accuracy of over 95% for six gestures. The system’s low power consumption, long-distance communication, and strong anti-interference capabilities offer broad prospects for its application in complex environments, particularly in resource-constrained scenarios such as underground mine gesture monitoring and remote control in dynamic environments and other practical applications. This study demonstrates the feasibility of gesture recognition systems based on LoRa technology and provides a new solution for low-power, long-distance non-contact gesture recognition.https://www.mdpi.com/1424-8220/25/5/1446gesture recognitionLoRadeep learningfeature extractionsignal processing
spellingShingle Peihao Zhang
Baofeng Zhao
Gesture Recognition Achieved by Utilizing LoRa Signals and Deep Learning
Sensors
gesture recognition
LoRa
deep learning
feature extraction
signal processing
title Gesture Recognition Achieved by Utilizing LoRa Signals and Deep Learning
title_full Gesture Recognition Achieved by Utilizing LoRa Signals and Deep Learning
title_fullStr Gesture Recognition Achieved by Utilizing LoRa Signals and Deep Learning
title_full_unstemmed Gesture Recognition Achieved by Utilizing LoRa Signals and Deep Learning
title_short Gesture Recognition Achieved by Utilizing LoRa Signals and Deep Learning
title_sort gesture recognition achieved by utilizing lora signals and deep learning
topic gesture recognition
LoRa
deep learning
feature extraction
signal processing
url https://www.mdpi.com/1424-8220/25/5/1446
work_keys_str_mv AT peihaozhang gesturerecognitionachievedbyutilizinglorasignalsanddeeplearning
AT baofengzhao gesturerecognitionachievedbyutilizinglorasignalsanddeeplearning