Enhancing Human Activity Recognition with LoRa Wireless RF Signal Preprocessing and Deep Learning
This paper introduces a novel approach for enhancing human activity recognition through the integration of LoRa wireless RF signal preprocessing and deep learning. We tackle the challenge of extracting features from intricate LoRa signals by scrutinizing the unique propagation process of linearly mo...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-01-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/13/2/264 |
| _version_ | 1797344192610959360 |
|---|---|
| author | Mingxing Nie Liwei Zou Hao Cui Xinhui Zhou Yaping Wan |
| author_facet | Mingxing Nie Liwei Zou Hao Cui Xinhui Zhou Yaping Wan |
| author_sort | Mingxing Nie |
| collection | DOAJ |
| description | This paper introduces a novel approach for enhancing human activity recognition through the integration of LoRa wireless RF signal preprocessing and deep learning. We tackle the challenge of extracting features from intricate LoRa signals by scrutinizing the unique propagation process of linearly modulated LoRa signals—a critical aspect for effective feature extraction. Our preprocessing technique involves converting intricate data into real numbers, utilizing Short-Time Fourier Transform (STFT) to generate spectrograms, and incorporating differential signal processing (DSP) techniques to augment activity recognition accuracy. Additionally, we employ frequency-to-image conversion for the purpose of intuitive interpretation. In comprehensive experiments covering activity classification, identity recognition, room identification, and presence detection, our carefully selected deep learning models exhibit outstanding accuracy. Notably, ConvNext attains 96.7% accuracy in activity classification, 97.9% in identity recognition, and 97.3% in room identification. The Vision TF model excels with 98.5% accuracy in presence detection. Through leveraging LoRa signal characteristics and sophisticated preprocessing techniques, our transformative approach significantly enhances feature extraction, ensuring heightened accuracy and reliability in human activity recognition. |
| first_indexed | 2024-03-08T10:58:48Z |
| format | Article |
| id | doaj.art-04b6f1a5d308464db155af6b4c1c7938 |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-08T10:58:48Z |
| publishDate | 2024-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-04b6f1a5d308464db155af6b4c1c79382024-01-26T16:12:22ZengMDPI AGElectronics2079-92922024-01-0113226410.3390/electronics13020264Enhancing Human Activity Recognition with LoRa Wireless RF Signal Preprocessing and Deep LearningMingxing Nie0Liwei Zou1Hao Cui2Xinhui Zhou3Yaping Wan4School of Computer Science, University of South China, Hengyang 421001, ChinaSchool of Computer Science, University of South China, Hengyang 421001, ChinaSchool of Computer Science, University of South China, Hengyang 421001, ChinaSchool of Computer Science, University of South China, Hengyang 421001, ChinaSchool of Computer Science, University of South China, Hengyang 421001, ChinaThis paper introduces a novel approach for enhancing human activity recognition through the integration of LoRa wireless RF signal preprocessing and deep learning. We tackle the challenge of extracting features from intricate LoRa signals by scrutinizing the unique propagation process of linearly modulated LoRa signals—a critical aspect for effective feature extraction. Our preprocessing technique involves converting intricate data into real numbers, utilizing Short-Time Fourier Transform (STFT) to generate spectrograms, and incorporating differential signal processing (DSP) techniques to augment activity recognition accuracy. Additionally, we employ frequency-to-image conversion for the purpose of intuitive interpretation. In comprehensive experiments covering activity classification, identity recognition, room identification, and presence detection, our carefully selected deep learning models exhibit outstanding accuracy. Notably, ConvNext attains 96.7% accuracy in activity classification, 97.9% in identity recognition, and 97.3% in room identification. The Vision TF model excels with 98.5% accuracy in presence detection. Through leveraging LoRa signal characteristics and sophisticated preprocessing techniques, our transformative approach significantly enhances feature extraction, ensuring heightened accuracy and reliability in human activity recognition.https://www.mdpi.com/2079-9292/13/2/264human activity recognitionLoRa wireless RF signal preprocessingdeep learningfeature extractiondifferential signal processing |
| spellingShingle | Mingxing Nie Liwei Zou Hao Cui Xinhui Zhou Yaping Wan Enhancing Human Activity Recognition with LoRa Wireless RF Signal Preprocessing and Deep Learning Electronics human activity recognition LoRa wireless RF signal preprocessing deep learning feature extraction differential signal processing |
| title | Enhancing Human Activity Recognition with LoRa Wireless RF Signal Preprocessing and Deep Learning |
| title_full | Enhancing Human Activity Recognition with LoRa Wireless RF Signal Preprocessing and Deep Learning |
| title_fullStr | Enhancing Human Activity Recognition with LoRa Wireless RF Signal Preprocessing and Deep Learning |
| title_full_unstemmed | Enhancing Human Activity Recognition with LoRa Wireless RF Signal Preprocessing and Deep Learning |
| title_short | Enhancing Human Activity Recognition with LoRa Wireless RF Signal Preprocessing and Deep Learning |
| title_sort | enhancing human activity recognition with lora wireless rf signal preprocessing and deep learning |
| topic | human activity recognition LoRa wireless RF signal preprocessing deep learning feature extraction differential signal processing |
| url | https://www.mdpi.com/2079-9292/13/2/264 |
| work_keys_str_mv | AT mingxingnie enhancinghumanactivityrecognitionwithlorawirelessrfsignalpreprocessinganddeeplearning AT liweizou enhancinghumanactivityrecognitionwithlorawirelessrfsignalpreprocessinganddeeplearning AT haocui enhancinghumanactivityrecognitionwithlorawirelessrfsignalpreprocessinganddeeplearning AT xinhuizhou enhancinghumanactivityrecognitionwithlorawirelessrfsignalpreprocessinganddeeplearning AT yapingwan enhancinghumanactivityrecognitionwithlorawirelessrfsignalpreprocessinganddeeplearning |