Hand-Crafted Features With A Simple Deep Learning Architecture For Sensor-Based Human Activity Recognition

With the growth in the wearable device market, wearable sensor-based human activity recognition systems have been gaining increasing interest in research because of their rising demands in many areas. This research presents a novel sensor-based human activity recognition system that utilizes a uniqu...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Albadawi, Yaman (author)
مؤلفون آخرون: Shanableh, Tamer (author)
التنسيق: article
منشور في: 2024
الموضوعات:
الوصول للمادة أونلاين:https://hdl.handle.net/11073/25564
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1864513444170956800
author Albadawi, Yaman
author2 Shanableh, Tamer
author2_role author
author_facet Albadawi, Yaman
Shanableh, Tamer
author_role author
dc.creator.none.fl_str_mv Albadawi, Yaman
Shanableh, Tamer
dc.date.none.fl_str_mv 2024-07-21T08:25:11Z
2024-07-21T08:25:11Z
2024-07-10
dc.format.none.fl_str_mv application/pdf
dc.identifier.none.fl_str_mv Albadawi, Y., & Shanableh, T. (2024). Hand-Crafted Features With A Simple Deep Learning Architecture For Sensor-Based Human Activity Recognition. In IEEE Sensors Journal (pp. 1–1). Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/jsen.2024.3422272
1558-1748
https://hdl.handle.net/11073/25564
10.1109/JSEN.2024.3422272
dc.language.none.fl_str_mv en_US
dc.publisher.none.fl_str_mv IEEE
dc.relation.none.fl_str_mv https://doi.org/10.1109/JSEN.2024.3422272
dc.subject.none.fl_str_mv Bidirectional long-short-term-memory
Long-short-term-memory
Sensor-based human activity recognition
Attention
Time-series differencing
dc.title.none.fl_str_mv Hand-Crafted Features With A Simple Deep Learning Architecture For Sensor-Based Human Activity Recognition
dc.type.none.fl_str_mv Peer-Reviewed
Postprint
info:eu-repo/semantics/publishedVersion
info:eu-repo/semantics/article
description With the growth in the wearable device market, wearable sensor-based human activity recognition systems have been gaining increasing interest in research because of their rising demands in many areas. This research presents a novel sensor-based human activity recognition system that utilizes a unique feature extraction technique associated with a deep learning method for classification. One of the main contributions of this work is dividing the sensor sequences time-wise into non-overlapping 2D segments. Then, statistical features are computed from each 2D segment using two approaches; the first approach computes features from the raw sensor readings, while the second approach applies time-series differencing to sensor readings prior to feature calculations. Applying time-series differencing to 2D segments helps in identifying the underlying structure and dynamics of the sensor reading across time. This work experiments with different numbers of 2D segments of sensor reading sequences. Also, it reports results with and without the use of different components of the proposed system. Additionally, it analyses the best-performing models’ complexity, comparing them with other models trained by integrating the proposed method with an existing transformer network. All of these arrangements are tested with different deep-learning architectures supported by an attention layer to enhance the model. Four benchmark datasets are used to perform several experiments, namely, mHealth, USC-HAD, UCI-HAR, and DSA. The experimental results revealed that the proposed system outperforms human activity recognition rates reported in the most recent studies. Specifically, this work reports recognition rates of 99.17%, 81.07%, 99.44%, and 94.03% for the four datasets, respectively.
format article
id aus_491b48522bf84b04a96b6b13f0ecc3dc
identifier_str_mv Albadawi, Y., & Shanableh, T. (2024). Hand-Crafted Features With A Simple Deep Learning Architecture For Sensor-Based Human Activity Recognition. In IEEE Sensors Journal (pp. 1–1). Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/jsen.2024.3422272
1558-1748
10.1109/JSEN.2024.3422272
language_invalid_str_mv en_US
network_acronym_str aus
network_name_str aus
oai_identifier_str oai:repository.aus.edu:11073/25564
publishDate 2024
publisher.none.fl_str_mv IEEE
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
spelling Hand-Crafted Features With A Simple Deep Learning Architecture For Sensor-Based Human Activity RecognitionAlbadawi, YamanShanableh, TamerBidirectional long-short-term-memoryLong-short-term-memorySensor-based human activity recognitionAttentionTime-series differencingWith the growth in the wearable device market, wearable sensor-based human activity recognition systems have been gaining increasing interest in research because of their rising demands in many areas. This research presents a novel sensor-based human activity recognition system that utilizes a unique feature extraction technique associated with a deep learning method for classification. One of the main contributions of this work is dividing the sensor sequences time-wise into non-overlapping 2D segments. Then, statistical features are computed from each 2D segment using two approaches; the first approach computes features from the raw sensor readings, while the second approach applies time-series differencing to sensor readings prior to feature calculations. Applying time-series differencing to 2D segments helps in identifying the underlying structure and dynamics of the sensor reading across time. This work experiments with different numbers of 2D segments of sensor reading sequences. Also, it reports results with and without the use of different components of the proposed system. Additionally, it analyses the best-performing models’ complexity, comparing them with other models trained by integrating the proposed method with an existing transformer network. All of these arrangements are tested with different deep-learning architectures supported by an attention layer to enhance the model. Four benchmark datasets are used to perform several experiments, namely, mHealth, USC-HAD, UCI-HAR, and DSA. The experimental results revealed that the proposed system outperforms human activity recognition rates reported in the most recent studies. Specifically, this work reports recognition rates of 99.17%, 81.07%, 99.44%, and 94.03% for the four datasets, respectively.American University of SharjahIEEE2024-07-21T08:25:11Z2024-07-21T08:25:11Z2024-07-10Peer-ReviewedPostprintinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfAlbadawi, Y., & Shanableh, T. (2024). Hand-Crafted Features With A Simple Deep Learning Architecture For Sensor-Based Human Activity Recognition. In IEEE Sensors Journal (pp. 1–1). Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/jsen.2024.34222721558-1748https://hdl.handle.net/11073/2556410.1109/JSEN.2024.3422272en_UShttps://doi.org/10.1109/JSEN.2024.3422272oai:repository.aus.edu:11073/255642024-08-22T12:07:53Z
spellingShingle Hand-Crafted Features With A Simple Deep Learning Architecture For Sensor-Based Human Activity Recognition
Albadawi, Yaman
Bidirectional long-short-term-memory
Long-short-term-memory
Sensor-based human activity recognition
Attention
Time-series differencing
status_str publishedVersion
title Hand-Crafted Features With A Simple Deep Learning Architecture For Sensor-Based Human Activity Recognition
title_full Hand-Crafted Features With A Simple Deep Learning Architecture For Sensor-Based Human Activity Recognition
title_fullStr Hand-Crafted Features With A Simple Deep Learning Architecture For Sensor-Based Human Activity Recognition
title_full_unstemmed Hand-Crafted Features With A Simple Deep Learning Architecture For Sensor-Based Human Activity Recognition
title_short Hand-Crafted Features With A Simple Deep Learning Architecture For Sensor-Based Human Activity Recognition
title_sort Hand-Crafted Features With A Simple Deep Learning Architecture For Sensor-Based Human Activity Recognition
topic Bidirectional long-short-term-memory
Long-short-term-memory
Sensor-based human activity recognition
Attention
Time-series differencing
url https://hdl.handle.net/11073/25564