Exploring Cutout and Mixup for Robust Human Activity Recognition on Sensor and Skeleton Data

被引:0
|
作者
Dingeto, Hiskias [1 ]
Kim, Juntae [1 ]
机构
[1] Dongguk Univ, Dept Comp Engn, Seoul 04620, South Korea
来源
APPLIED SCIENCES-BASEL | 2024年 / 14卷 / 22期
基金
新加坡国家研究基金会;
关键词
human activity recognition; transformers; mixup; cutout; data augmentation; time-series data; human skeleton data;
D O I
10.3390/app142210286
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
Human Activity Recognition (HAR) is an essential area of research in Artificial Intelligence and Machine Learning, with numerous applications in healthcare, sports science, and smart environments. While several advancements in the field, such as attention-based models and Graph Neural Networks, have made great strides, this work focuses on data augmentation methods that tackle issues like data scarcity and task variability in HAR. In this work, we investigate and expand the use of mixup and cutout data augmentation methods to sensor-based and skeleton-based HAR datasets. These methods were first widely used in Computer Vision and Natural Language Processing. We use both augmentation techniques, customized for time-series and skeletal data, to improve the robustness and performance of HAR models by diversifying the data and overcoming the drawbacks of having limited training data. Specifically, we customize mixup data augmentation for sensor-based datasets and cutout data augmentation for skeleton-based datasets with the goal of improving model accuracy without adding more data. Our results show that using mixup and cutout techniques improves the accuracy and generalization of activity recognition models on both sensor-based and skeleton-based human activity datasets. This work showcases the potential of data augmentation techniques on transformers and Graph Neural Networks by offering a novel method for enhancing time series and skeletal HAR tasks.
引用
收藏
页数:14
相关论文
共 50 条
  • [1] Sensor Data Augmentation from Skeleton Pose Sequences for Improving Human Activity Recognition
    Zolfaghari, Parham
    Rey, Vitor Fortes
    Ray, Lala
    Kim, Hyun
    Suh, Sungho
    Lukowicz, Paul
    2024 INTERNATIONAL CONFERENCE ON ACTIVITY AND BEHAVIOR COMPUTING, ABC 2024, 2024,
  • [2] Joint Orientations from Skeleton Data for Human Activity Recognition
    Franco, Annalisa
    Magnani, Antonio
    Maio, Dario
    IMAGE ANALYSIS AND PROCESSING,(ICIAP 2017), PT I, 2017, 10484 : 152 - 162
  • [3] A Data Efficient Vision Transformer for Robust Human Activity Recognition from the Spectrograms of Wearable Sensor Data
    McQuire, Jamie
    Watson, Paul
    Wright, Nick
    Hiden, Hugo
    Catt, Michael
    2023 IEEE STATISTICAL SIGNAL PROCESSING WORKSHOP, SSP, 2023, : 364 - 368
  • [4] Synthetic Sensor Data for Human Activity Recognition
    Alharbi, Fayez
    Ouarbya, Lahcen
    Ward, Jamie A.
    2020 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2020,
  • [5] Robust Recognition of Human Activities using Smartphone Sensor Data
    Hussein, Ramy
    Lin, Jianzhe
    Madden, Kenneth
    Wang, Z. Jane
    2017 INTERNATIONAL CONFERENCE ON THE FRONTIERS AND ADVANCES IN DATA SCIENCE (FADS), 2017, : 107 - 111
  • [6] Exploring Variability in IoT Data for Human Activity Recognition
    Sakuma, Yuiko
    Kleisarchaki, Sofia
    Gurgen, Levent
    Nishi, Hiroaki
    45TH ANNUAL CONFERENCE OF THE IEEE INDUSTRIAL ELECTRONICS SOCIETY (IECON 2019), 2019, : 5312 - 5318
  • [7] Improved Human Activity Recognition Model based on Sequence Mixup
    Tan, Ran
    Yan, Xuefeng
    2020 IEEE INTL SYMP ON PARALLEL & DISTRIBUTED PROCESSING WITH APPLICATIONS, INTL CONF ON BIG DATA & CLOUD COMPUTING, INTL SYMP SOCIAL COMPUTING & NETWORKING, INTL CONF ON SUSTAINABLE COMPUTING & COMMUNICATIONS (ISPA/BDCLOUD/SOCIALCOM/SUSTAINCOM 2020), 2020, : 417 - 424
  • [8] A multimodal approach for human activity recognition based on skeleton and RGB data
    Franco, Annalisa
    Magnani, Antonio
    Maio, Dario
    PATTERN RECOGNITION LETTERS, 2020, 131 (293-299) : 293 - 299
  • [9] Human activity recognition using skeleton data and support vector machine
    Mandira, Komang G. A.
    Michrandi, Surya N.
    Astuti, Ratna N.
    2ND INTERNATIONAL CONFERENCE ON DATA AND INFORMATION SCIENCE, 2019, 1192
  • [10] A Human Activity Recognition System Based on Dynamic Clustering of Skeleton Data
    Manzi, Alessandro
    Dario, Paolo
    Cavallo, Filippo
    SENSORS, 2017, 17 (05)