Optimal Sensor Placement and Multimodal Fusion for Human Activity Recognition in Agricultural Tasks

被引:2
|
作者
Benos, Lefteris [1 ]
Tsaopoulos, Dimitrios [1 ]
Tagarakis, Aristotelis C. [1 ]
Kateris, Dimitrios [1 ]
Bochtis, Dionysis [1 ,2 ]
机构
[1] Ctr Res & Technol Hellas CERTH, Inst Bioecon & Agritechnol IBO, GR-57001 Thessaloniki, Greece
[2] FarmB Digital Agr, Doiraniis 17, Thessaloniki GR-54639, Greece
来源
APPLIED SCIENCES-BASEL | 2024年 / 14卷 / 18期
关键词
Long Short-Term Memory (LSTM) networks; wearable sensors; multi-sensor information fusion; human-robot collaboration; human factors; cost-optimal system configuration; ROBOTS; SPINE;
D O I
10.3390/app14188520
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
This study examines the impact of sensor placement and multimodal sensor fusion on the performance of a Long Short-Term Memory (LSTM)-based model for human activity classification taking place in an agricultural harvesting scenario involving human-robot collaboration. Data were collected from twenty participants performing six distinct activities using five wearable inertial measurement units placed at various anatomical locations. The signals collected from the sensors were first processed to eliminate noise and then input into an LSTM neural network for recognizing features in sequential time-dependent data. Results indicated that the chest-mounted sensor provided the highest F1-score of 0.939, representing superior performance over other placements and combinations of them. Moreover, the magnetometer surpassed the accelerometer and gyroscope, highlighting its superior ability to capture crucial orientation and motion data related to the investigated activities. However, multimodal fusion of accelerometer, gyroscope, and magnetometer data showed the benefit of integrating data from different sensor types to improve classification accuracy. The study emphasizes the effectiveness of strategic sensor placement and fusion in optimizing human activity recognition, thus minimizing data requirements and computational expenses, and resulting in a cost-optimal system configuration. Overall, this research contributes to the development of more intelligent, safe, cost-effective adaptive synergistic systems that can be integrated into a variety of applications.
引用
收藏
页数:16
相关论文
共 50 条
  • [31] Lightweight Multiattention Enhanced Fusion Network for Omnidirectional Human Activity Recognition With FMCW Radar
    Li, Xinglong
    Qiu, Ye
    Deng, Zhenmiao
    Liu, Xinyu
    Huang, Xiaohong
    IEEE INTERNET OF THINGS JOURNAL, 2025, 12 (05): : 5755 - 5768
  • [32] A Dual Pipeline With Spatio-Temporal Attention Fusion Approach for Human Activity Recognition
    Wang, Xiaodong
    Li, Ying
    Fang, Aiqing
    He, Pei
    Guo, Yangming
    IEEE SENSORS JOURNAL, 2024, 24 (15) : 25150 - 25162
  • [33] Multi-sensor fusion based on multiple classifier systems for human activity identification
    Nweke, Henry Friday
    Teh, Ying Wah
    Mujtaba, Ghulam
    Alo, Uzoma Rita
    Al-garadi, Mohammed Ali
    HUMAN-CENTRIC COMPUTING AND INFORMATION SCIENCES, 2019, 9 (01)
  • [34] Spectro-Temporal Modeling for Human Activity Recognition Using a Radar Sensor Network
    Luo, Fei
    Bodanese, Eliane
    Khan, Salabat
    Wu, Kaishun
    IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2023, 61
  • [35] HARMamba: Efficient and Lightweight Wearable Sensor Human Activity Recognition Based on Bidirectional Mamba
    Li, Shuangjian
    Zhu, Tao
    Duan, Furong
    Chen, Liming
    Ning, Huansheng
    Nugent, Christopher
    Wan, Yaping
    IEEE INTERNET OF THINGS JOURNAL, 2025, 12 (03): : 2373 - 2384
  • [36] A Survey on Human Activity Recognition Using Deep Learning Techniques and Wearable Sensor Data
    Dua, Nidhi
    Singh, Shiva Nand
    Challa, Sravan Kumar
    Semwal, Vijay Bhaskar
    Kumar, M. L. S. Sai
    MACHINE LEARNING, IMAGE PROCESSING, NETWORK SECURITY AND DATA SCIENCES, MIND 2022, PT I, 2022, 1762 : 52 - 71
  • [37] Outlier Detection in Wearable Sensor Data for Human Activity Recognition (HAR) Based on DRNNs
    Munoz-Organero, Mario
    IEEE ACCESS, 2019, 7 : 74422 - 74436
  • [38] Binarized Neural Network for Edge Intelligence of Sensor-Based Human Activity Recognition
    Luo, Fei
    Khan, Salabat
    Huang, Yandao
    Wu, Kaishun
    IEEE TRANSACTIONS ON MOBILE COMPUTING, 2023, 22 (03) : 1356 - 1368
  • [39] Enhancing Sensor-Based Human Activity Recognition using Efficient Channel Attention
    Jitpattanakul, Anuchit
    Mekruksavanich, Sakorn
    2023 IEEE SENSORS, 2023,
  • [40] Merging-Squeeze-Excitation Feature Fusion for Human Activity Recognition Using Wearable Sensors
    Laitrakun, Seksan
    APPLIED SCIENCES-BASEL, 2023, 13 (04):