Performance of long short-term memory networks in predicting athlete injury risk

被引:0
|
作者
Tao, Hong [1 ]
Deng, Yue [1 ]
Xiang, Yunqiu [1 ]
Liu, Long [1 ]
机构
[1] Chongqing Presch Educ Coll, Sch Phys Educ, Chongqing 404047, Peoples R China
关键词
Athlete injury; risk prediction; long short-term memory network; performance analysis; temporal dependence; LSTM; ALGORITHM; AREA;
D O I
10.3233/JCM-247563Press
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
Conventional approaches to forecasting the risk of athlete injuries are constrained by their narrow scope in feature extraction, often failing to adequately account for temporal dependencies and the effects of long-term memory. This paper enhances the Long Short-Term Memory (LSTM) network, specifically tailoring it to harness temporal data pertaining to athletes. This advancement significantly boosts the accuracy and effectiveness of predicting the risk of injuries among athletes. The network structure of the LSTM model was improved, and the collected data was converted into the temporal data form of the LSTM input. Finally, historical data labeled with injury labels were used to train the improved LSTM model, and gradient descent iterative optimization was used to adjust the parameters of the improved LSTM model. The improved LSTM network model was compared with the traditional athlete injury risk prediction model in terms of performance. The incorporation of enhanced LSTM networks for the analysis of temporal athlete data holds significant research significance. This approach has the potential to substantially enhance the accuracy and effectiveness of athlete injury risk prediction, contributing to a deeper understanding of the temporal dynamics influencing injuries in sports.
引用
收藏
页码:3155 / 3171
页数:17
相关论文
共 50 条
  • [1] Tailings Pond Risk Prediction Using Long Short-Term Memory Networks
    Li, Jianwei
    Chen, Haoyu
    Zhou, Ting
    Li, Xiaowen
    IEEE ACCESS, 2019, 7 : 182527 - 182537
  • [2] ANALYSIS AND COMPARISON OF LONG SHORT-TERM MEMORY NETWORKS SHORT-TERM TRAFFIC PREDICTION PERFORMANCE
    Dogan, Erdem
    SCIENTIFIC JOURNAL OF SILESIAN UNIVERSITY OF TECHNOLOGY-SERIES TRANSPORT, 2020, 107 : 19 - 32
  • [3] Early Prediction of Pressure Injury with Long Short-term Memory Networks
    Fang, Xudong
    Wang, Yunfeng
    Maeda, Ryutaro
    Kitayama, Akio
    Takashi, En
    SENSORS AND MATERIALS, 2022, 34 (07) : 2759 - 2769
  • [4] Predicting Hourly Bitcoin Prices Based on Long Short-Term Memory Neural Networks
    Schulte, Maximilian
    Eggert, Mathias
    INNOVATION THROUGH INFORMATION SYSTEMS, VOL II: A COLLECTION OF LATEST RESEARCH ON TECHNOLOGY ISSUES, 2021, 47 : 754 - 769
  • [5] Performance Analysis of Long Short-Term Memory Predictive Neural Networks on Time Series Data
    Bolboaca, Roland
    Haller, Piroska
    MATHEMATICS, 2023, 11 (06)
  • [6] Diagnosing Dysarthria with Long Short-Term Memory Networks
    Mayle, Alex
    Mou, Zhiwei
    Bunescu, Razvan
    Mirshekarian, Sadegh
    Xu, Li
    Liu, Chang
    INTERSPEECH 2019, 2019, : 4514 - 4518
  • [7] Short-Term Traffic Prediction Using Long Short-Term Memory Neural Networks
    Abbas, Zainab
    Al-Shishtawy, Ahmad
    Girdzijauskas, Sarunas
    Vlassov, Vladimir
    2018 IEEE INTERNATIONAL CONGRESS ON BIG DATA (IEEE BIGDATA CONGRESS), 2018, : 57 - 65
  • [8] LONG SHORT-TERM MEMORY NEURAL NETWORKS FOR PREDICTING DYNAMIC RESPONSE OF STRUCTURES OF HIGH COMPLEXITIES
    Liao, Yabin
    Poudel, Biswas
    Kumar, Priyanshu
    Sensmeier, Mark
    PROCEEDINGS OF ASME 2022 INTERNATIONAL MECHANICAL ENGINEERING CONGRESS AND EXPOSITION, IMECE2022, VOL 5, 2022,
  • [9] Forecasting container throughput with long short-term memory networks
    Shankar, Sonali
    Ilavarasan, P. Vigneswara
    Punia, Sushil
    Singh, Surya Prakash
    INDUSTRIAL MANAGEMENT & DATA SYSTEMS, 2020, 120 (03) : 425 - 441
  • [10] Facade Layout Completion with Long Short-Term Memory Networks
    Hensel, Simon
    Goebbels, Steffen
    Kada, Martin
    COMPUTER VISION, IMAGING AND COMPUTER GRAPHICS THEORY AND APPLICATIONS, VISIGRAPP 2021, 2023, 1691 : 21 - 40