The International Arab Journal of Information Technology (IAJIT)


Evaluation Model of Athletes’ Lower Extremity Training Ability Based on LSTM Algorithm

To achieve intelligent evaluation of the lower limb movement ability of athletes with sports disabilities, this article selects young athletes and middle-aged and young athletes with sports disabilities as the research objects, and healthy young athletes as the control group. Gait videos, GRF and knee angles of the subjects were collected to extract and analyse gait contours and features. The improved Visual Background extractor (ViBe) algorithm has the highest accuracy of 0.978 in PETS2006 video sequences; the recall rate of three algorithms in Highway video sequence is the highest, and the recall rate of improved ViBe algorithm is the highest, up to 0.965. AtƐ=0.7, the accuracy of the improved myloss training set is higher than that corresponding to other values; when the number of iterations is 98, the accuracy rate of improved myloss training set is 0.963, while the accuracy rate corresponding to the cross entropy loss function is 0.945. When the number of iterations is 151, the accuracy rate of the Xeption LSTM model is 0.956, higher than that of other models. Among corresponding mean ± standard deviation (GSA- MS) indicators, the GSA-MS values of Group L are significantly higher than those of group N and group Z (P<0.001). The correlation between GAS indicators and Gait Abnormality Rating Scale (GARS-M) is strong, with a correlation coefficient of 0.90.

[1] Ercolano G. and Rossi S., “Combining CNN and LSTM for Activity of Daily Living Recognition with a 3D Matrix Skeleton Representation,” Intelligent Service Robotics, vol. 14, no. 8, pp. 1- 11, 2021. DOI:10.1007/s11370-021-00358-7

[2] Guan Y., Fang J., and Wu X., “Multi-Pose Face Recognition Using Cascade Alignment Network and Incremental Clustering,” Signal, Image and Video Processing, vol. 15, pp. 63-71, 2021.

[3] Higgins M., Defroda S., Yang D., Brown S., and Mulcahey M., “Professional Athlete Return to Play and Performance After Shoulder Arthroscopy Varies by Sport,” Arthroscopy Sports Medicine and Rehabilitation, vol. 2. no. 3, pp. 391-397, 2021. DOI: 10.1016/j.asmr.2020.10.001

[4] Jones S., Fuller J., Chalmers S., Debenedictis T., and Zacharia A., “Combining Physical performance and Functional Movement Screen Testing to Identify Elite Junior Australian Football Athletes at Risk of Injury,” Scandinavian Journal of Medicine and Science in Sports, vol. 30 no. 8, pp. 1449-1456, 2020. doi: 10.1111/sms.13686

[5] Lebedev G., Gureeva A., and Tikhonova Y., “Software System for Dynamic Athlete Health Monitoring,” Procedia Computer Science, vol. 112 no. 1, pp. 1664-1669, 2017.

[6] Manju D., Seetha M., and Sammulal P., “Early Action Prediction using 3DCNN with LSTM and Bidirectional LSTM,” Turkish Journal of Computer and Mathematics Education, vol. 12 no. 6, pp. 2275-2281, 2021.

[7] Maria-Sacheli L., Laura Z., Matteo P., Santis C., and Pelosi C., “A Functional Limitation to the Lower Limbs Affects the Neural Bases of Motor Imagery of Gait,” NeuroImage: Clinical, vol. 20, pp. 177-187, 2018.  0.7ε=  0.3= 156 The International Arab Journal of Information Technology, Vol. 21, No. 1, January 2024

[8] Nankervis B., Ferguson L., Gosling C., Storr M., and Ilic D., “How Do Professional Australian Football League (AFL) Players Utilise Social Media During Periods of Injury? A Mixed Methods Analysis,” Journal of Science and Medicine in Sport, vol. 21 no. 7, pp. 681-685, 2018. DOI: 10.1016/j.jsams.2017.10.034

[9] Nunes H., Faria E., Martinez P., and Oliveira- Júnior S., “Cardiovascular Health Indicators in Soccer Exercise During Adolescence: Systematic Review,” International Journal of Adolescent Medicine and Health, vol. 33 no. 3, pp. 53-63, 2021. DOI: 10.1515/ijamh-2020-0301

[10] Pandya T., Dale S., Donnison E., and Kluzek S., “Conservative Management of Fifth Metacarpal Head Fracture in a Professional Cricketer: A Case Study and Literature Review,” Clinical Case Reports, vol. 8, no. 9, pp. 1682-1685, 2020. doi: 10.1002/ccr3.2960

[11] Pollen T., Keitt F., and Trojian T., “Do Normative Composite Scores on the Functional Movement Screen Differ Across High School, Collegiate, and Professional Athletes? A Critical Review,” Clinical Journal of Sport Medicine, vol. 31, no. 1, pp. 91-102, 2021. DOI: 10.1097/JSM.0000000000000672

[12] Radarapu R., Gopal A., Madhusudhan N., and Anand K., “Video Summarization and Captioning Using Dynamic Mode Decomposition for Surveillance,” International Journal of Information Technology, vol. 13, no. 9, pp. 1927- 1936, 2021. 00668-0

[13] Ramaswamy S., and Chinnappan J., “RecogNet- LSTM+CNN: A Hybrid Network with Attention Mechanism for Aspect Categorization and Sentiment Classification,” Journal of Intelligent Information Systems, vol. 58, pp. 379-404, 2022.

[14] Strack S., Macdonald C., Valencia E., and Davison M., “Case for the Specialised Sports Physical Therapist to Be an Essential Part of Professional Athlete Care: Letter from America no. 1,” British Journal of Sports Medicine, vol. 53, no. 10, pp. 587-588, 2018. DOI: 10.1136/bjsports-2017- 097575

[15] Su Y., Xia H., Liang Q., and Nie W., “Exposing DeepFake Videos Using Attention Based Convolutional LSTM Network,” Neural Processing Letters, vol. 53, no. 5, pp. 4159-4175, 2021. 6

[16] Surbhi K., Akashdeep S., Amandeep V., Vishal D., and Chahat G., “A Comparative Study on Deep Learning and Machine Learning Models for Human Action Recognition in Aerial Videos,” The International Arab Journal of Information Technology, vol. 20, no. 04, pp. 567 - 574, 2023.

[17] Verma T. and Dubey S., “Prediction of Diseased Rice Plant Using Video Processing and LSTM- Simple Recurrent Neural Network with Comparative Study,” Multimedia Tools and Applications, vol. 80, no. 19, pp. 29267-29298, 2021. x

[18] Yadav S., Tiwari K., Pandey H., and Akbar S., “Skeleton-based Human Activity Recognition Using Convlstm and Guided Feature Learning,” Soft Computing: A Fusion of Foundations, Methodologies and Applications, vol. 26, no. 2, pp. 877-890, 2022. 021-06238-7

[19] Zhang L. and Xiang X., “Video Event Classification Based on Two-Stage Neural Network,” Multimedia Tools and Applications, vol. 79, no. 4, pp. 1-16, 2020.