Relative Analysis and Performance of Machine Learning Approaches in Sports

Ishwarya, K.; Nithya, A.

doi:10.1109/iceca52323.2021.9676147

Cited by 4 publications

(2 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As shown in equation (5), where θ = fθ 1 , θ 2 , ⋯θ q g denotes coefficient values respective to every feature, θ values. It can be determined by resolving the maximum probability estimation functions.…”

Section: Preposition 1 (Machine Learning For Athlete Data Gathering)mentioning

confidence: 99%

“…As a complete and systematic approach to health management, smart sports health management [ 3 ] has attracted the public's curiosity. Smart sports health management attempts to syndicate conventional medicine's fundamental diagnostic tools [ 4 ] with new information technology to evaluate health status using a summary and classification of previous health management research [ 5 ]. A large amount of technologically-based biomechanical and physiological data [ 6 ] is combined with mathematical algorithms to define sports monitoring [ 7 ].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

System Construction of Athlete Health Information Protection Based on Machine Learning Algorithm

Liu

Xiao-dong

2022

BioMed Research International

View full text Add to dashboard Cite

The exercise volume and exercise level can be quantitatively assessed by measuring and collecting athletes’ health and exercise data. The protection of athletes’ health information has lately become an important research topic due to a rise in sports activities. However, due to the nature of the data and the limits of protection models, protecting athlete health data is a complex undertaking. Machine learning and blockchain have caused worldwide technological innovation, and it is bound to bring deep modifications to the sports industry. The main purpose of blockchain is security, decentralization, traceability, and credibility of the athlete’s health data protection and gathering system. To progress and increase the sports industry and methodically assess the physical fitness of sportspersons’ health information, this study concentrates on the Machine Learning and Blockchain-based Athlete Health Information Protection System (MLB-AHIPS) proposed in the sports industry. The ML technique is utilized to clean and handle the information to comprehend the recognition and secure managing of the sportsperson’s fitness information. The system uses attribute-based access control, which permits dynamic and fine-grained access to athlete health data, and then stores the health data in the blockchain, which can be secured and tamper-proof by expressing the respective smart contracts. The simulation outcomes illustrate that the suggested MLB-AHIPS attains a high accuracy ratio of 97.8%, security ratio of 98.3%, an efficiency ratio of 97.1%, scalability ratio of 98.9%, and data access rate of 97.2% compared to other existing approach.

show abstract

Section: Preposition 1 (Machine Learning For Athlete Data Gathering)mentioning

confidence: 99%