From past to future: a review of methods for assessing physical activity energy expenditure

从过去到未来:体力活动能量消耗评估方法的回顾

阅读:1

Abstract

BACKGROUND: Physical activity energy expenditure (PAEE) assessment is important for helping individuals maintain energy balance. This study adopts a technological evolution perspective to systematically examine the historical evolution and current progress of PAEE assessment methods, aiming to clarify future development directions. METHODS: This study employs a narrative review methodology. The "Past" section presents a chronological account of the historical development of the PAEE assessment methodology, whereas the "Present" section synthesizes recent advances in the application of intelligent technologies to PAEE assessment based on a systematic literature search. Relevant literature was identified through comprehensive searches of the Web of Science, PubMed, IEEE Xplore, and China National Knowledge Infrastructure (CNKI) databases. RESULTS: The historical evolution of PAEE assessment methods can be divided into three periods: initial emergence (late 18th century to mid-19th century), gradual exploration (late 19th century to early 20th century), and steady development (mid-20th century to late 20th century). PAEE assessment enters the intelligent era now, with the application of artificial intelligence (AI) technology primarily focused on two main areas: machine learning (ML) and computer vision (CV). However, there are still some shortcomings. Therefore, future efforts should focus on advancing technological innovations in intelligent PAEE assessment, expanding the application scenarios of intelligent PAEE assessment, and mitigating the ethical risks associated with intelligent PAEE assessment to enhance the effect of AI in PAEE assessment. CONCLUSIONS: The historical evolution of PAEE assessment has undergone three stages: initial formation, gradual exploration, and steady development. Currently, the application of AI technology in PAEE assessment is mainly concentrated in the two major fields of ML and CV, but it still faces many challenges. In the future, it will be necessary to promote technological innovation, expand application scenarios, and mitigate ethical risks.

特别声明

1、本页面内容包含部分的内容是基于公开信息的合理引用;引用内容仅为补充信息,不代表本站立场。

2、若认为本页面引用内容涉及侵权,请及时与本站联系,我们将第一时间处理。

3、其他媒体/个人如需使用本页面原创内容,需注明“来源:[生知库]”并获得授权;使用引用内容的,需自行联系原作者获得许可。

4、投稿及合作请联系:info@biocloudy.com。