首页|Multimedia University Reports Findings in Machine Learning (Fall risk prediction using temporal gait features and machine learning approaches)
Multimedia University Reports Findings in Machine Learning (Fall risk prediction using temporal gait features and machine learning approaches)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – New research on Machine Learning is th e subject of a report. According to news reporting from Melaka, Malaysia, by New sRx journalists, research stated, “Falls have been acknowledged as a major publi c health issue around the world. Early detection of fall risk is pivotal for pre ventive measures.” The news correspondents obtained a quote from the research from Multimedia Unive rsity, “Traditional clinical assessments, although reliable, are resource-intens ive and may not always be feasible. This study explores the efficacy of artifici al intelligence (AI) in predicting fall risk, leveraging gait analysis through c omputer vision and machine learning techniques. Data was collected using the Tim ed Up and Go (TUG) test and JHFRAT assessment from MMU collaborators and augment ed with a public dataset from Mendeley involving older adults. The study introdu ces a robust approach for extracting and analyzing gait features, such as stride time, step time, cadence, and stance time, to distinguish between fallers and n on-fallers. Two experimental setups were investigated: one considering separate gait features for each foot and another analyzing averaged features for both fee t. Ultimately, the proposed solutions produce promising outcomes, greatly enhanc ing the model’s ability to achieve high levels of accuracy. In particular, the L ightGBM demonstrates a superior accuracy of 96% in the prediction task. The findings demonstrate that simple machine learning models can successfu lly identify individuals at higher fall risk based on gait characteristics, with promising results that could potentially streamline fall risk assessment proces ses. However, several limitations were discovered throughout the experiment, inc luding an insufficient dataset and data variation, limiting the model’s generali zability. These issues are raised for future work consideration.”
MelakaMalaysiaAsiaCyborgsEmergin g TechnologiesHealth and MedicineMachine LearningPublic HealthRisk and P revention
NETL
NSTL
