当前位置: X-MOL 学术Measurement › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Under the background of healthy China: Regulating the analysis of hybrid machine learning in sports activities to control chronic diseases
Measurement ( IF 5.6 ) Pub Date : 2020-06-12 , DOI: 10.1016/j.measurement.2020.107847
Lingling Guo

One of the most important concerns in human life is concentrating on health. Major threats to human life are chronic diseases such as cancer and diabetes. China government mainly focusing on understanding the progression and spreading of chronic diseases over the population for allocating medical resources and designing a strategy in healthcare. Various conventional methods have been used for fetching chronic disease indicators in large scale based on the population health. But they are costly, not time effective and less accuracy in prediction. But this paper used Hybrid Predicting Model designed by incorporating the main features of the Gaussian Mixture Method and Collaborating Topic Modelling to increase the prediction accuracy. The proposed HPM method experimented on human mobility pattern dataset collected from the various metropolitan area of China. From the dataset, HPM predicts the rate of chronic disease presence and relative activity. GMM obtain the health condition whereas CTM obtains the data sparsity. The proposed hybrid prediction method is implemented in MATLAB software and experimented. Form the obtained results and comparing with the other existing methods, it is identified that the HPM outperforms in terms of prediction accuracy. HPM is evaluated using real-time check-in and chronic disease dataset in China cities. The proposed HPM method obtained 0.09% of the value which is high than the other baseline methods. From the obtained MSE and value, it is well clear the proposed HPM outperforms than the baseline methods.

更新日期:2020-06-12
down
wechat
bug