Medical Big Data Analysis with Attention and Large Margin Loss Model for Skin Lesion Application

Wu, Jian; Guo, Hong; Wen, Yonggang; Hu, Wei; Li, YiNing; Liu, TianYi; Liu, Xiaoming

doi:10.1007/s11265-021-01664-0

Cited by 3 publications

(1 citation statement)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent years, with the rapid development of information science, the combination of medical treatment and information technology to achieve hospital information construction is of great significance to the improvement of the efficiency of residents' health management and the efficiency of medical treatment [ 1 ]. After hospital informatization, there will be a large number of patients and a large amount of disease information, namely, medical big data.…”

Section: Introductionmentioning

confidence: 99%

[Retracted] Obesity Mass Monitoring in Medical Big Data Based on High‐Order Simulated Annealing Neural Network Algorithm

Ren

Zhao

2021

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

With the rapid development of information technology, hospital informatization has become the general trend. In this context, disease monitoring based on medical big data has been proposed and has aroused widespread concern. In order to overcome the shortcomings of the BP neural network, such as slow convergence speed and easy to fall into local extremum, simulated annealing algorithm is used to optimize the BP neural network and high-order simulated annealing neural network algorithm is constructed. After screening the potential target indicators using the random forest algorithm, based on medical big data, the experiment uses high-order simulated annealing neural network algorithm to establish the obesity monitoring model to realize obesity monitoring and prevention. The results show that the training times of the SA-BP neural network are 1480 times lower than those of the BP neural network, and the mean square error of the SA-BP neural network is 3.43 times lower than that of the BP neural network. The MAE of the SA-BP neural network is 1.81 times lower than that of the BP neural network, and the average output error of the obesity monitoring model is about 2.35 at each temperature. After training, the average accuracy of the obesity monitoring model was 98.7%. The above results show that the obesity monitoring model based on medical big data can effectively complete the monitoring of obesity and has a certain contribution to the diagnosis, treatment, and early warning of obesity.

show abstract

Section: Introductionmentioning

confidence: 99%