Association of artificial intelligence use and the retention of elderly caregivers: A cross-sectional study based on empowerment theory



The purpose of this study is to investigate how the use of artificial intelligence (AI) is associated with the retention of elderly caregivers.


The turnover of elderly caregivers is high and increasing. Elderly care institutions are beginning to use artificial intelligence (AI) to support caregivers in their work, and the use of technology is critical to staff retention. Empowerment of elderly caregivers has been neglected by managers and researchers.


This cross-sectional study involved 511 elderly caregivers in 25 elderly institutions. Six validated standardized scales were used for data collection, and the softwares SPSS and SmartPLS were used for data analysis.


The quality of artificial intelligence (AI) has a significant positive effect on empowerment. artificial intelligence (AI) psychological empowerment (β = 0.355, p < 0.001) and artificial intelligence (AI) structural empowerment (β = 0.375, p < 0.001) both had positive effects on retention intention, and the jointly explained variance (R2 ) was 42.6%.


The results show that a significant relationship exists between artificial intelligence (AI) empowerment and retention intention. Elderly caregivers with more structural empowerment have higher retention intention.

Implications for nursing management:

artificial intelligence (AI) suppliers need to pay attention to the role of product quality in elderly care services, continuously improve artificial intelligence (AI) quality, and strengthen the application and routine maintenance of artificial intelligence (AI) technology. Elderly care institution managers should pay special attention to artificial intelligence (AI) structural empowerment (such as AI-related education and training, learning and development opportunities, and resource support).


artificial intelligence; empowerment; psychological empowerment; retention; structural empowerment.


Source link

CNN Multi-Position Wearable Sensor Human Activity Recognition Used in Basketball Training


. 2022 Sep 19;2022:9918143.

doi: 10.1155/2022/9918143.

eCollection 2022.


Item in Clipboard

Biao Tang et al.

Comput Intell Neurosci.



With the development trend of artificial intelligence technology and the popularization of wearable sensors, human activity recognition based on sensor data information has received widespread attention and has great application value. In order to better optimize the network structure and reduce the total number of main training parameters in the convolutional layer, a convolutional network entity model based on shared resources of main parameters is clearly proposed. We analyzed the CNN multi-position wearable sensor human activity recognition used in basketball training. According to the entity model of the main parameters of shared resources, the effectiveness of the entity model is verified from both the total number of sensors and the accuracy of single-class recognition. In addition to maintaining the actual effect of recognition, the main training parameters are also reduced. The simulation results verify the actual effect of the SVM algorithm and motion simulation of the convolutional network entity model. On this basis, scientific research physical exercise methods are selected to reasonably ensure the smooth progress of appropriate physical exercise at a certain level, improve the quality of training and the actual effect.

Conflict of interest statement

The authors declare that they have no conflicts of interest.


Figure 1

Figure 1

Convolution structure based on multi-channel time series data.

Figure 2

Figure 2

Multi-position three-axis sensor input construction method.

Figure 3

Figure 3

Two-dimensional convolution model network structure M.2DCNN based on multi-position hybrid sensor.

Figure 4

Figure 4

Two-dimensional convolution calculation process.

Algorithm 1

Algorithm 1

Two dimensional input algorithm of moving image based on multi position hybrid sensor.


    1. Alcalá D. H., García C. G., Garijo A. H. Combat versus team sports: the effects of gender in a climate of peer-motivation, and levels of fun and violence in physical education students. Ido Movement for Culture . 2017;17(3):11–20.

    1. Chen Y. Study on neural network model-based senior high school Men’s basketball training strategy and approach. Journal of Computational and Theoretical Nanoscience . 2016;13(12):10059–10063. doi: 10.1166/jctn.2016.6210.


    1. Kirkup J. A., Rowlands D. D., Thiel D. V. Team Player tracking using sensors and signal strength for indoor basketball. IEEE Sensors Journal . 2016;16(11):4622–4630. doi: 10.1109/jsen.2016.2542359.


    1. Vaquera A., Mielgo-Ayuso J., Calleja-González J., Leicht A. S. Match intensity and heart rate predictors in top level basketball referees during men’s Eurobasket. The Journal of Sports Medicine and Physical Fitness . 2016;56(9):1034–1040.


    1. Huang Q., Ko K. T., Iversen V. B. An approximation method for multiservice loss performance in hierarchical networks. Proceedings of the Managing Traffic Performance in Converged Networks; May 2007; Berlin, Heidelberg. Springer; pp. 901–912.