Co-occurrence trend and association study of Internet addiction and depressive symptoms among students in Inner Mongolia Autonomous Region / 中国学校卫生

Objective@#To investigate the prevalence of Internet addiction and depression of students, and to analyze the co-occurrence and trend, so as to provide a theoretical basis for prevention and controlling measures of Internet addiction and depression.@*Methods@#A total of 6 317,7 152,81 808,71 180 and 89 932 students aged 10 to 24 years from 12 leagues (103 banners) in Inner Mongolia Autonomous Region were selected by stratified random cluster sampling in September each year from 2017 to 2021. The Internet Addiction Scale and the Central for Epidemiologic Studies Depression Scale(CES-D) was used to measure Internet addiction and depression. And the annual inspection rate, group difference and annual change trend in students were calculated. Multivariate linear regression and restricted cubic spline analysis were used to estimate the linear and non linear associations between Internet addiction and depression in students.@*Results@#The Internet addiction proportion in students gradually decreased from 4.1% in 2017 to 2.1% in 2020, but increased to 3.9% in 2021. And the depressive symptoms proportion increased from 20.9% in 2017 to 28.0% in 2020 and 27.0% in 2021. The detection rate of Internet addiction and depression comorbidities remained at 1.8% to 2.5 %. The Internet addiction proportion in boys was higher than that in girls( χ 2=42.82， P <0.05). The depressive symptoms prevalence in girls was higher than that in boys( χ 2= 553.90， P <0.05). Taking reversal in prevalence of Internet addiction in urban and rural areas was observed in 2019. The detection rates of depressive symptoms and comorbidity were higher in urban areas than these in suburban counties on the whole, and the difference showed a trend of decreasing or even equalizing year by year. Internet addiction was positively correlated with depressive symptoms score ( B=1.67, 95%CI =1.64-1.71), the proportion of depressive symptoms ( OR=1.39, 95%CI =1.38-1.41) and the proportion of major depressive symptoms ( OR=1.35, 95%CI =1.33-1.36) among students in 2021 ( P <0.05). An N-shaped curve was found in the significant nonlinear associations between internet addiction and depression across sex, region and school stage.@*Conclusion@#Internet addiction and depression in students show significant linear and non-linear associations, which are consistent in different sexes, regions and school stages. Therefore, relevant measures should be made and implemented in each region, especially in suburb areas, so as to prevent the increasingly development of adolescents and children s Internet addiction and depression.

Human activity recognition based on the inertial information and convolutional neural network / 生物医学工程学杂志

With the rapid improvement of the perception and computing capacity of mobile devices such as smart phones, human activity recognition using mobile devices as the carrier has been a new research hot-spot. The inertial information collected by the acceleration sensor in the smart mobile device is used for human activity recognition. Compared with the common computer vision recognition, it has the following advantages: convenience, low cost, and better reflection of the essence of human motion. Based on the WISDM data set collected by smart phones, the inertial navigation information and the deep learning algorithm-convolutional neural network (CNN) were adopted to build a human activity recognition model in this paper. The K nearest neighbor algorithm (KNN) and the random forest algorithm were compared with the CNN network in the recognition accuracy to evaluate the performance of the CNN network. The classification accuracy of CNN model reached 92.73%, which was much higher than KNN and random forest. Experimental results show that the CNN algorithm model can achieve more accurate human activity recognition and has broad application prospects in predicting and promoting human health.