Objective: This study aimed to investigate the most notable obesity index and its optimal cut-off point of hypertension in different age groups stratified by sexes among community residents in southern China. Methods: In this cross-sectional study, 620 men and 631 women aged 18–59 years were enrolled. The independent-samples t-test and chi-square test were conducted to analyze continuous and categorical variables, respectively. Multivariate logistic regression analysis and receiver operating characteristic (ROC) curve analysis assessed the association between the obesity indices and hypertension risk. Results: Waist–stature ratio (WSR) and waist–hip ratio (WHR) were the most notable risk factors for hypertension in young men and women, respectively. The odds ratios (ORs) of hypertension risk increased with per standard deviation (SD) in WSR and WHR (WSR: OR = 2.877, 95% confidence interval [CI] = 1.602 to 5.167; WHR: OR = 10.683, 95%CI = 2.179 to 52.376). In the middle-aged group of both sexes, body mass index (BMI) was the most distinctive risk factor for hypertension, the ORs of hypertension risk increased with per SD in BMI (men: OR = 2.297, 95%CI = 1.683 to 3.136; women: OR = 1.810, 95%CI = 1.338 to 2.450). ROC curve analysis demonstrated WSR and PI were better indicators than other indices among young men, and WSR was the best marker among young women. However, BMI and WC were the most sensitive markers in middle-aged men and women, respectively. Conclusions: In this Chinese population, the association of obesity indices and hypertension is inconsistent in different age groups and sexes. It is important to choose appropriate indicators for specific groups of people.

3D Dynamic simulator such as Gazebo has become a popular substitution for unmanned aerial vehicle (UAV) because of its user-friendly in real-world scenarios. At this point, well-functioning algorithms on the UAV controller are needed for guidance, navigation, and control for autonomous navigation. Deep reinforcement learning (DRL) comes into sight as its famous self-learning characteristic. This goal-orientated algorithm can learn how to attain a complex objective or maximize along a particular dimension over many steps. In this paper, we propose a general framework to incorporate DRL with the UAV simulation environment. The whole system consists of the DRL algorithm for attitude control, packing algorithm on the Robot Operation System (ROS) to connect DRL with PX4 controller, and a Gazebo simulator that emulates the real-world environment. Experimental results demonstrate the effectiveness of the proposed framework.