Search

Providing safety guarantees for Autonomous Vehicle (AV) systems with machine-learning-based controllers remains a challenging issue. In this work, we propose Simplex-Drive, a framework that can achieve runtime safety assurance for machine-learning enabled controllers of AVs. The proposed Simplex-Drive consists of an unverified Deep Reinforcement Learning (DRL)-based advanced controller (AC) that achieves desirable performance in complex scenarios, a Velocity-Obstacle (VO) based baseline safe controller (BC) with provably safety guarantees, and a verified mode management unit that monitors the operation status and switches the control authority between AC and BC based on safety-related conditions. We provide a formal correctness proof of Simplex-Drive and conduct a lane-changing case study in dense traffic scenarios. The simulation experiment results demonstrate that Simplex-Drive can always ensure operation safety without sacrificing control performance, even if the DRL policy may lead to deviations from the safe status.

Background: Weight loss surgery is a way of weight loss that can quickly reduce the weight of patients and improve their health. However, complications such as skeletal muscle loss, basal metabolism decline, fatigue and low blood sugar are common in the early stages of surgery. Exercise plays a positive role in maintaining muscle mass, improving metabolism and improving cardiopulmonary function in patients with weight loss. However, whether exercise training after weight-loss surgery can improve the postoperative complications of obese patients still needs further verification. Purpose: In this study, through 4-week exercise intervention and routine postoperative management of female obese patients after weight loss, the changes of body composition and insulin resistance of obese patients after weight loss were observed, hoping to reduce the postoperative adverse reactions through exercise training. to provide theoretical reference for obese patients to make scientific exercise prescription after weight loss. Methods: In this paper, 17 obese female patients after weight loss (laparoscopic sleeve gastrectomy) were studied. Body mass index (BMI) 28-40kg/m2, age 20-40 years old, good health and no other diseases. They were randomly divided into exercise group (n = 8) and control group (n = 9). Sports training lasts 4 weeks, 3 times a week (alternate day training), 30min strength training, the intensity is 40% 1RM, during the training period, the 1RM is re-measured every week in order to adjust the strength training load in a timely manner. 30min aerobic training, the intensity is 50% HRmax, mainly in the way of fast walking. The maximum heart rate was calculated as: maximum heart rate = (220-age). The control group did not take any exercise except for normal physical activity. The diet of the subjects was uniformly managed by the dietitian of the China-Japan Friendship Hospital.SPSS22.0 statistical software is used to process the data, and the experimental data are expressed in the way of average ��standard deviation (x ��SD). First, whether the experimental data belong to normal distribution is detected, and independent sample T test is used for comparison between groups. Nonparametric Mann-Whitney U test is used for non-normal distribution. The significant level was P < 0.05, and the very significant level was P < 0.01. Results: After 4-week exercise intervention, there was no significant difference in body weight and BMI between the exercise group and the control group. There was no significant difference in heart rate, systolic blood pressure (SBP) and diastolic blood pressure (DBP)between the two groups. The decrease of SBP in control group and exercise group was 3.44��12.91mmHg and 7.75��11.18mmHg, respectively, DBP control group increased 0.01��12.47 mmHg, exercise group decreased 5��6.44 mmHg. In terms of body composition, the exercise group was superior to the control group in reducing body fat percentage (BF%)(P���0.05), visceral fat area (VFA) (P���0.01)and trunk fat (TF) (P < 0.05). Among them, the decrease of protein weight, muscle weight and skeletal muscle in the control group was 0.90 ��0.49 kg, 3.93 ��2.40kg and 2.62 ��1.45 kg, respectively, and that in the exercise group was 0.54 ��0.45 kg, 2.26 ��2.11kg and 1.65 ��1.39kg, respectively. The exercise group was superior to the control group in delaying the decrease of basal metabolic rate (BMR)(P���0.05). There was no significant difference in fasting insulin (FINS), C-peptide (CP), Homeostatic model assessment for insulin (HOMA-IR) and insulin sensitivity index (ISI) between the two groups. The decrease of FINS, CP and HOMA-IR in the control group was 14.27 ��10.12 ulU/ml, 1.71 ��0.94 ng/ml and 4.81 ��3.42 respectively, and that in the exercise group was 12.47 ��9.68 ulU/ml, 0.75 ��0.97 ng/ml and 3.03 ��2.18 respectively. The increase of ISI in control group and exercise group was 0.09 ��0.11,0.02 ��0.02 respectively. Conclusions: The main results are as follows: (1) Although there is no significant difference in body weight between the control group and the exercise group, the exercise group is superior to the control group in improving BF%, VFA and TF, indicating that exercise training has additional benefits for fat reduction after weight loss surgery. (2) BMR is determined by the total weight of the body, mainly the total amount of non-fat, and the massive loss of muscle after operation will reduce the level of BMR, so the difference of BMR between the two groups can indirectly reflect that exercise training can slow down the loss of protein and skeletal muscle. From the point of view of body composition, exercise can also reduce the loss rate of protein and muscle mass after operation. (3) Compared with the control group, although there was no statistical difference in heart rate and blood pressure between the exercise group and the control group, the overall data of the exercise group decreased more than that of the control group.(4) There was no statistical difference in the effect of exercise training on FINS, CP, ISI and HOMA-IR of patients after weight loss, but exercise training could reduce the decline of the above-mentioned indexes. Funding: No., The Health & Fitness Journal of Canada, Vol. 14 No. 3 (2021): Proceedings from the 8th International Society for Physical Activity and Health Congress

Additional file 4. Supporting information, include supplementary figures. Fig. S1. (A) Schematic diagram of the construction of mouse alveolar organoids. (B) Quantitative of SPC+/total cells ratio per 20 �� field, day 7 differentiating organoids. (C) Quantitative of HOPX+/total cells ratio per 20 �� field, day 7 differentiating organoids. (D) Quantitative of HOPX+/total cells ratio at day 7 and day 17 in differentiating organoids exposed to PM2.5. Fig. S2. The validation of AT2 cells. (A) The purity of AT2 cells. Lungs from C57BL/6 mice were digested into a single-cell suspension and sorted by MicroBeads, the sorted cells were detected by CD326-APC. (B) Immunofluorescence staining of AT2 marker SPC and AT1 marker HOPX in CD45 negative CD326 positive cells.