Objective: Ghrelin regulates body weight, food intake and blood glucose. It also regulates insulin secretion from pancreatic islet cells. LEAP2 is a newly discovered endogenous ligand of growth hormone secretagogue’s receptor (GHSR). It not only antagonizes the stimulation of GHSR by ghrelin but also inhibits constitutive activation of GHSR as an inverse agonist. Type 2 diabetes (T2D) patients have endocrine disorders with metabolic imbalance. Plasma levels of ghrelin and LEAP2 may be changed in obese and T2D patients. However, there is no report yet on circulating LEAP2 levels or ghrelin/LEAP2 ratio in T2D patients. In this study, fasting serum ghrelin and LEAP2 levels in healthy adults and T2D patients were assessed to clarify the association of two hormones with different clinical anthropometric and metabolic parameters. Design: A total of 16 females and 40 males, ages 23-68 years old normal (n = 27) and T2D patients (n = 29) were enrolled as a cross-sectional cohort. Results: Serum levels of ghrelin were lower but serum levels of LEAP2 were higher in T2D patients. Ghrelin levels were positively correlated with fasting serum insulin levels and HOMA-IR in healthy adults. LEAP2 levels were positively correlated with age and HbA1c in all tested samples. Ghrelin/LEAP2 ratio was negatively correlated with age, fasting blood glucose and HbA1c. Conclusions: This study demonstrated a decrease in serum ghrelin levels and an increase in serum LEAP2 levels in T2D patients. LEAP2 levels were positively correlated with HbA1c, suggesting that LEAP2 was associated with T2D development. The ghrelin/LEAP2 ratio was closely associated with glycemic control in T2D patients showing negative correlation with glucose and HbA1c.

The graph Laplacian regularization term is usually used in semi-supervised node classification to provide graph structure information for a model f (X). However, with the recent popularity of graph neural networks (GNNs), directly encoding graph structure A into a model, i.e., f (A, X), has become the more common approach. While we show that graph Laplacian regularization f (X) ∆f (X) brings little-to-no benefit to existing GNNs, we propose a simple but non-trivial variant of graph Laplacian regularization, called Propagation-regularization (P-reg), to boost the performance of existing GNN models. We provide formal analyses to show that P-reg not only infuses extra information (that is not captured by the traditional graph Laplacian regularization) into GNNs, but also has the capacity equivalent to an infinite-depth graph convolutional network. The code is available at https://github.com/yang-han/P-reg.

No abstract

No abstract

Smart wearable robotic system, such as exoskeleton assist device and powered lower limb prostheses can rapidly and accurately realize man–machine interaction through locomotion mode recognition system. However, previous locomotion mode recognition studies usually adopted more sensors for higher accuracy and effective intelligent algorithms to recognize multiple locomotion modes simultaneously. To reduce the burden of sensors on users and recognize more locomotion modes, we design a novel decision tree structure (DTS) based on using an improved backpropagation neural network (IBPNN) as judgment nodes named IBPNN-DTS, after analyzing the experimental locomotion mode data using the original values with a 200-ms time window for a single inertial measurement unit to hierarchically identify nine common locomotion modes (level walking at three kinds of speeds, ramp ascent/descent, stair ascent/descent, Sit, and Stand). In addition, we reduce the number of parameters in the IBPNN for structure optimization and adopted the artificial bee colony (ABC) algorithm to perform global search for initial weight and threshold value to eliminate system uncertainty because randomly generated initial values tend to result in a failure to converge or falling into local optima. Experimental results demonstrate that recognition accuracy of the IBPNN-DTS with ABC optimization (ABC-IBPNN-DTS) was up to 96.71% (97.29% for the IBPNN-DTS). Compared to IBPNN-DTS without optimization, the number of parameters in ABC-IBPNN-DTS shrank by 66% with only a 0.58% reduction in accuracy while the classification model kept high robustness.