Intelligent finite-time formation control for flapping wing micro aerial vehicles.

This paper investigates the intelligent finite time formation control for multiple Flapping wing micro aerial vehicles (FWMAVs) system. Firstly, the translational and the rotational attitude motion equations are proposed based on the Lagrangian equation for FWMAVs. The motion system is decouple into an internal and an external dual loop subsystems. An adaptive neural network estimation algorithm is proposed based on the internal and external double loop system of the coupled model to effectively estimate the uncertainties and the external disturbances of the model. In addition, two effective intelligent control protocols are presented for the translational and the rotational attitude motion subsystem, respectively, by utilizing potential energy function, generalized inverse matrix, and finite-time stability. The main contribution of this paper is the case that, four control objectives are achieved for multiple FWMAVs system, including the estimation of uncertainties, collision avoidance, connectivity preservation, and finite time convergence. Finally, a simulation example of formation tracking control is given by using matlab software in the numerical simulation part, and the effectiveness of the obtained results and the superiority of the control protocol are verified.

Fabricating carbon quantum dots of graphitic carbon nitride vis ultrasonic exfoliation for highly efficient H2O2 production.

A promising and sustainable approach for producing hydrogen peroxide is the two-electron oxygen reduction reaction (2e- ORR), which uses very stable graphitic carbon nitride (g-C3N4). However, the catalytic performance of pristine g-C3N4 is still far from satisfactory. Here, we demonstrate for the first time the controlled fabrication of carbon quantum dots (CQDs)-modified graphitic carbon nitride carbon (g-C3N4/CQDs-X) by ultrasonic stripping for efficient 2e- ORR electrocatalysis. HRTEM, UV-vis, EPR and EIS analyses are in good consistent which prove the in-situ generation of CQDs. The effect of sonication time on the physical properties and ORR activity of g-C3N4 is discussed for the first time. The g-C3N4/CQDs-12 catalyst shows a selectivity of up to 95% at a potential of 0.35 V vs. RHE, which is much higher than that of the original g-C3N4 catalyst (88%). Additionally, the H2O2 yield is up to 1466.6 mmol g-1 in 12 h, which is twice as high as the original g-C3N4 catalyst. It is discovered that the addition of CQDs through ultrasonic improves the g-C3N4 catalyst's electrical conductivity and electron transfer capability in addition to its high specific surface area and distinctive porous structure, speeding up the reaction rate. This research offers a green method for enhancing g-C3N4 activity.

Machine learning models for prognosis prediction in endodontic microsurgery.

OBJECTIVES: This study aimed to establish and validate machine learning models for prognosis prediction in endodontic microsurgery, avoiding treatment failure and supporting clinical decision-making. METHODS: A total of 234 teeth from 178 patients were included in this study. We developed gradient boosting machine (GBM) and random forest (RF) models. For each model, 80% of the data were randomly selected for the training set and the remaining 20% were used as the test set. A stratified 5-fold cross-validation approach was used in model training and testing. Correlation analysis and importance ranking were conducted for feature selection. The predictive accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), F1 score, and the area under the curve (AUC) of receiver operating characteristic (ROC) curves were calculated to evaluate the predictive performance. RESULTS: There were eight important predictors, including tooth type, lesion size, type of bone defect, root filling density, root filling length, apical extension of post, age, and sex. For the GBM model, the predictive accuracy was 0.80, with a sensitivity of 0.92, specificity of 0.71, PPV of 0.71, NPV of 0.92, F1 of 0.80, and AUC of 0.88. For the RF model, the accuracy was 0.80, with a sensitivity of 0.85, specificity of 0.76, PPV of 0.73, NPV of 0.87, F1 of 0.79, and AUC of 0.83. CONCLUSIONS: The trained models were developed by eight common variables, showing the potential ability to predict the prognosis of endodontic microsurgery. The GBM model outperformed the RF model slightly on our dataset. CLINICAL SIGNIFICANCE: Clinicians can use machine learning models for preoperative analysis in endodontic microsurgery. The models are expected to improve the efficiency of clinical decision-making and assist in clinician-patient communication.