The video super-resolution (VSR) task refers to the use of corresponding low-resolution (LR) frames and multiple neighboring frames to generate high-resolution (HR) frames. An important step in VSR is to fuse the features of the reference frame with the features of the supporting frame. The existing VSR method does not make full use of the information provided by the distant neighboring frame, and usually fuses in a one-stage manner. In this paper, we propose a deep fusion video super-resolution network based on temporal grouping. We divide the input sequence into groups according to different frame rates to provide more accurate supplementary information, and the method aggregates temporal and spatial information at different stages of fusion.
Wind power output is influenced by many factors, and its changing trend is complex, so it is difficult to use a single forecasting method to effectively forecast wind power. Moreover, an excellent power prediction model will have a significant impact on rational energy dispatching, demand management, energy conservation and emission reduction. In this paper, based on the classic machine learning model, multiple models are fused to predict the power and optimize the performance of energy. A number of algorithm models are used as base learners to fuse the weights of the prediction results to keep the feature relevance. Then, the weight fusion models are also used as base learners for training, and further high-level models are obtained through Stacking model fusion, which is compared with a number of classical algorithm models to synthesize the best performance energy prediction model. By comparison, the power prediction model fused by multiple models has higher running speed and accuracy, and higher performance in energy power prediction. The results show that the multiple model fusion of classical algorithm models can effectively improve the accuracy of power prediction, thus obtaining the best performance power prediction model.
Diabetes mellitus (DM) prediction facilitates timely targeted treatment and interventions in the early stages of DM, and is important for reducing the incidence of DM and analyzing risk factors. In this paper, we proposed an integrated learning model GC-Stacking based on Genetic Algorithm (GA) and improved CatBoost method. Firstly, we selected the most optimal set of traits associated with diabetes risk factors based on the global search capability of genetic algorithm (GA); Then, the improved CatBoost method is combined with KNN, SVM and other algorithms with excellent prediction performance as the main learner, and then, the stack ensemble learning strategy is adopted. RF is used as a secondary learner to train this integrated prediction model, which uses the selected features for diabetes prediction. The model was validated on the Qingdao CDC physical examination dataset and the UCI public diabetes dataset. The experimental results showed that the GC-stacking model based on 7-fold cross validation has better predictive performance. It outperforms other algorithms in terms of accuracy, Fl-score and other performance metrics.
In this research, an automatic navigation system for a bipedal humanoid robot is proposed. The robot firstly moves around in the working space to build a 3D map by using SLAM (Simultaneous Localization and Mapping), and then move toward its destination according to the generated global and local path by using Dijkstra's algorithm and Dynamics Window Approach separately. The effectiveness of the proposed system is proven by simulation experiments.
A path planning framework for an omnidirectional mobile robot based on modified A * algorithm with energy model is proposed. The kinematic model of the omnidirectional mobile robot is established, and the energy consumption model of the omnidirectional mobile robot during motion is established based on the detailed derivation of formulas and used to improve the A* algorithm. The derived results show that the extra power consumed in steering movement is only related to the steering angle.
