In order to solve the problem of group renting in the city and eliminate the hidden safety hazards caused by which, we take use of the isolated forest model to filter out non -group renting users from the general electricity customers in the first step. So in this case, a semi-supervised learning problem is transformed into a supervised classification and identification problem. Then a random forest model is built to train the classifier which can discriminate the electricity consumption data of group renters from the non-group renting ones. Finally, the electricity consumption data of the Yuhuatai District of Nanjing City are employed in the experiment of this paper, and the classification accuracy on the 99-household test set reached 99.89%, which shows the effectiveness of the proposed classification model and method in this paper.
In order to solve the problems of low efficiency and accuracy in the traditional evaluation methods of practical writing teaching, this paper proposes a new method based on transfer matrix analysis. This method analyzes the teaching characteristics of practical writing and excavates the teaching data of practical writing. Based on the obtained data, Bayesian classification method is used to calculate the weight of teaching data and data feature weight. The evaluation standard is calculated by the principle of membership degree, and the evaluation results are graded. The teaching state transition matrix is constructed, the teaching efficiency evaluation model is obtained, and the teaching efficiency evaluation of practical writing is completed. The experimental results show that the proposed evaluation method of practical writing teaching efficiency has high evaluation accuracy and efficiency, and can be widely used in the actual teaching process.
Aiming at the need of evaluating the correctness of navigation data in non-general format when navigation equipment is upgraded and updated, a correctness checking method is proposed to overcome the problem of relying on spacecraft data and lack of flexibility in the original technology. The method uses the observation error equation of each satellite in the navigation and positioning calculation to determine whether the equipment data is consistent, so as to quickly verify the correctness of the data interface. The example indicates the effectiveness of the method. Compared with previous technologies, the new method can realize data structure transformation and parameter mapping customization, simultaneously process data from different sources and interfaces, and judge the self-consistency of all data of shipboard navigation equipment. In the past three years, this method has been applied in the upgrade, modification and replacement of shipboard navigation equipment, and many data interface problems have been found.
In order to reduce the time complexity and space complexity of constructing hierarchical quotient space, a method of incremental generation of hierarchical quotient space is proposed and applied to feature selection to reduce the data dimension. The stratified sampling is used to process the initial data set, and then the quotient space structure is constructed by the incremental generation method of hierarchical quotient space. The values are clustered to reduce the complexity in the processing of construct, and then the optimal granularity is selected to calculate the positive region to realize feature selection. The experimental results show that compared with other feature selection methods, the classification accuracy of the proposed method in this paper is improved to some extent. The experimental results show that the influence of different sampling percentage on classification accuracy is small, and the change of classification accuracy under different thresholds is analyzed.
In order to ensure the safe transmission of the brine pipeline, this paper designs a leakage detection terminal based on STM32F7. This terminal uses GPS to added time stamps to the collected data. And each distributed terminal uses second pulse signal of GPS to realize the function of synchronously collecting signals. Finally, the data is transmitted to the cloud computing platform through the 4G wireless transmission module system. This paper uses the S transform algorithm to analyze the characteristics of these transmitted data. S transform algorithm fully extracts the characteristics of the data in the time-frequency-mode domain. The simulation results show that the data generates high-frequency signals at default point. Through the whole system, it can effectively realize real-time monitoring.
