Search Results (2)

Earth Observation satellite imaging helps building diagnosis during a disaster. Several models are put forward on the xBD dataset, which can be divided into two levels: the building level and the pixel level. Models from two levels evolve into several versions that will be reviewed in this paper. There are four key challenges hindering researchers from moving forward on this task, and this paper tries to give technical solutions. First, metrics on different levels could not be compared directly. We put forward a fairer metric and give a method to convert between metrics of two levels. Secondly, drone images may be another important source, but drone data may have only a post-disaster image. This paper shows and compares methods of directly detecting and generating. Thirdly, the class imbalance is a typical feature of the xBD dataset and leads to a bad F1 score for minor damage and major damage. This paper provides four specific data resampling strategies, which are Main-Label Over-Sampling (MLOS), Discrimination After Cropping (DAC), Dilation of Area with Minority (DAM) and Synthetic Minority Over-Sampling Technique (SMOTE), as well as cost-sensitive re-weighting schemes. Fourthly, faster prediction meets the need for a real-time situation. This paper recommends three specific methods, feature-map subtraction, parameter sharing, and knowledge distillation. Finally, we developed our AI-driven Damage Diagnose Platform (ADDP). This paper introduces the structure of ADDP and technical details. Customized settings, interface preview, and upload and download satellite images are major services our platform provides. Full article

Bad data as a result of measurement errors in secondary substation (SS) monitoring equipment is difficult to detect and negatively affects power system state estimation performance by both increasing the computational burden and jeopardizing the state estimation accuracy. In this paper a short-term load forecasting (STLF) hybrid strategy based on singular spectrum analysis (SSA) in combination with artificial neural networks (ANN), is presented. This STLF approach is aimed at detecting, identifying and eliminating and/or correcting such bad data before it is provided to the state estimator. This approach is developed to improve the accuracy of the load forecasts and it is tested against real power load data provided by electricity suppliers. Depending on the week considered, mean absolute percentage error (MAPE) values which range from 1.6% to 3.4% are achieved for STLF. Different systematic errors, such as gain and offset error levels and outliers, are successfully detected with a hit rate of 98%, and the corresponding measurements are corrected before they are sent to the control center for state estimation purposes. Full article