The corrupted information in training samples is an important factor affecting the accuracy and generalizability of the machine learning models. Due to the extremely high memory capacity of deep learning models, the interference of excessive corrupted information makes the model prone to bad generalization behavior. This paper proposes a method of estimating training sample quality using the value calculated by the loss function in the process of gradient descent optimization. The method includes a model accuracy variation degree algorithm and a sample quality analysis algorithm. The model accuracy variation degree algorithm provides a basis for determining the intervention time of the sample quality analysis algorithm by calculating the intensity of the model accuracy variation change. The data error evaluation algorithm analyzes the distribution characteristics of the training error and estimates the error degree of the training samples to control the quality of the input samples. This study includes a water segmentation experiment performed on GF1 remote sensing images, which demonstrates that the optimization method can significantly improve the model accuracy and training stability.
High-resolution satellite images contain valuable road semantic information, but the occlusion of vegetation and buildings and the sparse distribution and heterogeneous appearance of roads limit the accuracy of road extraction models. In this paper, we propose a novel method for extracting roads using an ensemble learning model with a postprocessing stage. The network weights and biases of our proposed deep learning model are transmitted through the random combination of layers of different submodels during forward and backward propagation. In the gradient descent process, a superior loss function is designed to solve the problem of class imbalance caused by road sparseness, and more attention is given to hard classification samples to extract narrow and covered roads. In addition, we solve road disconnection issues in the results obtained with the neural network by extracting and analyzing the geometric structures and feature points of the roads. Experiments on two challenging datasets of remote sensing imagery show that the proposed method performs better than other models and can extract road information from complex scenes.
Owing to the effects of camera, illumination, extraction algorithm defect, and other reasons, vector data for reservoir waterbodies extracted from remote sensing data may have quality issues, impacting the efficiency of data utilization in areas such as water resource management and reservoir monitoring. To efficiently detect abnormal data from massive vector products of reservoir waterbodies, a semi-automatic detection method for reservoir waterbody vector data is presented. The method has three phases. First, the original reservoir vector data are preprocessed to obtain the time series of the area of reservoir waterbodies. Second, data modeling with time series of reservoir waterbodies area data is done using the extensible generic anomaly detection system (EGADS) plug-in framework and time series modeling is conducted using the Olympic model. Third, data that have quality problems are identified with K\sigma model was used to determine the outliers; thereby, the date of the outliers is detected. Results of accuracy verification show that the sensitivity and specificity of the method were 94.44 and 83.87%, respectively, showing its feasibility for use in anomaly detection in polygonal reservoir waterbody vector data with far greater efficiency than traditional manual inspection.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.