High-resolution remote sensing image scene classification is a challenging visual task due to the large intravariance and small intervariance between the categories. To accurately recognize the scene categories, it is essential to learn discriminative features from both global and local critical regions. Recent efforts focus on how to encourage the network to learn multigranularity features with the destruction of the spatial information on the input image at different scales, which leads to meaningless edges that are harmful to training. In this study, we propose a novel method named Semantic Multigranularity Feature Learning Network (SMGFL-Net) for remote sensing image scene classification. The core idea is to learn both global and multigranularity local features from rearranged intermediate feature maps, thus, eliminating the meaningless edges. These features are then fused for the final prediction. Our proposed framework is compared with a collection of state-of-the-art (SOTA) methods on two fine-grained remote sensing image scene datasets, including the NWPU-RESISC45 and Aerial Image Datasets (AID). We justify several design choices, including the branch granularities, fusion strategies, pooling operations, and necessity of feature map rearrangement through a comparative study. Moreover, the overall performance results show that SMGFL-Net consistently outperforms other peer methods in classification accuracy, and the superiority is more apparent with less training data, demonstrating the efficacy of feature learning of our approach.

In corporate customer management, companies are required to evaluate the costs and benefits of investment expenditures and determine the optimal resource allocation for marketing and sales activities within a period. Understanding the buying behavior of customers in the future is a key driving force for the sales and marketing departments to effectively allocate resources. This paper proposes a combined prediction model that uses the Stacking method to integrate multiple decision tree models to predict whether users will buy in the future and their specific purchase time. The model uses the idea of stacking model fusion to fuse the prediction results of three different integrated decision tree models of Light GBM, XG Boost, and Random Forest, and then uses a simple logistic regression classification model and a linear regression model to predict separately based on the fused prediction results Whether the user will buy in the future and the specific time of purchase. In addition, in this study, we used real retail sales data to evaluate the predictive performance of the proposed method.

No abstract