This paper proposes an SFNN (a sales factor model using a neural network), which uses a back-propagation multilayer perceptron neural network and weight matrix operation, to study the mechanism of the influencing factors of online product sales in the e-commerce platform. To achieve this objective, this study analyzes the factors and relative strength of online product sales based on four aspects: online reviews, review system curation, online promotional marketing, and seller guarantees. The empirical analysis of the SFNN model based on the data of Taobao.com shows whether the 14 factors, in relation to the four aspects, have any impact on product sales. In addition, the findings indicate that the number of sentiment words greatly affects product sales. Other factors affecting online product sales significantly include the review volume, the number of uploaded pictures, the negative review rate, the discount rate, 7+ day returns and money-back guarantees, and the freight insurance. This study examines the interactions among the various factors affecting product sales on the e-commerce platform and provides management inspiration for e-commerce enterprises to manipulate online reviews, undertake effective promotion and fulfill after-sales promises.

With the increasing scale of e‐commerce, the complexity of image content makes commodity image classification face great challenges. Image feature extraction often determines the quality of the final classification results. At present, the image feature extraction part mainly includes the underlying visual feature and the intermediate semantic feature. The intermediate semantics of the image acts as a bridge between the underlying features and the advanced semantics of the image, which can make up for the semantic gap to a certain extent and has strong robustness. As a typical intermediate semantic representation method, the bag‐of‐visual‐words (BoVW) model has received extensive attention in image classification. However, the traditional BoVW model loses the location information of local features, and its local feature descriptors mainly focus on the texture shape information of local regions but lack the expression of color information. Therefore, in this paper, the improved bag‐of‐visual‐words model is presented, which contains three aspects of improvement: (1) multiscale local region extraction; (2) local feature description by speeded up robust features (SURF) and color vector angle histogram (CVAH); and (3) diagonal concentric rectangular pattern. Experimental results show that the three aspects of improvement to the BoVW model are complementary, while compared with the traditional BoVW and the BoVW adopting SURF + SPM, the classification accuracy of the improved BoVW is increased by 3.60% and 2.33%, respectively.

Fractional Fourier transform was used in this paper to realize the localization and velocity estimations in both directions, ground range direction and azimuth direction, when it comes to a one-aperture radar system. The theoretical analysis started with the echo signal model of SAR moving point targets and the computer simulation results of motion parameter estimations were given in this paper. The experimental results indicate that using fractional Fourier transform to detect the moving target, nice effect of localization and velocity estimation can be obtained in different signal-to-noise ratio conditions, and there is no cross-term interference when several moving targets exist.

Lung cancer has become the world's human cancer disease in the "first killer." In this paper, three aspects of lung CT images were treated. Firstly, based on the CT image preprocessing, the lung parenchyma was segmented by random walk algorithm and the ROI was extracted from the pulmonary parenchyma; Secondly, the 10-dimensional feature vectors of pulmonary nodule ROI were extracted by the gray level co-occurrence matrix algorithm; Finally, support vector machine as a classifier is to identify the pulmonary nodules and the accuracy rate is more than 94%. The experimental results show that the study of automatic CT image recognition can provide some data reference for doctors and play a supporting role in the course of treatment.

Based on the existing commodity image classification research, there is a lack of the use of the most recent color and texture features of the combination of commodity image classification. According to the local oppugnant color vector angle pattern (LOCVAP) feature extraction algorithm and the Deep Believe Network (DBN) classifier, the image classification is simulated and analyzed. The experimental results show that the results of LOCVAP descriptor have a greater improvement than those of other subcategories of feature descriptors.