A Lightweight Convolutional Neural Network Based on Channel Multi-Group Fusion for Remote Sensing Scene Classification

With the development of remote sensing scene image classification, convolutional neural networks have become the most commonly used method in this field with their powerful feature extraction ability. In order to improve the classification performance of convolutional neural networks, many studies extract deeper features by increasing the depth and width of convolutional neural networks, which improves classification performance but also increases the complexity of the model. To solve this problem, a lightweight convolutional neural network based on channel multi-group fusion (LCNN-CMGF) is presented. For the proposed LCNN-CMGF method, a three-branch downsampling structure was designed to extract shallow features from remote sensing images. In the deep layer of the network, the channel multi-group fusion structure is used to extract the abstract semantic features of remote sensing scene images. The structure solves the problem of lack of information exchange between groups caused by group convolution through channel fusion of adjacent features. The four most commonly used remote sensing scene datasets, UCM21, RSSCN7, AID and NWPU45, were used to carry out a variety of experiments in this paper. The experimental results under the conditions of four datasets and multiple training ratios show that the proposed LCNN-CMGF method has more significant performance advantages than the compared advanced method.

Group recommendation method combining short-term interest and long-term preference

Based on self-attention and outer product-based neural collaborative filtering,this paper proposed a SLAR model.The model uses the recent interaction information of each user in the group and self-attention mechanism to obtain the short-term interest vector of the group.The attention mechanism and self-attention mechanism are used to calculate the influence of each user and the influence between members during the interaction between the target group and item, so as to aggregate them into the long-term preference vector of the group, and then the sum of short-term interest and long-term preference is input into ONCF model as the embedding vector of the group to mine the interaction between the group and the project from the data, and finally complete the group recommendation. Compared with the traditional group fusion strategy on CAMR2011 data set, the experimental results show that SLGR model achieves better results.

Extensions of tensor categories by finite group fusion categories

We study exact sequences of finite tensor categories of the form Rep G → 𝒞 → 𝒟, where G is a finite group. We show that, under suitable assumptions, there exists a group Γ and mutual actions by permutations ⊳ : Γ × G → G and ⊲ : Γ × G→ Γ that make (G, Γ) into matched pair of groups endowed with a natural crossed action on 𝒟 such that 𝒞 is equivalent to a certain associated crossed extension 𝒟(G,Γ) of 𝒟. Dually, we show that an exact sequence of finite tensor categories Vec G → 𝒞 → 𝒟 induces an Aut(G)-grading on 𝒞 whose neutral homogeneous component is a (Z(G), Γ)-crossed extension of a tensor subcategory of 𝒟. As an application we prove that such extensions 𝒞 of 𝒟 are weakly group-theoretical fusion categories if and only if 𝒟 is a weakly group-theoretical fusion category. In particular, we conclude that every semisolvable semisimple Hopf algebra is weakly group-theoretical.

WHAT IS THE BEST DISTAL LEVEL OF ARTHRODESIS IN LUMBAR FUSION IN PATIENTS WITH ADOLESCENT IDIOPATHIC SCOLIOSIS: L3 OR L4?

ABSTRACT Objective To evaluate coronal alignment in patients with idiopathic adolescent scoliosis with structured lumbar curves submitted to surgical treatment by comparing coronal alignment in the group fusion up to L3 and the group fusion up to L4. Methods Retrospective cohort study. We evaluated patients submitted to surgical treatment with arthrodesis of the lumbar curve with high density of screws with at least 6 months of follow-up. Radiographically, coronal alignment, shoulder height and functional outcome were analyzed through SRS30 questionnaire. Results A total of 25 patients were analyzed, of which 23 were female and 2 were male, with a mean age of 15.2 years (12 to 29 years) at the time of surgery. The patients were divided into two groups. Group A, n = 15: Distal level of fusion in L3 and Group B, n = 10: distal level of fusion in L4. There was no statistically significant difference between Groups A and B when compared to coronal alignment (balanced vs. unbalanced). However, when compared with the coronal alignment (CA) values, lower values of CA were observed in Group A, with statistical significance. No difference was observed between Groups A and B with respect to the SRS30 questionnaire. Conclusions Patients with idiopathic adolescent scoliosis submitted to arthrodesis of the lumbar curve have a better coronal alignment when the distal fusion level is L3. Level of evidence III; Comparative Retrospective Study (based on prospectively collected data).