Search

Due to the rapid expansion of online platforms, review-based recommender systems have become the standard way to determine consumers' preferences for various goods. The purpose of this study is to address three significant issues with review-based approaches. First, these techniques suffer from a class-imbalance problem, where rating levels with lower proportions are partially neglected. As a result, their rating performance for such rare levels is unsatisfactory. To address this drawback, this paper proposes a flexible dual-optimizer network that enhances performance by utilizing classification and regression losses in the first attempt to solve this problem. Second, the typical review-based approach of preprocessing review texts with word embeddings will result in inadequate contextual information extraction. Thus, the bidirectional encoder representations from the transformers (BERT) method is introduced as the preprocessing technique to fully extract semantic information. Third, existing techniques make recommendations without considering that the user preferences may change over time. We suggest a time-varying feature extraction scheme that includes a multiscale convolutional neural network and bidirectional long short-term memory to solve this problem. We then develop an interactive component that summarizes the contextual information associated with the user-item pairings. The efficiency of the proposed time-varying attention with dual-optimizer (TADO) model is demonstrated through extensive tests on 12 benchmark datasets derived from Amazon Product Reviews. Regarding the existing state-of-the-art techniques, the proposed model attains a substantial performance increase of 22.69%, 8.75%, and 17.35%, respectively, over the Aspect-aware Latent Factor Model (ALFM), Multi-Pointer Co-Attention Networks for recommendation (MPCN), and Aspect-based Neural Recommender (ANR). Moreover, an ablation study demonstrates the importance of jointly employing the components developed for TADO. [ABSTRACT FROM AUTHOR]

Human vision system can receive the RGB and depth information at the same time and make an accurate judgment on human behaviors. However, in an ordinary camera, there is a loss in information when a 3D image is projected to a 2D plane. The depth and RGB information collected simultaneously by Kinect can provide more discriminant information for human behaviors than traditional cameras. Therefore, RGB-D camera is thought to be the key of solving human behavior recognition for a long time. In this paper, we develop 3D motion scale invariant feature transform for the description of the depth and motion information. It serves as a more effective descriptor for the RGB and depth videos. Hidden Markov Model is utilized for improving the accuracy of human behavior recognition. Experiments show that our framework provides richer information for discriminative point of behavior analysis and obtains better recognition performance. [ABSTRACT FROM AUTHOR]

This study is intended to explore the role of human umbilical-cord-derived mesenchymal stem cells (HUC-MSCs) in nerve end-to-side anastomosis, as well as in the induction and promotion of growth of nerve lateral bud. The chitosan nerve conduit was prepared based on the biological characteristics of chitosan, and the nerve conduit was filled with HUC-MSCs, and was used to bridge the nerve end-to-side anastomotic stoma. The experimental animals were randomly assigned into three groups (10 in each group), and the nerve end-to-side anastomosis was conducted: (1) group A (control group): traditional tibial nerve-common peroneal nerve end-to-side anastomosis; (2) group B (experimental group 1): tibial nerve-common peroneal nerve end-to-side anastomotic stoma bridged with chitosan nerve conduit; (3) group C (experimental group 2): tibial nerve-common peroneal nerve end-to-side anastomotic stoma bridged by chitosan nerve conduit filled with HUC-MSCs. General morphological observation, nerve electrophysiology, and anti-S-100 immunohistochemistry were performed. All experimental animals survived, and no infections were found at operative incisions. The nerve continuity was in good condition through visual observation when sampling, which is mild adhesion to the surrounding tissue and easy to be separated. 12 W HUC-MSCs chitosan composite nerve conduits were degraded completely after operation. Electrophysiological test showed that the nerve conduction velocity (NCV) in group C was significantly higher than that in group A or group B ( p < 0.01). There were no significant differences between NCVs of group A and group B. Toluidine blue staining and transmission electron microscope showed that the number of the medullated fibers and the myelin sheath thickness in group C were larger than those in group A or B. There were no significant differences between the numbers of the medullated fibers and between the myelin sheath thicknesses of groups A and B. By means of anti-S-100 immunohistochemistry, the arrangement of a large number of brown-red proliferating schwann cells around the regenerated nerve fibers in group C could be found, while fewer and sparse brown-red matters and very poor growth of schwann cells could be observed in groups A and B. Slightly more favorable situation could be observed in group B compared with group A. HUC-MSCs play obviously an important role in promoting nerve regeneration during the nerve end-to-side anastomosis, which induces the growth of axis bud, accelerates the growth velocity of regenerated fiber, and promotes the growth and maturity of schwann cells. [ABSTRACT FROM AUTHOR]

Osteosarcoma is the most malignant bone tumor characterized by high local aggressiveness and poor therapeutic outcome. Tumor-associated macrophages (TAM) have been shown to participate in the development and progress of many types of cancer cells. However, whether TAM may play a role in the pathogenesis of osteosarcoma is largely unknown. In a mouse model of human osteosarcoma implantation, we showed that the recruited macrophages at the site of the implanted tumor were polarized to an M2 subtype (same as TAM) during the development and growth of the osteosarcoma. In a loss-of-function experiment, we deleted these TAM with a specific macrophage-eliminating liposome, which resulted in decreased tumor growth. Moreover, when the epidermal growth factor receptor (EGFR) in the implanted cancer cells was inhibited by shRNA, the tumor failed to grow in response to the recruited macrophages. Taken together, for the first time, we show that the growth of an osteosarcoma is EGFR signaling-dependent and TAM-mediated. Our data suggest that TAM and EGFR may be good targets for treating human osteosarcoma. [ABSTRACT FROM AUTHOR]