Search

In view of the problem that some recommendation algorithms based on knowledge graphs only aggregate one end of the neighbors and cannot effectively determine the relationship between entities and users, this paper proposes a dual-end neighbor aggregation recommendation algorithm based on knowledge graphs. This algorithm explores the internal connections of knowledge graphs to discover the potential relationship between users and items. On the user side, this paper proposes a method of aggregating user neighbor information. In the relational space of the knowledge graph, the knowledge graph is used to spread and extract the user’s potential interest, and iteratively inject the potential interest into the user characteristics with attention bias to generate user embedding representation vector. At the item side, the user vector that aggregates the user’s neighbor information is sent to the KGCN (knowledge graph convolutional networks) model, and when the polymer product and its neighbor infor-mation are used, a new aggregation method is used to generate the item embedding representation. Finally, the obtained vector is sent to train. Through the inner product operation of the vector and normalization, the association score between the user and the item is obtained. Then the training is carried out in the training set to optimize the parameters. Comparative experiments are conducted on two public datasets. Compared with the baseline, on the Book-Crossing dataset, AUC and ACC are increased by 1.72% and 4.24%, and on the Last.FM dataset, AUC and ACC are increased by 1.07% and 1.14%. It is proven that the effectiveness of the algorithm is improved after the information of neighbors at both ends is aggregated.

This work focuses on the improvement of the density peaks clustering (DPC) algorithm and its application to point cloud segmentation in LiDAR. The improvement of DPC focuses on avoiding the manual determination of the cut-off distance and the manual selection of cluster centers. And the clustering process of the improved DPC is automatic without manual intervention. The cut-off distance is avoided by forming a voxel structure and using the number of points in the voxel as the local density of the voxel. The automatic selection of cluster centers is realized by selecting the voxels whose gamma values are greater than the gamma value of the inflection point of the fitted γ curve as cluster centers. Finally, a new merging strategy is introduced to overcome the over-segmentation problem and obtain the final clustering result. To verify the effectiveness of the improved DPC, experiments on point cloud segmentation of LiDAR under different scenes were conducted. The basic DPC, K-means, and DBSCAN were introduced for comparison. The experimental results showed that the improved DPC is effective and its application to point cloud segmentation of LiDAR is successful. Compared with the basic DPC, K-means, the improved DPC has better clustering accuracy. And, compared with DBSCAN, the improved DPC has comparable or slightly better clustering accuracy without nontrivial parameters. [ABSTRACT FROM AUTHOR]

Fusarium wilt (FW) is widespread in global cotton production, but the mechanism underlying FW resistance in superior‐fiber‐quality Sea Island cotton is unclear. This study reveals that FW resistance has been the target of genetic improvement of Sea Island cotton in China since the 2010s. The key nonsynonymous single nucleotide polymorphism (SNP, T/C) of gene Gbar_D03G001670 encoding protein phosphatase 2C 80 (PP2C80) results in an amino acid shift (L/S), which is significantly associated with FW resistance of Sea Island cotton. Silencing GbPP2C80 increases FW resistance in Sea Island cotton, whereas overexpressing GbPP2C80 reduces FW resistance in Arabidopsis. GbPP2C80 and GbWAKL14 exist synergistically in Sea Island cotton accessions with haplotype forms "susceptible–susceptible" (TA) and "resistant–resistant" (CC), and interact with each other. CRISPR/Cas9‐mediated knockout of GbWAKL14 enhances FW and Verticillium wilt (VW) resistance in upland cotton and overexpression of GbWAKL14 and GbPP2C80 weakens FW and VW resistance in Arabidopsis. GbPP2C80 and GbWAKL14 respond to FW and VW by modulating reactive oxygen species (ROS) content via affecting MPK3 expression. In summary, two tandem genes on chromosome D03, GbPP2C80, and GbWAKL14, functions as cooperative negative regulators in cotton wilt disease defense, providing novel genetic resources and molecular markers for the development of resistant cotton cultivars. [ABSTRACT FROM AUTHOR]

This article has been retracted. A retraction notice can be found at https://doi.org/10.3233/JIFS-219433. [ABSTRACT FROM AUTHOR]

Capacitively coupled electrical impedance tomography (CCEIT) is an attractive improvement of electrical resistance tomography (ERT) that offers contactless measurement and utilizes both the real and imaginary parts of the impedance for monitoring conductive gas-liquid two-phase flows in the industry. The conventional CCEIT adopts the finite element method under the benchmark of conductive liquid background to obtain the sensitivity matrices, which has been validated effective in ERT for the usage of the real part information. However, few researches on the usage of the imaginary part information of the conductive fluid have been reported. More research work should be undertaken to seek the most effective sensitivity calculation benchmark for the imaginary part utilization in CCEIT. In this work, the usage of the imaginary part information under different sensitivity calculation benchmarks is studied and a new image reconstruction strategy is proposed for CCEIT. By comparing the imaginary part sensitivity matrices and the corresponding imaging performance under different backgrounds, the benchmark that can make better use of the imaginary part information is determined. With the determined benchmark, a new image reconstruction strategy of CCEIT, which utilizes the respective effective benchmarks for the image reconstruction of the two parts of the fluid impedance, and employs a novel hybrid image fusion method to obtain the final image, is presented. Research results show that the benchmark of non-conductive gas background is more effective for the usage of the imaginary part information of the conductive gas-liquid two-phase flow. And the experimental results demonstrate the effectiveness of the proposed strategy in obtaining high-quality images. Compared with the conventional image reconstruction strategy of CCEIT, the proposed strategy has better imaging performance. This research provides valuable experience in utilizing the imaginary part information of the fluid impedance and lays a good foundation for the further development of CCEIT. [ABSTRACT FROM AUTHOR]