To address the issues of data sparsity and cold-start problems in paper recommendation,as well as the limitations of general document representation methods in representing paper datasets,this study proposes a paper r...To address the issues of data sparsity and cold-start problems in paper recommendation,as well as the limitations of general document representation methods in representing paper datasets,this study proposes a paper recommendation method based on SPECTER and Graph Convolutional Networks(PR-SGCN method).This method leverages pre-trained document-level representation learning and the citation-aware transformer SPECTER to learn paper content representations,thereby overcoming the limitations of existing methods in representational capability.Additionally,it employs network representation learning and Graph Convolutional Networks(GCN)to mine hidden information from both attribute and structural perspectives,effectively mitigating the problems of data sparsity and cold starts.Experiments conducted on the ACL Anthology Network(AAN)and DBLP datasets demonstrate that,compared with the academic paper recommendation method based on heterogeneous graphs—Citation Recommendation based on Weighted Heterogeneous Information Network with Citation Semantic Links(WHIN-CSL)—and the academic literature recommendation method integrating network representation learning and textual information,the PR-SGCN method achieves improvements in Recall@25 by 59 and 72 percentage points,and by 67 and 65 percentage points,respectively.展开更多
Radiation damage is an important factor that must be considered while designing nuclear facilities and nuclear materials. In this study, radiation damage is investigated in graphite, which is used as a neutron reflect...Radiation damage is an important factor that must be considered while designing nuclear facilities and nuclear materials. In this study, radiation damage is investigated in graphite, which is used as a neutron reflector in the Tehran Research Reactor (TRR) core. Radiation damage is shown by displacement per atom (dpa) unit. A cross section of the material was created by using the SPECOMP code. The concentration of impurities present in the non-irradiated graphite was measured by using the ICP-AES method. In the present study the MCNPX code had identified the most sensitive location for radiation damage inside the reactor core. Subsequently, the radiation damage (spectral-averaged dpa values) in the aforementioned location was calculated by using the SPECTER, SRIM Monte Carlo codes, and Norgett, Robinson and Torrens (NRT) model. The results of “Ion Distribution and Quick Calculation of Damage”(QD) method groups had a minor difference with the results of the SPECTER code and NRT model. The maximum radiation damage rate calculated for the graphite present in the TRR core was 1.567 9 10^-8 dpa/s. Finally, hydrogen retention was calculated as a function of the irradiation time.展开更多
文摘To address the issues of data sparsity and cold-start problems in paper recommendation,as well as the limitations of general document representation methods in representing paper datasets,this study proposes a paper recommendation method based on SPECTER and Graph Convolutional Networks(PR-SGCN method).This method leverages pre-trained document-level representation learning and the citation-aware transformer SPECTER to learn paper content representations,thereby overcoming the limitations of existing methods in representational capability.Additionally,it employs network representation learning and Graph Convolutional Networks(GCN)to mine hidden information from both attribute and structural perspectives,effectively mitigating the problems of data sparsity and cold starts.Experiments conducted on the ACL Anthology Network(AAN)and DBLP datasets demonstrate that,compared with the academic paper recommendation method based on heterogeneous graphs—Citation Recommendation based on Weighted Heterogeneous Information Network with Citation Semantic Links(WHIN-CSL)—and the academic literature recommendation method integrating network representation learning and textual information,the PR-SGCN method achieves improvements in Recall@25 by 59 and 72 percentage points,and by 67 and 65 percentage points,respectively.
文摘Radiation damage is an important factor that must be considered while designing nuclear facilities and nuclear materials. In this study, radiation damage is investigated in graphite, which is used as a neutron reflector in the Tehran Research Reactor (TRR) core. Radiation damage is shown by displacement per atom (dpa) unit. A cross section of the material was created by using the SPECOMP code. The concentration of impurities present in the non-irradiated graphite was measured by using the ICP-AES method. In the present study the MCNPX code had identified the most sensitive location for radiation damage inside the reactor core. Subsequently, the radiation damage (spectral-averaged dpa values) in the aforementioned location was calculated by using the SPECTER, SRIM Monte Carlo codes, and Norgett, Robinson and Torrens (NRT) model. The results of “Ion Distribution and Quick Calculation of Damage”(QD) method groups had a minor difference with the results of the SPECTER code and NRT model. The maximum radiation damage rate calculated for the graphite present in the TRR core was 1.567 9 10^-8 dpa/s. Finally, hydrogen retention was calculated as a function of the irradiation time.
