Abstract Topic-to-Essay generation task aims to generate topic related and coherence text based on user input. Previous research generates text solely based on the input words and the generation results in not satisfactory. The traditional methods using semantic relationships of words from corpus to guide the model, which made the model rely heavily on the corpus. In this paper, we propose a sememe-based topic-to-essay generation model(S-TEG), which integrates sememes from external knowledge graph HowNet with input topic words to guide the model. In order to prevent introducing noise, we elaborately devise measuring the similarity of the non-current topic words to filter sememes information. The experiment results demonstrate that our approach achieved 4.10 average score in subjective evaluation and a 3.60 BLEU score, which shows that our model is able to generate text that is more coherence, topic-related and fits the daily logic.
Background: As known that the semi-supervised algorithm is a classical algorithm in semi-supervised learning algorithm. Methods: In the paper, it proposed improved cooperative semi-supervised learning algorithm, and the algorithm process is presented in detailed, and it is adopted to predict unlabeled electronic components image. Results: In the experiments of classification and recognition of electronic components, it show that through the method the accuracy the proposed algorithm in electron device image recognition can be significantly improved, the improved algorithm can be used in the actual recognition process . Conclusion: With the continuous development of science and technology, machine vision and deep learning will play a more important role in people's life in the future. The subject research based on the identification of the number of components is bound to develop towards the direction of high precision and multi-dimension, which will greatly improve the production efficiency of electronic components industry.
Traditionally, knowledge actionability has been investigated mainly by developing and improving technical interestingness. Recently, initial work on technical subjective interestingness and business-oriented profit mining presents general potential, while it is a long-term mission to bridge the gap between technical significance and business expectation. In this paper, we propose a two-way significance framework for measuring knowledge actionability, which highlights both technical interestingness and domain-specific expectations. We further develop a fuzzy interestingness aggregation mechanism to generate a ranked final pattern set balancing technical and business interests. Real-life data mining applications show the proposed knowledge actionability framework can complement technical interestingness while satisfy real user needs.
Reliable traffic flow prediction is of great value in the field of transportation, which, for example, contributes to traffic control and public safety. The key of achieving better performance is to well capture the non-linear spatial-temporal dependency. The state-of-the-art works consider both aspects, but they ignore the effect of the global trend on local dynamics and fail to capture long-term dynamic dependencies. In this article, we propose a novel Global-Local Temporal Convolutional Network (GL-TCN) to break through these limitations. Specifically, a novel local temporal convolutional mechanism is proposed to capture the long-term local dynamics effectively. Meanwhile, the global and local flow patterns are integrated to handle the effect of the global flow trend on local dynamics. To the best of our knowledge, this is the first work to utilize the temporal convolutional network for traffic flow prediction. Experiments on two real-world datasets demonstrate the superior performance of our method over several state-of-the-art baselines.
Bus services play a crucial role in urban transit. It is significant to achieve the fine-grained service-level passenger flow prediction (SPFP), namely to predict the total number of passengers for each service of each bus line passing through each station during the next short-term interval. However, it faces great challenges due to complex factors including inter-station and inter-line spatial dependencies, intra-station and inter-service temporal dependencies, and internal/external influences. To address these challenges, we propose a multitask deep-learning (MDL) approach, called MDL-SPFP, to jointly predict the arriving bus service flow, line-level on-board passenger flow and line-level boarding/alighting passenger flow by leveraging well-designed deep neural networks called ARM. The MDL framework can mutually reinforce the prediction of each type of flow, and finally integrate the outputs to achieve the fine-grained service-level prediction. The ARM network combines three modules, Attention mechanism, Residual block and Multi-scale convolution, to well capture various complex non-linear spatio-temporal dependencies and influence factors. Extensive experiments based on a large-scale realistic bus operation dataset are conducted to confirm that our MDL-SPFP approach outperforms 10 state-of-the-art baselines, and improves 22.39% accuracy than the best baseline.
As a large number of MTC devices try to access the radio resources in a very short period,the rapid growth in the number of machine-type communications(MTC) devices causes the radio access network(RAN) to overload.Several candidate schemes for RAN improvements for MTC have been under consideration for possible adoption in LTE-A by 3GPP.In the paper,several schemes to control the RAN overload coming from massive number of MTC devices were analyzed,and optimization schemes for further solution was designed.
The morphology and morphogenesis of a new soil hypotrich ciliate, Sterkiella multicirrata sp. nov., was investigated using live observation and protargol staining. The new species is characterised by: body elliptical, 110-180 × 45-75 μm in vivo, an average of 35 adoral membranelles; usually 19 frontoventral-transverse cirri, consisting of three frontal, five frontoventral, one buccal, four postoral ventral, two pretransverse, and four transverse cirri; four macronuclear nodules, and 2-5 micronuclei. S. multicirrata sp. nov. differs from its congeners mainly in the number of frontoventral-transverse cirri and macronuclear nodules. Morphogenesis of the new species is similar to its congeners; the primary difference exists in the segmentation of the frontoventral-transverse cirral anlagen, which is usually generated in a 1:2:3:3:5:5 pattern. Based on the small subunit ribosomal DNA sequence, the phylogenetic position of the new species is discussed.
Abstract Background: PHGDH (Phosphoglycerate Dehydrogenase) is the first branch enzyme in the serine biosynthetic pathway and plays a vital role in several cancers. However, little is known about the clinical significance of PHGDH in endometrial cancer. Methods: Clinicopathological data of endometrial cancer were downloaded from the Cancer Genome Atlas database (TCGA). First, the expression of PHGDH in pan-cancer was investigated, as well as the expression and prognostic value of PHGDH in endometrial cancer. The effect of PHGDH expression on the prognosis of endometrial cancer was analyzed by Kaplan-Meier plotter and Cox regression. The relationship between PHGDH expression and clinical characteristics of endometrial cancer was investigated by logistic regression. Receiver operating characteristic (ROC) curves and nomograms were developed. Possible cellular mechanisms were explored using the Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway enrichment analysis, the Gene Ontology (GO), and gene set enrichment analysis (GSEA). Finally, TIMER and CIBERSORT were used to analyze the relationship between PHGDH expression and immune infiltration. CellMiner TM was used to analyze the drug sensitivity of PHGDH. Results: The results showed that PHGDH expression was significantly higher in endometrial cancer tissues than in normal tissues at mRNA and protein levels. Kaplan-Meier survival curves showed that patients in the high expression group had shorter overall survival (OS) and disease free survival (DFS) than patients in the low PHGDH expression group. Multifactorial COX regression analysis further supported that high PHGDH expression was an independent risk factor associated with prognosis in patients with endometrial cancer. The results showed estrogen response, mTOR, K-RAS, and epithelial mesenchymal transition (EMT) were differentially elevated in the high-expression group of the PHGDH group. CIBERSORT analysis showed that PHGDH expression is related to the infiltration of multiple immune cells. When PHGDH is highly expressed, the number of CD8 + T cells decreases. Conclusions: PHGDH plays a vital role in the development of endometrial cancer, which is related to tumor immune infiltration, and can be used as an independent diagnostic and prognostic marker for endometrial cancer.
Avascular necrosis of the femoral head (ANFH) is a progressive, multifactorial, and challenging clinical condition that often leads to hip dysfunction and deterioration. The pathogenesis of ANFH is complex, and there is no foolproof treatment strategy. Although some pharmacologic and surgical treatments have been shown to improve ANFH, the associated side effects and poor prognosis are of concern. Therefore, there is an urgent need to explore therapeutic interventions with superior efficacy and safety to improve the quality of life of patients with ANFH. Salvia miltiorrhiza (SM), a traditional Chinese medicine with a long history, is widely used for the treatment of cardiovascular and musculoskeletal diseases due to its multiple pharmacological activities. However, the molecular mechanism of SM for the treatment of ANFH is still unclear. Therefore, this study aimed to explore the potential targets and mechanisms of SM for the treatment of ANFH using network pharmacology and molecular modeling techniques. By searching multiple databases, we screened 52 compounds and 42 common targets involved in ANFH therapy and identified dan-shexinkum d, cryptotanshinone, tanshinone iia, and dihydrotanshinlactone as key compounds. Based on the protein-protein interaction (PPI) network, TP53, AKT1, EGFR, STAT3, BCL2, IL6, and TNF were identified as core targets. Subsequent enrichment analysis revealed that these targets were mainly enriched in the AGE-RAGE, IL-17, and TNF pathways, which were mainly associated with inflammatory responses, apoptosis, and oxidative stress. In addition, molecular docking and 100 nanoseconds molecular dynamics (MD) simulations showed that the bioactive compounds of SM had excellent affinity and binding strength to the core targets. Among them, dan-shexinkum d possessed the lowest binding free energy (-215.874 kcal/mol and − 140.277 kcal/mol, respectively) for AKT1 and EGFR. These results demonstrated the multi-component, multi-target, and multi-pathway intervention mechanism of SM in the treatment of ANFH, which provided theoretical basis and clues for further experimental validation and development of anti-ANFH drugs.
This paper analyzes the relationships between orbit variations and MW rotation rates variations during station-keeping control and brings up a new evaluation algorithm of station-keeping control results by using variation of angular momentum. This algorithm can evaluate the control results rapidly and get precise semi-major axis, eccentricity, longitude drift rate variation after the control. The algorithm has characters of rapid evaluation and high precision. Then it has been successfully applied to GEO satellites operation.
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)