Search

Structural response prediction under earthquakes is crucial for evaluating the structural performance and subsequent functional restoration. Deep learning provides the potential to rapidly obtain the responses by skipping the time‐consuming nonlinear finite element analysis. However, a single deep learning network may only predict the time history responses of one specific structure, resulting in redundancy and resource waste when building multiple networks for modeling different structures. Thus, this study proposes a Structure Temporal Fusion Network (STFN) that can predict responses of various homogeneous structures using a single network. The key concept is that the seismic waves and the structural characteristics, such as story numbers, are fused together to predict diverse time history responses. Two numeric experiments are conducted, including predicting responses of ideal single‐degree‐of‐freedom (SDOF) structures and regular multistory reinforced concrete frames. Furthermore, a series of ablation analyses are carried out to validate the network architecture. The results indicate that STFN can predict nonlinear time history responses of different structures with mean square errors in the magnitude of 10−4$10^{-4}$ and 10−5$10^{-5}$ for two experiments, respectively. The solutions also highlight the importance of fusing static characteristics for the modeling of various structures with only one network. The STFN presents a promising solution for time history response prediction across multiple structures in regions. [ABSTRACT FROM AUTHOR]

Objective: To investigate the role of long non-coding RNA LINC00261 in regulating E26 transcription factor 1 (EST1) by interfering with the expression of miR-324-3p in promoting the development of gastric cancer (GC). Methods: Cancer tissues and corresponding adjacent normal tissues of GC patients (n=80) who underwent surgical treatment in 363 Hospital from June 2018 to October 2020 were collected as research samples, and the expression levels of LINC00261 and miR-324-3p were detected by qRT-PCR. The correlation between LINC00261 and clinicopathological parameters were analyzed. siRNA (si-LINC00261), miRNA mimic (miR-324-3p), miRNA inhibitor (miR-324-3p in) and their corresponding controls were transfected into MGC-803 and SGC- 7901 cells. Clonogenesis assay was used to evaluate cell proliferation. The Transwell assay assessed cell migration and invasion. The protein expression levels of E-cadherin, N-cadherin and ETS1 were detected by Western blot. Tumor xenotransplantation assay was used to detect the tumorigenesis of LINC00261 in vivo. Luciferase report and RNA precipitation were used to analyze the interaction between LINC00261, miR-324-3p and EST1. Results: Compared with adjacent tissues, the expression of LINC00261 in GC tissues was significantly up-regulated with statistical significance (P<0.05). The expression of LINC00261 was correlated with TNM stage, tissue differentiation degree, lymph node metastasis and microvascular invasion (P<0.05). The database prediction, firefly luciferase assay and RNA immunoprecipitation results showed that LINC00261 had a targeted relationship with miR-324-3p. The level of miRdoi: 324-3p in GC tissues was significantly lower than that in paracellular normal tissues (P<0.05). There was a negative correlation between miR-324-3p level and LINC00261 expression (P<0.05). Compared with in NC+si-NC group, the cell proliferation, migration and invasion ability and the expression of N-cadherin in in NC+si-LINC00261 group were significantly inhibited (P<0.05), while the expression of E-cadherin was significantly increased (P<0.05). Compared with in NC+si-LINC00261 group, cell proliferation, migration and invasion ability and expression of N-cadherin in si-LINC00261+miR-324-3p in group were significantly increased (P<0.05), while the expression of E-cadherin was significantly decreased (P<0.05). Targetscan prediction and firefly luciferase assay showed that ETS1 was the downstream binding site of miR-324-3p. After transfection with miR-324-3p, ETS1 protein level was significantly down-regulated (P<0.05), but after transfection with miR-324-3p in, ETS1 protein level was significantly up-regulated (P<0.05). The expression of ETS1 in GC tissue was significantly higher than that in adjacent normal tissue (P<0.05). The miR-324-3p level was negatively correlated with ETS1 (P<0.05). The tumor weight of MGC-803 cells transfected with si-LINC00261 was lower than that of MGC-803 cells transfected with si-NC (P<0.05), and the protein level of ETS1 in si-LINC00261-derived tumors was lower than that of si-NC tumors (P<0.05). Conclusion: LINC00261 is highly expressed in GC tissue, which may affect EST1 expression and promote GC progress by regulating miR-324-3p. [ABSTRACT FROM AUTHOR]

Software defect prediction can identify defective modules in advance by mining the defect datasets,helping testers to achieve more targeted testing.However,the ubiquity of label noise in the datasets affects the performance of the prediction mo-del.Few feature selection methods have been used to specifically design noise tolerance.In addition,the strategy selection in the mainstream noise tolerable feature selection framework can only be performed manually based on human experience,which is difficult to be applied in software engineering.In view of this,this paper proposes a novel method NTFES (noise tolerable feature selection).In particular,NTFES first generates multiple Bootstrap samples by Bootstrap sampling method.Then it divides the original features into different groups on Bootstrap samples by approximate Markov blanket and selects candidate features from each group based on two heuristic feature selection strategies. Sequently it uses genetic algorithm (GA) to search the optimal feature subset in the candidate feature space.To verify the effectiveness of the proposed method,this paper chooses NASA MDP dataset,and inject label noises simultaneously to imitate noisy datasets.Then it compares NTFES with other classical baseline methods,such as FULL,FCBF and CFS,by controlling the ratio of label noises.The experimental results show that the proposed method has the advantages of achieving higher classification performance and has better noise tolerable while the ratio of label noises is acceptable.

IntroductionBody dysmorphic disorder (BDD) and depression have been reported to be both prevalent among young people worldwide, resulting in serious implications in their quality of life and social functioning. This is worrying especially in men where mental disorders are often overlooked and under-researched. This study aims to determine the proportion of male university students with symptoms suggestive of body dysmorphic disorder and depression, as well as their perception on their body image.MethodsIn this cross-sectional study, 1,308 male students between the aged of 17–26 years in a private university in Malaysia via self-administered online questionnaire comprising the Patient Health Questionnaire (PHQ)-9, the Body Dysmorphic Disorder Questionnaire (BQQD) and the Body Self-Image Questionnaire (BSIQ), in addition to their sociodemographic parameters. Data analyses were performed with Mann Whitney test, chi square test and Fisher's exact test.Results3.3 and 54.2% of the students had symptoms suggestive of BDD and depression respectively, with up to 9.02% of the students reporting having moderate to severe depression. There was a significant association between BDD symptoms and students staying alone, whilst depression was significantly associated with studying in the rural campus. Furthermore, a significant association was demonstrated between presence of BDD and depression symptoms. Most of the students were dissatisfied with their whole body, especially their height.ConclusionThe proportion of BDD and depression symptoms among male students in our university is quite high. Universities and the public health sector should develop better support service targeting male university students.

A three-wave prospective study was conducted to provide a better understanding of the ability of the integrated model of self-determination theory (SDT) and the theory of planned behavior (TPB) to predict future physical activity (PA) engagement among adolescents. Nearly 2500 secondary school students from China were recruited to test the hypothesized pathway from autonomous motivation from SDT at baseline (T1) through the constructs of TPB one month later (T2) on leisure-time PA levels of secondary school students three months later (T3). The findings revealed that the structural equation models yielded excellent fit indices with χ2 = 1858.989, df = 257, CFI = 0.936, TLI = 0.926, RMSEA = 0.050 [90% CI = 0.048 to 0.052], and SRMR = 0.032. In particular, autonomous motivation at T1 was positively associated with attitude (R2 = 0.160), subjective norms (R2 = 0.160), and perceived behavioral control (PBC) (R2 = 0.173) at T2 (β = 0.395 to 0.414, p < 0.001) and subsequently associated with intention at T2 (R2 = 0.875, β = 0.112 to 0.478, p < 0.001). T2 intention was positively associated with leisure-time PA levels (R2 = 0.004) at T3. Our findings contribute to a better understanding of the motivational mechanisms and social cognition processes involved in predicting adolescents' leisure-time PA levels among adolescents. [ABSTRACT FROM AUTHOR]

As vehicles with high accident and casualty rates within the road transportation system, engineering vehicles have been receiving much attention and emphasis in terms of safety. Accurate analyses and evaluations of risk factors in vehicle operation are imperative for enhancing the management level of engineering vehicles. This study explores the differences between various types of drivers by analyzing the driving characteristics of professional drivers. The evaluation index system is developed and quantified by integrating factors related to engineering vehicle drivers, road environment, and industry management. Additionally, the risk assessment model is developed using the error backpropagation algorithm. The optimal model is determined by comparing the number of nodes in different hidden layers, the activation function, and regularization optimization. The prediction accuracy of this model's coefficient of determination is 0.912, indicating that the model has validity. This study is conducive to improving the safety level of engineering vehicle operation in order to reduce the rate of vehicle traffic accidents, the severity of accidents, and the consequences of losses. It also has practical application value in safeguarding social security. [ABSTRACT FROM AUTHOR]