Spatial-Temporal 3D Residual Correlation Network for Urban Traffic Status Prediction

Accurate traffic status prediction is of great importance to improve the security and reliability of the intelligent transportation system. However, urban traffic status prediction is a very challenging task due to the tight symmetry among the Human–Vehicle–Environment (HVE). The recently proposed spatial–temporal 3D convolutional neural network (ST-3DNet) effectively extracts both spatial and temporal characteristics in HVE, but ignores the essential long-term temporal characteristics and the symmetry of historical data. Therefore, a novel spatial–temporal 3D residual correlation network (ST-3DRCN) is proposed for urban traffic status prediction in this paper. The ST-3DRCN firstly introduces the Pearson correlation coefficient method to extract a high correlation between traffic data. Then, a dynamic spatial feature extraction component is constructed by using 3D convolution combined with residual units to capture dynamic spatial features. After that, based on the idea of long short-term memory (LSTM), a novel architectural unit is proposed to extract dynamic temporal features. Finally, the spatial and temporal features are fused to obtain the final prediction results. Experiments have been performed using two datasets from Chengdu, China (TaxiCD) and California, USA (PEMS-BAY). Taking the root mean square error (RMSE) as the evaluation index, the prediction accuracy of ST-3DRCN on TaxiCD dataset is 21.4%, 21.3%, 11.7%, 10.8%, 4.7%, 3.6% and 2.3% higher than LSTM, convolutional neural network (CNN), 3D-CNN, spatial–temporal residual network (ST-ResNet), spatial–temporal graph convolutional network (ST-GCN), dynamic global-local spatial–temporal network (DGLSTNet), and ST-3DNet, respectively.

Evolving Network Analysis of S&P500 Components: COVID-19 Influence of Cross-Correlation Network Structure

The economy is a system of complex interactions. The COVID-19 pandemic strongly influenced economies, particularly through introduced restrictions, which formed a completely new economic environment. The present work focuses on the changes induced by the COVID-19 epidemic on the correlation network structure. The analysis is performed on a representative set of USA companies—the S&P500 components. Four different network structures are constructed (strong, weak, typically, and significantly connected networks), and the rank entropy, cycle entropy, averaged clustering coefficient, and transitivity evolution are established and discussed. Based on the mentioned structural parameters, four different stages have been distinguished during the COVID-19-induced crisis. The proposed network properties and their applicability to a crisis-distinguishing problem are discussed. Moreover, the optimal time window problem is analysed.

Identifying the hub genes for Duchenne muscular dystrophy and Becker muscular dystrophy by weighted correlation network analysis

Background The goal of this study is to identify the hub genes for Duchenne muscular dystrophy (DMD) and Becker muscular dystrophy (BMD) via weighted correlation network analysis (WGCNA). Methods The gene expression profile of vastus lateralis biopsy samples obtained in 17 patients with DMD, 11 patients with BMD and 6 healthy individuals was downloaded from the Gene Expression Omnibus (GEO) database (GSE109178). After obtaining different expressed genes (DEGs) via GEO2R, WGCNA was conducted using R package, modules and genes that highly associated with DMD, BMD, and their age or pathology were screened. Gene Ontology (GO) and Kyoto Encyclopaedia of Genes and Genomes (KEGG) enrichment analysis and protein–protein interaction (PPI) network analysis were also conducted. Hub genes and highly correlated clustered genes were identified using Search Tool for the Retrieval of Interacting Genes (STRING) and Cystoscape software. Results One thousand four hundred seventy DEGs were identified between DMD and control, with 1281 upregulated and 189 downregulated DEGs. Four hundred and twenty DEGs were found between BMD and control, with 157 upregulated and 263 upregulated DEGs. Fourteen modules with different colors were identified for DMD vs control, and 7 modules with different colors were identified for BMD vs control. Ten hub genes were summarized for DMD and BMD respectively, 5 hub genes were summarized for BMD age, 5 and 3 highly correlated clustered genes were summarized for DMD age and BMD pathology, respectively. In addition, 20 GO enrichments were found to be involved in DMD, 3 GO enrichments were found to be involved in BMD, 3 GO enrichments were found to be involved in BMD age. Conclusion In DMD, several hub genes were identified: C3AR1, TLR7, IRF8, FYB and CD33(immune and inflammation associated genes), TYROBP, PLEK, AIF1(actin reorganization associated genes), LAPTM5 and NT5E(cell death and arterial calcification associated genes, respectively). In BMD, a number of hub genes were identified: LOX, ELN, PLEK, IKZF1, CTSK, THBS2, ADAMTS2, COL5A1(extracellular matrix associated genes), BCL2L1 and CDK2(cell cycle associated genes).

Weighted gene coexpression correlation network analysis reveals a potential molecular regulatory mechanism of anthocyanin accumulation under different storage temperatures in ‘Friar’ plum

Background Flesh is prone to accumulate more anthocyanin in postharvest ‘Friar’ plum (Prunus salicina Lindl.) fruit stored at an intermediate temperature. However, little is known about the molecular mechanism of anthocyanin accumulation regulated by storage temperature in postharvest plum fruit. Results To reveal the potential molecular regulation mechanism of anthocyanin accumulation in postharvest ‘Friar’ plum fruit stored at different temperatures (0 °C, 10 °C and 25 °C), the fruit quality, metabolite profile and transcriptome of its flesh were investigated. Compared to the plum fruit stored at 0 °C and 25 °C, the fruit stored at 10 °C showed lower fruit firmness after 14 days and reduced the soluble solids content after 21 days of storage. The metabolite analysis indicated that the fruit stored at 10 °C had higher contents of anthocyanins (pelargonidin-3-O-glucoside, cyanidin-3-O-glucoside, cyanidin-3-O-rutinoside and quercetin-3-O-rutinose), quercetin and sucrose in the flesh. According to the results of weighted gene coexpression correlation network analysis (WGCNA), the turquoise module was positively correlated with the content of anthocyanin components, and flavanone 3-hydroxylase (F3H) and chalcone synthase (CHS) were considered hub genes. Moreover, MYB family transcription factor APL (APL), MYB10 transcription factor (MYB10), ethylene-responsive transcription factor WIN1 (WIN1), basic leucine zipper 43-like (bZIP43) and transcription factor bHLH111-like isoform X2 (bHLH111) were closely related to these hub genes. Further qRT–PCR analysis verified that these transcription factors were specifically more highly expressed in plum flesh stored at 10 °C, and their expression profiles were significantly positively correlated with the structural genes of anthocyanin synthesis as well as the content of anthocyanin components. In addition, the sucrose biosynthesis-associated gene sucrose synthase (SS) was upregulated at 10 °C, which was also closely related to the anthocyanin content of plum fruit stored at 10 °C. Conclusions The present results suggest that the transcription factors APL, MYB10, WIN1, bZIP43 and bHLH111 may participate in the accumulation of anthocyanin in ‘Friar’ plum flesh during intermediate storage temperatures by regulating the expression of anthocyanin biosynthetic structural genes. In addition, the SS gene may play a role in anthocyanin accumulation in plum flesh by regulating sucrose biosynthesis.

Physical capacity, subjective health, and life satisfaction in older women: a 10-year follow-up study

Background Physical capacity and subjective wellbeing are important for healthy aging. Our aim was to study how objective/subjective physical capacity and subjective health relate to life satisfaction, in a 10-year follow-up of aging women. Methods The participants (n = 1485, mean age 67.4 years) consisted of community-dwelling older women living in Kuopio, Finland. Grip strength and one-legged stance test time were used as objective, and self-rated mobility (SRM) as subjective physical capacity measures. Self-rated health (SRH) and SRM were assessed with one-item scales and life satisfaction with a 4-item scale. Correlation and linear regression were used to analyze these relationships and correlation network analysis to visualize them. Age and BMI were included in the analysis as adjusting factors. Results All the study variables were significantly correlated with baseline and follow-up life satisfaction, except BMI, which was only associated with life satisfaction at follow-up. On both occasions, SRH and SRM were the two strongest correlates of life satisfaction, but their mutual correlation was still higher. In linear regression analyses, SRH was positively associated with both baseline and follow-up life satisfaction, but physical capacity measures became non-significant after including SRH and SRM in the model. In the partial correlation network analyses, SRH and SRM were the most central nodes, connecting every other variable. Conclusions Self-reports on health, mobility, and life satisfaction are closely intertwined and provide easily accessible health information among aging women, but the impacts of objective physical capacity measures warrant further longitudinal studies in respect to subjective wellbeing among aging people.

Innovation Efficiency and the Spatial Correlation Network Characteristics of Intelligent-Manufacturing Enterprises

A data envelopment analysis cross-efficiency model was used to measure the innovation efficiency of Chinese intelligent-manufacturing (IM) enterprises. This paper took as samples the number of granted patents and R&D investments of IM enterprises listed from 2015 to 2020. This research used the modified gravity model to determine the innovation efficiency and the spatial correlation of IM enterprises in China and used UCINET software to reveal the innovation efficiency and spatial network characteristics of IM enterprises through a social network analysis. The study found that the relationship was significant and frequently close between innovation efficiency and the spatial correlation network of IM enterprises. The distribution of the spatial association network was “core-edge,” and IM enterprises in Eastern China were at the network core and mostly played an intermediary role. The spatial correlation network had four modules. The distribution of the enterprise innovation correlation was uneven within each module, amalgamation was poor among the subgroups, and characteristics of highly cohesive subgroups were present.