Traffic flow prediction has emerged as a critical component in advancing smart cities. Nevertheless, precisely forecasting traffic flow remains a formidable challenge, attributable to the intricate and dynamic spatiotemporal interdependencies inherent within traffic data. Contemporary methodologies often overlook the different impacts exerted at each timestamp and treat temporal correlations, rendering them incapable of extracting temporal patterns at multiple scales. Furthermore, these approaches fail to account for the neighboring and functional relationships among nodes within the spatial module. In this work, we introduce an innovative Multiscale and Gated transFormer (MSGFormer) architecture, MSGFormer, to overcome the inherent limitations for accurate traffic flow estimation. We have introduced a multiscale sampling strategy wherein we sample from the original data at three scales: 1) recent; 2) daily; and 3) weekly. This approach enables the generation of corresponding subsequences that encapsulate temporal information across different granularities. Subsequently, each generated subsequence is projected into a latent space and systematically combined with positional, temporal, and spatial embeddings. The positional embedding comprises relative positional embedding and time stamp embedding corresponding to days and weeks, aiming at capturing the sequential and cyclical characteristics of the data. Furthermore, at the inception of the transformer encoder, a gated unit, composed of a neighboring mask and a functioning mask, is employed to capture both static and dynamic spatial correlations effectively. Comprehensive experiments have been conducted on four real-world traffic data sets. The experimental results robustly validate that our model attains significantly higher predictive accuracy in comparison to other baseline models.

Neonatal mortality reduction in China over past two decades was reported from nationwide sampling surveys, however, how high risk pregnancy affected neonatal outcome is unknown. The objective of this study was to explore relations of pregnancy complications and neonatal outcomes from a regional birth population. In a prospective, cross-sectional survey of complete birth population-based data file from 151 level I-III hospitals in Huai’an region in 2010, pregnancy complications were analyzed for perinatal morbidity and mortality in association with maternal and perinatal characteristics, hospital levels, mode of delivery, newborn birth weight and gestational age, using international definition for birth registry and morbidities. Pregnancy complications were found in 10% of all births, in which more than 70% were delivered at level II and III hospitals associated with higher proportions of fetal and neonatal death, preterm birth, death at delivery and congenital anomalies. High Cesarean section delivery was associated with higher pregnancy complications, and more neonatal critical illnesses. The pregnancy complications related perinatal morbidity and mortality in level III were 2–4 times as high as in level I and II hospitals. By uni- and multi-variate regression analysis, impact of pregnancy complications was along with congenital anomalies and preterm birth, and maternal child-bearing age and school education years contributing to the prevalence. This survey revealed variable links of pregnancy complications to perinatal outcome in association with very high Cesarean section deliveries, which warrants investigation for causal relations between high risk pregnancy and neonatal outcome in this emerging region.

Monocular 3D human pose estimation is used to calculate a 3D human pose from monocular images or videos. It still faces some challenges due to the lack of depth information. Traditional methods have tried to disambiguate it by building a pose dictionary or using temporal information, but these methods are too slow for real-time application. In this paper, we propose a real-time method named G2O-pose, which has a high running speed without affecting the accuracy so much. In our work, we regard the 3D human pose as a graph, and solve the problem by general graph optimization (G2O) under multiple constraints. The constraints are implemented by algorithms including 3D bone proportion recovery, human orientation classification and reverse joint correction and suppression. When the depth of the human body does not change much, our method outperforms the previous non-deep learning methods in terms of running speed, with only a slight decrease in accuracy.

Multi-view 3D reconstruction technology based on deep learning is developing rapidly. Unsupervised learning has become a research hotspot because it does not need ground truth labels. The current unsupervised method mainly uses 3DCNN to regularize the cost volume to regression image depth. This approach results in high memory requirements and long computing time. In this paper, we propose an end-to-end unsupervised multi-view 3D reconstruction network framework based on PatchMatch, Unsup_patchmatchnet. It dramatically reduces memory requirements and computing time. We propose a feature point consistency loss function. We incorporate various self-supervised signals such as photometric consistency loss and semantic consistency loss into the loss function. At the same time, we propose a high-resolution loss method. This improves the reconstruction of high-resolution images. The experiment proves that the memory usage of the network is reduced by 80% and the running time is reduced by more than 50% compared with the network using 3DCNN method. The overall error of reconstructed 3D point cloud is only 0.501 mm. It is superior to most current unsupervised multi-view 3D reconstruction networks. Then, we test on different data sets and verify that the network has good generalization.