Study on the Influence of Label Image Accuracy on the Performance of Concrete Crack Segmentation Network Models.

A high-quality dataset is a basic requirement to ensure the training quality and prediction accuracy of a deep learning network model (DLNM). To explore the influence of label image accuracy on the performance of a concrete crack segmentation network model in a semantic segmentation dataset, this study uses three labelling strategies, namely pixel-level fine labelling, outer contour widening labelling and topological structure widening labelling, respectively, to generate crack label images and construct three sets of crack semantic segmentation datasets with different accuracy. Four semantic segmentation network models (SSNMs), U-Net, High-Resolution Net (HRNet)V2, Pyramid Scene Parsing Network (PSPNet) and DeepLabV3+, were used for learning and training. The results show that the datasets constructed from the crack label images with pix-el-level fine labelling are more conducive to improving the accuracy of the network model for crack image segmentation. The U-Net had the best performance among the four SSNMs. The Mean Intersection over Union (MIoU), Mean Pixel Accuracy (MPA) and Accuracy reached 85.47%, 90.86% and 98.66%, respectively. The average difference between the quantized width of the crack image segmentation obtained by U-Net and the real crack width was 0.734 pixels, the maximum difference was 1.997 pixels, and the minimum difference was 0.141 pixels. Therefore, to improve the segmentation accuracy of crack images, the pixel-level fine labelling strategy and U-Net are the best choices.

Sustainable urban mobility: Flexible bus service network design in the post-pandemic era.

The excessive traffic congestion in vehicles lowers the service quality of urban bus system, reduces the social distance of bus passengers, and thus, increases the spread speed of epidemics, such as coronavirus disease. In the post-pandemic era, it is one of the main concerns for the transportation agency to provide a sustainable urban bus service to balance the travel convenience in accessibility and the travel safety in social distance for bus passengers, which essentially reduces the in-vehicle passenger congestion or smooths the boarding-alighting unbalance of passengers. Incorporating the route choice behavior of passengers, this paper proposes a sustainable service network design strategy by selecting one subset of the stops to maximize the total passenger-distance (person × kilometers) with exogenously given loading factor and stop-spacing level, which can be captured by constrained non-linear programming model. The loading factor directly determines the in-vehicle social distance, and the stop-spacing level can efficiently reduce the ridership with short journey distance. Therefore, the sustainable service network design can be used to help the government minimize the spread of the virus while guaranteeing the service quality of transport patterns in the post-pandemic era. A real-world case study is adopted to illustrate the validity of the proposed scheme and model.

Performance evaluation model of transportation infrastructure: Perspective of COVID-19.

The transportation systems are facing major challenges due to changes social environment caused by the COVID-19 pandemic. How to construct a suitable evaluation criterion system and suitable assessment method to evaluate the status of the urban transportation resilience has become a predicament nowadays. Firstly, the criteria for evaluating the current state of transportation resilience involve many aspects. New features of transportation resilience under epidemic normalization are exposed, and previous summaries focusing on resilience characteristics under natural disasters can hardly reflect the current state of urban transportation resilience comprehensively. Based on this, this paper attempts to incorporate the new criteria (Dynamicity, Synergy, Policy) into the evaluation system. Secondly, the assessment of urban transportation resilience involves numerous indicators, which make it difficult to obtain quantitative figures for the criteria. With this background, a comprehensive multi-criteria assessment model based on q-rung orthopair 2-tuple linguistic sets is constructed to evaluate the status of transportation infrastructure from perspective on the COVID-19. Then, an example of urban transportation resilience is given to demonstrate the feasibility of the proposed approach. Subsequently, sensitivity analysis about parameters and global robust sensitivity analysis are conducted, and comparative analysis of existing method is given. The results reveal that the proposed method is sensitive to global criteria weights, so it is suggested that more attention should be paid to the rationality of the weight of criteria to avoid the influence on the results when solving MCDM problems. Finally, the policy implications regarding transport infrastructure resilience and appropriate model development are given.

Hybrid Intelligence-Driven Medical Image Recognition for Remote Patient Diagnosis in Internet of Medical Things.

In ear of smart cities, intelligent medical image recognition technique has become a promising way to solve remote patient diagnosis in IoMT. Although deep learning-based recognition approaches have received great development during the past decade, explainability always acts as a main obstacle to promote recognition approaches to higher levels. Because it is always hard to clearly grasp internal principles of deep learning models. In contrast, the conventional machine learning (CML)-based methods are well explainable, as they give relatively certain meanings to parameters. Motivated by the above view, this paper combines deep learning with the CML, and proposes a hybrid intelligence-driven medical image recognition framework in IoMT. On the one hand, the convolution neural network is utilized to extract deep and abstract features for initial images. On the other hand, the CML-based techniques are employed to reduce dimensions for extracted features and construct a strong classifier that output recognition results. A real dataset about pathologic myopia is selected to establish simulative scenario, in order to assess the proposed recognition framework. Results reveal that the proposal that improves recognition accuracy about two to three percent.

Impacts of COVID-19 pandemic on user behaviors and environmental benefits of bike sharing: A big-data analysis.

The COVID-19 pandemic spreads rapidly around the world, and has given rise to huge impacts on all aspects of human society. This study utilizes big data techniques to analyze the impacts of COVID-19 on the user behaviors and environmental benefits of bike sharing. In this study, a novel method is proposed to calculate the trip distances and trajectories via a python package OSMnx so as to accurately estimate the environmental benefits of bike sharing. In addition, we employ the topological indices arising from complex network theory to quantitatively analyze the transformation of user behavior pattern of bike sharing during the COVID-19 pandemic. The results show that this pandemic has impacted the user behaviors and environmental benefits of bike sharing in Beijing significantly. During the pandemic, the estimated reductions of energy consumption and emissions on 6th Feb decreased to approximately 1 in 17 of those on a normal day, and the environmental benefits at most recovered to 70% of those in normal days. The impacts of COVID-19 on the environmental benefits in different districts are different. Furthermore, the decline of average strength and strength distribution obeying exponential distribution but with different slope rates suggests that people are less likely to take bike sharing to the places where were popular before. The pandemic has also increased the average trip time of bike sharing. Our research may facilitate the understanding of the impacts of COVID-19 pandemic on our society and environment, and also provide clues to adapt to this unprecedented pandemic so as to respond to similar events in the future.

Moderate SMFs attenuate bone loss in mice by promoting directional osteogenic differentiation of BMSCs.

BACKGROUND: Osteoporosis is a common metabolic bone disease without effective treatment. Bone marrow-derived mesenchymal stem cells (BMSCs) have the potential to differentiate into multiple cell types. Increased adipogenic differentiation or reduced osteogenic differentiation of BMSCs might lead to osteoporosis. Whether static magnetic fields (SMFs) might influence the adipo-osteogenic differentiation balance of BMSCs remains unknown. METHODS: The effects of SMFs on lineage differentiation of BMSCs and development of osteoporosis were determined by various biochemical (RT-PCR and Western blot), morphological (staining and optical microscopy), and micro-CT assays. Bioinformatics analysis was also used to explore the signaling pathways. RESULTS: In this study, we found that SMFs (0.2-0.6 T) inhibited the adipogenic differentiation of BMSCs but promoted their osteoblastic differentiation in an intensity-dependent manner. Whole genomic RNA-seq and bioinformatics analysis revealed that SMF (0.6 T) decreased the PPARγ-mediated gene expression but increased the RUNX2-mediated gene transcription in BMSCs. Moreover, SMFs markedly alleviated bone mass loss induced by either dexamethasone or all-trans retinoic acid in mice. CONCLUSIONS: Taken together, our results suggested that SMF-based magnetotherapy might serve as an adjunctive therapeutic option for patients with osteoporosis.

Mining urban sustainable performance: Spatio-temporal emission potential changes of urban transit buses in post-COVID-19 future.

Emission benefits of transit buses depend on ridership. Declines in ridership caused by COVID-19 leads uncertainty about the emission reduction capacity of buses. This paper provides a method framework for analyzing spatio-temporal emission patterns of buses in combination with real-time ridership and potential emission changes in the post-COVID-19 future. Based on GPS trajectory and Smart Card data of 2056 buses from 278 routes covering 1.5 million ridership in Qingdao, China, spatio-temporal emissions characteristics of buses are studied. 7589 taxis with 0.2 million passengers' trips are used for acquiring private cars' emissions to evaluate the emissions difference between buses and cars. Empirical results show that the average difference between buses and cars with 2 persons can reach up to 117 g/km-person during 7:00-8:59 and 115 g/km-person during 17:00-18:59. However, buses have various emission benefits around the city at different periods. A double increase in emissions during non-rush hours can be observed compared with rush hours. 224 online survey data are used to study the potential ridership reduction trend in post-COVID-19. Results show that 56.3% of respondents would decrease the usage of buses in the post-COVID-19 future. Based on this figure, our analysis shows that per kilometer-person emissions of buses are higher than cars during non-rush hours, however, still lower than cars during rush hours. We conclude that when ridership reduces by more than 40%, buses cannot be "greener" travel modal than cars as before. Finally, several feasible policies are suggested for this potential challenge. Our study provides convincing evidence for understanding the emission patterns of buses, to support better buses investment decisions and promotion on eco-friendly public transport service in the post-COVID-19 future.

Inhibition of α1-adrenoceptor reduces TGF-ß1-induced epithelial-to-mesenchymal transition and attenuates UUO-induced renal fibrosis in mice.

Renal fibrosis is a common pathological hallmark of chronic kidney disease (CKD). Renal sympathetic nerve activity is elevated in patients and experimental animals with CKD and contributes to renal interstitial fibrosis in obstructive nephropathy. However, the mechanisms underlying sympathetic overactivation in renal fibrosis remain unknown. Norepinephrine (NE), the main sympathetic neurotransmitter, was found to promote TGF-ß1-induced epithelial-mesenchymal transition (EMT) and fibrotic gene expression in the human renal proximal epithelial cell line HK-2. Using both genetic and pharmacological approaches, we identified that NE binds Gαq-coupled α1-adrenoceptor (α1-AR) to enhance EMT of HK-2 cells by activating p38/Smad3 signaling. Inhibition of p38 diminished the NE-exaggerated EMT process and increased the fibrotic gene expression in TGF-ß1-treated HK-2 cells. Moreover, the pharmacological blockade of α1-AR reduced the kidney injury and renal fibrosis in a unilateral ureteral obstruction mouse model by suppressing EMT in the kidneys. Thus, sympathetic overactivation facilitates EMT of renal epithelial cells and fibrosis via the α1-AR/p38/Smad3 signaling pathway, and α1-AR inhibition may be a promising approach toward treating renal fibrosis.

Static Magnetic Field Accelerates Diabetic Wound Healing by Facilitating Resolution of Inflammation.

Impaired wound healing is commonly encountered in patients with diabetes mellitus, which may lead to severe outcomes such as amputation, if untreated timely. Macrophage plays a critical role in the healing process including the resolution phase. Although magnetic therapy is known to improve microcirculation, its effect on wound healing remains uncertain. In the present study, we found that 0.6 T static magnetic field (SMF) significantly accelerated wound closure and elevated reepithelialization and revascularization in diabetic mice. Notably, SMF promoted the wound healing by skewing the macrophage polarization towards M2 phenotype, thus facilitating the resolution of inflammation. In addition, SMF upregulated anti-inflammatory gene expression via activating STAT6 and suppressing STAT1 in macrophage. Taken together, our results indicate that SMF may be a promising adjuvant therapeutic tool for treating diabetic wounds.