Catalogue Search | MBRL
Are you sure you want to remove the book from the shelf?
{{itemTitle}}
6,433
result(s) for
"Zhang, Mi"
Sort by:
PGA-SiamNet: Pyramid Feature-Based Attention-Guided Siamese Network for Remote Sensing Orthoimagery Building Change Detection
In recent years, building change detection has made remarkable progress through using deep learning. The core problems of this technique are the need for additional data (e.g., Lidar or semantic labels) and the difficulty in extracting sufficient features. In this paper, we propose an end-to-end network, called the pyramid feature-based attention-guided Siamese network (PGA-SiamNet), to solve these problems. The network is trained to capture possible changes using a convolutional neural network in a pyramid. It emphasizes the importance of correlation among the input feature pairs by introducing a global co-attention mechanism. Furthermore, we effectively improved the long-range dependencies of the features by utilizing various attention mechanisms and then aggregating the features of the low-level and co-attention level; this helps to obtain richer object information. Finally, we evaluated our method with a publicly available dataset (WHU) building dataset and a new dataset (EV-CD) building dataset. The experiments demonstrate that the proposed method is effective for building change detection and outperforms the existing state-of-the-art methods on high-resolution remote sensing orthoimages in various metrics.
Journal Article
Automotive power transmission systems
'Automotive Power Transmission Systems' provides technical details and developments for all automotive power transmission systems. The transmission system of an automotive vehicle is the key to the dynamic performance, drivability and comfort, and fuel economy.
Book
The efficacy and safety of omega-3 fatty acids on depressive symptoms in perinatal women: a meta-analysis of randomized placebo-controlled trials
Omega-3 fatty acids (FA), as a nutrient, has been proven effective in major depressive disorder (MDD), however, the results of monotherapy in perinatal depression (PND) remain unclear. To examine the efficacy and safety of omega-3 fatty acids (FA) monotherapy for perinatal depression (PND) compared with placebo. PubMed, Embase, PsycINFO, MEDLINE, Cochrane Library, and CINAHL were searched from inception up to November 2019. The reference lists of relevant review articles and included studies were also reviewed. Randomized placebo-controlled trials examining the efficacy and safety of omega-3 FA monotherapy in perinatal women with depressive symptoms were included. Pooled standard mean differences (SMD) were calculated and random-effects models were adopted for all analyses. Subgroups analyses and meta-regression were performed to quantify characteristics of the subjects and trials influencing the omega-3 response. In addition, meta-regression was conducted to identify the source of heterogeneity. The study protocol was registered at PROSPERO, CRD42020159542. Eight eligible randomized placebo-controlled trials were included involving 638 participants. There was a significant effect of omega-3 FA on perinatal depression. Omega-3 with higher ratio of EPA/DHA (≥1.5) had significant efficacy both in mild-to-moderate pregnant and postpartum depression with low incidence of side effects. Among the included trials reporting adverse effects, there was no significant difference in incidence of gastrointestinal and neurologic events between the omega-3 and placebo groups. There was no evidence of publication bias. Our findings suggested that omega-3 FA significantly improved depressive symptoms in perinatal women regardless of pregnant or postpartum and well-tolerated. Furthermore, the omega-3 response was linked to higher EPA proportion in omega-3 formula and mild- to-moderate depression.
Journal Article
Urban heat islands in China enhanced by haze pollution
The urban heat island (UHI), the phenomenon of higher temperatures in urban land than the surrounding rural land, is commonly attributed to changes in biophysical properties of the land surface associated with urbanization. Here we provide evidence for a long-held hypothesis that the biogeochemical effect of urban aerosol or haze pollution is also a contributor to the UHI. Our results are based on satellite observations and urban climate model calculations. We find that a significant factor controlling the nighttime surface UHI across China is the urban–rural difference in the haze pollution level. The average haze contribution to the nighttime surface UHI is 0.7±0.3 K (mean±1 s.e.) for semi-arid cities, which is stronger than that in the humid climate due to a stronger longwave radiative forcing of coarser aerosols. Mitigation of haze pollution therefore provides a co-benefit of reducing heat stress on urban residents.
The impact of locally-sourced aerosols on the Urban Heat Island (UHI) effect has been difficult to quantify due to opposing long and shortwave radiation effects. Here, using satellite observations and climate model simulations, the authors reveal that urban haze pollution intensifies the nighttime UHI in China.
Journal Article
Multi-Label Remote Sensing Image Scene Classification by Combining a Convolutional Neural Network and a Graph Neural Network
As one of the fundamental tasks in remote sensing (RS) image understanding, multi-label remote sensing image scene classification (MLRSSC) is attracting increasing research interest. Human beings can easily perform MLRSSC by examining the visual elements contained in the scene and the spatio-topological relationships of these visual elements. However, most of existing methods are limited by only perceiving visual elements but disregarding the spatio-topological relationships of visual elements. With this consideration, this paper proposes a novel deep learning-based MLRSSC framework by combining convolutional neural network (CNN) and graph neural network (GNN), which is termed the MLRSSC-CNN-GNN. Specifically, the CNN is employed to learn the perception ability of visual elements in the scene and generate the high-level appearance features. Based on the trained CNN, one scene graph for each scene is further constructed, where nodes of the graph are represented by superpixel regions of the scene. To fully mine the spatio-topological relationships of the scene graph, the multi-layer-integration graph attention network (GAT) model is proposed to address MLRSSC, where the GAT is one of the latest developments in GNN. Extensive experiments on two public MLRSSC datasets show that the proposed MLRSSC-CNN-GNN can obtain superior performance compared with the state-of-the-art methods.
Journal Article
Global lake evaporation accelerated by changes in surface energy allocation in a warmer climate
Lake evaporation is a sensitive indicator of the hydrological response to climate change. Variability in annual lake evaporation has been assumed to be controlled primarily by the incoming surface solar radiation. Here we report simulations with a numerical model of lake surface fluxes, with input data based on a high-emissions climate change scenario (Representative Concentration Pathway 8.5). In our simulations, the global annual lake evaporation increases by 16% by the end of the century, despite little change in incoming solar radiation at the surface. We attribute about half of this projected increase to two effects: periods of ice cover are shorter in a warmer climate and the ratio of sensible to latent heat flux decreases, thus channelling more energy into evaporation. At low latitudes, annual lake evaporation is further enhanced because the lake surface warms more slowly than the air, leading to more long-wave radiation energy available for evaporation. We suggest that an analogous change in the ratio of sensible to latent heat fluxes in the open ocean can help to explain some of the spread among climate models in terms of their sensitivity of precipitation to warming. We conclude that an accurate prediction of the energy balance at the Earth’s surface is crucial for evaluating the hydrological response to climate change.
Journal Article
Individual differences in trait creativity moderate the state-level mood-creativity relationship
The relationship between mood states and state creativity has long been investigated. Exploring individual differences may provide additional important information to further our understanding of the complex mood-creativity relationship. The present study explored the state-level mood-creativity relationship from the perspective of trait creativity. We employed the experience sampling method (ESM) in a cohort of 56 college students over five consecutive days. The participants reported their state creativity on originality and usefulness dimensions at six random points between 9:00 a.m. and 11:00 p.m., along with a 10-item concurrent mood state report. Their trait creativity was measured by the Guildford Alternative Uses Test (AUT) and the Remote Associates Test (RAT). We found moderating effects of the participants' trait creativity on their state-level mood-creativity relationship. Specifically, whereas the positive correlation between positive mood state and originality of state creativity was stronger for the participants with higher AUT flexibility scores, stronger positive correlations between negative mood state and originality of state creativity were observed for individuals with higher AUT originality scores. Our findings provide evidence in support of introducing individual differences to achieve a more comprehensive understanding of the mood-creativity link. The results could be of practical value, in developing individualized mood state regulation strategies for promoting state creativity.
Journal Article
Parthenolide Suppresses T Helper 17 and Alleviates Experimental Autoimmune Encephalomyelitis
T helper (Th) cells play crucial roles in inflammation and adaptive immune system. Importantly, Th17 cells, a major pathogenic Th cell subset, are involved in the pathogenesis of multiple sclerosis (MS) and its classical animal modal experimental autoimmune encephalomyelitis (EAE). Previous studies have shown that parthenolide (PTL), a sesquiterpene lactone, possesses potent anti-cancer and anti-inflammatory activities. However, the immunosuppressive effect of PTL on the pathogenic Th17 cell and MS is unclear. In this study, we showed that PTL treatment could alleviate clinical symptoms by inhibiting inflammatory cell infiltration, reducing inflammation and demyelination of CNS. In addition, the mRNA expression of cytokines and inflammatory factors in CD4 + T cells, especially Th1 and Th17 cells, reduced in both CNS and peripheral immune tissue of EAE mice. Furthermore, PTL could inhibit the reactivation of MOG-specific T cells and the differentiation of naïve CD4 + T cells into Th17 cells in vitro . We also found that PTL inhibited nuclear factor kappa B (NF-κB) signaling and retinoid-related orphan receptor-γt (RORγt) in mouse Th17 cell and human Jurkat cell line. Taken together, our data demonstrated a critical immune-suppressive effect of PTL on autoimmune inflammation through regulating Th17 cells and the NF-κB/RORγt pathway.
Journal Article
Efficient electron transmission in covalent organic framework nanosheets for highly active electrocatalytic carbon dioxide reduction
Efficient conversion of carbon dioxide (CO
2
) into value-added products is essential for clean energy research. Design of stable, selective, and powerful electrocatalysts for CO
2
reduction reaction (CO
2
RR) is highly desirable yet largely unmet. In this work, a series of metalloporphyrin-tetrathiafulvalene based covalent organic frameworks (M-TTCOFs) are designed. Tetrathiafulvalene, serving as electron donator or carrier, can construct an oriented electron transmission pathway with metalloporphyrin. Thus-obtained M-TTCOFs can serve as electrocatalysts with high FE
CO
(91.3%, −0.7 V) and possess high cycling stability (>40 h). In addition, after exfoliation, the FE
CO
value of Co-TTCOF nanosheets (~5 nm) is higher than 90% in a wide potential range from −0.6 to −0.9 V and the maximum FE
CO
can reach up to almost 100% (99.7%, −0.8 V). The electrocatalytic CO
2
RR mechanisms are discussed and revealed by density functional theory calculations. This work paves a new way in exploring porous crystalline materials in electrocatalytic CO
2
RR.
The study of covalent organic frameworks (COFs) in electrocatalytic CO
2
reduction reaction (CO
2
RR) has drawn much attention. Here the authors show a series of tetrathiafulvalene based COFs designed and exfoliated into nanosheets which exhibit high electrocatalytic CO
2
RR performance.
Journal Article