Search

With the development of remote sensing technology, content-based remote sensing image retrieval has become a research hotspot. Remote sensing image datasets not only contain rich location, semantic and scale information but also have large intra-class differences. Therefore, the key to improving the performance of remote sensing image retrieval is to make full use of the limited sample information to extract more comprehensive class features. In this paper, we propose a proxy-based deep metric learning method and an adaptive multi-proxy framework. First, we propose an intra-cluster sample synthesis strategy with a random factor, which uses the limited samples in batch to synthesize more samples to enhance the network's learning of unobvious features in the class. Second, we propose an adaptive proxy assignment method to assign multiple proxies according to the cluster of samples within a class, and to determine weights for each proxy according to the cluster scale to accurately and comprehensively measure the sample-class similarity. Finally, we incorporate a rigorous evaluation metric mAP@R and a variety of dataset partitioning methods, and conduct extensive experiments on commonly used remote sensing image datasets. [ABSTRACT FROM AUTHOR]

Purpose: To understand the relationship between body mass index (BMI), age, prostate volume (PV), prostate-specific antigen (PSA), International Prostate Symptom Score (IPSS) and quality of life (QoL) in Zhengzhou.Materials and Methods: In the cross-sectional study, men living in Zhengzhou were invited to participate in this study. Men who were 40 years or older were subjected to the IPSS and related examination. A total of 1360 participants were included. Body mass index < 18.5 kg/m2 was determined as underweight, 18.5-24.99 kg/m2 normal, 25-29.99 kg/m2 overweight, and ≥30 kg/m2 obese.Results: The mean BMI was 24.92 ± 3.37 kg/m2. The mean PSA was 1.06 ± 0.85 ng/mL. The mean PV was 20.10 ± 9.96 mL. The mean age was 62.72 ± 11.03 years. The mean IPSS was 5.87 ± 3.48 scores. The mean QoL was 2.33 ± 1.28 scores. PSA showed a significant tendency to decrease with increasing BMI (r = -0.061, p = 0.018, ptrend = 0.037). The same with age (r = -0.109, p < .001; ptrend = .045). But the result suggested that both IPSS and QoL were positively correlated with BMI (r = 0.120, p < .001, ptrend < .001; r = 0.083, p = .001, ptrend = .021, respectively). PV increased with increasing BMI (r = 0.110, p < .001, ptrend = 0.045 ).Conclusions: Age, PSA decreased with increasing BMI. But larger PV, IPSS, and QoL were associated with higher BMI. [ABSTRACT FROM AUTHOR]

The fabric clip is an important component in textile machine. The creep deformation on the clip body hole at high temperature acted on different pulling forces during a period of 6 240 h was researched by using ABAQUS software. The Norton-Bailey's with time hardening constitutive equation was used to simulate the creep deformation on the clip body hole made of A380 aluminum alloy at high temperature, and the simulation results showed that for different pulling forces, the creep deformation on the clip body hole increased with an increase in the pulling force. Then, the experimental dimensional changes test was performed on three different specimens of the clip body hole at different service time(l 200 h, 4 800 h, 6 240 h) by using a Global Performance test machine. A comparison between the finite element method (FEM) and the experimental results show a good correlation. The simulation results also indicate that the creep deformation on the clip body hole has an important effect on the relaxation of the blade clamping fastness which leads to fabric clip failure. [ABSTRACT FROM AUTHOR]