Synthetic aperture radar (SAR) imagery has been used as a promising data source for monitoring maritime activities, and its application for oil and ship detection has been the focus of many previous research studies. Many object detection methods ranging from traditional to deep learning approaches have been proposed. However, majority of them are computationally intensive and have accuracy problems. The huge volume of the remote sensing data also brings a challenge for real time object detection. To mitigate this problem a high performance computing (HPC) method has been proposed to accelerate SAR imagery analysis, utilizing the GPU based computing methods. In this paper, we propose an enhanced GPU based deep learning method to detect ship from the SAR images. The You Only Look Once version 2 (YOLOv2) deep learning framework is proposed to model the architecture and training the model. YOLOv2 is a state-of-the-art real-time object detection system, which outperforms Faster Region-Based Convolutional Network (Faster R-CNN) and Single Shot Multibox Detector (SSD) methods. Additionally, in order to reduce computational time with relatively competitive detection accuracy, we develop a new architecture with less number of layers called YOLOv2-reduced. In the experiment, we use two types of datasets: A SAR ship detection dataset (SSDD) dataset and a Diversified SAR Ship Detection Dataset (DSSDD). These two datasets were used for training and testing purposes. YOLOv2 test results showed an increase in accuracy of ship detection as well as a noticeable reduction in computational time compared to Faster R-CNN. From the experimental results, the proposed YOLOv2 architecture achieves an accuracy of 90.05% and 89.13% on the SSDD and DSSDD datasets respectively. The proposed YOLOv2-reduced architecture has a similarly competent detection performance as YOLOv2, but with less computational time on a NVIDIA TITAN X GPU. The experimental results shows that the deep learning can make a big leap forward in improving the performance of SAR image ship detection.
This work demonstrates the effects of nanoimprinting on poly(3-hexylthiophene) and 1-(3-methoxycarbonyl)-propyl-1-phenyl-(6,6)C61 (P3HT:PCBM)-blended organic solar cells at room temperature. Textured Si wafer was used as a stamp. Nanoimprinting significantly increased the open-circuit voltage, the short-circuit current, and the fill factor, increasing the power conversion efficiency by ∼50%. The fill factor contributed most to the cell efficiency. Upon nanoimprinting, not only the surface structure but also the applied pressure contributed to the performance of the device. The origin of the hydrostatic pressure-induced efficiency improvement was also investigated. The proposed approach has potential to be applied in the future to improve the efficiency of various organic solar cells.
Gender and a history of headaches, a history of sexual abuse, drinking, running away from school, or suicidal attempts were factors associated with DSH among Taiwanese adolescents. School personnel should be aware of these to formulate appropriate and timely interventions.
The aim of this study was to investigate the influence of serotonin on anxiety and autonomic nervous system (ANS) function; the correlation between subjective anxiety rating and changes of ANS function following tryptophan depletion (TD) in healthy volunteers was examined. Twenty-eight healthy participants, consisting of 15 females and 13 males, with an average age of 33.3 years, were recruited.Baseline Chinese Symptom Checklist-90-Revised and ANS function measurements were taken. TD was carried out on the testing day, and participants provided blood samples right before and 5 hours after TD. ANS function, somatic symptoms, and Visual Analogue Scales (VASs) were determined after TD. Wilcoxon signed rank test and Spearman ρ correlation were adapted for analyses of the results.The TD procedure reduced total and free plasma tryptophan effectively. After TD, the sympathetic nervous activity increased and parasympathetic nervous activity decreased. Baseline anxiety ratings positively correlated with post-TD changes in sympathetic nervous activity, VAS ratings, and physical symptoms. However, a negative correlation with post-TD changes in parasympathetic nervous activity was found.The change in ANS function after TD was associated with the severity of anxiety in healthy volunteers. This supports the fact that the effect of anxiety on heart rate variability is related to serotonin vulnerability. Furthermore, it also shows that the subjective anxiety rating has a biological basis related to serotonin.
We demonstrate the first high‐permittivity ceramic oxide for use as the gate oxide of the GaN‐based metal‐oxide‐semiconductor (MOS) capacitor. An ilmenite magnesium titanate (MgTiO3) thin film prepared by sputtering was studied. When oxygen was introduced during sputtering, the preferred orientation changed from spinel Mg2TiO4 (111) to ilmenite MgTiO3 (003). The X‐ray diffractometry θ−2θ and φ‐scans were performed to identify the preferred films. Possible epitaxial relationships at the Mg2TiO4 (111)/GaN (001) and MgTiO3 (003)/GaN (001) interfaces were proposed. Finally, the electrical properties of the Al/MgTiO3 (003)/GaN (001)/Al MOS capacitor were presented.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.