, "Residential roof condition assessment system using deep learning," J. Appl. Remote Sens. 12(1), 016040 (2018), doi: 10.1117/1.JRS.12.016040. Abstract. The emergence of high resolution (HR) and ultra high resolution (UHR) airborne remote sensing imagery is enabling humans to move beyond traditional land cover analysis applications to the detailed characterization of surface objects. A residential roof condition assessment method using techniques from deep learning is presented. The proposed method operates on individual roofs and divides the task into two stages: (1) roof segmentation, followed by (2) condition classification of the segmented roof regions. As the first step in this process, a self-tuning method is proposed to segment the images into small homogeneous areas. The segmentation is initialized with simple linear iterative clustering followed by deep learned feature extraction and region merging, with the optimal result selected by an unsupervised index, Q.After the segmentation, a pretrained residual network is fine-tuned on the augmented roof segments using a proposed k-pixel extension technique for classification. The effectiveness of the proposed algorithm was demonstrated on both HR and UHR imagery collected by EagleView over different study sites. The proposed algorithm has yielded promising results and has outperformed traditional machine learning methods using hand-crafted features. © The Authors.Published by SPIE under a Creative Commons Attribution 3.0 Unported License. Distribution or reproduction of this work in whole or in part requires full attribution of the original publication, including its DOI.
In future dc distributed power systems, high performance high voltage dc-dc converters with redundancy ability are welcome. However, most existing high voltage dc-dc converters do not have redundancy ability. To solve this problem, a wide load range zero-voltage switching (ZVS) three-level (TL) dc-dc converter is proposed, which has some definitely good features. The primary switches have reduced voltage stress, which is only Vin/2. Moreover, no extra clamping component is needed, which results simple primary structure. Redundancy ability can be obtained by both primary and secondary sides, which means high system reliability. With proper designing of magnetizing inductance, all primary switches can obtain ZVS down to 0 output current, and in addition, the added conduction loss can be neglected. TL voltage waveform before the output inductor is obtained, which leads small volume of the output filter. Four secondary MOSFETs can be switched in zero-current switching (ZCS) condition over wide load range. Finally, both the primary and secondary power stages are modular architecture, which permits realizing any given system specifications by low voltage, standardized power modules. The operation principle, soft switching characteristics are presented in this paper, and the experimental results from a 1 kW prototype are also provided to validate the proposed converter.
Typically, sweet corn, particularly sh2 sweet corn, has low seed vigor owing to its high sugar and low starch content, which is a major problem in sweet corn production, particularly at low temperatures. There is considerable variation in the germination rates among sweet corn varieties under low-temperature conditions, and the underlying mechanisms behind this phenomenon remain unclear. In this study, we screened two inbred sweet corn lines (tolerant line L282 and sensitive line L693) differing in their low-temperature germination rates; while no difference was observed in their germination rates at normal temperatures. To identify the specifically induced genes influencing the germination capacity of sweet corn at low temperatures, a transcriptome analysis of the two lines was conducted at both normal and low temperatures. Compared to the lines at a normal temperature, 3926 and 1404 differently expressed genes (DEGs) were identified from L282 and L693, respectively, under low-temperature conditions. Of them, 830 DEGs were common DEGs (cDEGs) that were identified from both L282 and L693, which were majorly enriched in terms of microtubule-based processes, histone H3-K9 modification, single-organism cellular processes, and carbohydrate metabolic processes. In addition, 3096 special DEGs (sDEGs), with 2199 upregulated and 897 downregulated, were detected in the tolerant line L282, but not in the sensitive line L693. These sDEGs were primarily related to plasma membranes and oxygen-containing compounds. Furthermore, electric conductivity measurements demonstrated that the membrane of L282 experienced less damage, which is consistent with its strong tolerance at low temperatures. These results expand our understanding of the complex mechanisms involved in the cold germination of sweet corn and provide a set of candidate genes for further genetic analysis.
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.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.