This paper presents a novel approach to retrieve indoor structures from raster images of complicated floor plans. We extract the building elements in the floor plan and process them into a vectorized form to provide indoor layout information. Unlike conventional approaches, the proposed model is robust when recognizing rooms and openings surrounded by obscuring patterns, including superimposed graphics and irregular notation. To this end, we integrate various floor plan formats into a unified style using conditional generative adversarial networks prior to vectorization. This style-transferred plan that follows the unified style represents the room structure intuitively and is readily vectorized due to its concise expression. Raster-to-vector conversion is conducted with a combinatorial optimization in junction units of the layout. The experimental results demonstrate that when implemented with complex drawings, our model is comparable to existing methods in the detection and recognition of rooms and provides a much better score in one-to-one matches.

Automatic floor plan analysis has gained increased attention in recent research. However, numerous studies related to this area are mainly experiments conducted with a simplified floor plan dataset with low resolution and a small housing scale due to the suitability for a data-driven model. For practical use, it is necessary to focus more on large-scale complex buildings to utilize indoor structures, such as reconstructing multi-use buildings for indoor navigation. This study aimed to build a framework using CNN (Convolution Neural Networks) for analyzing a floor plan with various scales of complex buildings. By dividing a floor plan into a set of normalized patches, the framework enables the proposed CNN model to process varied scale or high-resolution inputs, which is a barrier for existing methods. The model detected building objects per patch and assembled them into one result by multiplying the corresponding translation matrix. Finally, the detected building objects were vectorized, considering their compatibility in 3D modeling. As a result, our framework exhibited similar performance in detection rate (87.77%) and recognition accuracy (85.53%) to that of existing studies, despite the complexity of the data used. Through our study, the practical aspects of automatic floor plan analysis can be expanded.

The osteologic and myologic characteristics of the family Pentacerotidae are described in detail. The family Pentaceroti-dae is a monophyletic group supported by 11 synapomorphies found in all family members. Of their synapomorphies, two(the second infraorbital and endopterygoid articulate with lateral ethmoid conditions) are considerably rare in percoidsand strongly support the monophyly of the family. A comparison of 44 transformation series among all species revealedfour equally parsimonious trees, and a strict consensus tree was adopted. On the basis of the inferred phylogenetic rela-tionships of the Pentacerotidae, this family was cladistically classified into two subfamilies and seven genera: Histiopter-inae (Histiopterus, Evistias, Zanclistius, Pentaceropsis, Paristiopterus, and Parazanclistius) and Pentacerotinae(Pentaceros). The center of origin of pentacerotids was inferred to be the Southern Australian region. I propose that the two families, Ostracoberycidae and Chaetodontidae, are closely related with Pentacerotidae.

Roll-to-roll (R2R) gravure printing is mainly used in the manufacture of conductive lines or electronic devices because complex patterns can be printed quickly and accurately on flexible substrates using an engraved pattern roll. Gravure printing has several advantages including multi-layer printing of large-area functional layers and continuous production of electronic devices such as thin-film transistors (TFTs) or complex electronic circuits. Existing studies have demonstrated that printing quality can be improved by determining the desired conditions of coating and printing machine without changing the ink and web properties. However, few studies have focused on controlling the geometry of printed patterns and coated layers according to the web tension and web speed, considering spreading effect and ink transfer. In this study, the effects of the controllable parameters in R2R gravure printing, namely web tension and web speed, on the geometry of the gate electrode, dielectric layer, and source–drain electrode of a TFT are examined. We obtained metamodels to estimate the thicknesses and widths of the conductive and dielectric patterns of a printed TFT according to the web tension and speed of a pilot-scale R2R gravure printing machine using design of experiment. The developed metamodels exhibited superior performance, with an average estimation error of 4.18 ± 3.05%. We further analyzed variations in the thickness of the gate electrode and dielectric layer according to fluctuations in the tension in the R2R printing process. Our results show that fluctuations in the tension should be maintained constant to achieve a uniform geometry of the printed pattern. This study demonstrates that the geometry of the printed pattern can be controlled using web tension and web speed, without changing the ink properties.