Representation Of Layout Research Articles

Predicting wind farm wake losses with deep convolutional hierarchical encoder–decoder neural networks

Wind turbine wakes are the most significant factor affecting wind farm performance, decreasing energy production and increasing fatigue loads in downstream turbines. Wind farm turbine layouts are designed to minimize wake interactions using a suite of predictive models, including analytical wake models and computational fluid dynamics simulations (CFD). CFD simulations of wind farms are time-consuming and computationally expensive, which hinder their use in optimization studies that require hundreds of simulations to converge to an optimal turbine layout. In this work, we propose DeepWFLO, a deep convolutional hierarchical encoder–decoder neural network architecture, as an image-to-image surrogate model for predicting the wind velocity field for Wind Farm Layout Optimization (WFLO). We generate a dataset composed of image representations of the turbine layout and undisturbed flow field in the wind farm, as well as images of the corresponding wind velocity field, including wake effects generated with both analytical models and CFD simulations. The proposed DeepWFLO architecture is then trained and optimized through supervised learning with an application-tailored loss function that considers prediction errors in both wind velocity and energy production. Results on a commonly used test case show median velocity errors of 1.0%–8.0% for DeepWFLO networks trained with analytical and CFD data, respectively. We also propose a model-fusion strategy that uses analytical wake models to generate an additional input channel for the network, resulting in median velocity errors below 1.8%. Spearman rank correlations between predictions and data, which evidence the suitability of DeepWFLO for optimization purposes, range between 92.3% and 99.9%.

A study on the cross-application of fractal geometry and garden design aesthetics

Abstract Currently there is a lack of research on garden design combined with fractal geometry, and most of the research results remain in qualitative analysis and subjective analysis. In this paper, we quantitatively analyze garden design based on fractal geometry to promote the development and innovation of aesthetics in garden design. Based on the reading of literature and other materials, the theory of fractal geometry and its application in the field of garden design are summarized. Based on Gabriel Lame’s design, we constructed the basic unit shape and layout representation using AutoCAD software to realize mathematical modeling design. A good fit of plant fractal dimension was indicated by the coefficient of determination of plant fractal dimension in the study subject garden being 0.9583. Based on the known logN(r) and log(1/r) of 0.1563 and 0.1013, respectively, the value of the fractal dimension of the garden site was derived as 1.54294 by applying the corresponding formula.The regression equation for the contribution of the fractal dimension of each element of the landscape of the mountains and rocks = 0.118-0.0407*Wigwam + 0.277*Wigwam and building combination+0.438*Wigwam and plant combination-0.019*Building+0.306*Building and plant combination-0.022*Plant, and the model R2 is 0.863. This study not only provides reference for future design and quantitative analysis of the antique gardens, but also provides new ideas for the construction of a better human environment and landscaping works.

Does a row of objects comprise a boundary? How children miss the forest for the trees in spatial navigation.

Unlike children's early ability to navigate by continuous boundaries, their ability to extract geometric information from an array of objects emerges gradually over childhood. To investigate children's developing representation of object arrays for navigation and its relation to their mental representation of the global spatial layout, reorientation behavior was tested in 146 children (4-9 years, 78 male children and 68 female children, Italian) with rectangular arrays made up of 20 objects. Posttest questions on children's spatial language and their mental and pictorial representation of the environment were administered. Although children of all ages navigated by the geometry of continuous boundary-like arrays, they only succeeded with separated object arrays at around 7 years of age. This developmental change was predicted by children's individual ability to extract the abstract geometry of the spatial layout in a two-dimensional picture of the room. (PsycInfo Database Record (c) 2023 APA, all rights reserved).

The impact of spatial scale on layout learning and individual evacuation behavior in indoor fires: single-scale learning perspectives

The detail and representation of a spatial layout varies with scale. This affects an individual’s learning effectiveness and understanding, in turn directly influencing their behavior in a fire evacuation. However, the impact of layout learning methods with different spatial scales on fire evacuation behavior, and the relationship between spatial cognition and evacuation effects, remains unclear. We conducted spatial layout learning across three scales with 81 participants and simulated a fire evacuation scenario in a mobile virtual reality for groups. We collected evacuation decision-making and user experience questionnaires as supplementary data. The results demonstrate that small-scale learning objects are the easiest for participants to understand in terms of spatial layout and relationships, but their performance in fire evacuation is poor. Large-scale learning objects significantly improve participants’ evacuation efficiency. Spatial layout learning plays a crucial role in fire evacuation outcomes, but traditional spatial knowledge acquisition measurement methods cannot predict fire evacuation performance. This study sheds light on how spatial cognition influences fire evacuation behavior and provides a more reliable fire evacuation simulation method based on mobile virtual reality (MVR).

The quad layout immersion: A mathematically equivalent representation of a surface quadrilateral layout

Quadrilateral layouts on surfaces are essential for defining quadrilateral meshes, for fitting splines for engineering design and analysis, and for texture mapping in computer graphics. Previous work has characterized such layouts as a special mapping with extensive integer constraints, as a special metric on a surface, or as a meromorphic quartic differential with finite trajectories. In this work, a surface quadrilateral layout is alternatively characterized as a special immersion of a cut representation of the surface into the Euclidean plane. We call this a quad layout immersion. This characterization, while posed in smooth topology, naturally generalizes to piecewise-linear representations. As such, it mathematically describes and generalizes integer grid maps, which represent the current state-of-the-art. Due to its generality, the proposed representation supports a range of different computational methods to extract quadrilateral layouts. This is demonstrated by several computational examples, including the extraction of quadrilateral layouts on a 1996 Dodge Neon.

Intelligent layout generation based on deep generative models: A comprehensive survey

Layout generation, as a crucial stage in Artificial Intelligence-Generated Content (AIGC) task information presentation generation, is a fascinating and significant research topic. Automatically generating layouts intrigued the computer vision community dating back to the 1990s, and the advancement was sluggish for a time due to the inherent complexity of the issue. Thanks to the success of deep learning, layout generation is leading to a surge in both academic literature and business applications recently. Yet a systematic and comprehensive literature review of this domain is still missing. In this study, we provide a comprehensive overview of the state-of-the-art layout generation methods. Primarily, we discuss the problem of layout generation and associated background knowledge including layout representation, layout aesthetics, and generative models. Subsequently, recent advances in the field of intelligent layout generation are organized and summarized from three perspectives: innovations, models & algorithms, and applications. Furthermore, the paper outlines the datasets and evaluation methodology, both qualitative and quantitative, and briefly analyzes the selection of them for specific tasks. To sum up, we conclude the current challenges of intelligent layout generation and suggest possible directions for future endeavors.

Layout Representation Learning with Spatial and Structural Hierarchies

We present a novel hierarchical modeling method for layout representation learning, the core of design documents (e.g., user interface, poster, template). Existing works on layout representation often ignore element hierarchies, which is an important facet of layouts, and mainly rely on the spatial bounding boxes for feature extraction. This paper proposes a Spatial-Structural Hierarchical Auto-Encoder (SSH-AE) that learns hierarchical representation by treating a hierarchically annotated layout as a tree format. On the one side, we model SSH-AE from both spatial (semantic views) and structural (organization and relationships) perspectives, which are two complementary aspects to represent a layout. On the other side, the semantic/geometric properties are associated at multiple resolutions/granularities, naturally handling complex layouts. Our learned representations are used for effective layout search from both spatial and structural similarity perspectives. We also newly involve the tree-edit distance (TED) as an evaluation metric to construct a comprehensive evaluation protocol for layout similarity assessment, which benefits a systematic and customized layout search. We further present a new dataset of POSTER layouts which we believe will be useful for future layout research. We show that our proposed SSH-AE outperforms the existing methods achieving state-of-the-art performance on two benchmark datasets. Code is available at github.com/yueb17/SSH-AE.

FanoutNet: A Neuralized PCB Fanout Automation Method Using Deep Reinforcement Learning

In modern electronic manufacturing processes, multi-layer Printed Circuit Board (PCB) routing requires connecting more than hundreds of nets with perplexing topology under complex routing constraints and highly limited resources, so that takes intense effort and time of human engineers. PCB fanout as a pre-design of PCB routing has been proved to be an ideal technique to reduce the complexity of PCB routing by pre-allocating resources and pre-routing. However, current PCB fanout design heavily relies on the experience of human engineers, and there is no existing solution for PCB fanout automation in industry, which limits the quality of PCB routing automation. To address the problem, we propose a neuralized PCB fanout method by deep reinforcement learning. To the best of our knowledge, we are the first in the literature to propose the automation method for PCB fanout. We combine with Convolution Neural Network (CNN) and attention-based network to train our fanout policy model and value model. The models learn representations of PCB layout and netlist to make decisions and evaluations in place of human engineers. We employ Proximal Policy Optimization (PPO) to update the parameters of the models. In addition, we apply our PCB fanout method to a PCB router to improve the quality of PCB routing. Extensive experimental results on real-world industrial PCB benchmarks demonstrate that our approach achieves 100% routability in all industrial cases and improves wire length by an average of 6.8%, which makes a significant improvement compared with the state-of-the-art methods.

Learning robust features for indoor scene recognition

As digital image acquisition becomes ubiquitous in recent years, the need for indoor scene recognition becomes more pronounced. Existing methods leverage the features of composing objects in a scene and overlook the adverse impacts of the common objects reoccurring in other scenes. This drawback decreases the feature discrimination between scenes (e.g., living room, dining room, and bedroom) due to reoccurring objects (e.g., tables, chairs, and toys). We propose a method of training convolutional networks by punishing or discounting the local object representations’ predictive ability and encouraging the network to learn global scene layout representations. To retain more vital information for the scene feature representation, we introduce an activation function (with unbounded above, bounded below, smooth, and non-monotonic properties) to allow more low-negative values to flow through the network, discarding high negative values. We evaluate the proposed methods on MIT Indoor 67 and Scene 15 datasets. The experiment findings show that the proposed methods capture global scene concepts and improve performance.

Optimization of spatial layouts for deep underground infrastructure in central business districts based on a multi-agent system model

In central business districts (CBDs), shallow underground spaces are being rapidly saturated owing to the increasing scale of urban underground development. Compared to shallow underground spaces, deep underground spaces are better suited for the installation of infrastructural facilities, and therefore, they are expected to become important in future urban space development. However, deep underground infrastructure (DUI) planning in CBDs is a complex and dynamic process involving numerous players because of the different service objectives and layout-related requirements of each facility. Thus, the requirements and rules of DUI layouts need to be investigated for the orderly development of underground spaces. This paper proposes a method for optimizing DUI layouts based on a multi-agent system model to maximize the benefit in DUI layouts. In this method, each DUI is represented by an agent, and deep underground space including spatial scale, ground utilization form, geological conditions and other factors was constructed, and six layout expectations of different types of DUI agents were set within the framework of the spatial relationships between DUI and ground demand, DUI and deep subsurface resource development, and different DUIs. The simulation obtained a spatial representation of the optimal DUI layout within a spatial environment that represents the deep underground space of a CBD through the exploration of DUI space and DUI–DUI interactions as well as the adaptive behaviors of the agents. The results indicate that the overall spatial utilization form of deep underground space presents a parabolic wave-like pattern with shallow central aggregation. In the vertical dimension, the facility distribution exhibits clear vertical zonation. In the horizontal dimension, the facility distribution is dominated by the ground demand, but it is greatly affected by the infrastructure of high-rise buildings and reduces the service efficiency of DUI. According to the key influencing factors affecting the DUI layout, DUI is divided into demand-driven, cost-sensitive, and supporting-service types, and targeted DUI planning and development strategies are proposed. This model can effectively describe the laws of using deep underground space to set up infrastructure and provides policy development support for the decision-making process when developing deep underground space.

Slow global representation of scene layout impacts fast local reconstruction of image elements

Slow global representation of scene layout impacts fast local reconstruction of image elements

A new representation of scene layout improves saliency detection in traffic scenes

It has been well established that scene context plays an important role in directing visual attention. A robust representation of scene layout is expected to facilitate further analysis of traffic scenes, especially under challenging visual conditions like nighttime and/or on a small-scale dataset. In this work, a new layout representation for traffic scenes is proposed and applied to the popular visual task of saliency detection. First, a general layout representation for traffic scenes is defined as a combination of an original point (Vanishing Point, VP) and two axes along roadsides. Then, a simple algorithm is proposed to build a robust layout representation for traffic scenes, along with an improved VP detection method. Finally, to verify the contribution of the proposed layout representation, a layout-guided saliency detection framework is proposed to improve existing methods by integrating layout-guided prior learned from human fixations collected with an eye-tracking recorder. Experimental results show that the proposed layout representation can significantly improve the performance of various saliency detection methods including classical bottom-up methods and deep-learning-based methods. Moreover, compared with the deep-learning methods, the layout-guided method has an obvious advantage in terms of robustness when only a small-scale dataset is available and under varying visual scenes.

Računska metodologija za sintezu konfiguracija sistema epicikličkog zupčastog prenosa sa više planetarnih zupčanika

Epicyclic Gear Transmission Systems (EGTs) find a wide variety of applications in automatic transmission systems due to their flexibility to deliver a variety of speed ratios. The design of EGT involves the enumeration of all possible layouts, typically called structural synthesis. Thus, the structural synthesis of an EGT consists of defining a topology for EGT with coupled planetary gear trains (PGTs) along with constraining elements such as connections, brakes, and clutches while delivering a definite transmission ratio between the input and output shafts. Given the number of PGTs, permanent connection, clutches, and brakes, the methodology systematically introduces these elements of PGTs to deliver the given number of distinct speed ratios. Determining the number of distinct speed ratios for a given combination of brakes and clutches has been expressed as a transformation of a graph representation of the EGT layout. A computer program has been developed for the structural synthesis of EGTs and validated against the 3 epicyclic, 6-speed EGT systems. The viability aspects of the synthesized structure are carried out. Also, an isomorphism test is addressed in the synthesis methodology to detect unique EGT structures at every synthesis stage.

Multisensory spatial perception in visually impaired infants

SummaryCongenitally blind infants are not only deprived of visual input but also of visual influences on the intact senses. The important role that vision plays in the early development of multisensory spatial perception1, 2, 3, 4, 5, 6, 7 (e.g., in crossmodal calibration8, 9, 10 and in the formation of multisensory spatial representations of the body and the world1,2) raises the possibility that impairments in spatial perception are at the heart of the wide range of difficulties that visually impaired infants show across spatial,8, 9, 10, 11, 12 motor,13, 14, 15, 16, 17 and social domains.8,18,19 But investigations of early development are needed to clarify how visually impaired infants’ spatial hearing and touch support their emerging ability to make sense of their body and the outside world. We compared sighted (S) and severely visually impaired (SVI) infants’ responses to auditory and tactile stimuli presented on their hands. No statistically reliable differences in the direction or latency of responses to auditory stimuli emerged, but significant group differences emerged in responses to tactile and audiotactile stimuli. The visually impaired infants showed attenuated audiotactile spatial integration and interference, weighted more tactile than auditory cues when the two were presented in conflict, and showed a more limited influence of representations of the external layout of the body on tactile spatial perception.20 These findings uncover a distinct phenotype of multisensory spatial perception in early postnatal visual deprivation. Importantly, evidence of audiotactile spatial integration in visually impaired infants, albeit to a lesser degree than in sighted infants, signals the potential of multisensory rehabilitation methods in early development.Video abstract

Neuronal vector coding in spatial cognition.

Several types of neurons involved in spatial navigation and memory encode the distance and direction (that is, the vector) between an agent and items in its environment. Such vectorial information provides a powerful basis for spatial cognition by representing the geometric relationships between the self and the external world. Here, we review the explicit encoding of vectorial information by neurons in and around the hippocampal formation, far from the sensory periphery. The parahippocampal, retrosplenial and parietal cortices, as well as the hippocampal formation and striatum, provide a plethora of examples of vector coding at the single neuron level. We provide a functional taxonomy of cells with vectorial receptive fields as reported in experiments and proposed in theoretical work. The responses of these neurons may provide the fundamental neural basis for the (bottom-up) representation of environmental layout and (top-down) memory-guided generation of visuospatial imagery and navigational planning.

Motor Cognition: The Role of Sentience in Perception and Action

The function of the conscious field remains mysterious from a scientific point of view. This article reviews theoretical approaches (passive frame theory and ideomotor approaches) that elucidate how the conscious field is intimately related to a special kind of action selection. This form of action selection is peculiar to the skeletal-muscle output system. The notion of encapsulation and how it explains many properties of the conscious field are discussed, including why the conscious field, though in the service of adaptive action, contains contents that are not action-relevant; why the field has a first-person perspective; and why the field is so thorough, in terms of its contents, the contrasts among contents, and the representation of spatial layout. The authors discuss subordinate encapsulation and the hypothesis that the conscious field is what allows for encapsulated conscious contents to influence action selection collectively, yielding what in everyday life is called voluntary behavior.

On the sandpile group of Eulerian series-parallel graphs

A sandpile configuration is a representation of the current layout of theoretical sand on a graph in which every vertex is assigned a nonnegative integer value. The Abelian sandpile group is a finite group composed of the recurrent sandpile configurations of a graph. We investigate the sandpile group of graphs constructed using the composition rules of series-parallel graphs, and determine the sandpile groups of parallel compositions of path-graphs.

3D voxel homogenized limit analysis of single-leaf non-periodic masonry

This paper presents an extensive investigation on the out-of-plane collapse behavior of single-leaf non-periodic masonry walls. This is achieved by deriving out-of-plane homogenized failure surfaces from test-windows that are extracted from various location within the same non-periodic masonry wall. The concept of “test-window” is inspired by that of Statistically Equivalent Periodic Unit Cell (SEPUC), which is an evolution of that of Representative Element of Volume (REV), and is needed for successfully applying homogenization to non-periodic masonry. An innovative feature introduced in this paper is the automatic generation of a suitable 3D finite element mesh directly from the sketch of the considered masonry test-window, based on a so-called “voxel strategy” that converts each voxel (the 3D equivalent of a pixel) into a finite element. Moreover, this mesh generating procedure enables the correct representation of the transversal layout of the test-window, and it also contains a coarsening strategy that allows a reduction of the overall number of finite elements in the 3D mesh. For the derivation of the out-of-plane homogenized failure surfaces a linear programming problem is solved, which is based on the upper bound theorem of limit analysis coupled with a homogenization approach. The investigation is performed on six real case studies displaying different degrees of non-periodicity: for the four test-windows of each case study, two out-of-plane homogenized failure surfaces are extracted (flexural and torsional) as well as three relevant deformed modes at collapse. Eventually, the results are critically commented; comparisons are drawn among the case studies, highlighting the influence of each non-periodic masonry bond on the results.

Representation of scene layout in human OPA is fast and invariant to surface-texture

Representation of scene layout in human OPA is fast and invariant to surface-texture

Scene Perception in the Human Brain.

Humans are remarkably adept at perceiving and understanding complex real-world scenes. Uncovering the neural basis of this ability is an important goal of vision science. Neuroimaging studies have identified three cortical regions that respond selectively to scenes: parahippocampal place area, retrosplenial complex/medial place area, and occipital place area. Here, we review what is known about the visual and functional properties of these brain areas. Scene-selective regions exhibit retinotopic properties and sensitivity to low-level visual features that are characteristic of scenes. They also mediate higher-level representations of layout, objects, and surface properties that allow individual scenes to be recognized and their spatial structure ascertained. Challenges for the future include developing computational models of information processing in scene regions, investigating how these regions support scene perception under ecologically realistic conditions, and understanding how they operate in the context of larger brain networks.