Automatic assessments of building plans are uncommon in the early design stages, especially when schematic sketches are in raster format. Existing design evaluation tools, such as fire code reviewers, primarily evalua...
详细信息
ISBN:
(纸本)9781713873280
Automatic assessments of building plans are uncommon in the early design stages, especially when schematic sketches are in raster format. Existing design evaluation tools, such as fire code reviewers, primarily evaluate vector format images that contain complete building information in the late design stage. These tools use conditional shape-embedding techniques to analyze the vector images. However, there are limitations to identifying and evaluating drawings through vector-shape relationships. Our research aimed to develop tools that can automatically assess schematic sketches in raster format to overcome the limitations of existing tools. We integrated a conditional shape-embedding tool, named Shape Machine, to assess vector images, with machine learning techniques to assess raster sketches. This integration enables the evaluation of fire evacuation sketches in the early stages of the designprocess, thereby improving design efficiency and reducing costs. Moreover, in the future, this integration could allow the evaluation of designs in multiple image formats.
Traditional foundation structure for unmanned vehicle typically adopts conventional plate-stiffener structures, and the low-frequency vibration reduction effect is not ideal, and the space for further optimization is ...
详细信息
design tools and probing, in particular, have long offered critical perspectives in HCI, broadening the understanding of who benefits from the design. Further, the designerly implementation of critical perspectives an...
详细信息
This paper represents an action research-based inductive teaching approach to structural design to architecture students through a given task of freestyle footbridge design. The objective is to educate undergraduate a...
详细信息
'What are we learning this for?' is a common refrain heard in education. Showing how engineering practices are relevant to everyday needs like building science models in K-12 classes may lead to greater motiva...
详细信息
ISBN:
(纸本)9798350336429
'What are we learning this for?' is a common refrain heard in education. Showing how engineering practices are relevant to everyday needs like building science models in K-12 classes may lead to greater motivation for students in STEM learning. This paper investigates how horizontal integration of different streams of learning may enable students to see why and how each element of knowledge is relevant to the whole. By combining microcontroller-based electronics, programming, and 3D design and fabrication to build science models, students may develop a stronger appreciation of how the component technologies interrelate (internal contextualization) and how these integrated computational models contribute to the enterprise of science (external contextualization). Furthermore, students in science classrooms see how computation can make physical models dynamic to represent changes and relationships more effectively. The implicit representational science models and the incorporation of technology and computation into a regular science curriculum make the knowledge transferable beyond an individual lesson. Students learn the component technologies cumulatively through a sustained process of engagement across multiple science modeling projects. The major challenges of this approach are how the science modeling projects may be designed and what factors have to be considered in the designs to realize this learning progression. To answer these questions, this paper describes a rigorous designprocess for the Physical Computational Models (PCMs) that incorporates science model correctness, progression of learning across all streams, pedagogical efficacy, classroom dynamics and manufacturability. In addition, we implemented a year-long project using our Horizontal Learning (HL) approach at two local public schools. This paper reports in detail two PCMs we developed for authentic 5th and 6th grade classrooms to illustrate the integration of the learning streams in science, compu
Somatosensory interaction is another new starting point for the transformation of human-computer interaction mode after mouse and multi-touch. through the analysis of the sensory characteristics of the human body, the...
详细信息
This research is dedicated to the design and application of a data-driven employee training and development path recommendation system that aims to improve the efficiency and personalization of employee training. By c...
详细信息
This paper proposes a novel Class Conditional Generative Adversarial Network (CCGAN) tailored for the inverse design of high-resolution nanophotonic device images, with a focus on achieving optimal transmittance at sp...
详细信息
ISBN:
(纸本)9798350385304;9798350385298
This paper proposes a novel Class Conditional Generative Adversarial Network (CCGAN) tailored for the inverse design of high-resolution nanophotonic device images, with a focus on achieving optimal transmittance at specific wavelengths. The motivation of this research is rooted in the limitations of conventional computational methodologies in nanophotonics, which rely heavily on expert intuition and computational simulators to validate designs. These approaches not only demand extensive computational resources but also bear the risk of escalated costs due to potential design failures. Addressing these challenges, our study leverages the inverse design paradigm, utilizing generative models, to directly derive device structures from desired features. Our proposed CCGAN model introduces significant enhancements to the StyleGAN2-ADA architecture, integrating a classifier that utilizes contrastive loss alongside classification loss to refine the design generation process. This integration facilitates the learning of complex data distributions and the generation of detailed patterns, overcoming the limitations of previous models. The experimental framework employs datasets generated with MaxwellFDFD, a solver for finite-difference frequency-domain (FDFD) Maxwell's equations, categorized by maximum transmittance at specific wavelengths. Quantitative evaluation through the Frechet Inception Distance (FID) metric demonstrates our model's superior performance, achieving significant reductions in FID values compared to the baseline StyleGAN2-ADA model and other prior models. Moreover, our model also demonstrates superior accuracy in comparison to other models. This research not only advances the field of nanophotonics by providing a robust computational framework for the inverse design of nanodevices but also opens avenues for future exploration into advanced techniques such as diffusion models for further enhancing design accuracy and quality.
The paper presents a practical process model that integrates design thinking and strategic foresight. The model is proposed by comparing different design thinking and strategic foresight processes, with the methods re...
详细信息
Existing methods in electronic product debugging processes often suffer from low standardization and design efficiency. To address these shortcomings, our proposed method combines ontology technology and semantic reas...
详细信息
暂无评论