AI-assisted Design Research Articles

When generative artificial intelligence meets multimodal composition: Rethinking the composition process through an AI-assisted design project

This study explores the integration of generative artificial intelligence (GenAI) design technologies, including Adobe Firefly and DALL·E, into the teaching and learning of multimodal composition. Through focus group discussions and case studies, this paper demonstrates the potential of GenAI in reshaping the various stages of the composition process, including invention, designing, and revising. The findings reveal that GenAI technologies have the potential to enhance students’ multimodal composition practices and offer alternative solutions to the wicked problems encountered during the design process. Specifically, GenAI facilitates invention by offering design inspirations and enriches designing by expanding, removing, and editing the student-produced design contents. The students in this study also shared their critical stance on the revision process by modifying and iterating their designs after their uses of GenAI. Through showcasing both the opportunities and challenges of GenAI technologies, this paper contributes to the ongoing scholarly conversations on multimodal composition and pedagogy. Moreover, the paper offers implications for the future research and teaching of GenAI-assisted multimodal composition projects, with the aim of encouraging thoughtful integration of GenAI technologies to foster critical AI literacy among college composition students.

AI-assisted design and robotic wire bending of Hawley retainer

AI-assisted design and robotic wire bending of Hawley retainer

Automated design of architectured polymer-concrete composites with high specific flexural strength and toughness using sequential learning

Architectured polymer-concrete composite (APCC) is a promising structural material with high mechanical performance while optimizing the design of APCC for a high flexural strength, high toughness, and light weight remains a challenge. This paper presents a machine learning-based approach to design APCC with high specific flexural strength and toughness. The proposed approach integrates sequential surrogate modelling, Latin hypercube sampling, and Lion Pride Optimization to predict and optimize the flexural properties of APCC. The proposed approach was implemented into designing APCC beams, which were fabricated via 3D printing and tested under flexural loads. Results show that the APCC beams achieved high flexural strength, high toughness, and light weight, simultaneously. The devised architecture of APCC arrested crack propagation and promoted energy dissipation. Parametric studies were performed to evaluate the effect of key design variables of APCC on flexural properties. This research advances the basic knowledge and capabilities of AI-assisted design of APCC.

An intelligent method for temperature load of arch dams

Temperature load significantly affects the deformation and stress of arch dams. Traditional methods for determining temperature loads may not adapt to complex environments, such as high-altitude regions with large temperature variations. This study proposes an intelligent method for temperature load of arch dams. Based on the measured data from existing dams, a physics-informed convolutional neural network is developed, enabling direct application to newly designed dams. The intelligent method delivers annual temperature boundaries on the dam surface, aiding the finite element model in predicting deformation and stress during operational phases. Validation demonstrates accurate results for dam body temperature and deformation, aligning closely with measured data, while also pinpointing critical stress areas within the dam. This method advances the AI-assisted design by predicting temperature loads during dam operation, providing strong support for determining the most unfavorable loading without measured data and ensuring the safety of the structure.

Inverse design of lateral hybrid metasurfaces structural colour: an AI approach.

In conventional metasurface structural colour design, simulations combined with human intuition are used for design and optimization, making it challenging to find the best solution. Here we introduce an innovative AI-assisted design process that bypasses the need for complex simulations, enabling swift and precise mapping between metasurface parameters and colour coordinates. Instead of assigning one colour to one geometry, we demonstrate that multiple colours can be generated from a single geometry under varying levels of strain. This can be achieved through a single model, facilitating the development of active metasurfaces using AI. This finding enables designers to create active metasurfaces that account for both geometric properties and dynamic responses in a unified model which could accelerate the development of active metamaterials closer to practical applications in the real world.

Discovery of a peptide proteolysis-targeting chimera (PROTAC) drug of p300 for prostate cancer therapy

The E1A-associated protein p300 (p300) has emerged as a promising target for cancer therapy due to its crucial role in promoting oncogenic signaling pathways in various cancers, including prostate cancer. This need is particularly significant in prostate cancer. While androgen deprivation therapy (ADT) has demonstrated promising efficacy in prostate cancer, its long-term use can eventually lead to the development of castration-resistant prostate cancer (CRPC) and neuroendocrine prostate cancer (NEPC). Notably, p300 has been identified as an important co-activator of the androgen receptor (AR), highlighting its significance in prostate cancer progression. Moreover, recent studies have revealed the involvement of p300 in AR-independent oncogenes associated with NEPC. Therefore, the blockade of p300 may emerge as an effective therapeutic strategy to address the challenges posed by both CRPC and NEPC. We employed AI-assisted design to develop a peptide-based PROTAC (proteolysis-targeting chimera) drug that targets p300, effectively degrading p300 invitro and invivo utilizing nano-selenium as a peptide drug delivery system. Our p300-targeting peptide PROTAC drug demonstrated effective p300 degradation and cancer cell-killing capabilities in both CRPC, AR-negative, and NEPC cells. This study demonstrated the efficacy of a p300-targeting drug in NEPC cells. In both AR-positive and AR-negative mouse models, the p300 PROTAC drug showed potent p300 degradation and tumor suppression. The design of peptide PROTAC drug targeting p300 is feasible and represents an efficient therapeutic strategy for CRPC, AR-negative prostate cancer, and NEPC. The funding details can be found in the Acknowledgements section.

AI-Assisted Design in Film Post-Production Course Teaching

This paper discusses the application of AI-assisted design in film post-production course teaching, emphasizing its importance in enhancing students’ practical abilities and innovative thinking. The article first outlines the revolutionary role of AI technology in film post-production, including functions such as content-aware editing and color correction, and points out that integrating AI technology into teaching can help students better adapt to industry demands. The research background section reviews the history and current status of AI applications in post-production education, emphasizing its role in cultivating students’ technical skills and creative abilities. The article details teaching design strategies, including heuristic teaching, practice-oriented strategies, and multimedia-assisted strategies, and elaborates on the teaching implementation plan by modules. Finally, the article analyzes the impact of AI-assisted design on the field of education and proposes prospects for future research directions, aiming to promote innovation and development in the field of education.

AI-assisted design integration of MVDC control and protection

AI-assisted design integration of MVDC control and protection

Unleashing the potential: AI empowered advanced metasurface research

Abstract In recent years, metasurface, as a representative of micro- and nano-optics, have demonstrated a powerful ability to manipulate light, which can modulate a variety of physical parameters, such as wavelength, phase, and amplitude, to achieve various functions and substantially improve the performance of conventional optical components and systems. Artificial Intelligence (AI) is an emerging strong and effective computational tool that has been rapidly integrated into the study of physical sciences over the decades and has played an important role in the study of metasurface. This review starts with a brief introduction to the basics and then describes cases where AI and metasurface research have converged: from AI-assisted design of metasurface elements up to advanced optical systems based on metasurface. We demonstrate the advanced computational power of AI, as well as its ability to extract and analyze a wide range of optical information, and analyze the limitations of the available research resources. Finally conclude by presenting the challenges posed by the convergence of disciplines.

AI-Assisted design for better privacy communication in human-robot co-existence

AI-Assisted design for better privacy communication in human-robot co-existence

Self-updatable AI-assisted design of low-carbon cost-effective ultra-high-performance concrete (UHPC)

Machine learning has exhibited high efficiency in designing concrete. However, collecting the dataset for training machine learning models is challenging. To address this challenge, this paper develops an approach to collect concrete design data automatically based on information extraction techniques. The approach enables machine learning models to automatically track, extract, and learn knowledge embedded in data from relevant publications. The approach has been incorporated into AI-assisted design of low-carbon cost-effective ultra-high-performance concrete (UHPC) via integrating the capabilities of automatically collecting and processing data, predicting UHPC properties, and optimizing UHPC properties regarding the material cost, carbon footprint, and compressive strength. A self-updating mechanism is imparted to continuously learn available data. Such a mechanism enables the self-updatable automatic discovery of low-carbon cost-effective UHPC. The results showed increasing prediction accuracy and optimization performance of the proposed approach over time when more knowledge was learned from new data, therefore accelerating the design of UHPC.

Product Design Enhancement for Fashion Retailing

As the fashion industry increasingly embraces artificial intelligence (AI), we investigate how a fast-fashion retailer should choose between using a manual design strategy or an AI-assisted design strategy to enhance existing products. A manual design is a traditional and basic approach that involves human designers only, whereas an AI-assisted design is a more innovative approach that involves both human designers and AI technologies. In this paper, the overall product enhancement is measured by two key attributes: product quality and product trendiness. Product quality can be measured by the product’s longevity as reflected by the quality of the materials and types of fabric and stitching used, where the product’s improvement level can be determined by the retailer in a continuous range. Consequently, the retailer may choose different levels of product quality under different design strategies. The two design approaches also lead to different natures of product trendiness, which is reflected by features such as styles, new materials, and colors, to name just a few. Specifically, we assume that the traditional manual design can predict well how trendy or popular the new product is. Hence, the trendiness attribute under the manual design is deterministic. However, given the uncertain nature of the AI-assisted design technology and the needed coordination between human designers and the adopted technologies, the trendiness of the new product designed under the AI-assisted approach is assumed uncertain. Two sets of designing costs are considered in product enhancement: the fixed design cost that is irrespective of the production volume and the variable marginal cost. Our analysis of the base model highlights the importance of decomposing different costs in determining the optimal design strategy. Specifically, the manual design is preferred when the fixed cost carries more weight, whereas the AI-assisted design is preferred when the marginal cost is a more important factor. Moreover, a higher level of innovation uncertainty under the AI-assisted design gives this strategy an advantage over the manual design. In our extended models, we demonstrate that (1) these results are robust even if the retailer does not have the flexibility to offer the existing product when the AI-assisted design is unpopular, and (2) the relative position of human designers in the two design approaches has an impact on the effects of these costs. Supplemental Material: The online appendix is available at https://doi.org/10.1287/serv.2023.0315 .

AI-assisted Design, 3d Printing, and Evaluation of Architecture Polymer-concrete Composites (APCC) With High Specific Flexural Strength and High Specific Toughness

AI-assisted Design, 3d Printing, and Evaluation of Architecture Polymer-concrete Composites (APCC) With High Specific Flexural Strength and High Specific Toughness

AI-guided electro-decomposition of persistent organic pollutants: a long-awaited vision becoming reality?

AI-assisted design of high-entropy alloys for electro-degradation of POPs could greatly accelerate and improve the design–synthesis–test cycle, hence providing a practical strategy to solve the challenges we might face during mitigation of POPs.

AI-assisted optimization of the ECCE tracking system at the Electron Ion Collider

The Electron-Ion Collider (EIC) is a cutting-edge accelerator facility that will study the nature of the “glue” that binds the building blocks of the visible matter in the universe. The proposed experiment will be realized at Brookhaven National Laboratory in approximately 10 years from now, with detector design and R&D currently ongoing. Notably, EIC is one of the first large-scale facilities to leverage Artificial Intelligence (AI) already starting from the design and R&D phases. The EIC Comprehensive Chromodynamics Experiment (ECCE) is a consortium that proposed a detector design based on a 1.5 T solenoid. The EIC detector proposal review concluded that the ECCE design will serve as the reference design for an EIC detector. Herein we describe a comprehensive optimization of the ECCE tracker using AI. The work required a complex parametrization of the simulated detector system. Our approach dealt with an optimization problem in a multidimensional design space driven by multiple objectives that encode the detector performance, while satisfying several mechanical constraints. We describe our strategy and show results obtained for the ECCE tracking system. The AI-assisted design is agnostic to the simulation framework and can be extended to other sub-detectors or to a system of sub-detectors to further optimize the performance of the EIC detector.

Artificial Intelligence for imaging Cherenkov detectors at the EIC

Imaging Cherenkov detectors form the backbone of particle identification (PID) at the future Electron Ion Collider (EIC). Currently all the designs for the first EIC detector proposal use a dual Ring Imaging CHerenkov (dRICH) detector in the hadron endcap, a Detector for Internally Reflected Cherenkov (DIRC) light in the barrel, and a modular RICH (mRICH) in the electron endcap. These detectors involve optical processes with many photons that need to be tracked through complex surfaces at the simulation level, while for reconstruction they rely on pattern recognition of ring images. This proceeding summarizes ongoing efforts and possible applications of AI for imaging Cherenkov detectors at EIC. In particular we will provide the example of the dRICH for the AI-assisted design and of the DIRC for simulation and particle identification from complex patterns and discuss possible advantages of using AI.

An AI-Assisted Design Method for Topology Optimization without Pre-Optimized Training Data

AbstractEngineers widely use topology optimization during the initial process of product development to obtain a first possible geometry design. The state-of-the-art method is iterative calculation, which requires both time and computational power. This paper proposes an AI-assisted design method for topology optimization, which does not require any optimized data. The presented AI-assisted design procedure generates geometries that are similar to those of conventional topology optimizers, but require only a fraction of the computational effort.

AI-Assisted Design Concept Exploration Through Character Space Construction.

We propose an AI-assisted design concept exploration tool, the “Character Space Construction” (“CSC”). Concept designers explore and articulate the target product aesthetics and semantics in language, which is expressed using “Design Concept Phrases” (“DCPs”), that is, compound adjective phrases, and contrasting terms that convey what are not their target design concepts. Designers often utilize this dichotomy technique to communicate the nature of their aesthetic and semantic design concepts with stakeholders, especially in an early design development phase. The CSC assists this designers' cognitive activity by constructing a “Character Space” (“CS”), which is a semantic quadrant system, in a structured manner. A CS created by designers with the assistance of the CSC enables them to discern and explain their design concepts in contrast with opposing terms. These terms in a CS are retrieved and combined in the CSC by using a knowledge graph. The CSC presents terms and phrases as lists of candidates to users from which users will choose in order to define the target design concept, which is then visualized in a CS. The participants in our experiment, who were in the “arts and design” profession, were given two conditions under which to create DCPs and explain them. One group created and explained the DCPs with the assistance of the proposed CSC, and the other did the same task without this assistance, given the freedom to use any publicly available web search tools instead. The result showed that the group assisted by the CSC indicated their tasks were supported significantly better, especially in exploration, as measured by the Creativity Support Index (CSI).

An Artificial Intelligence–Assisted Design Method for Topology Optimization without Pre-Optimized Training Data

Engineers widely use topology optimization during the initial process of product development to obtain a first possible geometry design. The state-of-the-art method is iterative calculation, which requires both time and computational power. This paper proposes an AI-assisted design method for topology optimization, which does not require any optimized data. An artificial neural network—the predictor—provides the designs on the basis of boundary conditions and degree of filling as input data. In the training phase, the so-called evaluators evaluate the generated geometries on the basis of random input data with respect to given criteria. The results of those evaluations flow into an objective function, which is minimized by adapting the predictor’s parameters. After training, the presented AI-assisted design procedure generates geometries that are similar to those of conventional topology optimizers, but require only a fraction of the computational effort. We believe that our work could be a clue for AI-based methods that require data that are difficult to compute or unavailable.

Refining the Paradigm of Sketching in AI-Based Level Design

This paper describes computational processes which can simulate how human designers sketch and then iteratively refine their work. The paper uses the concept of a map sketch as an initial, low-resolution and low-fidelity prototype of a game level, and suggests how such map sketches can be refined computationally. Different case studies with map sketches of different genres showcase how refinement can be achieved via increasing the resolution of the game level, increasing the fidelity of the function which evaluates it, or a combination of the two. While these case studies use genetic algorithms to automatically generate levels at different degrees of refinement, the general method described in this paper can be used with most procedural generation methods, as well as for AI-assisted design alongside a human creator.