Mark Fuge's research while affiliated with University of Maryland, College Park and other places
What is this page?
This page lists the scientific contributions of an author, who either does not have a ResearchGate profile, or has not yet added these contributions to their profile.
It was automatically created by ResearchGate to create a record of this author's body of work. We create such pages to advance our goal of creating and maintaining the most comprehensive scientific repository possible. In doing so, we process publicly available (personal) data relating to the author as a member of the scientific community.
If you're a ResearchGate member, you can follow this page to keep up with this author's work.
If you are this author, and you don't want us to display this page anymore, please let us know.
It was automatically created by ResearchGate to create a record of this author's body of work. We create such pages to advance our goal of creating and maintaining the most comprehensive scientific repository possible. In doing so, we process publicly available (personal) data relating to the author as a member of the scientific community.
If you're a ResearchGate member, you can follow this page to keep up with this author's work.
If you are this author, and you don't want us to display this page anymore, please let us know.
Publications (80)
Design optimization, and particularly adjoint-based multi-physics shape and topology optimization, is time-consuming and often requires expensive iterations to converge to desired designs. In response, researchers have developed Machine Learning (ML) approaches — often referred to as Inverse Design methods — to either replace or accelerate tools li...
Many design problems involve reasoning about points in high-dimensional space. A common strategy is to first embed these high-dimensional points into a low-dimensional latent space. We propose that a good embedding should be isometric---i.e., preserving the geodesic distance between points on the data manifold in the latent space. However, enforcin...
Design researchers have struggled to produce quantitative predictions for exactly why and when diversity might help or hinder design search efforts. This paper addresses that problem by studying one ubiquitously used search strategy—Bayesian optimization (BO)—on a 2D test problem with modifiable convexity and difficulty. Specifically, we test how p...
Data-driven machine learning techniques can be useful for the rapid evaluation of material properties in extreme environments, particularly in cases where direct access to the materials is not possible. Such problems occur in high-throughput material screening and material design approaches where many candidates may not be amenable to direct experi...
When performing time-intensive optimization tasks, such as those in Topology Optimization or Shape Optimization, researchers have turned to Machine Learned (ML) Inverse Design methods — i.e., algorithms that predict the optimized geometry from input conditions — to either replace or warm start traditional optimizers. Almost exclusively, such method...
Although learning low-dimensional airfoil manifolds can facilitate aerodynamic optimizations, the properties of these latent spaces are not well understood. This paper investigates airfoil manifolds to provide greater insight into the effects of optimized geometry and data set features on latent spaces. Specifically, we investigate if optimized geo...
Cellular structures with controlled local structures can realize heterogeneous material properties and hence enable a much wider range of functions than homogeneous structures. However, the design of heterogeneous cellular structures is challenging due to the high degrees of design freedom. We propose a simple yet principled way to achieve the fast...
Variable-density cellular structures can overcome connectivity and manufacturability issues of topologically optimized structures, particularly those represented as discrete density maps. However, the optimization of such cellular structures is challenging due to the multiscale design problem. Past work addressing this problem generally either only...
As the amount and variety of energetics research increases, machine aware topic identification is necessary to streamline future research pipelines. The makeup of an automatic topic identification process consists of creating document representations and performing classification. However, the implementation of these processes on energetics researc...
Objective:
Fontan surgical planning involves designing grafts to perform optimized hemodynamic performance for the patient's long-term health benefit. The uncertainty of post-operative boundary conditions (BC) and graft anastomosis displacements can significantly affect optimized graft designs and lead to undesirable outcomes, especially for hepat...
View Video Presentation: https://doi.org/10.2514/6.2022-2352.vid The manifold hypothesis forms a pillar of many modern machine learning techniques. Within the context of design, it proposes that valid designs reside on low dimensional manifolds in the high dimensional design spaces. Our previous research—BézierGAN—suggests learning the low dimensio...
Objective
Fontan surgical planning involves designing grafts to perform optimized hemodynamic performance for the patient’s long-term health benefit. The uncertainty of post-operative boundary conditions (BC) and graft anastomisis displacements may significantly affect the optimized graft designs and lead to undesired outcomes, especially for hepat...
Catheter-based endovascular interventional procedures have become increasingly popular in recent years as they are less invasive and patients spend less time in the hospital with less recovery time and less pain. These advantages have led to a significant growth in the number of procedures that are performed annually. However, it is still challengi...
This paper shows how to use conditional generative models in 2D airfoil optimization to probabilistically predict good initialization points within the vicinity of the optima given the input boundary conditions, thus warm starting and accelerating further optimization. We accommodate the possibility of multiple optimal designs corresponding to the...
Catheter-based diagnosis and therapy have grown increasingly in recent years due to their improved clinical outcomes including decreased morbidity, shorter recovery time and minimally invasiveness compared to open surgeries. Although the scalability, customizability, and diversity of soft catheter robots are widely recognized, designers and robotic...
Computational design methods provide opportunities to discover novel and diverse designs that traditional optimization approaches cannot find or that use physical phenomena in ways that engineers have overlooked. However, existing methods require supervised objectives to search or optimize for explicit behaviors or functions — e.g., optimizing aero...
Current computational Design Synthesis approaches have had trouble generating components with higher kinematic pairs and have instead relied on libraries of predefined components. However, higher kinematic pairs are ubiquitous in many mechanical devices such as ratchets, latches, locks, trigger mechanisms , clock escapements, and materials handling...
This paper proposes a semi-automatic Fontan surgery planning method for designing and manufacturing hemodynamically optimized patient-specific grafts. Fontan surgery is a palliative procedure for patients with a single ventricle heart defect by creating a new path using a vascular graft for the deoxygenated blood to be directed to the lungs, bypass...
Design variety metrics measure how much a design space is explored. This article proposes that a generalized class of entropy metrics based on Sharma–Mittal entropy offers advantages over existing methods to measure design variety. We show that an exemplar metric from Sharma–Mittal entropy, namely, the Herfindahl–Hirschman index for design (HHID) h...
Deep learning has shown great potential for generating molecules with desired properties. But the cost and time required to obtain relevant property data have limited study to only a few classes of materials for which extensive data have already been collected. We develop a deep learning method that combines a generative model with a property predi...
Variable-density cellular structures can overcome connectivity and manufacturability issues of topologically-optimized, functionally graded structures, particularly when those structures are represented as discrete density maps. One na\"ive approach to creating variable-density cellular structures is simply replacing the discrete density map with a...
Design researchers have long sought to understand the mechanisms that support creative idea development. However, one of the key challenges faced by the design community is how to effectively measure the nebulous construct of creativity. The social science and engineering communities have adopted two vastly different approaches to solving this prob...
Global optimization of aerodynamic shapes usually requires a large number of expensive computational fluid dynamics simulations because of the high dimensionality of the design space. One approach to combat this problem is to reduce the design space dimension by obtaining a new representation. This requires a parametric function that compactly and...
Human interactions are paramount to the user experience, satisfaction, and risk of user errors. For products, anthropometry has traditionally been used in product sizing. However, structured methods that accurately map static and dynamic capabilities (e.g., functional mapping) of musculoskeletal regions for the conceptualization and redesign of pro...
Design researchers have long sought to understand the mechanisms that support creative idea development. However, one of the key challenges faced by the design community is how to effectively measure the nebulous construct of creativity. The social science and engineering communities have adopted two vastly different approaches to solving this prob...
While current neural networks (NNs) are becoming good at deriving single types of abstractions for a small set of phenomena, for example, using a single NN to predict a flow velocity field, NNs are not good at composing large systems as compositions of small phenomena and reasoning about their interactions. We want to study how NNs build both the a...
Bipartite b-matching, where agents on one side of a market are matched to one or more agents or items on the other, is a classical model that is used in myriad application areas such as healthcare, advertising, education, and general resource allocation. Traditionally, the primary goal of such models is to maximize a linear function of the constitu...
This paper proposes a computational framework for automatically optimizing the shapes of patient-specific tissue engineered vascular grafts. We demonstrate a proof-of-concept design optimization for aortic coarctation repair. The computational framework consists of three main components including 1) a free-form deformation technique exploring graft...
Global optimization of aerodynamic shapes usually requires a large number of expensive computational fluid dynamics simulations because of the high dimensionality of the design space. One approach to combat this problem is to reduce the design space dimension by obtaining a new representation. This requires a parametric function that compactly and...
This paper proposes a computational framework for automatically optimizing the shapes of patient-specific tissue engineered vascular grafts. We demonstrate a proof-of-concept design optimization for aortic coarctation repair. The computational framework consists of three main components including 1) a free-form deformation technique exploring graft...
Collaborative work often benefits from having teams or organizations with heterogeneous members. In this paper, we present a method to form such diverse teams from people arriving sequentially over time. We define diversity using a submodular function and adopt an online algorithm to solve monotone submodular maximization problem with multiple capa...
Recovering a system’s underlying structure from its historical records (also called structure mining) is essential to making valid inferences about that system’s behavior. For example, making reliable predictions about system failures based on maintenance work order data requires determining how concepts described within the work order are related....
Collaborative work often benefits from having teams or organizations with heterogeneous members. In this paper, we present a method to form such diverse teams from people arriving sequentially over time. We define a monotone submodular objective function that combines the diversity and quality of a team and propose an algorithm to maximize the obje...
Bayesian optimization is normally performed within fixed variable bounds. In cases like hyperparameter tuning for machine learning algorithms, setting the variable bounds is not trivial. It is hard to guarantee that any fixed bounds will include the true global optimum. We propose a Bayesian optimization approach that only needs to specify an initi...
Modern Machine Learning (ML) techniques are transforming many disciplines ranging from transportation to healthcare by uncovering pattern in data, developing autonomous systems that mimic human abilities, and supporting human decision-making. Modern ML techniques, such as deep neural networks, are fueling the rapid developments in artificial intell...
In this paper, we propose a new design variety metric based on the Herfindahl index. We also propose a practical procedure for comparing variety metrics via the construction of ground truth datasets from pairwise comparisons by experts. Using two new datasets, we show that this new variety measure aligns with human ratings more than some existing a...
From engineering analysis and topology optimization to generative design and machine learning, many modern computational design approaches require either large amounts of data or a method to generate that data. This paper addresses key issues with automatically generating such data through automating the construction of Finite Element Method (FEM)...
Human- or expert-generated records that describe the behavior of engineered systems over a period of time can be useful for statistical learning techniques like pattern detection or output prediction. However, such data often assumes familiarity of a reader with the relationships between entities within the system — that is, knowledge of the system...
Real-world designs usually consist of parts with interpart dependencies, i.e., the geometry of one part is dependent on one or multiple other parts. We can represent such dependency in a part dependency graph. This paper presents a method for synthesizing these types of hierarchical designs using generative models learned from examples. It decompos...
Exposing people to concepts created by others can inspire novel combinations of concepts, or conversely, lead people to simply emulate others. But how does the type of exposure affect creative outcomes in online collaboration where dyads interact for short tasks? In this paper, we study the creative outcomes of dyads working together online on a sl...
In the space of only a few years, deep generative modeling has revolutionized how we think of artificial creativity, yielding autonomous systems which produce original images, music, and text. Inspired by these successes, researchers are now applying deep generative modeling techniques to the generation and optimization of molecules- in our review...
In the space of only a few years, deep generative modeling has revolutionized how we think of artificial creativity, yielding autonomous systems which produce original images, music, and text. Inspired by these successes, researchers are now applying deep generative modeling techniques to the generation and optimization of molecules - in our review...
The number of scientific journal articles and reports being published about energetic materials every year is growing exponentially, and therefore extracting relevant information and actionable insights from the latest research is becoming a considerable challenge. In this work we explore how techniques from natural language processing and machine...
Due to its high computational speed and accuracy compared to ab-initio quantum chemistry and forcefield modeling, the prediction of molecular properties using machine learning has received great attention in the fields of materials design and drug discovery. A main ingredient required for machine learning is a training dataset consisting of molecul...
Design creativity - Volume 32 Special Issue - Katherine Fu, Mark Fuge, David C. Brown
Assessing similarity between design ideas is an inherent part of many design evaluations to measure novelty. In such evaluation tasks, humans excel at making mental connections among diverse knowledge sets to score ideas on their uniqueness. However, their decisions about novelty are often subjective and difficult to explain. In this paper, we demo...
his work demonstrates fully 3D printed donut type HASEL actuators fabricated using inkjet additive manufacturing. In addition, we also present a coupled electrical, hydraulic, non-linear elastic model of these actuators to predict the actuation strain. This model was tested on 3D printed HASEL actuators and was found to be in good agreement with ex...
Many real-world objects are designed by smooth curves, especially in the domain of aerospace and ship, where aerodynamic shapes (e.g., airfoils) and hydrodynamic shapes (e.g., hulls) are designed. To facilitate the design process of those objects, we propose a deep learning based generative model that can synthesize smooth curves. The model maps a...
Real-world designs usually consist of parts with hierarchical dependencies, i.e., the geometry of one component (a child shape) is dependent on another (a parent shape). We propose a method for synthesizing this type of design. It decomposes the problem of synthesizing the whole design into synthesizing each component separately but keeping the int...
Assessing similarity between design ideas is an inherent part of many design evaluations to measure novelty. In such evaluation tasks, humans excel at making mental connections among diverse knowledge sets and scoring ideas on their uniqueness. However, their decisions on novelty are often subjective and difficult to explain. In this paper, we demo...
Computer Aided Design (CAD) software can be difficult to learn. A major contributor to this entry barrier is CAD interfaces’ usage of symbols associated with CAD operations. This paper studies which symbols minimize recall time and optimize retention via two studies. We performed an initial exploratory study to identify which 2D symbols intuitively...
In this work, we discuss use of machine learning techniques for rapid prediction of detonation properties including explosive energy, detonation velocity, and detonation pressure. Further, analysis is applied to individual molecules in order to explore the contribution of bonding motifs to these properties. Feature descriptors evaluated include Mor...
Additive manufacturing (AM) processes allow for complex geometries to be developed in a cost- and time-efficient manner in small-scale productions. The unique functionality of AM offers an ideal collaboration between specific applications of human variability and thermal management. This research investigates the intersection of AM, human variabili...
We present a proof of concept that machine learning techniques can be used to predict the properties of CNOHF energetic molecules from their molecular structures. We focus on a small but diverse dataset consisting of 109 molecular structures spread across ten compound classes. Up until now, candidate molecules for energetic materials have been scre...
Many engineering problems require identifying feasible domains under implicit constraints. One example is finding acceptable car body styling designs based on constraints like aesthetics and functionality. Current active-learning based methods learn feasible domains for bounded input spaces. However, we usually lack prior knowledge about how to set...
We present a proof of concept that machine learning techniques can be used to predict the properties of CNOHF energetic molecules from their molecular structures. We focus on a small but diverse dataset consisting of 109 molecular structures spread across ten compound classes. Up until now, candidate molecules for energetic materials have been scre...
Bisociative knowledge discovery is an approach that combines elements from two or more "incompatible" domains to generate creative solutions and insight. Inspired by Koestler's notion of bisociation, in this paper we propose a computational framework for the discovery of new connections between domains to promote creative discovery and inspiration...
Recent work in 3D printing has focused on tools and techniques to design deformation behaviors using mechanical structures such as joints and metamaterials. In this poster, we explore how to embed and control mechanical springs to create deformable 3D-printed objects. We propose an initial design space of 3D-printable spring-based structures to sup...
When selecting ideas or trying to find inspiration, designers often must sift through hundreds or thousands of ideas. This paper provides an algorithm to rank design ideas such that the ranked list simultaneously maximizes the quality and diversity of recommended designs. To do so, we first define and compare two diversity measures using Determinan...
Bipartite matching, where agents on one side of a market are matched to agents or items on the other, is a classical problem in computer science and economics, with widespread application in healthcare, education, advertising, and general resource allocation. A practitioner's goal is typically to maximize a matching market's economic efficiency, po...
To solve a design problem, sometimes it is necessary to identify the feasible design space. For design spaces with implicit constraints, sampling methods are usually used. These methods typically bound the design space; that is, limit the range of design variables. But bounds that are too small would fail to cover all possible designs; while bounds...
We propose a tool-based workflow that allows novice users to create deformable 3D-printed objects with embedded spring structures. In our early exploration, we investigated possible deformation behaviors, implemented a GUI-based computational tool, and made minor modifications to a commodity 3D printer to support spring printing. The goal of this p...
This paper shows how to measure the intrinsic complexity and dimensionality of a design space. It assumes that high dimensional design parameters actually lie in a much lower dimensional space that represents semantic attributes-a design manifold. Past work has shown how to embed designs using techniques like autoencoders; in contrast, the method p...
This paper describes how to find or filter high-quality ideas submitted by members collaborating together in online communities. Typical means of organizing community submissions, such as aggregating community or crowd votes, suffer from the cold-start problem, the rich-get-richer problem, and the sparsity problem. To circumvent those, our approach...
Bipartite matching, where agents on one side of a market are matched to agents or items on the other, is a classical problem in computer science and economics, with widespread application in healthcare, education, advertising, and general resource allocation. A practitioner's goal is typically to maximize a matching market's economic efficiency, po...
This paper shows how to measure the complexity and reduce the dimensionality of a geometric design space. It assumes that high-dimensional design parameters actually lie in a much lower-dimensional space that represents semantic attributes. Past work has shown how to embed designs using techniques like autoencoders; in contrast, this paper quantifi...
This paper describes how to select diverse, high quality, representative ideas when the number of ideas grow beyond what a person can easily organize. When designers have a large number of ideas, it becomes prohibitively difficult for them to explore the scope of those ideas and find inspiration. We propose a computational method to recommend a div...
The number of design studies using statistical testing has increased dramatically over the past decade. While this has benefits, statistical testing requires scrutiny to protect against common errors and misconceptions. To illuminate how these issues affect design, this paper provides a comprehensive analysis of the past decade of studies within th...
While there is increasing interest in designing for the developing world, identifying appropriate design research methods for understanding user needs and preferences in these unfamiliar contexts is a major challenge. This paper demonstrates how to apply a variety of statistical techniques to an online design case study repository, Human-Centered D...
Additive Manufacturing (AM) technology, or 3D-printing, sits at the heart of the Maker Movement-the growing desire for wider-ranges of people to design physical objects. However, despite advances in AM capabilities, most users that wish to design functional moving devices face a prohibitive barrier-to-entry: they need fluency in a Computer Aided De...
Every year design practitioners and researchers develop new methods for understanding users and solving problems. This increasingly large collection of methods causes a problem for novice designers: How does one choose which design methods to use for a given problem? Experienced designers can provide case studies that document which methods they us...
While there is increasing interest in designing for the developing world, one major challenge lies in understanding when to apply different design methods in unfamiliar contexts. This paper uses HCD Connect, an online design case study repository, to compare what types of methods people frequently apply to developing world problems. Specifically, i...
While companies are turning to online communities of outside designers to bring new ideas into their product development process, several questions remain unanswered: How do design communities form, evolve, and die out over time? What integrates newcomers into the community? How can one grow community without impeding idea inspiration? This paper e...
This paper presents a large-scale empirical study of OpenIDEO, an online collaborative design community. Using network analysis techniques, we describe the properties of this collaborative design network and discuss how it differs from common models of network formation seen in other social or technological networks. One major finding is that in Op...
OpenIDEO.com is an online collaborative platform developed to crowd source design talent across the Internet to tackle difficult interdisciplinary problems. Many of their design Challenges have focused upon issues concerning impoverished communities. Challenges include human sanitation solutions, alternatives for serving maternal health issues with...
Measuring design creativity is crucial to evaluating the effectiveness of idea generation methods. Historically, there has been a divide between easily-computable metrics, which are often based on arbitrary scoring systems, and human judgement metrics, which accurately reflect human opinion but rely on the expensive collection of expert ratings. Th...
Citations
... In comparison to traditional approaches, this paradigm can result in the discovery and creation of new materials with significantly higher computational efficiency. The Inverse Homogenization (IH) mapping from attributes to cell shapes can also be learned using a Generative Adversarial Network (GAN) model, which can then be used to optimize functionally graded cell structures [173]. Using input parameters like tensile modulus, elongation at break, and tensile strength of natural cartilage, ML algorithms have also been used to predict the most suitable polymer/blends for replacing cartilage [174]. ...
![[object Object]](https://i1.rgstatic.net/ii/profile.image/697852615462914-1543392437311_Q64/Jun-Wang-19.jpg)
![[object Object]](https://i1.rgstatic.net/ii/profile.image/718449512824833-1548303120511_Q64/Wei-Chen-127.jpg)
![[object Object]](https://i1.rgstatic.net/ii/profile.image/936806728089600-1600363537865_Q64/Daicong-Da.jpg)
![[object Object]](https://i1.rgstatic.net/ii/profile.image/278879496359936-1443501461025_Q64/Rahul-Rai-21.jpg)
... The overall methodology for this study is consistent with what has been previously described in our published work. [18][19][20][21][22] Cardiovascular magnetic resonance imaging datasets from 12 patients with single ventricle FIGURE 1. Differences in the total cavopulmonary connection (TCPC) and our novel convergent cavopulmonary connection (CCPC), revealing the superior, inferior, and common limbs of the conduit. The CCPC common limb provides a single inflow and a single outflow to allow easy institution of mechanical circulatory support (MCS (Table 1) and no fenestration were anonymized and exported in Digital Imaging and Communications in Medicine format. ...
![[object Object]](https://i1.rgstatic.net/ii/profile.image/669724862058517-1536686258414_Q64/Xiaolong-Liu-19.jpg)
![[object Object]](https://i1.rgstatic.net/ii/profile.image/894807417319424-1590350121219_Q64/Yue-Hin-Loke.jpg)
![[object Object]](https://i1.rgstatic.net/ii/profile.image/278595890106377-1443433844562_Q64/Star-Kim.jpg)