Matching Items (328)
Filtering by
- All Subjects: artificial intelligence
- Resource Type: Text
Description
Collecting accurate collective decisions via crowdsourcing
is challenging due to cognitive biases, varying
worker expertise, and varying subjective scales. This
work investigates new ways to determine collective decisions
by prompting users to provide input in multiple
formats. A crowdsourced task is created that aims
to determine ground-truth by collecting information in
two different ways: rankings and numerical estimates.
Results indicate that accurate collective decisions can
be achieved with less people when ordinal and cardinal
information is collected and aggregated together
using consensus-based, multimodal models. We also
show that presenting users with larger problems produces
more valuable ordinal information, and is a more
efficient way to collect an aggregate ranking. As a result,
we suggest input-elicitation to be more widely considered
for future work in crowdsourcing and incorporated
into future platforms to improve accuracy and efficiency.
is challenging due to cognitive biases, varying
worker expertise, and varying subjective scales. This
work investigates new ways to determine collective decisions
by prompting users to provide input in multiple
formats. A crowdsourced task is created that aims
to determine ground-truth by collecting information in
two different ways: rankings and numerical estimates.
Results indicate that accurate collective decisions can
be achieved with less people when ordinal and cardinal
information is collected and aggregated together
using consensus-based, multimodal models. We also
show that presenting users with larger problems produces
more valuable ordinal information, and is a more
efficient way to collect an aggregate ranking. As a result,
we suggest input-elicitation to be more widely considered
for future work in crowdsourcing and incorporated
into future platforms to improve accuracy and efficiency.
ContributorsKemmer, Ryan Wyeth (Author) / Escobedo, Adolfo (Thesis director) / Maciejewski, Ross (Committee member) / Computing and Informatics Program (Contributor) / Computer Science and Engineering Program (Contributor) / Barrett, The Honors College (Contributor)
Created2020-05
Description
The purpose of this investigation is to apply a machine learning algorithm with de-identified, historic oncology clinical trial data to assess the theoretical understanding of predictive modeling to derive potential clinical practice recommendations. Within this study, electronic medical records from the HonorHealth Virginia G. Piper Institute will undergo data visualization to identify potential correlations and trends critical for model creation as well as further identify potential expansions or limitations of scope regarding model purpose. Hypothesis pursued post data visualization was the development of a predictive model for 6-month survival. Current standard is estimated physician accuracy at 56.5% accuracy at 6 months out. This study created supervised learning models using decision trees, KNN, SVM and Ensemble methods using combinations of LASSO Logistic Regression and Know-GRFF Random Forest for feature selection. SVM trained on a combined set of LASSO and Know-GRRF featured produced the highest performing model at 75.5% with an AUC of 0.82. This study demonstrates the potential for applying predictive modeling on readily available EMR records to drive clinical practice recommendations. The models developed could potentially, with further development, be used as an ancillary tool for jumpstarting patient-physician conversations on survival and life expectancy.
ContributorsLi, Richard Longfei (Co-author) / Liu, Li (Co-author, Thesis director) / Gosselin, Kevin (Co-author, Committee member) / Harrington Bioengineering Program (Contributor, Contributor) / Barrett, The Honors College (Contributor)
Created2019-05
Description
As automation research into penetration testing has developed, several methods have been proposed as suitable control mechanisms for use in pentesting frameworks. These include Markov Decision Processes (MDPs), partially observable Markov Decision Processes (POMDPs), and POMDPs utilizing reinforcement learning. Since much work has been done automating other aspects of the pentesting process using exploit frameworks and scanning tools, this is the next focal point in this field. This paper shows a fully-integrated solution comprised of a POMDP-based planning algorithm, the Nessus scanning utility, and MITRE's CALDERA pentesting platform. These are linked in order to create an autonomous AI attack platform with scanning, planning, and attack capabilities.
ContributorsDejarnett, Eric Andrew (Author) / Huang, Dijiang (Thesis director) / Chowdhary, Ankur (Committee member) / Computer Science and Engineering Program (Contributor) / Barrett, The Honors College (Contributor)
Created2020-05
Description
Vulnerability testing/evaluation is a regular task for cyber-security groups. Conducting tasks like this can take up a great amount of time and may not be perfect. Automating these tasks helps speed up the rate at which experts can test systems. However, script based or static programs that run automatically often do not have the versatility required to properly replace human analysis. With the advances in Artificial Intelligence and Machine Learning, a utility can be developed that would allow for the creation of penetration testing plans rather than manually testing vulnerabilities. A variety of existing cyber-security programs and utilities provide an API layer that commonly interacts with the Python environment. With the commonality of AI/ML tools within the Python ecosystem, a plugin like interface can be developed to feed any AI/ML program real world data and receive a response/report in return. Using Python 2.7+, Python 3.6+, pymdptoolbox, and POMDPy, a program was developed that ingests real-world data from scanning tools and returned a suggested course of action to be used by analysts in order to perform a practical validation of the algorithms in a real world setting. This program was able to successfully navigate a test network and produce results that were expected to be found on the target machines without needing human analysis of the network. Using POMDP based systems for more cyber-security type tasks may be a valuable use case for future developments and help ease the burden faced in a rapid paced world.
ContributorsBelanger, Connor Lawrence (Author) / Huang, Dijiang (Thesis director) / Chowdhary, Ankur (Committee member) / Computer Science and Engineering Program (Contributor) / Barrett, The Honors College (Contributor)
Created2020-05
Description
It is interesting to reflect that the American legal system has not seriously applied any significant technological advances in many decades. It is fascinating that the same processes used to draft a will or estate plan are virtually the same as they were in the 1960’s. This seems to be a problem that should be concerning in this modern age. We would be hard pressed to observe doctors in the U.S. currently performing medical procedures as they would have in 1960 considering the technological advancements that have taken place in society since then. Many of the processes in the legal system are extremely static and even archaic. It seems to be an opportune time to revolutionize the whole system as advancements continue; but, this revolution must take into account both the positive and negative repercussions that are possible moving forward.
ContributorsWilladson, Conor Calista Carolena (Author) / Koretz, Lora (Thesis director) / Forst, Bradley (Committee member) / Dean, W.P. Carey School of Business (Contributor) / Department of Psychology (Contributor) / Barrett, The Honors College (Contributor)
Created2020-05
Description
The adaptive artificial-intelligence (AI) medical device industry is a novel industry in the United States offering innovations to the healthcare field. The rapid expansion of this industry in recent years has drawn attention from multiple stakeholders causing a heated debate about how to introduce these innovations into the market while maintaining patient safety and treatment efficacy. Since early 2019, the U.S. Food and Drug Administration (FDA) has been releasing statements in regards to the improvement of regulation for this new technology, but has yet to take further actions. Dilemmas including 1) a difficult regulatory process, 2) a heightening financial burden and 3) looming liability issues, are reasons adaptive AI medical devices have struggled to be advanced. By conducting a thorough analysis of these 3 issues, recognizing the intricacies of them separately and together, this study develops a better understanding of the landscape adaptive AI technology is facing and provides a clearer picture for the future of the industry.
ContributorsOgden, Ravyn Nicole (Author) / Coursen, Jerry (Thesis director) / Pizziconi, Vincent (Committee member) / Harrington Bioengineering Program (Contributor) / Barrett, The Honors College (Contributor)
Created2020-05
Description
While there are many existing systems which take natural language descriptions and use them to generate images or text, few systems exist to generate 3d renderings or environments based on natural language. Most of those systems are very limited in scope and require precise, predefined language to work, or large well tagged datasets for their models. In this project I attempt to apply concepts in NLP and procedural generation to a system which can generate a rough scene estimation of a natural language description in a 3d environment from a free use database of models. The primary objective of this system, rather than a completely accurate representation, is to generate a useful or interesting result. The use of such a system comes in assisting designers who utilize 3d scenes or environments for their work.
ContributorsHann, Jacob R. (Author) / Kobayashi, Yoshihiro (Thesis director) / Srivastava, Siddharth (Committee member) / Computer Science and Engineering Program (Contributor) / Computing and Informatics Program (Contributor) / Barrett, The Honors College (Contributor)
Created2019-05
Description
The premise of this thesis developed from my personal interests and undergraduate educational experiences in both industrial engineering and design studies, particularly those related to product design. My education has stressed the differences in the ways that engineers and designers approach problem solving and creating solutions, but I am most interested in marrying the two mindsets of designers and engineers to better solve problems creatively and efficiently.
This thesis focuses on the recent appearance of generative design technology into the world of industrial design and engineering as it relates to product development. An introduction to generative design discusses the uses and benefits of this tool for both designers and engineers and also addresses the challenges of this technology. The relevance of generative design to the world of product development is discussed as well as the implications of how this technology will change the roles of designers and engineers, and especially their traditional design processes. The remainder of this paper is divided into two elements. The first serves as documentation of my own exploration of using generative design software to solve a product design challenge and my reflections on the benefits and challenges of using this tool. The second element addresses the need for employing quantitiative methodologies within the generative design process to aid designers in selecting the most advantageous design option when presented with generative outcomes. Both sections aim to provide more context to this new design process and seek to answer questions about some of the ambiguous processes of generative design.
This thesis focuses on the recent appearance of generative design technology into the world of industrial design and engineering as it relates to product development. An introduction to generative design discusses the uses and benefits of this tool for both designers and engineers and also addresses the challenges of this technology. The relevance of generative design to the world of product development is discussed as well as the implications of how this technology will change the roles of designers and engineers, and especially their traditional design processes. The remainder of this paper is divided into two elements. The first serves as documentation of my own exploration of using generative design software to solve a product design challenge and my reflections on the benefits and challenges of using this tool. The second element addresses the need for employing quantitiative methodologies within the generative design process to aid designers in selecting the most advantageous design option when presented with generative outcomes. Both sections aim to provide more context to this new design process and seek to answer questions about some of the ambiguous processes of generative design.
ContributorsElgin, Mariah Crystal (Author) / Bacalzo, Dean (Thesis director) / Gel, Esma (Committee member) / Industrial, Systems & Operations Engineering Prgm (Contributor) / Dean, Herberger Institute for Design and the Arts (Contributor) / Barrett, The Honors College (Contributor)
Created2019-05
Description
Advances in computational processing have made big data analysis in fields like music information retrieval (MIR) possible. Through MIR techniques researchers have been able to study information on a song, its musical parameters, the metadata generated by the song's listeners, and contextual data regarding the artists and listeners (Schedl, 2014). MIR research techniques have been applied within the field of music and emotions research to help analyze the correlative properties between the music information and the emotional output. By pairing methods within music and emotions research with the analysis of the musical features extracted through MIR, researchers have developed predictive models for emotions within a musical piece. This research has increased our understanding of the correlative properties of certain musical features like pitch, timbre, rhythm, dynamics, mel frequency cepstral coefficients (MFCC's), and others, to the emotions evoked by music (Lartillot 2008; Schedl 2014) This understanding of the correlative properties has enabled researchers to generate predictive models of emotion within music based on listeners' emotional response to it. However, robust models that account for a user's individualized emotional experience and the semantic nuances of emotional categorization have eluded the research community (London, 2001). To address these two main issues, more advanced analytical methods have been employed. In this article we will look at two of these more advanced analytical methods, machine learning algorithms and deep learning techniques, and discuss the effect that they have had on music and emotions research (Murthy, 2018). Current trends within MIR research, the application of support vector machines and neural networks, will also be assessed to explain how these methods help to address the two main issues within music and emotion research. Finally, future research within the field of machine and deep learning will be postulated to show how individuate models may be developed from a user or a pool of user's listening libraries. Also how developments of semi-supervised classification models that assess categorization by cluster instead of by nominal data, may be helpful in addressing the nuances of emotional categorization.
ContributorsMcgeehon, Timothy Makoto (Author) / Middleton, James (Thesis director) / Knowles, Kristina (Committee member) / Mechanical and Aerospace Engineering Program (Contributor) / Barrett, The Honors College (Contributor)
Created2018-12
Description
Classical planning is a field of Artificial Intelligence concerned with allowing autonomous agents to make reasonable decisions in complex environments. This work investigates
the application of deep learning and planning techniques, with the aim of constructing generalized plans capable of solving multiple problem instances. We construct a Deep Neural Network that, given an abstract problem state, predicts both (i) the best action to be taken from that state and (ii) the generalized “role” of the object being manipulated. The neural network was tested on two classical planning domains: the blocks world domain and the logistic domain. Results indicate that neural networks are capable of making such
predictions with high accuracy, indicating a promising new framework for approaching generalized planning problems.
the application of deep learning and planning techniques, with the aim of constructing generalized plans capable of solving multiple problem instances. We construct a Deep Neural Network that, given an abstract problem state, predicts both (i) the best action to be taken from that state and (ii) the generalized “role” of the object being manipulated. The neural network was tested on two classical planning domains: the blocks world domain and the logistic domain. Results indicate that neural networks are capable of making such
predictions with high accuracy, indicating a promising new framework for approaching generalized planning problems.
ContributorsNakhleh, Julia Blair (Author) / Srivastava, Siddharth (Thesis director) / Fainekos, Georgios (Committee member) / Computer Science and Engineering Program (Contributor) / School of International Letters and Cultures (Contributor) / Barrett, The Honors College (Contributor)
Created2019-05