Matching Items (25)

133880-Thumbnail Image.png

ReL GoalD (Reinforcement Learning for Goal Dependencies)

Description

In this project, the use of deep neural networks for the process of selecting actions to execute within an environment to achieve a goal is explored. Scenarios like this are common in crafting based games such as Terraria or Minecraft.

In this project, the use of deep neural networks for the process of selecting actions to execute within an environment to achieve a goal is explored. Scenarios like this are common in crafting based games such as Terraria or Minecraft. Goals in these environments have recursive sub-goal dependencies which form a dependency tree. An agent operating within these environments have access to low amounts of data about the environment before interacting with it, so it is crucial that this agent is able to effectively utilize a tree of dependencies and its environmental surroundings to make judgements about which sub-goals are most efficient to pursue at any point in time. A successful agent aims to minimizes cost when completing a given goal. A deep neural network in combination with Q-learning techniques was employed to act as the agent in this environment. This agent consistently performed better than agents using alternate models (models that used dependency tree heuristics or human-like approaches to make sub-goal oriented choices), with an average performance advantage of 33.86% (with a standard deviation of 14.69%) over the best alternate agent. This shows that machine learning techniques can be consistently employed to make goal-oriented choices within an environment with recursive sub-goal dependencies and low amounts of pre-known information.

Contributors

Agent

Created

Date Created
2018-05

133874-Thumbnail Image.png

State Press Live

Description

As our relationship with technology continues to encourage people to spend more time engaged online, traditional means of journalism must adapt in order to communicate with audiences. While many news organizations default to social media outlets, the goal of this

As our relationship with technology continues to encourage people to spend more time engaged online, traditional means of journalism must adapt in order to communicate with audiences. While many news organizations default to social media outlets, the goal of this project is to allow users a more direct experience with reporters, photographers and editors. It will allow The State Press, the official, student-run news organization covering ASU, to create content within Slack, an internal messaging platform commonly used in newsrooms. Secondly, it will provide a means for viewers to conveniently ingest their news as it unfolds, with updates, media, and analysis appearing in front of them without having to refresh the page.

Contributors

Agent

Created

Date Created
2018-05

132566-Thumbnail Image.png

Developing a Curriculum to Prepare Software Engineers for the Technical Interview Process

Description

ASU’s Software Engineering (SER) program adequately prepares students for what happens after they become a developer, but there is no standard for preparing students to secure a job post-graduation in the first place. This project creates and executes a supplemental

ASU’s Software Engineering (SER) program adequately prepares students for what happens after they become a developer, but there is no standard for preparing students to secure a job post-graduation in the first place. This project creates and executes a supplemental curriculum to prepare students for the technical interview process. The trial run of the curriculum was received positively by study participants, who experienced an increase in confidence over the duration of the workshop.

Contributors

Agent

Created

Date Created
2019-05

132547-Thumbnail Image.png

Automated Bicycle Human-in-the-Loop Control

Description

Bicycles are already used for daily transportation by a large share of the world's population and provide a partial solution for many issues facing the world today. The low environmental impact of bicycling combined with the reduced requirement for road

Bicycles are already used for daily transportation by a large share of the world's population and provide a partial solution for many issues facing the world today. The low environmental impact of bicycling combined with the reduced requirement for road and parking spaces makes bicycles a good choice for transportation over short distances in urban areas. Bicycle riding has also been shown to improve overall health and increase life expectancy. However, riding a bicycle may be inconvenient or impossible for persons with disabilities due to the complex and coordinated nature of the task. Automated bicycles provide an interesting area of study for human-robot interaction, due to the number of contact points between the rider and the bicycle. The goal of the Smart Bike project is to provide a platform for future study of the physical interaction between a semi-autonomous bicycle robot and a human rider, with possible applications in rehabilitation and autonomous vehicle research.

This thesis presents the development of two balance control systems, which utilize actively controlled steering and a control moment gyroscope to stabilize the bicycle at high and low speeds. These systems may also be used to introduce disturbances, which can be useful for studying human reactions. The effectiveness of the steering balance control system is verified through testing with a PID controller in an outdoor environment. Also presented is the development of a force sensitive bicycle seat which provides feedback used to estimate the pose of the rider on the bicycle. The relationship between seat force distribution is demonstrated with a motion capture experiment. A corresponding software system is developed for balance control and sensor integration, with inputs from the rider, the internal balance and steering controller, and a remote operator.

Contributors

Agent

Created

Date Created
2019-05

Using an automated attendance monitoring system to maximize time for class activities

Description

Class instructors at Arizona State University monitor students’ attendance for classes in which attendance is either mandatory or encouraged. Class monitoring can be done using traditional systems such as sign sheets and roll calls. From my initial observations while attending

Class instructors at Arizona State University monitor students’ attendance for classes in which attendance is either mandatory or encouraged. Class monitoring can be done using traditional systems such as sign sheets and roll calls. From my initial observations while attending a class which utilized a sign sheet for class attendance monitoring, I thought the process took long and was inefficient. As a result, I created an automated system that would replace the traditional systems and improve the class monitoring process. Thus, this study aims to determine whether the automated system reduced the time it takes to monitor class attendance, and whether it was efficient.

To examine the above question, the automated system was deployed to 2 classes at Arizona State University. Additionally, surveys were distributed to 2 instructors and 33 students and they were asked to respond to questions relating to class attendance and the monitoring systems which were being used alternatively with the newly-created automated system. Analysis of the responses demonstrated that use of an automated system reduced the time it takes students to mark their presence, and thus increase the time used for other class activities. The results also indicate that the design of the automated system affects the overall time it takes to monitor attendance. On this basis, it is recommended that instructors utilize an automated system to monitor class attendance. Further research is needed to study the time it takes instructors to set up different monitoring systems in order to ascertain that an automated system reduces the overall time it takes to monitor attendance compared to other traditionally used systems.

Contributors

Agent

Created

Date Created
2019-05

133057-Thumbnail Image.png

Understanding the Impact of a Culturally-Relevant Engineering Design Curriculum Module Through a Lens of Tribal Critical Race Theory

Description

The purpose of this paper is to develop an understanding of Navajo students' perspectives on how engineering can be used to improve life in their own communities on the Navajo reservation. Branching off an existing study that aims to develo

The purpose of this paper is to develop an understanding of Navajo students' perspectives on how engineering can be used to improve life in their own communities on the Navajo reservation. Branching off an existing study that aims to develop a culturally-contextualized engineering design curriculum for middle schools in the Navajo Nation, this research focuses on a curriculum module entitled, "Future Chapter Presidents". This module is inspired by the Future City Competition where middle school students are tasked with imagining a better future. To make "Future Chapter Presidents" more culturally-relevant, students are instead tasked with proposing solutions that will improve life on the reservation. This module emphasizes engineering design alongside teaching Navajo Nation government standards by having students in the class run for a position in their local government. Students are prompted with creating a campaign poster that showcases their proposed solutions directed at their own communities. In order to analyze students' perspectives and understanding of how engineering can be used to improve life on the reservation, thematic analysis is used to study each individual poster. Meanwhile, because the researchers conducting this study are not Navajo, Tribal Critical Race Theory (Brayboy, 2006) was applied to ensure that the content of the posters are interpreted from an Indigenous lens. The results of this study can be used to inform future curriculum development for engineering design modules in the Navajo Nation and expand upon existing literature that provides understanding of how Navajo students experience and understand engineering in the context of their culture.

Contributors

Agent

Created

Date Created
2018-12

132708-Thumbnail Image.png

PRACTICAL APPLICATION OF CONVOLUTIONAL NEURAL NETWORKS FOR SKIN LESION CLASSIFICATION

Description

In this paper, I explore practical applications of neural networks for automated skin lesion identification. The visual characteristics are of primary importance in the recognition of skin diseases, hence, the development of deep neural network models proven capable of classifying

In this paper, I explore practical applications of neural networks for automated skin lesion identification. The visual characteristics are of primary importance in the recognition of skin diseases, hence, the development of deep neural network models proven capable of classifying skin lesions can potentially change the face of modern medicine by extending the availability and lowering the cost of diagnostic care. Previous work has demonstrated the effectiveness of convolutional neural networks in image classification in general, with even higher accuracy achievable by data augmentation techniques, such as cropping, rotating, and flipping input images, along with more advanced computationally intensive approaches. In this research, I provide an overview of Convolutional Neural Networks (CNN) and CNN implementation with TensorFlow and Keras API in context of image recognition and classification. I also experiment with custom convolutional neural network model architecture trained using HAM10000 dataset. The dataset used for the case study is obtained from Harvard Dataverse and is maintained by Medical University of Vienna. The HAM10000 dataset is a large collection of multi-source dermatoscopic images of common pigmented skin lesions and is available for academic research under Creative Commons Attribution-Noncommercial 4.0 International Public License. With over ten thousand dermatoscopic images of seven classes of benign and malignant skin lesions, the dataset is substantial for academic machine learning purposes for multiclass image classification. I discuss the successes and shortcomings of the model in respect to its application to the dataset.

Contributors

Agent

Created

Date Created
2019-05

133510-Thumbnail Image.png

Modules of Intelligence

Description

Intelligence is a loosely defined term, but it is a quality that we try to measure in humans, animals, and recently machines. Progress in artificial intelligence is slow, but we have recently made breakthroughs by paying attention to biology and

Intelligence is a loosely defined term, but it is a quality that we try to measure in humans, animals, and recently machines. Progress in artificial intelligence is slow, but we have recently made breakthroughs by paying attention to biology and neuroscience. We have not fully explored what biology has to offer us in AI research, and this paper explores aspects of intelligent behavior in nature that machines still struggle with.

Contributors

Agent

Created

Date Created
2018-05

133424-Thumbnail Image.png

Educating Future Engineers in the Art of Communication through Presenting

Description

Effective communication and engineering are not a natural pairing. The incongruence is because engineering students are focused on making, designing and analyzing. Since these are the core functions of the field there is not a direct focus on developing communication

Effective communication and engineering are not a natural pairing. The incongruence is because engineering students are focused on making, designing and analyzing. Since these are the core functions of the field there is not a direct focus on developing communication skills. This honors thesis explores the role and expectations for student engineers within the undergraduate engineering education experience to present and communicate ideas. The researchers interviewed faculty about their perspective on students' abilities with respect to their presentation skills to inform the design of a workshop series of interventions intended to make engineering students better communicators.

Contributors

Agent

Created

Date Created
2018-05

133428-Thumbnail Image.png

The History and Application of Optical Communications in Deep Space

Description

Optical Communications are at a high point of interest by the space engineering community. After successful projects like the Lunar Laser Communications Demonstration (LLCD), NASA has become interested in augmenting their current Deep Space Network (DSN) with optical communication links.

Optical Communications are at a high point of interest by the space engineering community. After successful projects like the Lunar Laser Communications Demonstration (LLCD), NASA has become interested in augmenting their current Deep Space Network (DSN) with optical communication links. One such link is Deep Space Optical Communications (DSOC) which will be launching with the Psyche mission. To gain a full understanding of the advantages of this network, this thesis will go over the history and benefits of optical communications both on Earth and in space. This thesis will then go in depth on NASAs DSOC project through an algorithmic implementation of the communications channel.

Contributors

Agent

Created

Date Created
2018-05