With Great Power Comes Great Responsibility: Uses and Applications of Machine Learning in Commercial Aviation, A Literature Review

Description
This Honors thesis was written in partial fulfillment of the requirements for a Bachelor of Science in Human Systems Engineering with Honors. The project consists of a literature review that explores the uses and applications of Machine Learning and Artificial

This Honors thesis was written in partial fulfillment of the requirements for a Bachelor of Science in Human Systems Engineering with Honors. The project consists of a literature review that explores the uses and applications of Machine Learning and Artificial Intelligence techniques in the field of commercial aviation. After a brief introduction and explanation of the most commonly used algorithms in the field of aviation, it explores the applications of Machine Learning techniques for risk reduction, and for the betterment of in-flight operations, and pilot selection, training, and assessment.
Date Created
2023-12
Agent

An Exploration of Resilience for Complex Sociotechnical Human, Artificial Intelligence, and Robot Teams

189223-Thumbnail Image.png
Description
What makes a human, artificial intelligence, and robot team (HART) succeed despite unforeseen challenges in a complex sociotechnical world? Are there personalities that are better suited for HARTs facing the unexpected? Only recently has resilience been considered specifically at the

What makes a human, artificial intelligence, and robot team (HART) succeed despite unforeseen challenges in a complex sociotechnical world? Are there personalities that are better suited for HARTs facing the unexpected? Only recently has resilience been considered specifically at the team level, and few studies have addressed team resilience for HARTs. Team resilience here is defined as the ability of a team to reorganize team processes to rebound or morph to overcome an unforeseen challenge. A distinction from the individual, group, or organizational aspects of resilience for teams is how team resilience trades off with team interdependent capacity. The following study collected data from 28 teams comprised of two human participants (recruited from a university populace) and a synthetic teammate (played by an experienced experimenter). Each team completed a series of six reconnaissance missions presented to them in a Minecraft world. The research aim was to identify how to better integrate synthetic teammates for high-risk, high-stress dynamic operations to boost HART performance and HART resilience. All team communications were orally over Zoom. The primary manipulation was the communication given by the synthetic teammate (between-subjects, Task or Task+): Task only communicated the essentials, and Task+ offered clear and concise communications of its own capabilities and limitations. Performance and resilience were measured using a primary mission task score (based upon how many tasks teams completed), time-based measures (such as how long it took to recognize a problem or reorder team processes), and a subjective team resilience score (calculated from participant responses to a survey prompt). The research findings suggest the clear and concise reminders from Task+ enhanced HART performance and HART resilience during high-stress missions in which the teams were challenged by novel events. An exploratory study regarding what personalities may correlate with these improved performance metrics indicated that the Big Five trait taxonomies of extraversion and conscientiousness were positively correlated, whereas neuroticism was negatively correlated with higher HART performance and HART resilience. Future integration of synthetic teammates must consider the types of communications that will be offered to maximize HART performance and HART resilience.
Date Created
2023
Agent

The Impact of Team Cognitive Load on Compliance with Artificial Social Intelligence’s Advice and Its Relationship to Team Performance

187812-Thumbnail Image.png
Description
This study focuses on the impact of team cognitive load on compliance with an Artificial Social Intelligence agent’s (ASI) advice. It also expands on some of the factors that influence team performance, including cognitive load, compliance, and ASI interaction dynamics.

This study focuses on the impact of team cognitive load on compliance with an Artificial Social Intelligence agent’s (ASI) advice. It also expands on some of the factors that influence team performance, including cognitive load, compliance, and ASI interaction dynamics. The study design comprised three types of ASI agents that advised all-human teams, each generating their advice based on variations in message length and frequency: long messages at low frequency, moderate lengths and frequency, and short messages at high frequency. Three team members collaborated to locate and save victims in a simulated Urban Search and Rescue (USAR) task environment, while the ASI provided intervention messages (i.e., advice) through text chat. The ASI monitored the team members in the USAR task environment via its interaction-based analytic components. Then, ASI predicted human team members’ behaviors based on their past and current interactions to provide teamwork interventions to maintain team effectiveness. The findings indicate that (1) team cognitive load was not associated with team compliance with ASI advice, (2) both team cognitive load and compliance with ASI messages were positively related to team performance score, (3) Teams assigned an ASI that had moderate advice length and frequency performed better than the teams that were paired with the other two types of ASIs which demonstrated either short message length and high frequency or long message length and low frequency. Overall, these findings show that the ASI advice interventions are helpful as long as they have moderate-level message length and frequency and are complied with by the team members in the USAR task. Future designs of ASI agents should target these types of intervention message characteristics and prioritize compliance to improve team performance.
Date Created
2023
Agent

Unintentional Costs of Vehicle Warning Modality for Driving Hazards

187611-Thumbnail Image.png
Description
Proper allocation of attention while driving is imperative to driver safety, as well as the safety of those around the driver. There is no doubt that in-vehicle alerts can effectively direct driver attention. In fact, visual, auditory, and tactile alert

Proper allocation of attention while driving is imperative to driver safety, as well as the safety of those around the driver. There is no doubt that in-vehicle alerts can effectively direct driver attention. In fact, visual, auditory, and tactile alert modalities have all shown to be more effective than no alert at all. However, research on in-vehicle alerts has primarily been limited to single-hazard scenarios. The current research examines the effects of in-vehicle alert modality on driver attention towards simultaneously occurring hazards. When a driver is presented with multiple stimuli simultaneously, there is the risk that they will experience alert masking, when one stimulus is obscured by the presence of another stimulus. As the number of concurrent stimuli increases, the ability to report targets decreases. Meanwhile, the alert acts as another target that they must also process. Recent research on masking effects of simultaneous alerts has shown masking to lead to breakdowns in detection and identification of alarms during a task, outlining a possible cost of alert technology. Additionally, existing work has shown auditory alerts to be more effective in directing driver attention, resulting in faster reaction times (RTs) than visual alerts. Multiple Resource Theory suggests that because of the highly visual nature of driving, drivers may have more auditory resources than visual resources available to process stimuli without becoming overloaded. Therefore, it was predicted that auditory alerts would be more effective in allowing drivers to recognize both potential hazards, measured though reduced brake reaction times and increased accuracy during a post-drive hazard observance question. The current study did not support the hypothesis. Modality did not result in a significant difference in drivers’ attention to simultaneously occurring hazards. The salience of hazards in each scenario seemed to make the largest impact on whether participants observed the hazard. Though the hypothesis was not supported, there were several limitations. Additionally, and regardless, the study results did point to the importance of further research on simultaneously occurring hazards. These scenarios pose a risk to drivers, especially when their attention is allocated to only one of the hazards.
Date Created
2023
Agent

Examining Post-Error Behavior in a Complex Multitasking Environment

168319-Thumbnail Image.png
Description
Human operators are more prone to errors under high-workload conditions. However, error-commission research in cognitive science has been limited to studying behavior in single-choice reaction time tasks, which do not represent the complex multitasking scenarios faced in the real-world. In

Human operators are more prone to errors under high-workload conditions. However, error-commission research in cognitive science has been limited to studying behavior in single-choice reaction time tasks, which do not represent the complex multitasking scenarios faced in the real-world. In the current paper, prior evidence for a cognitive error-monitoring mechanism was applied toward predictions for how humans would react after making errors in a more ecologically valid multitasking paradigm. Previous work on neural and behavioral indices of error-monitoring strongly supports the idea that errors are distracting and can deplete attentional resources. Therefore, it was predicted that after committing an error, if a subject is subsequently presented with two simultaneously initiated task alerts (a conflict trial), they would be more likely to miss their response opportunity for one task and stay tunneled on the other task that originally caused the error. Additionally, it was predicted that this effect would dissipate after several seconds (under different lag conditions), making the error cascade less likely when subsequent tasks are delayed before presentation. A Multi-Attribute Task Battery was used to present the paradigm and collect post-error and post-correct performance measures. The results supported both predictions: Post-error accuracy was significantly lower as compared to post-correct accuracy (as measured through post-trial error rates). Post-trial error rates were also higher at shorter lags and dissipated over time, and the effects of pre-conflict performance on post-trial error rates was especially noticeable at shorter lags (although the interaction was not statistically significant). A follow-up analysis also demonstrated that following errors (as opposed to following correct trials), participants clicked significantly more on the task that originally caused the error (regardless of lag). This continued task-engagement further supports the idea that errors lead to a cognitive tunneling effect. The study provides evidence that in a multitasking scenario, the human cognitive error-monitoring mechanism can be maladaptive, where errors beget more errors. Additionally, the experimental paradigm provides a bridge between concepts originating in highly controlled methods of cognitive science research and more applied scenarios in the field of human factors.
Date Created
2021
Agent

Lyons First Draft (Spring 2022)

165774-Thumbnail Image.png
Description

During the height of COVID-19 in the summer of 2020, most major sports leagues were shut down or postponed, to limit the spread of COVID-19. However, people still yearned for the community of cheering on their favorite team. To that

During the height of COVID-19 in the summer of 2020, most major sports leagues were shut down or postponed, to limit the spread of COVID-19. However, people still yearned for the community of cheering on their favorite team. To that end, The Game Band, a Los Angeles-based game development studio, decided to make America's favorite pastime, baseball, virtual. Just like that, Blaseball was born. In this creative project, the Season Twelve version of Blaseball.com was subjected to analysis of its user interface and user experience elements by the author of this paper in the role of the researcher. The research questions posited by this project were as follows: - What user interface/user experience elements of the Season Twelve version of Blaseball.com were effective, and what elements detracted from the purpose of the site? - What recommendations could be made by the researcher to improve the user experience and allow for a more effective user experience of the Season Twelve version of Blaseball.com? To answer these questions, two deliverables were decided upon. The first was a research study consisting of a usability survey and interviews with web developers who worked on Blaseball or Blaseball-related projects. The second deliverable was an industry-level analysis of the Season Twelve version of Blaseball.com to be presented as a culmination of the research and work. Through this process, it had been discovered that while the site was simplistic and could easily direct users to other pages, as intended by the developers, UI elements on individual pages confused and misled users. As such, clarifications and a more in-depth UI were recommended.

Date Created
2022-05
Agent

Lyons Final Project (Spring 2022)

165773-Thumbnail Image.png
Description

During the height of COVID-19 in the summer of 2020, most major sports leagues were shut down or postponed, to limit the spread of COVID-19. However, people still yearned for the community of cheering on their favorite team. To that

During the height of COVID-19 in the summer of 2020, most major sports leagues were shut down or postponed, to limit the spread of COVID-19. However, people still yearned for the community of cheering on their favorite team. To that end, The Game Band, a Los Angeles-based game development studio, decided to make America's favorite pastime, baseball, virtual. Just like that, Blaseball was born. In this creative project, the Season Twelve version of Blaseball.com was subjected to analysis of its user interface and user experience elements by the author of this paper in the role of the researcher. The research questions posited by this project were as follows: - What user interface/user experience elements of the Season Twelve version of Blaseball.com were effective, and what elements detracted from the purpose of the site? - What recommendations could be made by the researcher to improve the user experience and allow for a more effective user experience of the Season Twelve version of Blaseball.com? To answer these questions, two deliverables were decided upon. The first was a research study consisting of a usability survey and interviews with web developers who worked on Blaseball or Blaseball-related projects. The second deliverable was an industry-level analysis of the Season Twelve version of Blaseball.com to be presented as a culmination of the research and work. Through this process, it had been discovered that while the site was simplistic and could easily direct users to other pages, as intended by the developers, UI elements on individual pages confused and misled users. As such, clarifications and a more in-depth UI were recommended.

Date Created
2022-05
Agent

Lyons Usability Report (Spring 2022)

165772-Thumbnail Image.png
Description

During the height of COVID-19 in the summer of 2020, most major sports leagues were shut down or postponed, to limit the spread of COVID-19. However, people still yearned for the community of cheering on their favorite team. To that

During the height of COVID-19 in the summer of 2020, most major sports leagues were shut down or postponed, to limit the spread of COVID-19. However, people still yearned for the community of cheering on their favorite team. To that end, The Game Band, a Los Angeles-based game development studio, decided to make America's favorite pastime, baseball, virtual. Just like that, Blaseball was born. In this creative project, the Season Twelve version of Blaseball.com was subjected to analysis of its user interface and user experience elements by the author of this paper in the role of the researcher. The research questions posited by this project were as follows: - What user interface/user experience elements of the Season Twelve version of Blaseball.com were effective, and what elements detracted from the purpose of the site? - What recommendations could be made by the researcher to improve the user experience and allow for a more effective user experience of the Season Twelve version of Blaseball.com? To answer these questions, two deliverables were decided upon. The first was a research study consisting of a usability survey and interviews with web developers who worked on Blaseball or Blaseball-related projects. The second deliverable was an industry-level analysis of the Season Twelve version of Blaseball.com to be presented as a culmination of the research and work. Through this process, it had been discovered that while the site was simplistic and could easily direct users to other pages, as intended by the developers, UI elements on individual pages confused and misled users. As such, clarifications and a more in-depth UI were recommended.

Date Created
2022-05
Agent

An Analysis and Exploration of the User Interface and User Experience Elements and
Design Principles Present in The Game Band’s Blaseball

Description
During the height of COVID-19 in the summer of 2020, most major sports leagues were shut down or postponed, to limit the spread of COVID-19. However, people still yearned for the community of cheering on their favorite team. To that

During the height of COVID-19 in the summer of 2020, most major sports leagues were shut down or postponed, to limit the spread of COVID-19. However, people still yearned for the community of cheering on their favorite team. To that end, The Game Band, a Los Angeles-based game development studio, decided to make America's favorite pastime, baseball, virtual. Just like that, Blaseball was born. In this creative project, the Season Twelve version of Blaseball.com was subjected to analysis of its user interface and user experience elements by the author of this paper in the role of the researcher. The research questions posited by this project were as follows: - What user interface/user experience elements of the Season Twelve version of Blaseball.com were effective, and what elements detracted from the purpose of the site? - What recommendations could be made by the researcher to improve the user experience and allow for a more effective user experience of the Season Twelve version of Blaseball.com? To answer these questions, two deliverables were decided upon. The first was a research study consisting of a usability survey and interviews with web developers who worked on Blaseball or Blaseball-related projects. The second deliverable was an industry-level analysis of the Season Twelve version of Blaseball.com to be presented as a culmination of the research and work. Through this process, it had been discovered that while the site was simplistic and could easily direct users to other pages, as intended by the developers, UI elements on individual pages confused and misled users. As such, clarifications and a more in-depth UI were recommended.
Date Created
2022-05
Agent

Team Situation Awareness in Next Generation Combat Vehicle

161495-Thumbnail Image.png
Description
In human-autonomy teams (HATs), the human needs to interact with one or more autonomous agents, and this new type of interaction is different than the existing human-to-human interaction. Next Generation Combat Vehicles (NGCVs), which are envisioned for the U.S. military

In human-autonomy teams (HATs), the human needs to interact with one or more autonomous agents, and this new type of interaction is different than the existing human-to-human interaction. Next Generation Combat Vehicles (NGCVs), which are envisioned for the U.S. military are associated with the concept of HAT. As NGCVs are in the early stage of development, it is necessary to develop different training methods and measures for team effectiveness. The way team members communicate and task complexity are factors affecting team efficiency. This study analyzes the impact of two interaction strategies and task complexity on team situation awareness among 22 different teams. Teams were randomly assigned different interaction conditions and went through two missions to finish their assigned tasks. Results indicate that the team with the procedural interaction strategy had better team situation awareness according to the Coordinated Awareness of the Situation by Teams (CAST) scores on the artillery calls. However, the difference between the strategies was not found on CAST scores of perturbations, map accuracy, or Situation Awareness Global Assessment Technique (SAGAT) scores. Additionally, the impact of task complexity on the team situation awareness was not found. Implications and suggestions for future work are discussed.
Date Created
2021
Agent