During applied signal-detection (e.g., airport-baggage screening) human operators can be assisted in their decision-making process by automated devices. Automation implementation is aimed at increasing performance relative to unaided levels. Generally, this intended effect is empirically observed. However, operators consistently fall short of optimal levels of aided performance, indicating suboptimal aid-use...
Sound is a crucial aspect of the underwater environment for fishes – various species use sound to communicate, identify predators, navigate, and many other activities needed for survival in their habitat. Disruptions and disturbances in the natural soundscape can have important impacts on all these activities and are likely to...
Ornithology is an exciting field with novel research emerging everyday. Researchers in bioacoustics often spend hours within the wilderness recording bird calls to analyze later in their lab. The burden of sifting through hours of audio recordings from the field continues to remain a time-consuming and manual task, despite the...
This project uses field recordings to examine the levels of noise pollution present in both rural and urban areas by creating an artistic translation of these soundscapes, representative of how wild birds experience different environments. The field recordings capture not only what is present in a given soundscape, but what...
Automated systems have become increasingly important to human decision making and task performance in a wide variety of complex fields and situations. Decision aids, a specific form of automation, assist human operators in making complex decisions under conditions of uncertainty, such as air traffic control or combat identification. When humans...
This study compares three approaches in the design of an autonomous machine listening agent that predicts harbor porpoise ultrasonic echolocation clicks in diverse noise environments. Considering the temporal variations of noisy coastal ocean soundscapes which the harbor porpoises inhabit, we propose a leave-one-day-out (LODO) cross-validation strategy in the training of...
One way to support the transgender and gender diverse (TGD) community is by calling out microaggressions. Bystander readiness to call out microaggressions may be influenced by a bystander’s perception of harm caused by the microaggression and stereotypes surrounding the identity of the microaggressor. In this study, I focused on the...
Automatic Music Transcription is a growing area of interest in Music Information Retrieval, and recent research has shown promise using onset detection on spectrograms. We propose a deep learning model that takes raw audio as input in order to transcribe a solo piano performance from audio to MIDI without complicated...
In discrete event simulation, probability distributions are used as models of various unpredictable system components. The times between equipment failures and job processing times are examples of such random system components. The commonly recommended and taught practice for selecting a probability distribution to represent a random component is a multistep...
Integrated Distributed Electric Augmented Lift (IDEAL) applies upper surface blowing in a novel way to achieve electric short take-off and landing to meet the growing need for urban air transportation. Additional research on propulsion airframe interaction (PAI) with trailing edge flaps at low Reynolds numbers was necessary to advance the...