Accurate estimation of the amount of water used by trees is important for a variety of agricultural applications. There are several current methodologies for measuring sap flow and water use in trees, however the heat ratio method has been identified as the ideal due to its ability to measure low...
The agricultural industry in the Western United States continues to possess issues of overwatering, accounting for over 80% of consumed water per year in the country. While technologies such as satellite imaging and sensor networks have slowly improved irrigation Best Management Practices to reduce superfluous water consumption, limitations associated with...
Project Loom is a system of sensors, actuators, processors, and wireless connectivity chips that the user can pick and choose from in order to create an Internet of Things application that fits their desired needs. The modularity of the system and ease of use allows for the user to create...
Currently available soil moisture sensors have intrinsic limitations that limit their adoption by industry. Depending on the technology, these limitations may include high costs, battery requirements, precice manual installation, high cost, and/or constrictive legislation that regulates their use. A passive soil moisture sensing system based around RFID technology would allay...
User studies in human-robot interaction and social robotics in general involve human participants and their reactions, observations and expectations of robots. This thesis presents two innovative experimental methods aimed at gaining access to high-stakes social data not typically collectable with traditional user studies. The Actor Method provides access to data...
The SpiderHarp is a bio-inspired electronic musical instrument that uses a localization algorithm developed at Oregon State University to translate plucks of its strings into musical notes. This localization algorithm was inspired by the way spiders locate prey in their webs. The SpiderHarp frame, sensors, and web design are also...
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...
Research in geoscience often requires transmission of significant amounts of data from remote locations. The emergence of microcontrollers and open-source sensors are allowing connectivity to affordable, distributed in-situ monitoring. This report describes the OPEnS Hub, a modular data hub orders of magnitude cheaper than commercial dataloggers when scaled to multiple...
In Earth science, we must often collect data from sensors installed in remote locations. Retrieving these data and storing them can be challenging. Present options include proprietary commercial dataloggers, communication devices, and protocols with rigid software and data structures that may require ongoing expenses. While there are open-source solutions that...