"Collaborative filtering algorithms’ performances have been evaluated using a variety of metrics.
These metrics, such as Mean Absolute Error and Precision, have often ignored recommendations for
which they do not have data. Ignoring these recommendations has provided numbers which do not
accurately represent the user experience. Qualitatively we have seen...
Standard geostatistical models used in abundance prediction assume that observed counts on each site are made without error. However, in some wildlife populations, assuming perfect detection of animal or plant counts is unrealistic.
We first construct an adjustment to a finite population block kriging (FPBK) estimator that allows the possibility...
Two striking characteristics of human beings are the diversity of resources that we use to sustain our lives and the extent to which we engage in coordinated, collective efforts to obtain and consume these resources. Together, these two characteristics are the foundation of human subsistence patterns. In many remote Alaskan...
Collaborative filtering (CF)-based recommender systems predict what items a user will like or find useful based on the recommendations (active or implicit) of other members of a networked community. In spite of more than ten years of research, there is little consensus on state-of-the-art knowledge regarding CF predictive algorithms. There...
The variety of natural disasters provide different sets of characteristics and properties with unique challenges. One significant difference between hazard types is prewarning lead time, the amount of time individuals have from a potential warning to the disaster occurring. Rapid onset disasters may not provide an official warning about a...
Long-term, large-scale studies of meta-ecosystems provide critical information about how global change influences communities. In my dissertation, I analyzed data from studies encompassing 18 years (2006 – 2023) and over 1,000 km of coastline to investigate drivers of rocky intertidal community structure and dynamics. Specifically, I explored the roles of...
How should reinforcement learning (RL) agents explain themselves to humans not trained in AI? To gain insights into this question, we conducted a 124 participant, four-treatment experiment to compare participants’ mental models of an RL agent in the context of a simple Real-Time Strategy (RTS) game. The four treatments isolated...
Dramatic and ongoing changes pervading the Arctic and subarctic seas over
recent decades have motivated this effort to track and better understand hydrographic
variability using chemical tracers. Particular emphasis has been paid to differentiating
freshwater contributions to upper layers: namely Pacific water, meteoric water, and
sea-ice melt/formation.
Data collected in...
Novel approaches to crop load management of pear orchards in the Pacific Northwest (PNW) are necessary, but will need to vary according to the unique vegetative and reproductive growth habits of the cultivar. 'D'Anjou' is vigorous and non-precocious; thus, strategies to limit vigor and induce early fruiting are required. In...
The Critical Power - W’ model has many advantages compared to the traditional VO2max test, including tracking fitness changes over time in well trained athletes, predicting performances due to its discrete aerobic and high intensity tolerance variables, and prescribing exercise intensities with increased accuracy. However, a major disadvantage of this...