Colorimetric assays are an important tool in point-of-care testing that offers several advantages to traditional testing methods such as rapid response times and inexpensive costs. A factor that currently limits the portability and accessibility of these assays are methods that can objectively determine the results of these assays. Current solutions consist of creating a test reader that standardizes the conditions the strip is under before being measured in some way. However, this increases the cost and decreases the portability of these assays. The focus of this study is to create a machine learning algorithm that can objectively determine results of colorimetric assays under varying conditions. To ensure the flexibility of a model to several types of colorimetric assays, three models were trained on the same convolutional neural network with different datasets. The images these models are trained on consist of positive and negative images of ETG, fentanyl, and HPV Antibodies test strips taken under different lighting and background conditions. A fourth model is trained on an image set composed of all three strip types. The results from these models show it is able to predict positive and negative results to a high level of accuracy.
Studies of animal contests often focus solely on a single static measurement of fighting ability, such as the size or the strength of the individual. However, recent studies have highlighted the importance of individual variation in the dynamic behaviors used during a fight, such as, assessment strategies, decision making, and fine motor control, as being strong predictors of the outcome of aggression. Here, I combined morphological and behavioral data to discover how these features interact during aggressing interactions in male virile crayfish, Faxonius virilis. I predicted that individual variation in behavioral skill for decision making (i.e., number of strikes thrown), would determine the outcome of contest success in addition to morphological measurements (e.g. body size, relative claw size). To evaluate this prediction, I filmed staged territorial interactions between male F. virilis and later analyzed trial behaviors (e.g. strike, pinches, and bout time) and aggressive outcomes. I found very little support for skill to predict win/loss outcome in trials. Instead, I found that larger crayfish engaged in aggression for longer compared to smaller crayfish, but that larger crayfish did not engage in a greater number of claw strikes or pinches when controlling for encounter duration. Future studies should continue to investigate the role of skill, by using finer-scale techniques such as 3D tracking software, which could track advanced measurements (e.g. speed, angle, and movement efficiency). Such studies would provide a more comprehensive understanding of the relative influence of fighting skill technique on territorial contests.