Plant diseases can cause up to 50% crop yield loss for the popular tomato plant. A mobile device-based method to identify diseases from photos of symptomatic leaves via computer vision can be more effective due to its convenience and accessibility. To enable a practical mobile solution, a “shallow” convolutional neural networks (CNNs) with few layers, and thus low computational requirement but with high accuracy similar to the deep CNNs is needed. In this work, we explored if such a model was possible.

Here, recognizing the vastly different opinion held regarding device usage, the authors considered the effects of technology use on middle and high school students' learning effectiveness. Using an anonymous online survey they found partial support that device use at school increases learning effectiveness, but found strong support for a negative effect of technology use at home on learning effectiveness. Based on their findings they suggest that the efficacy of technology depends on environmental context along with other important factors that need consideration.

Using facial recognition as a use-case scenario, we attempt to identify sources of bias in a model developed using transfer learning. To achieve this task, we developed a model based on a pre-trained facial recognition model, and scrutinized the accuracy of the model’s image classification against factors such as age, gender, and race to observe whether or not the model performed better on some demographic groups than others. By identifying the bias and finding potential sources of bias, his work contributes a unique technical perspective from the view of a small scale developer to emerging discussions of accountability and transparency in AI.

This study explored the various effects of three different produce-based biofertilizers on pea plant growth, using red apple, pear, strawberry, and control treatments. It was hypothesized that the application of fruit biomatter would increase the growth of pea plants, with the application of strawberry biomatter having the most significant effect due to strawberries containing a higher nutrient content compared to pears and apples. Analysis confirmed the hypothesis. The application of strawberry biomatter could prove to be an effective way to increase plant growth in commercial agriculture.

Here, the authors investigated if dietary Omega-3 fatty acids could reduce the potential for cerebral cavernous malformations, which are brain lesions that occur due to a genetic mutation where high membrane permeability occurs between endothelial cell junctions. In a bovine-based study where some cows were fed an Omega-3 diet, the authors found the membranes of bovine blood cells increased in thickness with Omega-3 supplementation. As a result, they suggest that dietary Omega-3 could be considered as a possible preventative measure for cerebral cavernous malformations.

Modern artificial neural networks have been remarkably successful in various applications, from speech recognition to computer vision. However, it remains less clear whether they can implement abstract concepts, which are essential to generalization and understanding. To address this problem, the authors investigated the above vs. below task, a simple concept-based task that honeybees can solve, using a conventional neural network. They found that networks achieved 100% test accuracy when a visual target was presented below a black bar, however only 50% test accuracy when a visual target was presented below a reference shape.

Here seeking to identify a method to remove harmful microplastics from water, the authors investigated the viability of using electrolysis to degrade microplastics in tap water. Compared to control samples, they found electrolysis treatment to significantly the number of net microplastics, suggesting that this treatment could potentially implemented into homes or drinking water treatment facilities.

Despite major advances in gender equality, men still far outnumber women in science, technology, engineering and math (STEM) professions. The purpose of this project was to determine whether mindset could affect a student’s future career choices and whether this effect differed based on gender. When looking within the gender groups, 86% of females who had a growth mindset were likely to consider a “male” career, whereas only 16% of females with fixed mindset would likely to consider a “male” career. Especially for girls, cultivating a growth mindset may be a great strategy to address the problem of fewer girls picking STEM careers.

In this study, the authors conducted a statistical investigation into the history of position-based racial segregation in the NFL. Specifically, they focused on the cornerback position, which they hypothesized would be occupied disproportionately by black players due to their historical stereotyping as more suitable for positions requiring extreme athletic ability. Using publicly available datasets on the demographics of NFL players over the past several decades, they confirmed their hypothesis that the cornerback position is skewed towards black players. They additionally discovered that, unlike in the quarterback position, this trend has shown no sign of decreasing over time.

In this study, the authors test whether providing a larger dataset of glass transition temperatures (T_g) to train the machine-learning platform Polymer Genome would improve its accuracy. Polymer Genome is a machine learning based data-driven informatics platform for polymer property prediction and T_g is one property needed to design new polymers in silico. They found that training the model with their larger, curated dataset improved the algorithm's T_g, providing valuable improvements to this useful platform.