Browse Articles

Here the authors investigated the relationship between fitness-related social media and the high usage of performance-enhancing drugs (PEDs) specifically by men in the US age 18-35. In a survey with 149 participants they identified that young men that use fitness-related social media are more likely to use PEDs. Their results suggest the necessity to consider potential risk behaviors which may be related to social media consumption.

Here, the authors investigated the integration of large language models (LLMs) with drug target affinity predictors (DTAPs) to improve drug repurposing, demonstrating a significant increase in prediction accuracy, particularly with GPT-4, for psychotropic drugs and the sigma-1 receptor. This novel approach offers to potentially accelerate and reduce the cost of drug discovery by efficiently identifying new therapeutic uses for existing drugs.

The mountain chain of the Western Ghats on the Indian peninsula, a UNESCO World Heritage site, is home to about 200 frog species, 89 of which are endemic. Distinctive to each frog species, their vocalizations can be used for species recognition. Manually surveying frogs at night during the rain in elephant and big cat forests is difficult, so being able to autonomously record ambient soundscapes and identify species is essential. An effective machine learning (ML) species classifier requires substantial training data from this area. The goal of this study was to assess data augmentation techniques on a dataset of frog vocalizations from this region, which has a minimal number of audio recordings per species. Consequently, enhancing an ML model’s performance with limited data is necessary. We analyzed the effects of four data augmentation techniques (Time Shifting, Noise Injection, Spectral Augmentation, and Test-Time Augmentation) individually and their combined effect on the frog vocalization data and the public environmental sounds dataset (ESC-50). The effect of combined data augmentation techniques improved the model's relative accuracy as the size of the dataset decreased. The combination of all four techniques improved the ML model’s classification accuracy on the frog calls dataset by 94%. This study established a data augmentation approach to maximize the classification accuracy with sparse data of frog call recordings, thereby creating a possibility to build a real-world automated field frog species identifier system. Such a system can significantly help in the conservation of frog species in this vital biodiversity hotspot.

Authors examine the effectiveness of Large Language Models (LLMs) like BERT, MathBERT, and OpenAI GPT-3.5 in assisting middle school students with math word problems, particularly following the decline in math performance post-COVID-19.

The authors looked at different models of semantic segmentation to determine which may be best used in the future for segmentation of CT scans to help diagnose certain conditions.

The authors test the effectiveness of machine learning to predict onset of cardiovascular disease.

In this article the authors look at sugar consumption and the relationship to productivity in the work/labor force.

Athletes with performance anxiety may struggle to play their best and enjoy the game. Various factors may impact how much anxiety an athlete feels, including how much experience they have in the sport. Concha-Ortiz and Navins survey teenage club volleyball players to look for relationships between years of experience and performance anxiety symptoms.

With growing demands for ethanol, many researchers are turning to Panicum virgatum (switchgrass) as a feedstock of cellulosic ethanol. In this study, Ferris and Gillan examine the germination, biomass, nitrogen, survival, and chlorophyll absorbance of two switchgrass cultivars of grown in competition with Bromus inermis (smooth brome) with two varying levels of nitrogen fertilizer. Results presented indicate that during establishment, competition from other species has a greater effect than nitrogen fertilizer.

Global reliance on extractive energy sources has many downsides, among which are inconsistent supply and consequent price volatility that distress companies and consumers. It is unclear if renewable energy offers stable and affordable solutions to extractive energy sources. The cost of solar energy generation has decreased sharply in recent years, prompting a surge of installations with a range of financing options. Even so, most existing options require upfront payment, making installation inaccessible for towns with limited financial resources. The primary objective of our research is to examine the use of green bonds to finance solar energy systems, as they eliminate the need for upfront capital and enable repayment through revenue generated over time. We hypothesized that if we modeled the usage of green bonds to finance the installation of a solar energy system in New Jersey, then the revenue generated over the system’s lifetime would be enough to repay the bond. After modeling the financial performance of a proposed solar energy-producing carport in Madison, New Jersey, financed with green bonds, we found that revenue from solar energy systems successfully covered the annual green bond payments and enabled the installers to obtain over 50% of the income for themselves. Our research demonstrated green bonds as a promising option for New Jersey towns with limited financial resources seeking to install solar energy systems, thereby breaking down a financial barrier.