Browse Articles

The authors train a neural network to detect text-based emotions including joy, sadness, anger, fear, love, and surprise.

Authors address the gender disparity in STEM fields, examining changes in gender diversity across male-dominated undergraduate programs over 19 years at 24 top universities. Analyzing data from NCES IPEDS, it identifies STEM as persistently male-dominated but notes increasing gender diversity in many disciplines, particularly in recent years. Results indicate that higher-ranked universities in disciplines like computer science and mechanical engineering show a weak correlation with improved gender diversity, suggesting effective initiatives can mitigate the gender gap in STEM, despite ongoing challenges.

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.

Osteosarcoma is a type of bone cancer that affects young adults and children. Early diagnosis of osteosarcoma is crucial to successful treatment. The current methods of diagnosis, which include imaging tests and biopsy, are time consuming and prone to human error. Hence, we used deep learning to extract patterns and detect osteosarcoma from histological images. We hypothesized that the combination of two different technologies (transfer learning and data augmentation) would improve the efficacy of osteosarcoma detection in histological images. The dataset used for the study consisted of histological images for osteosarcoma and was quite imbalanced as it contained very few images with tumors. Since transfer learning uses existing knowledge for the purpose of classification and detection, we hypothesized it would be proficient on such an imbalanced dataset. To further improve our learning, we used data augmentation to include variations in the dataset. We further evaluated the efficacy of different convolutional neural network models on this task. We obtained an accuracy of 91.18% using the transfer learning model MobileNetV2 as the base model with various geometric transformations, outperforming the state-of-the-art convolutional neural network based approach.

End Stage Renal Disease (ESRD) is a growing health concern in the United States. The authors of this study present a study of ESRD incidence over a 32-year period, providing an in-depth look at the contributions of age, race, gender, and underlying medical factors to this disease.

This article describes the classification of medical text data using vector databases and text embedding. Various large language models were used to generate this medical data for the classification task.

In this study, the authors develop an architecture to implement in a cloud-based database used by law firms to ensure confidentiality, availability, and integrity of attorney documents while maintaining greater efficiency than traditional encryption algorithms. They assessed whether the architecture satisfies necessary criteria and tested the overall file sizes the architecture could process. The authors found that their system was able to handle larger file sizes and fit engineering criteria. This study presents a valuable new tool that can be used to ensure law firms have adequate security as they shift to using cloud-based storage systems for their files.

One common age-related health problem is the loss of bone mineral density (BMD), which can lead to a variety of negative health outcomes, including increased risk of spinal fracture. In this study, the authors investigate risk factors that may be predictive of an individual's risk of spinal fracture. Their findings provide valuable information that clinicians can use in patient evaluations.

Although there has been great progress in the field of Natural language processing (NLP) over the last few years, particularly with the development of attention-based models, less research has contributed towards modeling keystroke log data. State of the art methods handle textual data directly and while this has produced excellent results, the time complexity and resource usage are quite high for such methods. Additionally, these methods fail to incorporate the actual writing process when assessing text and instead solely focus on the content. Therefore, we proposed a framework for modeling textual data using keystroke-based features. Such methods pay attention to how a document or response was written, rather than the final text that was produced. These features are vastly different from the kind of features extracted from raw text but reveal information that is otherwise hidden. We hypothesized that pairing efficient machine learning techniques with keystroke log information should produce results comparable to transformer techniques, models which pay more or less attention to the different components of a text sequence in a far quicker time. Transformer-based methods dominate the field of NLP currently due to the strong understanding they display of natural language. We showed that models trained on keystroke log data are capable of effectively evaluating the quality of writing and do it in a significantly shorter amount of time compared to traditional methods. This is significant as it provides a necessary fast and cheap alternative to increasingly larger and slower LLMs.

Social media is widely used and easily accessible for adolescents, it has the potential to increase STEM (Science, Technology, Engineering, and Math) identity in girls. We aimed to investigate the effects of exposure to counter-stereotypical portrayals of women in STEM on social media on the STEM identity of adolescent girls. The study concluded that social media alone may not be an effective tool to increase STEM identity in girls. Social media can still be used as a complementary tool to support and encourage women in STEM, but it should not be relied upon solely to address the gender disparity in STEM fields.