Browse Articles

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.

We are looking into natural ways to help hair grow better and stronger by studying keratin synthesis in human hair follicles. The reason for conducting this research was to have the ability to control hair growth through future innovations. We wanted to answer the question: How can we find natural ways to enhance hair growth by understanding the connection with natural resources, particularly keratin dynamics? The main focus of this experiment is understanding the promotion of keratin synthesis within human hair follicles, which is important for hair development and health. While keratin is essential for the growth and strength of body tissues, including skin and hair, our research hints at its specific synthesis within hair follicles. In our research utilizing castor oil, coconut oil, a turmeric and baking soda mixture, and a sugar, honey, and lemon mixture, we hypothesize that oils, specifically coconut oil and castor oil, will enhance keratin synthesis, whereas mixtures, such as the turmeric and baking soda mixture and the sugar, honey, and lemon mixture, will result in a decrease keratin synthesis. The methods used show how different natural substances influence keratin formation within the hair follicles. The experiment involved applying natural resources to hair strands and follicles, measuring their length under the microscope daily, and assessing their health and characteristics over seven days. In summary, our research helps us understand how hair grows better. We found that using natural items like essential oils effectively alters keratin growth within the hair follicles and hair strands.

The lexical decision task is designed to test aspects of vocabulary retrieval from short-term and long-term memory by prompting the subject to differentiate between words and non-words. From this task, researchers can determine the effects of certain stimuli on linguistic processing. Numerous studies have investigated the effects of music on various cognitive capacities, like memory and vocabulary. In the current study, we hypothesized that participants would show greater accuracy rates on the lexical decision task when exposed to a selected piece of classical music while completing the task, as compared to completing the task in silence. We tested this hypothesis on a group of 25 participants who completed the lexical decision task once in silence and once while listening to Beethoven's “Moonlight Sonata, 1st Movement”. The results suggest a positive association between the effects of classical background music and improved accuracy. Our results indicate that listening to certain types of music may enhance linguistic processes such as reading and writing. Further research with a larger group of participants is necessary to better understand the association between music and linguistic processing abilities.

Here, the authors sought to develop a new metric to evaluate the efficacy of baseball pitchers using machine learning models. They found that the frequency of balls, was the most predictive feature for their walks/hits allowed per inning (WHIP) metric. While their machine learning models did not identify a defining trait, such as high velocity, spin rate, or types of pitches, they found that consistently pitching within the strike zone resulted in significantly lower WHIPs.

The application of machine learning techniques has facilitated the automatic annotation of behavior in video sequences, offering a promising approach for ethological studies by reducing the manual effort required for annotating each video frame. Nevertheless, before solely relying on machine-generated annotations, it is essential to evaluate the accuracy of these annotations to ensure their reliability and applicability. While it is conventionally accepted that there cannot be a perfect annotation, the degree of error associated with machine-generated annotations should be commensurate with the error between different human annotators. We hypothesized that machine learning supervised with adequate human annotations would be able to accurately predict body parts from video sequences. Here, we conducted a comparative analysis of the quality of annotations generated by humans and machines for the body parts of sheep during treadmill walking. For human annotation, two annotators manually labeled six body parts of sheep in 300 frames. To generate machine annotations, we employed the state-of-the-art pose-estimating library, DeepLabCut, which was trained using the frames annotated by human annotators. As expected, the human annotations demonstrated high consistency between annotators. Notably, the machine learning algorithm also generated accurate predictions, with errors comparable to those between humans. We also observed that abnormal annotations with a high error could be revised by introducing Kalman Filtering, which interpolates the trajectory of body parts over the time series, enhancing robustness. Our results suggest that conventional transfer learning methods can generate behavior annotations as accurate as those made by humans, presenting great potential for further research.

Neuroinflammation and oxidative stress are both known to play a role in the occurrence and severity of seizures. This study tested effects of oxidative stress from seizures by evaluating the longevity, egg-laying, and electroshock resilience of C. elegans. Results revealed that oxidative stress and neuroinflammation diminish longevity and reproductivity while also increasing recovery time after seizures in C. elegans. This research can help lead to future studies and may also lead to finding new therapeutics for epilepsy.

Here, seeking to identify a method to locally produce and capture renewable energy in Hawai'i and other island communities, the authors built and tested a small-scale model wave energy converter. They tested various configurations of a floated magnet surrounded by a wire coal, where the motion of the magnet due to a wave results in induction current in the coil. While they identified methods to increase the voltage and current generated, they also found that corrosion results in significant deterioration.

Here, the authors considered the effects of relationship status and substance use on the mental health of colleges students, where they specifically examined their correlation with depression, anxiety, and the fear of missing out (FoMO). Through a survey of college students they found that those with higher substance misuse had higher levels of anxiety, depression, and FoMO, while those involved in longer-term relationships had lower levels of FoMo and alcohol use.

Here, seeking to identify the possible role of sports in helping teenagers navigate the troubles associated with societal changes during a pandemic, the authors surveyed 50 adolescents to collect Beck Depression Inventory scores. They found that 9 out of students with severe depressions did not do sports, while no significant relationship between depressive symptoms and either gender or place of exercise was observed.

Neural machine translation (NMT) is a software that uses neural network techniques to translate text from one language to another. However, one of the most famous NMT models—Google Translate—failed to give an accurate English translation of a famous Korean nursery rhyme, "Airplane" (비행기). The authors fine-tuned a pre-trained model first with a dataset from the lyrics domain, and then with a smaller dataset containing the rhythmical properties, to teach the model to translate rhythmically accurate lyrics. This stacked fine-tuning method resulted in an NMT model that could maintain the rhythmical characteristics of lyrics during translation while single fine-tuned models failed to do so.