Browse Articles

A novel approach for predicting Alzheimer’s disease using machine learning on DNA methylation in blood

Adami et al. | Sep 20, 2023

A novel approach for predicting Alzheimer’s disease using machine learning on DNA methylation in blood
Image credit: National Cancer Institute

Here, recognizing the difficulty associated with tracking the progression of dementia, the authors used machine learning models to predict between the presence of cognitive normalcy, mild cognitive impairment, and Alzheimer's Disease, based on blood DNA methylation levels, sex, and age. With four machine learning models and two dataset dimensionality reduction methods they achieved an accuracy of 53.33%.

Read More...

Maximizing anaerobic biogas production using temperature variance

Verma et al. | Aug 03, 2023

Maximizing anaerobic biogas production using temperature variance

We conducted this research as our start-up's research that addresses the problem of biogas production in cow-dense regions like India. We hypothesized that the thermophilic temperature (45-60oC) would increase biogas production. The production process is much faster and more abundant at temperatures around 55-60oC.

Read More...

The effect of sports on teenagers’ depression symptoms during the COVID-19 pandemic

Düzgezen et al. | Jun 12, 2023

The effect of sports on teenagers’ depression symptoms during the COVID-19 pandemic
Image credit: Izuddin Helmi Adnan

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.

Read More...

Rhythmic lyrics translation: Customizing a pre-trained language model using stacked fine-tuning

Chong et al. | May 01, 2023

Rhythmic lyrics translation: Customizing a pre-trained language model using stacked fine-tuning
Image credit: Pixabay

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.

Read More...

Using economic indicators to create an empirical model of inflation

Kasera et al. | Dec 01, 2022

Using economic indicators to create an empirical model of inflation

Here, seeking to understand the correlation of 50 of the most important economic indicators with inflation, the authors used a rolling linear regression to identify indicators with the most significant correlation with the Month over Month Consumer Price Index Seasonally Adjusted (CPI). Ultimately the concluded that the average gasoline price, U.S. import price index, and 5-year market expected inflation had the most significant correlation with the CPI.

Read More...