In this study, the authors investigate the effects of different algal growth media on algae's ability to perform carbon dioxide biofixation, or utilize carbon dioxide by fixing it into fatty acids within the cells. More specifically, carbon dioxide biofixation of Chlorella vulgaris was cultured in one of four media options and carbon dioxide was measured and compared to controls. The study results demonstrated that the use of media can enhance algae's capacity for biofixation and this has important implications for developing methods to reduce carbon dioxide in the environment.
Additive manufacturing (AM) is transforming the production of complex metal parts, but challenges like internal cracking can arise, particularly in critical sectors such as aerospace and automotive. Traditional methods to assess cracking susceptibility are costly and time-consuming, prompting the use of machine learning (ML) for more efficient predictions. This study developed a multi-model ML pipeline that predicts solidification cracking susceptibility (SCS) more accurately by considering secondary alloy properties alongside composition, with Random Forest models showing the best performance, highlighting a promising direction for future research into SCS quantification.
Pulmonary diseases like lung cancer and valley fever pose serious health challenges, making accurate and rapid diagnostics essential. This study developed a MATLAB-based software tool that uses computer vision techniques to differentiate between these diseases by analyzing features of lung nodules in CT scans, achieving higher precision than traditional methods.
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.
Research suggests that less effective styles of parenting tend to negatively affect grades, and more effective styles tend to produce higher grades. In this study, the authors verify previous research and confirm such relationships in a sample of African American students in a college preparatory program. By obtaining students’ perception of their school’s climate and parent’s parenting styles by various methods, the authors determined correlated these perceptions to student grades. They found no significant relationship between school climate and academic achievement.
Coronary heart disease (CHD) is the leading cause of death in the U.S., responsible for nearly 700,000 deaths in 2021, and is marked by artery clogging that can lead to heart attacks. Traditional prediction methods require expensive clinical tests, but a new study explores using machine learning on demographic, clinical, and behavioral survey data to predict CHD.
Reinforcement learning (RL) is a form of machine learning that can be harnessed to develop artificial intelligence by exposing the intelligence to multiple generations of data. The study demonstrates how reply buffer reward mechanics can inform the creation of new pruning methods to improve RL efficiency.
This study focused on finding more sustainable growing methods that reduce chemical fertilizer or water usage and can be used at the household level for garden plants. Metrics for healthy plant growth were height at first bloom, growing time, and survival rate. The Deep Water Culture (DWC) treatment for garden cress plants significantly increased the height at first bloom compared to the control group. For rates of surviving plants, the treatments had little effect on garden cress, but the Eggshell Grounds, Wick System, and DWC system groups outperformed the control group for marigolds.
How accurate are DNA parentage tests? In this study, the authors hypothesized that current parentage tests are reliable if the analysis involves only one or a few families of yellow perch fish Perca flavescens. Their results suggest that DNA parentage tests are reliable as long as the right methods are used, since these tests involve only one family in most cases, and that the results from parentage analyses of large populations can only be used as a reference.
In order for cells to successfully multiply, a number of proteins are needed to correctly coordinate the replication and division process. In this study, students use fluorescence microscopy and molecular methods to study CCDC11, a protein critical in the formation of cilia. Interestingly, they uncover a new role for CCDC11, critical in the cell division across multiple human cell lines.
