In this study, the authors test whether providing a larger dataset of glass transition temperatures (Tg) to train the machine-learning platform Polymer Genome would improve its accuracy. Polymer Genome is a machine learning based data-driven informatics platform for polymer property prediction and Tg is one property needed to design new polymers in silico. They found that training the model with their larger, curated dataset improved the algorithm's Tg, providing valuable improvements to this useful platform.
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.
In the United States, there are currently 17.8 million affected by atopic dermatitis (AD), commonly known as eczema. It is characterized by itching and skin inflammation. AD patients are at higher risk for infections, depression, cancer, and suicide. Genetics, environment, and stress are some of the causes of the disease. With the rise of personalized medicine and the acceptance of gene-editing technologies, AD-related variations need to be identified for treatment. Genome-wide association studies (GWAS) have associated the Filaggrin (FLG) gene with AD but have not identified specific problematic single nucleotide polymorphisms (SNPs). This research aimed to refine known SNPs of FLG for gene editing technologies to establish a causal link between specific SNPs and the diseases and to target the polymorphisms. The research utilized R and its Bioconductor packages to refine data from the National Center for Biotechnology Information's (NCBI's) Variation Viewer. The algorithm filtered the dataset by coding regions and conserved domains. The algorithm also removed synonymous variations and treated non-synonymous, frameshift, and nonsense separately. The non-synonymous variations were refined and ordered by the BLOSUM62 substitution matrix. Overall, the analysis removed 96.65% of data, which was redundant or not the focus of the research and ordered the remaining relevant data by impact. The code for the project can also be repurposed as a tool for other diseases. The research can help solve GWAS's imprecise identification challenge. This research is the first step in providing the refined databases required for gene-editing treatment.
Droughts have a wide range of effects, from ecosystems failing and crops dying, to increased illness and decreased water quality. Drought prediction is important because it can help communities, businesses, and governments plan and prepare for these detrimental effects. This study predicts drought conditions by using predictable weather patterns in machine learning models.
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.
Here, recognizing the difficulty that visually impaired people may have differentiating United States currency, the authors sought to use artificial intelligence (AI) models to identify US currencies. With a one-stage AI they reported a test accuracy of 89%, finding that multi-level deep learning models did not provide any significant advantage over a single-level AI.
In their paper, Kreiman et al. examined what it takes for an artificial neural network to be able to perform well on a new task without forgetting its previous knowledge. By comparing methods that stop task forgetting, they found that longer training times and maintenance of the most important connections in a particular task while training on a new one helped the neural network maintain its performance on both tasks. The authors hope that this proof-of-principle research will someday contribute to artificial intelligence that better mimics natural human intelligence.
The authors looked at using machine learning to identify skills needed to apply for certain jobs, specifically looking at different techniques to parse apart the text. They found that Bidirectional Encoder Representation of Transforms (BERT) performed best.
The challenge of accurately identifying shark species is crucial for biodiversity monitoring but is often hindered by time-consuming and labor-intensive manual methods. To address this, SharkNet, a CNN model based on AlexNet, achieved 93% accuracy in classifying shark species using a limited dataset of 1,400 images across 14 species. SharkNet offers a more efficient and reliable solution for marine biologists and conservationists in species identification and environmental monitoring.
The purpose of our study was to examine the correlation of glycosylated hemoglobin (HbA1c), blood pressure (BP) readings, and lipid levels with retinopathy. Our main hypothesis was that poor glycemic control, as evident by high HbA1c levels, high blood pressure, and abnormal lipid levels, causes an increased risk of retinopathy. We identified the top two features that were most important to the model as age and HbA1c. This indicates that older patients with poor glycemic control are more likely to show presence of retinopathy.
