Using facial recognition as a use-case scenario, we attempt to identify sources of bias in a model developed using transfer learning. To achieve this task, we developed a model based on a pre-trained facial recognition model, and scrutinized the accuracy of the model’s image classification against factors such as age, gender, and race to observe whether or not the model performed better on some demographic groups than others. By identifying the bias and finding potential sources of bias, his work contributes a unique technical perspective from the view of a small scale developer to emerging discussions of accountability and transparency in AI.

With advancements in machine learning a large data scale, high throughput virtual screening has become a more attractive method for screening drug candidates. This study compared the accuracy of molecular descriptors from two cheminformatics Mordred and PaDEL, software libraries, in characterizing the chemo-structural composition of 53 compounds from the non-nucleoside reverse transcriptase inhibitors (NNRTI) class. The classification model built with the filtered set of descriptors from Mordred was superior to the model using PaDEL descriptors. This approach can accelerate the identification of hit compounds and improve the efficiency of the drug discovery pipeline.

Machine learning and deep learning techniques can be used to predict the early onset of breast cancer. The main objective of this analysis was to determine whether machine learning algorithms can be used to predict the onset of breast cancer with more than 90% accuracy. Based on research with supervised machine learning algorithms, Gaussian Naïve Bayes, K Nearest Algorithm, Random Forest, and Logistic Regression were considered because they offer a wide variety of classification methods and also provide high accuracy and performance. We hypothesized that all these algorithms would provide accurate results, and Random Forest and Logistic Regression would provide better accuracy and performance than Naïve Bayes and K Nearest Neighbor.

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.

In this study, a deep learning model is used to classify post-traumatic stress disorder patients through novel markers to assist in finding candidate biomarkers for the disorder.

Here, seeking to identify an optimal method to classify tree species through remote sensing, the authors used a few machine learning algorithms to classify forest tree species through multispectral satellite imagery. They found the Random Forest algorithm to most accurately classify tree species, with the potential to improve model training and inference based on the inclusion of other tree properties.

In this study, the authors explored whether students' test scores were significantly higher on online exams during the COVID-19 school lockdown when compared to those of the in-person exams before the lockdown.

In this article, the authors identify the characteristics that make a book a best-seller. Knowing what, besides content, predicts the success of a book can help publishers maximize the success of their print products.

Previously established data indicate that cemeteries have contributed to groundwater and soil pollution, as embalming fluids can impact the microbiomes that exist in decomposing remains. In this study, Caputo et al hypothesized that microbial variation would be high between cemeteries from different eras due to dissimilarities between embalming techniques employed, and furthermore, that specific microbes would act as an indication for certain contaminants. Overall, they found that there is a variation in the microbiomes of the different eras’ cemeteries according to the concentrations of the phyla and their more specific taxa.

Ischemic stroke occurs when blood flow to the brain is interrupted, causing brain damage. This study investigated the effectiveness of different NOX inhibitors as treatments for ischemic stroke in silico. The results help corroborate previous in vivo and in vitro studies in an in silico format, and can be used towards developing drugs to treat ischemic stroke.