Dye-sensitized solar cells (DSSC) use dye as the photoactive material, which capture the incoming photon of light and use the energy to excite electrons. Research in DSSCs has centered around improving the efficacy of photosensitive dyes. A fruit's color is defined by a unique set of molecules, known as a pigment profile, which changes as a fruit progresses from ripe to rotten. This project investigates the use of fresh and rotten fruit extracts as the photoactive dye in a DSSC.
Mesenchymal stem cells(MSCs) play a role in tumor formation by differentiating into cancer associated fibroblasts (CAFs) which enable metastasis of tumors. The process of conversion of MSCs into CAFs is not clear. In this study, authors tested the hypothesis that cancers cells secrete soluble factors that induce differentiation by culturing bone marrow mesenchymal stem cells in media conditioned by a breast cancer cell line.
In this study, the authors investigate the suitability of using bacterial cellulose as a scaffold for cell transplants. Interestingly, this cellulose is a can be found in the discard from a symbiotic culture of bacteria and yeast (SCOBY) used to make kombucha.
Current drug discovery processes can cost billions of dollars and usually take five to ten years. People have been researching and implementing various computational approaches to search for molecules and compounds from the chemical space, which can be on the order of 1060 molecules. One solution involves deep generative models, which are artificial intelligence models that learn from nonlinear data by modeling the probability distribution of chemical structures and creating similar data points from the trends it identifies. Aiming for faster runtime and greater robustness when analyzing high-dimensional data, we designed and implemented a Hybrid Quantum-Classical Generative Adversarial Network (QGAN) to synthesize molecules.
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.
Two dams in Santa Clara County were evaluated for water and soil nitrate levels in order to determine whether nitrification rates were higher upstream than downstream of the dam. This could indicate a detrimental effect of dams on the nitration cycle in the environment.
In the modern world, communication and mobility are no longer obstacles. A natural consequence is that people from all over the world are mixing like never before and national identity can no longer be determined simply by a person's appearance or manner of speech. In this article, the authors study how a person's accent interferes with the perception of a their national identity and proposes ways to eliminate such biases.
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.
Semantic segmentation - labelling each pixel in an image to a specific class- models require large amounts of manually labeled and collected data to train.