In this study, the authors seek to improve a machine learning algorithm used for image classification: identifying male and female images. In addition to fine-tuning the classification model, they investigate how accuracy is affected by their changes (an important task when developing and updating algorithms). To determine accuracy, a set of images is used to train the model and then a separate set of images is used for validation. They found that the validation accuracy was close to the training accuracy. This study contributes to the expanding areas of machine learning and its applications to image identification.

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.

People are quick to accept the assumption that a light will appear dimmer the farther away they are, citing the inverse square relationship that illuminance obeys as rationale. However, repeated observations of light sources maintaining their brightness over large distances prompted us to explore how the brightness, or perceived illuminance of a light varies with the viewing distance from the object. We hypothesized that since both the illuminance of the light source and image size decrease at the same rate, then the concentration, or intensity of the image remains unchanged, and subsequently the perceived illuminance.

Triggered largely by the warming and pollution of oceans, corals are experiencing bleaching and a variety of diseases caused by the spread of bacteria, fungi, and viruses. Identification of bleached/diseased corals enables implementation of measures to halt or retard disease. Benthic cover analysis, a standard metric used in large databases to assess live coral cover, as a standalone measure of reef health is insufficient for identification of coral bleaching/disease. Proposed herein is a solution that couples machine learning with crowd-sourced data – images from government archives, citizen science projects, and personal images collected by tourists – to build a model capable of identifying healthy, bleached, and/or diseased coral.

Smartphones are not only becoming an inseparable part of our daily lives, but also a low-cost, powerful optical imaging tool for more and more scientific research applications. In this work, smartphones were used as a low-cost, high-speed, photographic alternative to expensive equipment, such as those typically found in scientific research labs, to accurately perform motion tracking and analysis of fast-moving objects. By analyzing consecutive images, the speed and flight trajectory of water droplets in the air were obtained, thereby enabling us to estimate the area of the water droplets landing on the ground.

There are believed to be ~20,000 nebulae in the Milky Way Galaxy. However, humans have only cataloged ~1,800 of them even though we have gathered 1.3 million nebula images. Classification of nebulae is important as it helps scientists understand the chemical composition of a nebula which in turn helps them understand the material of the original star. Our research on nebulae classification aims to make the process of classifying new nebulae faster and more accurate using a hybrid of deep learning and machine learning techniques.

Here, recognizing the potential harmful effects of algal blooms, the authors used satellite images to detect algal blooms in water bodies in Wyoming based on their reflectance of near infrared light. They found that remote monitoring in this way may provide a useful tool in providing early warning and advisories to people who may live in close proximity.

Molecules which bind to proteins that aggregate abnormally in neurodegenerative diseases could be promising drugs for these diseases. In this study, Zhang, Wu, Zhang, and Dang simulate the binding behavior of various molecules to screen for candidates which could be promising candidates for drug development.

Semantic segmentation - labelling each pixel in an image to a specific class- models require large amounts of manually labeled and collected data to train.

There are two types of competing TV screens on the market, organic light emitting diode (OLED) and liquid crystal display (LCD). The better capability to exhibit black results in higher contrast images. Here, authors compared the ability of the two types of screens to show black in an environment eliminating external light.