In this article, Harvell and Nicholson hypothesized that increased ocean acidity would decrease the photosynthetic ability of Chaetoceros gracilis, a diatom prolific in Monterey Bay, because of the usually corrosive effects of carbonic acid on both seashells and cells’ internal structures. They altered pH of algae environments and measured the photosynthetic ability of diatoms over four days by spectrophotometer. Overall, their findings indicate that C. gracilis may become more abundant in Monterey Bay as the pH of the ocean continues to drop, potentially contributing to harmful algal blooms.
Rhizopus stolonifer is a mold commonly found growing on bread that can cause many negative health effects when consumed. Preservatives are the well-known answer to this problem; however, many preservatives are not naturally found in food, and some have negative health effects of their own. We focused on honey as a possible solution because of its natural origin and self-preservation ability. We hypothesized that honey would decrease the growth rate of R. stolonifer . We evaluated the honey with a zone of inhibition (ZOI) test on agar plates. Sabouraud dextrose agar was mixed with differing volumes of honey to generate concentrations between 10.0% and 30.0%. These plates were then inoculated with a solution of spores collected from the mold. The ZOI was measured to determine antifungal effectiveness. A statistically significant difference was found between the means of all concentrations except for 20.0% and 22.5%. Our findings support the hypothesis as we showed a positive correlation between the honey concentration and growth rate of mold. By using this data, progress could be made on an all-natural, honey-based preservative.
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.
Dental resins can be a source of reactive oxygen species (ROS) which in unruly amounts can be toxic to cellular and overall health. In this report, the authors test whether the consumption of antioxidant rich foods like avocado and asparagus can protect against the effect of dental resin-derived ROS. However, rather than testing humans, they use fruit flies and their climbing abilities as an experimental readout.
As humans, not all our body organs can adequately regenerate after injury, an ability that declines with age. In some species, however, regeneration is a hallmark response that can occur limitless numbers of time throughout the life of an organism. Understanding how such species can regenerate so efficiently is of central importance to regenerative medicine. Sea urchins, unlike humans, can regenerate their spinal tissue after injury. Here the authors study the effect of a growth factor, FGF2, on sea urchin regeneration but find no conclusive evidence for a pro-regenerative effect after spinal tissue injury.
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.
The diagnosis of malaria remains one of the major hurdles to eradicating the disease, especially among poorer populations. Here, the authors use machine learning to improve the accuracy of deep learning algorithms that automate the diagnosis of malaria using images of blood smears from patients, which could make diagnosis easier and faster for many.
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.
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.
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.