Computer science · Paper · June 2022
Aakash Kumar
Convolutional Neural Networks (CNNs) are vulnerable to misclassifying images when small perturbations are present. With the increasing prevalence of CNNs in self-driving cars, it is vital to ensure these algorithms are robust to prevent collisions from occurring due to failure in recognizing a situation. In the Adversarial Self-Driving framework, a Generative Adversarial Network (GAN) is implemented to generate realistic perturbations in an image that cause a classifier CNN to misclassify data. This perturbed data is then used to train the classifier CNN further. The Adversarial Self-driving framework is applied to an image classification algorithm to improve the classification accuracy on perturbed images and is later applied to train a self-driving car to drive in a simulation. A small-scale self-driving car is also built to drive around a track and classify signs. The Adversarial Self-driving framework produces perturbed images through learning a dataset, as a result removing the need to train on significant amounts of data. Experiments demonstrate that the Adversarial Self-driving framework identifies situations where CNNs are vulnerable to perturbations and generates new examples of these situations for the CNN to train on. The additional data generated by the Adversarial Self-driving framework provides sufficient data for the CNN to generalize to the environment. Therefore, it is a viable tool to increase the resilience of CNNs to perturbations. Particularly, in the real-world self-driving car, the application of the Adversarial Self-Driving framework resulted in an 18% increase in accuracy, and the simulated self-driving model had no collisions in 30 minutes of driving.
Biology and biomedicine · Paper · June 2022
Ethan Liu
Cataracts are a leading cause of blindness, especially in the developing world. With clean water not always accessible in many third-world countries, the poor quality of water may trigger oxidative stress, a major inducer of cataracts, as demonstrated by previous studies, and one-way oxidation can occur is through Fenton reactions reacting with iron. Perhaps the iron in the untreated water causes oxidation, and this could be a potential cause of cataracts. The objective of the study is to find if the presence of iron ions in drinkable water sources is a contributing factor to cataracts. Pig eyes were soaked in iron solutions and stored under a UV light for 24 hours, simulating human eyes in contact with iron water over a long period, building up oxidative damage. The lenses were then analyzed by comparing the color of the lenses and the change in luminance compared to the control. The results were found to show how iron in water can induce oxidation in the eye due to the Fenton Reaction, leading to cataracts.
Computer science · Paper · June 2022
Christopher Sun, Jai Sharma, Milind Maiti
Roughly 6,800 natural disasters occur annually, and this alarming number continues to grow due to climate change. Effective methods to improve natural disaster response include change detection, map alignment, and vision-aided navigation to allow for the time-efficient delivery of life-saving aid. Current software functions optimally only on near-nadir images taken around ninety degrees above ground level. The inability to generalize to oblique images increases the need to compute an image's geocentric pose, which is its spatial orientation with respect to gravity. This Deep Learning investigation presents three convolutional models to predict geocentric pose using 5,923 nadir and off-nadir red, green, and blue (RGB) satellite images of cities worldwide. Prior to the ensemble, an autoencoder is assembled to condense the 256 x 256 x 3 images to 32 x 32 x 16 latent space representations, demonstrating the ability to learn useful features from the data. The first model in the ensemble is a U-Net Fully Convolutional Network (FCN) with skip connections used to predict each image's corresponding pixel-level above-ground elevation mask. This FCN achieves a median absolute deviation of 0.335 meters and an R2 of 0.865 on test data. Afterward, the elevation masks are concatenated with the RGB images to form four-channel inputs fed into the second model in the ensemble, which predicts each image's rotation angle and magnification scale, the components of its geocentric pose. This Deep Convolutional Model achieves an R2 of 0.943 on test data, significantly outperforming previous models designed by researchers. In addition to achieving superior model performance, outlier removal was performed through supervised interpolation, and the usefulness of data features was gauged through a sensitivity analysis of elevation masks, to target future avenues of feature engineering. The high-accuracy software built in this study contributes to mapping and navigation procedures to accelerate disaster relief and save human lives.
Earth and climate · Paper · June 2022
Christopher Sun
Since frequent severe droughts are lengthening the dry season in the Amazon Rainforest, it is important to detect wildfires promptly and forecast possible spread for effective suppression response. Current wildfire detection models are not versatile enough for the low-technology conditions of South American hot spots. This deep learning study first trains a Fully Convolutional Neural Network on Landsat 8 images of Ecuador and the Galapagos, using Green and Short-wave Infrared bands to predict pixel-level binary fire masks. This model achieves a 0.962 validation F2 score and a 0.932 F2 score on test data from Guyana and Suriname. Afterward, image segmentation is conducted on the Cirrus band using K-Means Clustering to simplify continuous pixel values into three discrete classes representing differing degrees of cirrus cloud contamination. Three additional Convolutional Neural Networks are trained to conduct a sensitivity analysis measuring the effect of simplified features on model accuracy and train time. The Experimental model trained on the segmented cirrus images provides a statistically significant decrease in train time compared to the Control model trained on raw cirrus images, without compromising binary accuracy. This proof of concept reveals that feature engineering can improve the performance of wildfire detection models by lowering computational expense.
Biology and biomedicine · Paper · June 2022
Christopher Sun, Jai Sharma, Milind Maiti
The pervasiveness of cardiovascular disease and physician misdiagnosis creates the urgent need for artificial intelligence models to improve diagnosis accuracy. The first objective of this study was to train machine learning models on publicly available data sets containing simple medical information of patients to diagnose cardiovascular disease. The Multilayer Perceptron (MLP) assembled for this task performed optimally with an F1 score of 0.8968. This prompted the creation of an open-source, automated cardiovascular disease diagnosis tool, powered by the MLP. The second objective of this study was to employ a meta-learning methodology called Local Interpretable Model-Agnostic Explanations (LIME) to understand the impact of different features on the model's diagnosis in the form of marginal probabilities. K-Means Clustering was employed to segment the data into ten clusters, after which each data example was passed through LIME. The resulting histograms depict the complex relationship between feature, cluster, and impact on diagnosis. A series of P-values with contrasting orders of magnitude shows the nuances in the MLP's understanding of patients from different clusters. The results of meta-learning analysis reveal that the most important features for cardiovascular disease diagnosis are fasting blood sugar, type of chest pain, and slope of the ST segment on an electrocardiogram. Future experiments should replicate the novel methodology introduced in this study on data sets containing more specialized medical features in order to gain practical medical insights about different types of cardiovascular disease represented by each cluster. Finally, feature engineering pathways should be explored with consideration of these results to create versatile diagnosis models not only for cardiovascular disease, but adaptable to other diseases as well.
Physics · Paper · June 2022
Jenna Van Dyke
The Kerr spacetime is investigated. The singularity structure and horizon structure of the spacetime are explored. Two sets of equations of motion for a particle orbiting a Kerr black hole are derived: the first by the calculating nonzero Christoffel symbols of the metric and utilizing the geodesic equation; the second by dot products of Killing vectors and the four-velocity. The effective potential of the radial motion is found and analyzed in comparison with the Schwarzschild effective potential. The Kerr/CFT correspondence and its recent use in predicting polarimetric images of the supermassive black hole in the galaxy M87 is also discussed briefly. An overview of special relativity, general relativity, and orbits is provided in the appendix to serve as background information for the body of the paper. The Mathematica programs used for this paper can be found here: https://bit.ly/3dlwYH7.