Search Content

Using Bag of Words Approach for Classifying Native Arizona Snakes in Images as Venomous or Non-Venomous

Description

Uninformed people frequently kill snakes without knowing whether they are venomous or harmless, fearing for their safety. To prevent unnecessary killings and to encourage people to be safe around venomous snakes, a proper identification is important. This work seeks to preserve wild native Arizona snakes and promote a general interest…

Uninformed people frequently kill snakes without knowing whether they are venomous or harmless, fearing for their safety. To prevent unnecessary killings and to encourage people to be safe around venomous snakes, a proper identification is important. This work seeks to preserve wild native Arizona snakes and promote a general interest in them by using a bag of features approach for classifying native Arizona snakes in images as venomous or non-venomous. The image category classifier was implemented in MATLAB and trained on a set of 245 images of native Arizona snakes (171 non-venomous, 74 venomous). To test this approach, 10-fold cross-validation was performed and the average accuracy was 0.7772. While this approach is functional, the results could be improved, ideally with a higher average accuracy, in order to be reliable. In false positives, the features may have been associated with the color or pattern, which is similar between venomous and non-venomous snakes due to mimicry. Polymorphic traits, color morphs, variation, and juveniles that may exhibit different colors can cause false negatives and misclassification. Future work involves pre-training image processing such as improving the brightness and contrast or converting to grayscale, interactively specifying or generating regions of interest for feature detection, and targeting reducing the false negative rate and improve the true positive rate. Further study is needed with a larger and balanced image set to evaluate its performance. This work may potentially serve as a tool for herpetologists to assist in their field research and to classify large image sets.

ContributorsIp, Melissa A (Author) / Li, Baoxin (Thesis director) / Chandakkar, Parag (Committee member) / Computer Science and Engineering Program (Contributor) / Barrett, The Honors College (Contributor)

Created2017-05

Using Machine Learning to Objectively Determine Colorimetric Assay Results from Cell Phone Photos Taken Under Ambient Lighting

Description

Colorimetric assays are an important tool in point-of-care testing that offers several advantages to traditional testing methods such as rapid response times and inexpensive costs. A factor that currently limits the portability and accessibility of these assays are methods that can objectively determine the results of these assays. Current solutions…

Colorimetric assays are an important tool in point-of-care testing that offers several advantages to traditional testing methods such as rapid response times and inexpensive costs. A factor that currently limits the portability and accessibility of these assays are methods that can objectively determine the results of these assays. Current solutions consist of creating a test reader that standardizes the conditions the strip is under before being measured in some way. However, this increases the cost and decreases the portability of these assays. The focus of this study is to create a machine learning algorithm that can objectively determine results of colorimetric assays under varying conditions. To ensure the flexibility of a model to several types of colorimetric assays, three models were trained on the same convolutional neural network with different datasets. The images these models are trained on consist of positive and negative images of ETG, fentanyl, and HPV Antibodies test strips taken under different lighting and background conditions. A fourth model is trained on an image set composed of all three strip types. The results from these models show it is able to predict positive and negative results to a high level of accuracy.

ContributorsFisher, Rachel (Author) / Blain Christen, Jennifer (Thesis director) / Anderson, Karen (Committee member) / School of Life Sciences (Contributor) / Harrington Bioengineering Program (Contributor) / Barrett, The Honors College (Contributor)

Created2021-05

Deep Learning Application to Improve Quality of Life in Diabetes

Description

Carbohydrate counting has been shown to improve HbA1c levels for people with diabetes. However, the learning curve and inconvenience of carbohydrate counting make it difficult for patients to adhere to it. A deep learning model is proposed to identify food from an image, where it can help the user manage…

Carbohydrate counting has been shown to improve HbA1c levels for people with diabetes. However, the learning curve and inconvenience of carbohydrate counting make it difficult for patients to adhere to it. A deep learning model is proposed to identify food from an image, where it can help the user manage their carbohydrate counting. This early model has a 68.3% accuracy of identifying 101 different food classes. A more refined model in future work could be deployed into a mobile application to identify food the user is about to consume and log it for easier carbohydrate counting.

ContributorsCarreto, Cesar (Author) / Pizziconi, Vincent (Thesis director) / Vernon, Brent (Committee member) / Harrington Bioengineering Program (Contributor) / Barrett, The Honors College (Contributor)

Created2021-05

Quantum Machine Learning for Brain Tumor Detection

Description

Recent advances in quantum computing have broadened the available techniques towards addressing existing computing problems. One area of interest is that of the emerging field of machine learning. The intersection of these fields, quantum machine learning, has the ability to perform high impact work such as that in the health…

Recent advances in quantum computing have broadened the available techniques towards addressing existing computing problems. One area of interest is that of the emerging field of machine learning. The intersection of these fields, quantum machine learning, has the ability to perform high impact work such as that in the health industry. Use cases seen in previous research include that of the detection of illnesses in medical imaging through image classification. In this work, we explore the utilization of a hybrid quantum-classical approach for the classification of brain Magnetic Resonance Imaging (MRI) images for brain tumor detection utilizing public Kaggle datasets. More specifically, we aim to assess the performance and utility of a hybrid model, comprised of a classical pretrained portion and a quantum variational circuit. We will compare these results to purely classical approaches, one utilizing transfer learning and one without, for the stated datasets. While more research should be done for proving generalized quantum advantage, our work shows potential quantum advantages in validation accuracy and sensitivity for the specified task, particularly when training with limited data availability in a minimally skewed dataset under specific conditions. Utilizing the IBM’s Qiskit Runtime Estimator with built in error mitigation, our experiments on a physical quantum system confirmed some results generated through simulations.

ContributorsDiaz, Maryannette (Author) / De Luca, Gennaro (Thesis director) / Chen, Yinong (Committee member) / Barrett, The Honors College (Contributor) / Computer Science and Engineering Program (Contributor)

Created2023-05

Elliptic Fourier Features for Robustness to Rotations and Translations in Neural Networks

Description

In image classification tasks, images are often corrupted by spatial transformationslike translations and rotations. In this work, I utilize an existing method that uses the Fourier series expansion to generate a rotation and translation invariant representation of closed contours found in sketches, aiming to attenuate the effects of distribution shift caused…

In image classification tasks, images are often corrupted by spatial transformationslike translations and rotations. In this work, I utilize an existing method that uses the Fourier series expansion to generate a rotation and translation invariant representation of closed contours found in sketches, aiming to attenuate the effects of distribution shift caused by the aforementioned transformations. I use this technique to transform input images into one of two different invariant representations, a Fourier series representation and a corrected raster image representation, prior to passing them to a neural network for classification. The architectures used include convolutional neutral networks (CNNs), multi-layer perceptrons (MLPs), and graph neural networks (GNNs). I compare the performance of this method to using data augmentation during training, the standard approach for addressing distribution shift, to see which strategy yields the best performance when evaluated against a test set with rotations and translations applied. I include experiments where the augmentations applied during training both do and do not accurately reflect the transformations encountered at test time. Additionally, I investigate the robustness of both approaches to high-frequency noise. In each experiment, I also compare training efficiency across models. I conduct experiments on three data sets, the MNIST handwritten digit dataset, a custom dataset (QD-3) consisting of three classes of geometric figures from the Quick, Draw! hand-drawn sketch dataset, and another custom dataset (QD-345) featuring sketches from all 345 classes found in Quick, Draw!. On the smaller problem space of MNIST and QD-3, the networks utilizing the Fourier-based technique to attenuate distribution shift perform competitively with the standard data augmentation strategy. On the more complex problem space of QD-345, the networks using the Fourier technique do not achieve the same test performance as correctly-applied data augmentation. However, they still outperform instances where train-time augmentations mis-predict test-time transformations, and outperform a naive baseline model where no strategy is used to attenuate distribution shift. Overall, this work provides evidence that strategies which attempt to directly mitigate distribution shift, rather than simply increasing the diversity of the training data, can be successful when certain conditions hold.

ContributorsWatson, Matthew (Author) / Yang, Yezhou YY (Thesis advisor) / Kerner, Hannah HK (Committee member) / Yang, Yingzhen YY (Committee member) / Arizona State University (Publisher)

Created2023