Filtering by
- All Subjects: Technology
- Creators: School of Mathematical and Statistical Sciences
- Creators: Harrington Bioengineering Program
- Member of: Barrett, The Honors College Thesis/Creative Project Collection
- Resource Type: Text
For many, a long-distance hike on the 2,650+ mile Pacific Crest Trail (PCT) is the adventure of a lifetime. The federally designated National Scenic Trail passes through 48 Wilderness Areas in California, Washington, and Oregon on its way from Mexico to Canada. The trail experience on the PCT has been changing rapidly over the last 20 years due to two main factors: a four-fold increase in hikers attempting the whole trail each season; and hikers’ rapid adoption of digital technology like smartphones, GPS, and satellite messengers. Through a literature review and accompanying hiker survey, this study aimed to determine how these two factors have combined to alter the trail experience. Despite increased traffic on the trail, hikers appear to still be able to find ample solitude and a feeling of escape from society, and they reported being more likely to form lasting friendships as part of a “trail family”. However, increased traffic has altered many of the sensitive natural landscapes along the trail, contributed to the retirement of some iconic “trail angels” and led to increased conflict between subcultures within the community. Digital technology usage, particularly the use of smartphones and GPS-capable mapping apps, seems to be linked to decreased feelings of solitude, self-sufficiency, and escape. However, digital devices have helped democratize long-distance hiking by simplifying the logistics of long-distance hikes. Users of the devices also did not report reduced feelings of freedom or challenge from their hikes. Moreover, device users still felt that they were disconnecting with technology when hiking on the trail. Acknowledging both positive and negative effects of the changing trail experience, hikers can make more informed decisions about how to mitigate the negative impacts and maximize the positive impacts on the aspects of the trail experience they care the most about.
(LC-MS/MS) is used to identify and quantify peptides and proteins. LC-MS/MS produces mass spectra, which must be searched by one or more engines, which employ
algorithms to match spectra to theoretical spectra derived from a reference database.
These engines identify and characterize proteins and their component peptides. By
training a convolutional neural network on a dataset of over 6 million MS/MS spectra
derived from human proteins, we aim to create a tool that can quickly and effectively
identify spectra as peptides prior to database searching. This can significantly reduce search space and thus run time for database searches, thereby accelerating LCMS/MS-based proteomics data acquisition. Additionally, by training neural networks
on labels derived from the search results of three different database search engines, we
aim to examine and compare which features are best identified by individual search
engines, a neural network, or a combination of these.
This thesis is part of a collaboration between ASU’s Interactive Robotics Laboratory and NASA’s Jet Propulsion Laboratory. In this thesis, the training pipeline from Sharma’s paper “Pose Estimation for Non-Cooperative Spacecraft Rendezvous Using Convolutional Neural Networks” was modified to perform pose estimation on a complex object - specifically, a segment of a hollow truss. After initial attempts to replicate the architecture used in the paper and train solely on synthetic images, a combination of synthetic dataset generation and transfer learning on an ImageNet-pretrained AlexNet model was implemented to mitigate the difficulty of gathering large amounts of real-world data. Experimentation with pose estimation accuracy and hyperparameters of the model resulted in gradual test accuracy improvement, and future work is suggested to improve pose estimation for complex objects with some form of rotational symmetry.
Breast cancer is one of the most common types of cancer worldwide. Early detection and diagnosis are crucial for improving the chances of successful treatment and survival. In this thesis, many different machine learning algorithms were evaluated and compared to predict breast cancer malignancy from diagnostic features extracted from digitized images of breast tissue samples, called fine-needle aspirates. Breast cancer diagnosis typically involves a combination of mammography, ultrasound, and biopsy. However, machine learning algorithms can assist in the detection and diagnosis of breast cancer by analyzing large amounts of data and identifying patterns that may not be discernible to the human eye. By using these algorithms, healthcare professionals can potentially detect breast cancer at an earlier stage, leading to more effective treatment and better patient outcomes. The results showed that the gradient boosting classifier performed the best, achieving an accuracy of 96% on the test set. This indicates that this algorithm can be a useful tool for healthcare professionals in the early detection and diagnosis of breast cancer, potentially leading to improved patient outcomes.