Matching Items (11)
Filtering by
- All Subjects: deep learning
- Resource Type: Text
Description
Science fiction has a unique ability to express, analyze, and critique concepts in a subtle way that emphasizes a point but is still entertaining to the audience. Because of science fiction's ability to do this it has long been a powerful way to ask questions that would normally not be addressed. As such, this paper provides an overview of the effects of biomedical technology in science fiction films. The discussions in this paper will analyze the different portrayals of the technology in the viewed cinematic pieces and the effects they have on the characters in the film. The discussion will begin with the films that have technology based in Genetic Engineering. This will then be followed by a discussion of the biomedical technology based in the fields of Endocrinology; Reanimation; Preservation; Prosthetics; Physical Metamorphosis; Super-Drugs and Super-Viruses; and Diagnostic, Surgical, and Monitoring Equipment. At the end of this paper movie summaries are provided to assist in clarifying plot details.
ContributorsGrzybowski, Amanda Ann (Author) / Foy, Joseph (Thesis director) / Facinelli, Diane (Committee member) / Barrett, The Honors College (Contributor) / School of Mathematical and Statistical Sciences (Contributor) / Harrington Bioengineering Program (Contributor)
Created2014-05
Description
Abstract Modern imaging techniques for sciatic nerves often use imaging techniques that can clearly find myelinated axons (Group A and Group B and analyze their properties, but have trouble with the more numerous Remak Fibers (Group C). In this paper, Group A and B fibers are analyzed while also analyzing Remak fibers using osmium tetroxide staining and imaging with the help of transmission electron microscopy. Using this method, nerves had various electrical stimuli attached to them and were analyzed as such. They were analyzed with a cuff electrode attached, a stimulator attached, and both, with images taken at the center of the nerve and the ends of them. The number and area taken by the Remak fibers were analyzed, along with the g-ratios of the Group A and B fibers. These were analyzed to help deduce the overall health of the fibers along with vacuolization, and mitochondria available. While some important information was gained from this evaluation, further testing has to be done to improve the myelin detection system, along with analyzing the proper and necessary Remak fibers and the role they play. The research tries to thoroughly look at the necessary material and find a way to use it as a guide to further experimentation with electrical stimuli, and notes the differences found within and without various groups, various points of observation, and various stimuli as a whole. Nevertheless, this research allows a strong look into the benefits of transmission electron microscopy and the ability to assess electrical stimulation from these points.
ContributorsNambiar, Karthik (Author) / Muthuswamy, Jitendran (Thesis director) / Towe, Bruce (Committee member) / Harrington Bioengineering Program (Contributor) / School of Mathematical and Statistical Sciences (Contributor) / Barrett, The Honors College (Contributor)
Created2018-05
Description
The role of retention and forgetting of context dependent sensorimotor memory of dexterous manipulation was explored. Human subjects manipulated a U-shaped object by switching the handle to be grasped (context) three times, and then came back two weeks later to lift the same object in the opposite context relative to that experience on the last block. On each context switch, an interference of the previous block of trials was found resulting in manipulation errors (object tilt). However, no significant re-learning was found two weeks later for the first block of trials (p = 0.826), indicating that the previously observed interference among contexts lasted a very short time. Interestingly, upon switching to the other context, sensorimotor memories again interfered with visually-based planning. This means that the memory of lifting in the first context somehow blocked the memory of lifting in the second context. In addition, the performance in the first trial two weeks later and the previous trial of the same context were not significantly different (p = 0.159). This means that subjects are able to retain long-term sensorimotor memories. Lastly, the last four trials in which subjects switched contexts were not significantly different from each other (p = 0.334). This means that the interference from sensorimotor memories of lifting in opposite contexts was weaker, thus eventually leading to the attainment of steady performance.
ContributorsGaw, Nathan Benjamin (Author) / Santello, Marco (Thesis director) / Helms Tillery, Stephen (Committee member) / Buneo, Christopher (Committee member) / Barrett, The Honors College (Contributor) / School of Mathematical and Statistical Sciences (Contributor) / Harrington Bioengineering Program (Contributor)
Created2013-05
Description
Rupture of intracranial aneurysms causes a subarachnoid hemorrhage, which is often lethal health event. A minimally invasive method of solving this problem may involve a material, which can be administered as a liquid and then becomes a strong solid within minutes preventing flow of blood in the aneurysm. Here we report on the development of temperature responsive copolymers, which are deliverable through a microcatheter at body temperature and then rapidly cure to form a highly elastic hydrogel. To our knowledge, this is the first physical-and chemical-crosslinked hydrogel capable of rapid crosslinking at temperatures above the gel transition temperature. The polymer system, poly(N-isopropylacrylamide-co-cysteamine-co-Jeffamine® M-1000 acrylamide) and poly(ethylene glycol) diacrylate, was evaluated in wide-neck aneurysm flow models to evaluate the stability of the hydrogels. Investigation of this polymer system indicates that the Jeffamine® M-1000 causes the gels to retain water, resulting in gels that are initially weak and viscous, but become stronger and more elastic after chemical crosslinking.
ContributorsLee, Elizabeth Jean (Author) / Vernon, Brent (Thesis director) / Brennecka, Celeste (Committee member) / Overstreet, Derek (Committee member) / Barrett, The Honors College (Contributor) / School of Mathematical and Statistical Sciences (Contributor)
Created2013-05
Description
The development of computational systems known as brain-computer interfaces (BCIs) offers the possibility of allowing individuals disabled by neurological disorders such as Amyotrophic Lateral Sclerosis (ALS) and ischemic stroke the ability to perform relatively complex tasks such as communicating with others and walking. BCIs are closed-loop systems that record physiological signals from the brain and translate those signals into commands that control an external device such as a wheelchair or a robotic exoskeleton. Despite the potential for BCIs to vastly improve the lives of almost one billion people, one question arises: Just because we can use brain-computer interfaces, should we? The human brain is an embodiment of the mind, which is largely seen to determine a person's identity, so a number of ethical and philosophical concerns emerge over current and future uses of BCIs. These concerns include privacy, informed consent, autonomy, identity, enhancement, and justice. In this thesis, I focus on three of these issues: privacy, informed consent, and autonomy. The ultimate purpose of brain-computer interfaces is to provide patients with a greater degree of autonomy; thus, many of the ethical issues associated with BCIs are intertwined with autonomy. Currently, brain-computer interfaces exist mainly in the domain of medicine and medical research, but recently companies have started commercializing BCIs and providing them at affordable prices. These consumer-grade BCIs are primarily for non-medical purposes, and so they are beyond the scope of medicine. As BCIs become more widespread in the near future, it is crucial for interdisciplinary teams of ethicists, philosophers, engineers, and physicians to collaborate to address these ethical concerns now before BCIs become more commonplace.
ContributorsChu, Kevin Michael (Author) / Ankeny, Casey (Thesis director) / Robert, Jason (Committee member) / Frow, Emma (Committee member) / Harrington Bioengineering Program (Contributor) / School of Mathematical and Statistical Sciences (Contributor) / Barrett, The Honors College (Contributor) / School for the Future of Innovation in Society (Contributor) / Lincoln Center for Applied Ethics (Contributor)
Created2016-05
Description
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.
ContributorsMallya, Aatmik (Author) / De Luca, Gennaro (Thesis director) / Chen, Yinong (Committee member) / Barrett, The Honors College (Contributor) / School of Mathematical and Statistical Sciences (Contributor) / Computer Science and Engineering Program (Contributor)
Created2023-05
Description
The study tested the parameterized neural ordinary differential equation (PNODE) framework with a physical system exhibiting only advective phenomenon. Existing deep learning methods have difficulty learning multiple dynamic, continuous time processes. PNODE encodes the input data and initial parameter into a set of reduced states within the latent space. Then the reduced states are fitted to a system of ordinary differential equations. The outputs from the model are then decoded back to the data space for a desired input parameter and time. The application of the PNODE formalism to different types of physical systems is important to test the methods robustness. The linear advection data was generated through a high-fidelity numerical tool for multiple velocity parameters. The PNODE code was modified for the advection dataset, whose temporal domain and spatial discretization varied from the original study configuration. The L2 norm between the reconstruction and surrogate model and the reconstruction plots were used to analyze the PNODE model performance. The model reconstructions presented mixed results. For a temporal domain of 20-time units, where multiple advection cycles were completed for each advection speed, the reconstructions did not agree with the surrogate model. For a reduced temporal domain of 5-time units, the reconstructions and surrogate models were in close agreement. Near the end of the temporal domain, deviations occurred likely resulting from the accumulation of numerical errors. Note, over the 5-time units, smaller advection speed parameters were unable to complete a cycle. The behavior for the 20-time units highlighted potential issues with imbalanced datasets and repeated features. The 5-time unit model illustrates PNODEs adaptability to this class of problems when the dataset is better posed.
ContributorsReithal, Richard Robert (Author) / Kim, Jeonglae (Thesis director) / Lee, Kookjin (Committee member) / Barrett, The Honors College (Contributor) / Mechanical and Aerospace Engineering Program (Contributor) / School of Mathematical and Statistical Sciences (Contributor)
Created2022-12
Description
Accurate pose initialization and pose estimation are crucial requirements in on-orbit space assembly and various other autonomous on-orbit tasks. However, pose initialization and pose estimation are much more difficult to do accurately and consistently in space. This is primarily due to not only the variable lighting conditions present in space, but also the power requirements mandated by space-flyable hardware. This thesis investigates leveraging a deep learning approach for monocular one-shot pose initialization and pose estimation. A convolutional neural network was used to estimate the 6D pose of an assembly truss object. This network was trained by utilizing synthetic imagery generated from a simulation testbed. Furthermore, techniques to quantify model uncertainty of the deep learning model were investigated and applied in the task of in-space pose estimation and pose initialization. The feasibility of this approach on low-power computational platforms was also tested. The results demonstrate that accurate pose initialization and pose estimation can be conducted using a convolutional neural network. In addition, the results show that the model uncertainty can be obtained from the network. Lastly, the use of deep learning for pose initialization and pose estimation in addition with uncertainty quantification was demonstrated to be feasible on low-power compute platforms.
ContributorsKailas, Siva Maneparambil (Author) / Ben Amor, Heni (Thesis director) / Detry, Renaud (Committee member) / Economics Program in CLAS (Contributor) / School of Mathematical and Statistical Sciences (Contributor) / Computer Science and Engineering Program (Contributor) / Barrett, The Honors College (Contributor)
Created2020-05
Description
In shotgun proteomics, liquid chromatography coupled to tandem mass spectrometry
(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.
(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.
ContributorsWhyte, Cameron Stafford (Author) / Suren, Jayasuriya (Thesis director) / Gil, Speyer (Committee member) / Patrick, Pirrotte (Committee member) / School of Mathematical and Statistical Sciences (Contributor, Contributor) / Barrett, The Honors College (Contributor)
Created2020-05
Description
Convolutional neural networks boast a myriad of applications in artificial intelligence, but one of the most common uses for such networks is image extraction. The ability of convolutional layers to extract and combine data features for the purpose of image analysis can be leveraged for pose estimation on an object - detecting the presence and attitude of corners and edges allows a convolutional neural network to identify how an object is positioned. This task can assist in working to grasp an object correctly in robotics applications, or to track an object more accurately in 3D space. However, the effectiveness of pose estimation may change based on properties of the object; the pose of a complex object, complexity being determined by internal occlusions, similar faces, etcetera, can be difficult to resolve.
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.
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.
ContributorsDsouza, Susanna Roshini (Author) / Ben Amor, Hani (Thesis director) / Maneparambil, Kailasnath (Committee member) / Computer Science and Engineering Program (Contributor, Contributor) / School of Mathematical and Statistical Sciences (Contributor) / Barrett, The Honors College (Contributor)
Created2019-05