Matching Items (172)
Description
Cancer remains one of the leading killers throughout the world. Death and disability due to lung cancer in particular accounts for one of the largest global economic burdens a disease presents. The burden on third-world countries is especially large due to the unusually large financial stress that comes from late tumor detection and expensive treatment options. Early detection using inexpensive techniques may relieve much of the burden throughout the world, not just in more developed countries. I examined the immune responses of lung cancer patients using immunosignatures – patterns of reactivity between host serum antibodies and random peptides. Immunosignatures reveal disease-specific patterns that are very reproducible. Immunosignaturing is a chip-based method that has the ability to display the antibody diversity from individual sera sample with low cost. Immunosignaturing is a medical diagnostic test that has many applications in current medical research and in diagnosis. From a previous clinical study, patients diagnosed for lung cancer were tested for their immunosignature vs. healthy non-cancer volunteers. The pattern of reactivity against the random peptides (the ‘immunosignature’) revealed common signals in cancer patients, absent from healthy controls. My study involved the search for common amino acid motifs in the cancer-specific peptides. My search through the hundreds of ‘hits’ revealed certain motifs that were repeated more times than expected by random chance. The amino acids that were the most conserved in each set include tryptophan, aspartic acid, glutamic acid, proline, alanine, serine, and lysine. The most overall conserved amino acid observed between each set was D - aspartic acid. The motifs were short (no more than 5-6 amino acids in a row), but the total number of motifs I identified was large enough to assure significance. I utilized Excel to organize the large peptide sequence libraries, then CLUSTALW to cluster similar-sequence peptides, then GLAM2 to find common themes in groups of peptides. In so doing, I found sequences that were also present in translated cancer expression libraries (RNA) that matched my motifs, suggesting that immunosignatures can find cancer-specific antigens that can be both diagnostic and potentially therapeutic.
ContributorsShiehzadegan, Shima (Author) / Johnston, Stephen (Thesis director) / Stafford, Phillip (Committee member) / School of Life Sciences (Contributor) / Barrett, The Honors College (Contributor)
Created2015-12
Description
The influenza virus, also known as "the flu", is an infectious disease that has constantly affected the health of humanity. There is currently no known cure for Influenza. The Center for Innovations in Medicine at the Biodesign Institute located on campus at Arizona State University has been developing synbodies as a possible Influenza therapeutic. Specifically, at CIM, we have attempted to design these initial synbodies to target the entire Influenza virus and preliminary data leads us to believe that these synbodies target Nucleoprotein (NP). Given that the synbody targets NP, the penetration of cells via synbody should also occur. Then by Western Blot analysis we evaluated for the diminution of NP level in treated cells versus untreated cells. The focus of my honors thesis is to explore how synthetic antibodies can potentially inhibit replication of the Influenza (H1N1) A/Puerto Rico/8/34 strain so that a therapeutic can be developed. A high affinity synbody for Influenza can be utilized to test for inhibition of Influenza as shown by preliminary data. The 5-5-3819 synthetic antibody's internalization in live cells was visualized with Madin-Darby Kidney Cells under a Confocal Microscope. Then by Western Blot analysis we evaluated for the diminution of NP level in treated cells versus untreated cells. Expression of NP over 8 hours time was analyzed via Western Blot Analysis, which showed NP accumulation was retarded in synbody treated cells. The data obtained from my honors thesis and preliminary data provided suggest that the synthetic antibody penetrates live cells and targets NP. The results of my thesis presents valuable information that can be utilized by other researchers so that future experiments can be performed, eventually leading to the creation of a more effective therapeutic for influenza.
ContributorsHayden, Joel James (Author) / Diehnelt, Chris (Thesis director) / Johnston, Stephen (Committee member) / Legutki, Bart (Committee member) / Barrett, The Honors College (Contributor) / Department of Psychology (Contributor) / Department of Chemistry and Biochemistry (Contributor)
Created2014-05
Description
Currently, autonomous vehicles are being evaluated by how well they interact with humans without evaluating how well humans interact with them. Since people are not going to unanimously switch over to using autonomous vehicles, attention must be given to how well these new vehicles signal intent to human drivers from the driver’s point of view. Ineffective communication will lead to unnecessary discomfort among drivers caused by an underlying uncertainty about what an autonomous vehicle is or isn’t about to do. Recent studies suggest that humans tend to fixate on areas of higher uncertainty so scenarios that have a higher number of vehicle fixations can be reasoned to be more uncertain. We provide a framework for measuring human uncertainty and use the framework to measure the effect of empathetic vs non-empathetic agents. We used a simulated driving environment to create recorded scenarios and manipulate the autonomous vehicle to include either an empathetic or non-empathetic agent. The driving interaction is composed of two vehicles approaching an uncontrolled intersection. These scenarios were played to twelve participants while their gaze was recorded to track what the participants were fixating on. The overall intent was to provide an analytical framework as a tool for evaluating autonomous driving features; and in this case, we choose to evaluate how effective it was for vehicles to have empathetic behaviors included in the autonomous vehicle decision making. A t-test analysis of the gaze indicated that empathy did not in fact reduce uncertainty although additional testing of this hypothesis will be needed due to the small sample size.
ContributorsGreenhagen, Tanner Patrick (Author) / Yang, Yezhou (Thesis director) / Jammula, Varun C (Committee member) / Computer Science and Engineering Program (Contributor, Contributor) / Barrett, The Honors College (Contributor)
Created2021-05
Description
In the last decade, a large variety of algorithms have been developed for use in object tracking, environment mapping, and object classification. It is often difficult for beginners to fully predict the constraints that multirotors place on machine vision algorithms. The purpose of this paper is to explain some of the types of algorithms that can be applied to these aerial systems, why the constraints for these algorithms exist, and what could be done to mitigate them. This paper provides a summary of the processes involved in a popular filter-based tracking algorithm called MOSSE (Minimum Output Sum of Squared Error) and a particular implementation of SLAM (Simultaneous Localization and Mapping) called LSD SLAM.
ContributorsVan Hazel, Colton (Author) / Zhang, Wenlong (Thesis director) / Yang, Yezhou (Committee member) / Engineering Programs (Contributor, Contributor) / Barrett, The Honors College (Contributor)
Created2020-05
Description
A defense-by-randomization framework is proposed as an effective defense mechanism against different types of adversarial attacks on neural networks. Experiments were conducted by selecting a combination of differently constructed image classification neural networks to observe which combinations applied to this framework were most effective in maximizing classification accuracy. Furthermore, the reasons why particular combinations were more effective than others is explored.
ContributorsMazboudi, Yassine Ahmad (Author) / Yang, Yezhou (Thesis director) / Ren, Yi (Committee member) / School of Mathematical and Statistical Sciences (Contributor) / Economics Program in CLAS (Contributor) / Barrett, The Honors College (Contributor)
Created2019-05
Description
Propaganda bots are malicious bots on Twitter that spread divisive opinions and support political accounts. This project is based on detecting propaganda bots on Twitter using machine learning. Once I began to observe patterns within propaganda followers on Twitter, I determined that I could train algorithms to detect these bots. The paper focuses on my development and process of training classifiers and using them to create a user-facing server that performs prediction functions automatically. The learning goals of this project were detailed, the focus of which was to learn some form of machine learning architecture. I needed to learn some aspect of large data handling, as well as being able to maintain these datasets for training use. I also needed to develop a server that would execute these functionalities on command. I wanted to be able to design a full-stack system that allowed me to create every aspect of a user-facing server that can execute predictions using the classifiers that I design.
Throughout this project, I decided on a number of learning goals to consider it a success. I needed to learn how to use the supporting libraries that would help me to design this system. I also learned how to use the Twitter API, as well as create the infrastructure behind it that would allow me to collect large amounts of data for machine learning. I needed to become familiar with common machine learning libraries in Python in order to create the necessary algorithms and pipelines to make predictions based on Twitter data.
This paper details the steps and decisions needed to determine how to collect this data and apply it to machine learning algorithms. I determined how to create labelled data using pre-existing Botometer ratings, and the levels of confidence I needed to label data for training. I use the scikit-learn library to create these algorithms to best detect these bots. I used a number of pre-processing routines to refine the classifiers’ precision, including natural language processing and data analysis techniques. I eventually move to remotely-hosted versions of the system on Amazon web instances to collect larger amounts of data and train more advanced classifiers. This leads to the details of my final implementation of a user-facing server, hosted on AWS and interfacing over Gmail’s IMAP server.
The current and future development of this system is laid out. This includes more advanced classifiers, better data analysis, conversions to third party Twitter data collection systems, and user features. I detail what it is I have learned from this exercise, and what it is I hope to continue working on.
Throughout this project, I decided on a number of learning goals to consider it a success. I needed to learn how to use the supporting libraries that would help me to design this system. I also learned how to use the Twitter API, as well as create the infrastructure behind it that would allow me to collect large amounts of data for machine learning. I needed to become familiar with common machine learning libraries in Python in order to create the necessary algorithms and pipelines to make predictions based on Twitter data.
This paper details the steps and decisions needed to determine how to collect this data and apply it to machine learning algorithms. I determined how to create labelled data using pre-existing Botometer ratings, and the levels of confidence I needed to label data for training. I use the scikit-learn library to create these algorithms to best detect these bots. I used a number of pre-processing routines to refine the classifiers’ precision, including natural language processing and data analysis techniques. I eventually move to remotely-hosted versions of the system on Amazon web instances to collect larger amounts of data and train more advanced classifiers. This leads to the details of my final implementation of a user-facing server, hosted on AWS and interfacing over Gmail’s IMAP server.
The current and future development of this system is laid out. This includes more advanced classifiers, better data analysis, conversions to third party Twitter data collection systems, and user features. I detail what it is I have learned from this exercise, and what it is I hope to continue working on.
ContributorsPeterson, Austin (Author) / Yang, Yezhou (Thesis director) / Sadasivam, Aadhavan (Committee member) / Computer Science and Engineering Program (Contributor) / Barrett, The Honors College (Contributor)
Created2019-05
Description
In this study, we demonstrate the effectiveness of a cancer type specific FrAmeShifT (FAST) vaccine. A murine breast cancer (mBC) FAST vaccine and a murine pancreatic cancer (mPC) FAST vaccine were tested in the 4T1 breast cancer syngeneic mouse model. The mBC FAST vaccine, both with and without check point inhibitors (CPI), significantly slowed tumor growth, reduced pulmonary metastasis and increased the cell-mediated immune response. In terms of tumor volumes, the mPC FAST vaccine was comparable to the untreated controls. However, a significant difference in tumor volume did emerge when the mPC vaccine was used with CPI. The collective data indicated that the immune checkpoint blockade therapy was only beneficial with suboptimal neoantigens. More importantly, the FAST vaccine, though requiring notably less resources, performed similarly to the personalized version of the frameshift breast cancer vaccine in the same mouse model. Furthermore, because the frameshift peptide (FSP) array provided a strong rationale for a focused vaccine, the FAST vaccine can theoretically be expanded and translated to any human cancer type. Overall, the FAST vaccine is a promising treatment that would provide the most benefit to patients while eliminating most of the challenges associated with current personal cancer vaccines.
ContributorsMurphy, Sierra Nicole (Author) / Johnston, Stephen (Thesis director) / Peterson, Milene (Committee member) / School of Mathematical and Statistical Sciences (Contributor) / School of Molecular Sciences (Contributor) / School of Life Sciences (Contributor) / Barrett, The Honors College (Contributor)
Created2019-05
Description
In the field of machine learning, reinforcement learning stands out for its ability to explore approaches to complex, high dimensional problems that outperform even expert humans. For robotic locomotion tasks reinforcement learning provides an approach to solving them without the need for unique controllers. In this thesis, two reinforcement learning algorithms, Deep Deterministic Policy Gradient and Group Factor Policy Search are compared based upon their performance in the bipedal walking environment provided by OpenAI gym. These algorithms are evaluated on their performance in the environment and their sample efficiency.
ContributorsMcDonald, Dax (Author) / Ben Amor, Heni (Thesis director) / Yang, Yezhou (Committee member) / Barrett, The Honors College (Contributor) / Computer Science and Engineering Program (Contributor)
Created2018-12
Description
The goal of this paper is to discuss the most efficient method to achieve early detection in lung cancers by reducing the occurrences of false-positive readings. Imaging techniques (computed tomography screenings) have greater impact than non-imaging techniques in early detection for lung cancer. On the other hand, positron emission tomography and non-imaging techniques, such as liquid biopsy, are better at distinguishing cancer stages. Therefore, these techniques are not suitable early detection methods for lung cancer. Based on literature reviews, the combination that is most capable of early lung cancer detection incorporate low-dose computed tomography screenings, thin-section computed tomography screenings, and computer-aided diagnosis. Low-dose computed tomography screenings has lower radiation-associated risks compared to the standard-dose computed tomography. This technique can be used as both at the first examination and the follow-up examinations. Thin-section computed tomography screenings can be used as a supplement to check if there is any nodules that have not yet been discovered. Computer-aided diagnosis is an add-on method to make sure the computed tomography screenings images are being correctly labeled. Identifying other contributing factors to the effectiveness of the early lung cancer detection, such as the amount of forced expiratory volume, forced vital capacity, and the presence of emphysema, could also decrease the percentage of false positive outcomes.
ContributorsChuang, Hao-Yun (Author) / Johnston, Stephen (Thesis director) / Peterson, Milene (Committee member) / School of Life Sciences (Contributor) / Barrett, The Honors College (Contributor)
Created2019-05
iLieDown - Improved Display Orientation For Handheld Devices Using Convolutional Neural Networks.pdf
Description
91% of smartphone and tablet users experience a problem with their device screen being oriented the wrong way during use [11]. In [11], the authors proposed iRotate, a previous solution which uses computer vision to solve the orientation problem. We propose iLieDown, an improved method of automatically rotating smartphones, tablets, and other device displays. This paper introduces a new algorithm to correctly orient the display relative to the user’s face using a convolutional neural network (CNN). The CNN model is trained to predict the rotation of faces in various environments through data augmentation, uses a confidence threshold, and analyzes multiple images to be accurate and robust. iLieDown is battery and CPU efficient, causes no noticeable lag to the user during use, and is 6x more accurate than iRotate.
ContributorsTallman, Riley Paul (Author) / Yang, Yezhou (Thesis director) / Fang, Zhiyuan (Committee member) / Computer Science and Engineering Program (Contributor, Contributor) / Barrett, The Honors College (Contributor)
Created2019-12