Matching Items (209)
Filtering by
- All Subjects: Machine Learning
- Creators: Barrett, The Honors College
- Member of: Theses and Dissertations
Leveraging Machine Learning and Wireless Sensing for Robot Localization - Location Variance Analysis
Description
Object localization is used to determine the location of a device, an important aspect of applications ranging from autonomous driving to augmented reality. Commonly-used localization techniques include global positioning systems (GPS), simultaneous localization and mapping (SLAM), and positional tracking, but all of these methodologies have drawbacks, especially in high traffic indoor or urban environments. Using recent improvements in the field of machine learning, this project proposes a new method of localization using networks with several wireless transceivers and implemented without heavy computational loads or high costs. This project aims to build a proof-of-concept prototype and demonstrate that the proposed technique is feasible and accurate.
Modern communication networks heavily depend upon an estimate of the communication channel, which represents the distortions that a transmitted signal takes as it moves towards a receiver. A channel can become quite complicated due to signal reflections, delays, and other undesirable effects and, as a result, varies significantly with each different location. This localization system seeks to take advantage of this distinctness by feeding channel information into a machine learning algorithm, which will be trained to associate channels with their respective locations. A device in need of localization would then only need to calculate a channel estimate and pose it to this algorithm to obtain its location.
As an additional step, the effect of location noise is investigated in this report. Once the localization system described above demonstrates promising results, the team demonstrates that the system is robust to noise on its location labels. In doing so, the team demonstrates that this system could be implemented in a continued learning environment, in which some user agents report their estimated (noisy) location over a wireless communication network, such that the model can be implemented in an environment without extensive data collection prior to release.
Modern communication networks heavily depend upon an estimate of the communication channel, which represents the distortions that a transmitted signal takes as it moves towards a receiver. A channel can become quite complicated due to signal reflections, delays, and other undesirable effects and, as a result, varies significantly with each different location. This localization system seeks to take advantage of this distinctness by feeding channel information into a machine learning algorithm, which will be trained to associate channels with their respective locations. A device in need of localization would then only need to calculate a channel estimate and pose it to this algorithm to obtain its location.
As an additional step, the effect of location noise is investigated in this report. Once the localization system described above demonstrates promising results, the team demonstrates that the system is robust to noise on its location labels. In doing so, the team demonstrates that this system could be implemented in a continued learning environment, in which some user agents report their estimated (noisy) location over a wireless communication network, such that the model can be implemented in an environment without extensive data collection prior to release.
ContributorsChang, Roger (Co-author) / Kann, Trevor (Co-author) / Alkhateeb, Ahmed (Thesis director) / Bliss, Daniel (Committee member) / Electrical Engineering Program (Contributor) / Barrett, The Honors College (Contributor)
Created2020-05
Description
At present, the vast majority of human subjects with neurological disease are still diagnosed through in-person assessments and qualitative analysis of patient data. In this paper, we propose to use Topological Data Analysis (TDA) together with machine learning tools to automate the process of Parkinson’s disease classification and severity assessment. An automated, stable, and accurate method to evaluate Parkinson’s would be significant in streamlining diagnoses of patients and providing families more time for corrective measures. We propose a methodology which incorporates TDA into analyzing Parkinson’s disease postural shifts data through the representation of persistence images. Studying the topology of a system has proven to be invariant to small changes in data and has been shown to perform well in discrimination tasks. The contributions of the paper are twofold. We propose a method to 1) classify healthy patients from those afflicted by disease and 2) diagnose the severity of disease. We explore the use of the proposed method in an application involving a Parkinson’s disease dataset comprised of healthy-elderly, healthy-young and Parkinson’s disease patients.
ContributorsRahman, Farhan Nadir (Co-author) / Nawar, Afra (Co-author) / Turaga, Pavan (Thesis director) / Krishnamurthi, Narayanan (Committee member) / Electrical Engineering Program (Contributor) / Computer Science and Engineering Program (Contributor) / Barrett, The Honors College (Contributor)
Created2020-05
Description
In this project, the use of deep neural networks for the process of selecting actions to execute within an environment to achieve a goal is explored. Scenarios like this are common in crafting based games such as Terraria or Minecraft. Goals in these environments have recursive sub-goal dependencies which form a dependency tree. An agent operating within these environments have access to low amounts of data about the environment before interacting with it, so it is crucial that this agent is able to effectively utilize a tree of dependencies and its environmental surroundings to make judgements about which sub-goals are most efficient to pursue at any point in time. A successful agent aims to minimizes cost when completing a given goal. A deep neural network in combination with Q-learning techniques was employed to act as the agent in this environment. This agent consistently performed better than agents using alternate models (models that used dependency tree heuristics or human-like approaches to make sub-goal oriented choices), with an average performance advantage of 33.86% (with a standard deviation of 14.69%) over the best alternate agent. This shows that machine learning techniques can be consistently employed to make goal-oriented choices within an environment with recursive sub-goal dependencies and low amounts of pre-known information.
ContributorsKoleber, Derek (Author) / Acuna, Ruben (Thesis director) / Bansal, Ajay (Committee member) / W.P. Carey School of Business (Contributor) / Software Engineering (Contributor) / Barrett, The Honors College (Contributor)
Created2018-05
Description
This thesis dives into the world of artificial intelligence by exploring the functionality of a single layer artificial neural network through a simple housing price classification example while simultaneously considering its impact from a data management perspective on both the software and hardware level. To begin this study, the universally accepted model of an artificial neuron is broken down into its key components and then analyzed for functionality by relating back to its biological counterpart. The role of a neuron is then described in the context of a neural network, with equal emphasis placed on how it individually undergoes training and then for an entire network. Using the technique of supervised learning, the neural network is trained with three main factors for housing price classification, including its total number of rooms, bathrooms, and square footage. Once trained with most of the generated data set, it is tested for accuracy by introducing the remainder of the data-set and observing how closely its computed output for each set of inputs compares to the target value. From a programming perspective, the artificial neuron is implemented in C so that it would be more closely tied to the operating system and therefore make the collected profiler data more precise during the program's execution. The program is designed to break down each stage of the neuron's training process into distinct functions. In addition to utilizing more functional code, the struct data type is used as the underlying data structure for this project to not only represent the neuron but for implementing the neuron's training and test data. Once fully trained, the neuron's test results are then graphed to visually depict how well the neuron learned from its sample training set. Finally, the profiler data is analyzed to describe how the program operated from a data management perspective on the software and hardware level.
ContributorsRichards, Nicholas Giovanni (Author) / Miller, Phillip (Thesis director) / Meuth, Ryan (Committee member) / Computer Science and Engineering Program (Contributor) / Barrett, The Honors College (Contributor)
Created2018-05
Description
Transient Receptor Potential (TRP) ion channels are a diverse family of nonselective, polymodal sensors in uni- and multicellular eukaryotes that are implicated in an assortment of biological contexts and human disease. The cold-activated TRP Melastatin-8 (TRPM8) channel, also recognized as the human body's primary cold sensor, is among the few TRP channels responsible for thermosensing. Despite sustained interest in the channel, the mechanisms underlying TRPM8 activation, modulation, and gating have proved challenging to study and remain poorly understood. In this thesis, I offer data collected on various expression, extraction, and purification conditions tested in E. Coli expression systems with the aim to optimize the generation of a structurally stable and functional human TRPM8 pore domain (S5 and S6) construct for application in structural biology studies. These studies, including the biophysical technique nuclear magnetic spectroscopy (NMR), among others, will be essential for elucidating the role of the TRPM8 pore domain in in regulating ligand binding, channel gating, ion selectively, and thermal sensitivity. Moreover, in the second half of this thesis, I discuss the ligation-independent megaprimer PCR of whole-plasmids (MEGAWHOP PCR) cloning technique, and how it was used to generate chimeras between TRPM8 and its nearest analog TRPM2. I review steps taken to optimize the efficiency of MEGAWHOP PCR and the implications and unique applications of this novel methodology for advancing recombinant DNA technology. I lastly present preliminary electrophysiological data on the chimeras, employed to isolate and study the functional contributions of each individual transmembrane helix (S1-S6) to TRPM8 menthol activation. These studies show the utility of the TRPM8\u2014TRPM2 chimeras for dissecting function of TRP channels. The average current traces analyzed thus far indicate that the S2 and S3 helices appear to play an important role in TRPM8 menthol modulation because the TRPM8[M2S2] and TRPM8[M2S3] chimeras significantly reduce channel conductance in the presence of menthol. The TRPM8[M2S4] chimera, oppositely, increases channel conductance, implying that the S4 helix in native TRPM8 may suppress menthol modulation. Overall, these findings show that there is promise in the techniques chosen to identify specific regions of TRPM8 crucial to menthol activation, though the methods chosen to study the TRPM8 pore independent from the whole channel may need to be reevaluated. Further experiments will be necessary to refine TRPM8 pore solubilization and purification before structural studies can proceed, and the electrophysiology traces observed for the chimeras will need to be further verified and evaluated for consistency and physiological significance.
ContributorsWaris, Maryam Siddika (Author) / Van Horn, Wade (Thesis director) / Redding, Kevin (Committee member) / School of Molecular Sciences (Contributor) / Department of English (Contributor) / Barrett, The Honors College (Contributor)
Created2016-05
Description
This study looks to answer whether or not citizens have reason to believe the publicity statements from state government officials when speaking about gun-control laws during the time surrounding mass shootings. Citizens in America see the same, consistent pattern that politicians use mass shootings for, known as "The Shooting Cycle." Here, we will research whether or not these politicians are continuing to keep the same voting pattern that they have had in the past, in terms of gun control. This case study uses quantitative research to discover that almost all state representative and senators have consistent voting patterns when it comes to gun control legislation, regardless of time distances around mass shootings. We will then seek out seek out public statements and relevant periodicals and media clips in order to determine whether or not these voting patterns align with the public's perception of a politician's stance on gun control. It also uses qualitative research to discover that publicity from senators and representatives that support gun rights have more consistency in their public statements than those who are either inconsistent or consistently vote for gun control legislation. This study creates opportunities for new research in voting patterns and political transparency on state officials and the significant effects of mass shootings on public opinions and public statements from state officials.
ContributorsMoore, Travis David (Author) / Wu, Xu (Thesis director) / Wells, David (Committee member) / Barrett, The Honors College (Contributor) / Walter Cronkite School of Journalism and Mass Communication (Contributor) / School of Politics and Global Studies (Contributor)
Created2015-05
Description
A series of mitochondria targeting probes was synthesized for the purpose of exploring the feasibility of a mitochondria targeting fluorescent sensor. Of the probes, the probe with a two carbon spacer showed the best co-localization from staining with the established MitoTracker Red® FM, indicating a potential development of the probe into mitochondria targeting sensor. However, cytotoxicity was observed for the probe with a six carbon spacer. Three additional mitochondria targeting fluorescent probes of longer spacer groups were synthesized, but the cytotoxicity was not observed to be as high as that of the probe with a two carbon spacer. The cytotoxicity was characterized to be that of caspase dependent cell death. To screen for a possible effect on apoptosis due to the mitochondrial probe, three fluorescent fusion proteins binding the anti-apoptotic proteins were designed and expressed. Each purified fusion protein was then incubated with the cytotoxic mitochondrial probe, and the mixture was isolated by running an affinity column. The fluorescence analysis of eluted fractions showed preliminary data of possible interaction between the protein and the mitochondrial probe.
ContributorsLee, Fred (Author) / Meldrum, Deirdre R. (Thesis director) / Tian, Yanqing (Committee member) / Zhang, Liqiang (Committee member) / Barrett, The Honors College (Contributor) / Chemical Engineering Program (Contributor) / Department of Chemistry and Biochemistry (Contributor)
Created2014-12
Description
Epilepsy affects numerous people around the world and is characterized by recurring seizures, prompting the ability to predict them so precautionary measures may be employed. One promising algorithm extracts spatiotemporal correlation based features from intracranial electroencephalography signals for use with support vector machines. The robustness of this methodology is tested through a sensitivity analysis. Doing so also provides insight about how to construct more effective feature vectors.
ContributorsMa, Owen (Author) / Bliss, Daniel (Thesis director) / Berisha, Visar (Committee member) / Barrett, The Honors College (Contributor) / Electrical Engineering Program (Contributor)
Created2015-05
Description
As prices for fuel along with the demand for renewable resources grow, it becomes of paramount importance to develop new ways of obtaining the energy needed to carry out the tasks we face daily. Costs of production due to energy and time constraints impose severe limitations on what is viable. Biological systems, on the other hand, are innately efficient both in terms of time and energy by handling tasks at the molecular level. Utilizing this efficiency is at the core of this research. Proper manipulation of even common proteins can render complexes functionalized for specific tasks. In this case, the coupling of a rhenium-based organometallic ligand to a modified myoglobin containing a zinc porphyrin, allow for efficient reduction of carbon dioxide, resulting in energy that can be harnessed and byproducts which can be used for further processing. Additionally, a rhenium based ligand functionalized via biotin is tested in conjunction with streptavidin and ruthenium-bipyridine.
ContributorsAllen, Jason Kenneth (Author) / Ghirlanda, Giovanna (Thesis director) / Francisco, Wilson (Committee member) / Barrett, The Honors College (Contributor) / Chemical Engineering Program (Contributor)
Created2014-12
Description
Bots tamper with social media networks by artificially inflating the popularity of certain topics. In this paper, we define what a bot is, we detail different motivations for bots, we describe previous work in bot detection and observation, and then we perform bot detection of our own. For our bot detection, we are interested in bots on Twitter that tweet Arabic extremist-like phrases. A testing dataset is collected using the honeypot method, and five different heuristics are measured for their effectiveness in detecting bots. The model underperformed, but we have laid the ground-work for a vastly untapped focus on bot detection: extremist ideal diffusion through bots.
ContributorsKarlsrud, Mark C. (Author) / Liu, Huan (Thesis director) / Morstatter, Fred (Committee member) / Barrett, The Honors College (Contributor) / Computing and Informatics Program (Contributor) / Computer Science and Engineering Program (Contributor) / School of Mathematical and Statistical Sciences (Contributor)
Created2015-05