Matching Items (162)
Filtering by
- All Subjects: Machine Learning
- Creators: Barrett, The Honors College
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
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
Bacteria have been shown to possess a large array of regulatory mechanisms to not just respond to a diverse array of environmental stresses, but to injurious artificial proteins as well. A previous investigation introduced DX, a man-made ATP sequestering protein into Escherichia coli (E. coli) which resulted in the formation of novel endoliposome structures and induced a viable but non-culturable state (VBNC) that was not easily reversed. It was hypothesized that the broadly conserved bacterial stringent response pathway may have been responsible for the observed phenotypic changes. With the goal of unveiling the molecular mechanism behind this novel response, changes in cellular morphology and physiology upon DX expression were assessed in a population of E. coli encoding a dysfunctional relA gene, one of the two genes controlling the induction of the stringent response. It was ultimately shown that RelA directly contributed to cellular filamentation, endoliposome structure formation, and the induction of a VBNC state. While the stringent response has been extensively shown to induce a VBNC state, to our knowledge, relA has not yet been shown to induce filamentation or coordinate the formation of endoliposome structures in bacteria. As the stringent response has been shown to be increasingly involved in antibiotic tolerance, this study provided an exciting opportunity to further characterize this adaptive response pathway to aid in the future development of novel therapeutics. In addition to this, this study continued to highlight that the DX protein may serve one of the first tools to allow for the direct selection of bacteria in a VBNC state by morphologically distinguishing non-culturable cells through cellular filamentation.
ContributorsFrost, Fredrick Charles (Author) / Chaput, John (Thesis director) / Wachter, Rebekka (Committee member) / Korch, Shaleen (Committee member) / Barrett, The Honors College (Contributor) / Department of Chemistry and Biochemistry (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
Description
Nucleic acids encode the information required to create life, and polymerases are the gatekeepers charged with maintaining the storage and flow of this genetic information. Synthetic biologists utilize this universal property to modify organisms and other systems to create unique traits or improve the function of others. One of the many realms in synthetic biology involves the study of biopolymers that do not exist naturally, which is known as xenobiology. Although life depends on two biopolymers for genetic storage, it may be possible that alternative molecules (xenonucleic acids – XNAs), could be used in their place in either a living or non-living system. However, implementation of an XNA based system requires the development of polymerases that can encode and decode information stored in these artificial polymers. A strategy called directed evolution is used to modify or alter the function of a protein of interest, but identifying mutations that can modify polymerase function is made problematic by their size and overall complexity. To reduce the amount of sequence space that needs to be samples when attempting to identify polymerase variants, we can try to make informed decisions about which amino acid residues may have functional roles in catalysis. An analysis of Family B polymerases has shown that residues which are involved in substrate specificity are often highly conserved both at the sequence and structure level. In order to validate the hypothesis that a strong correlation exists between structural conservation and catalytic activity, we have selected and mutated residues in the 9°N polymerase using a loss of function mutagenesis strategy based on a computational analysis of several homologues from a diverse range of taxa. Improvement of these models will hopefully lead to quicker identification of loci which are ideal engineering targets.
ContributorsHaeberle, Tyler Matthew (Author) / Chaput, John (Thesis director) / Chen, Julian (Committee member) / Larsen, Andrew (Committee member) / Barrett, The Honors College (Contributor) / Department of Chemistry and Biochemistry (Contributor) / School of Life Sciences (Contributor)
Created2015-05
Description
Transgene expression in mammalian cells has been shown to meet resistance in the form of silencing due to chromatin buildup within the cell. Interactions of proteins with chromatin modulate gene expression profiles. Synthetic Polycomb transcription factor (PcTF) variants have the potential to reactivate these silence transgenes as shown in Haynes & Silver 2011. PcTF variants have been constructed via TypeIIS assembly to further investigate this ability to reactive transgenes. Expression in mammalian cells was confirmed via fluorescence microscopy and red fluorescent protein (RFP) expression in cell lysate. Examination of any variation in conferment of binding strength of homologous Polycomb chromodomains (PCDs) to its trimethylated lysine residue target on histone three (H3K27me3) was investigated using a thermal shift assay. Results indicate that PcTF may not be a suitable protein for surveying with SYPRO Orange, a dye that produces a detectable signal when exposed to the hydrophobic domains of the melting protein. A cell line with inducible silencing of a chemiluminescent protein was used to determine the effects PcTF variants had on gene reactivation. Results show down-regulation of the target reporter gene. We propose this may be due to PcTF not binding to its target; this would cause PcTF to deplete transcriptional machinery in the nucleus. Alternatively, the CMV promoter could be sequestering transcriptional machinery in its hyperactive transcription of PcTF leading to widespread down-regulation. Finally, the activation domain used may not be appropriate for this cell type. Future PcTF variants will address these hypotheses by including multiple Polycomb chromodomains (PCDs) to alter the binding dynamics of PcTF to its target, and by incorporating alternative promoters and activation domains.
ContributorsGardner, Cameron Lee (Author) / Haynes, Karmella (Thesis director) / Stabenfeldt, Sarah (Committee member) / Barrett, The Honors College (Contributor) / Department of Finance (Contributor) / Harrington Bioengineering Program (Contributor)
Created2015-05
Description
The OMFIT (One Modeling Framework for Integrated Tasks) modeling environment and the BRAINFUSE module have been deployed on the PPPL (Princeton Plasma Physics Laboratory) computing cluster with modifications that have rendered the application of artificial neural networks (NNs) to the TRANSP databases for the JET (Joint European Torus), TFTR (Tokamak Fusion Test Reactor), and NSTX (National Spherical Torus Experiment) devices possible through their use. This development has facilitated the investigation of NNs for predicting heat transport profiles in JET, TFTR, and NSTX, and has promoted additional investigations to discover how else NNs may be of use to scientists at PPPL. In applying NNs to the aforementioned devices for predicting heat transport, the primary goal of this endeavor is to reproduce the success shown in Meneghini et al. in using NNs for heat transport prediction in DIII-D. Being able to reproduce the results from is important because this in turn would provide scientists at PPPL with a quick and efficient toolset for reliably predicting heat transport profiles much faster than any existing computational methods allow; the progress towards this goal is outlined in this report, and potential additional applications of the NN framework are presented.
ContributorsLuna, Christopher Joseph (Author) / Tang, Wenbo (Thesis director) / Treacy, Michael (Committee member) / Orso, Meneghini (Committee member) / Barrett, The Honors College (Contributor) / School of Mathematical and Statistical Sciences (Contributor) / Department of Physics (Contributor)
Created2015-05