Matching Items (8)
Filtering by
- All Subjects: Neuroscience
- Creators: Bimonte-Nelson, Heather
- Creators: Bliss, Daniel
- Member of: Barrett, The Honors College Thesis/Creative Project Collection
- Resource Type: Text
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
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
There is preclinical evidence that the detrimental cognitive effects of hormone loss can be ameliorated by estrogen therapy (Bimonte, Acosta, & Talboom, 2010), however, one of the primary concerns with current hormone therapies is that they are nonselective, leading to increased risk of breast and endometrial cancers as well as heart disease. Thus, in order to achieve a successful and clinically relevant long-term hormone therapy option, it is optimal to find an estrogen therapy regimen that is selective to its target tissue. Recently, phytoestrogens have been found to exert selective, beneficial effects on cognition and brain. For example, genistein and diadzein produce neuroprotective effects in cognitive brain regions (Zhao, Chen, & Diaz Brinton, 2002). The purpose of this study was threefold: 1) to examine the cognitive impact of phytoestrogens in young ovariectomized rats, 2) to replicate the dose effects found in the Luine study (Luine et al., 2006), while controlling for manufacturer differences, and 3) to assess if the rodent diet used in our laboratory has an estrogenic-like cognitive impact.The current findings suggest that, at least for object memory, diets containing varying amounts of phytoestrogens can alter cognition, with diets containing high amounts of phytoestrogens showing potential benefits to this type of memory.
ContributorsWhitton, Elizabeth Nicole (Author) / Bimonte-Nelson, Heather (Thesis director) / Presson, Clark (Committee member) / Baxter, Leslie (Committee member) / Barrett, The Honors College (Contributor) / Department of Psychology (Contributor)
Created2013-05
Description
Multiple-channel detection is considered in the context of a sensor network where data can be exchanged directly between sensor nodes that share a common edge in the network graph. Optimal statistical tests used for signal source detection with multiple noisy sensors, such as the Generalized Coherence (GC) estimate, use pairwise measurements from every pair of sensors in the network and are thus only applicable when the network graph is completely connected, or when data are accumulated at a common fusion center. This thesis presents and exploits a new method that uses maximum-entropy techniques to estimate measurements between pairs of sensors that are not in direct communication, thereby enabling the use of the GC estimate in incompletely connected sensor networks. The research in this thesis culminates in a main conjecture supported by statistical tests regarding the topology of the incomplete network graphs.
ContributorsCrider, Lauren Nicole (Author) / Cochran, Douglas (Thesis director) / Renaut, Rosemary (Committee member) / Kosut, Oliver (Committee member) / Barrett, The Honors College (Contributor) / School of Mathematical and Statistical Sciences (Contributor)
Created2014-05
Description
The aim of this study was to determine whether IUD administration, with and without the presence of Levo, and with and without the presence of the ovaries, impacts cognition in a rat model. Rats received either Sham or Ovariectomy (Ovx) surgery (removal of the ovaries), plus either no IUD, a Blank IUD (without Levo), or a Levo-releasing IUD (Levo IUD), enabling us to evaluate the effects of Ovx and the effects of IUD administration on cognition. Two weeks after surgery, all treatment groups were tested on the water radial arm maze, Morris water maze, and visible platform task to evaluate cognition. At sacrifice, upon investigation of the uteri, it was determined that some of the IUDs were no longer present in animals from these groups: Sham\u2014Blank IUD, Ovx\u2014Blank IUD, and Sham\u2014Levo IUD. Results from the remaining three groups showed that compared to Sham animals with no IUDs, Ovx animals with no IUDs had marginally impaired working memory performance, and that Ovx animals with Levo IUDs as compared to Ovx animals with no IUDs had marginally enhanced memory performance, not specific to a particular memory type. Results also showed that Ovx animals with Levo IUDs had qualitatively more cells in their vaginal smears and increased uterine horn weight compared to Ovx animals with no IUDs, suggesting local stimulation of the Levo IUDs to the uterine horns. Overall, these results provide alternative evidence to the hypothesis that the Levo IUD administers Levo in solely a localized manner, and suggests that the possibility for the Levo IUD to affect reproductive cyclicity in ovary-intact animals is not rejected. The potential for the Levo IUD to exert effects on cognition suggests that either the hormone does in fact systemically circulate, or that the Levo IUD administration affects cognition by altering an as yet undetermined hormonal or other feedback between the uterus and the brain.
ContributorsStrouse, Isabel Martha (Author) / Bimonte-Nelson, Heather (Thesis director) / Glenberg, Arthur (Committee member) / Sirianni, Rachael (Committee member) / Conrad, Cheryl (Committee member) / School of Life Sciences (Contributor) / Department of Psychology (Contributor) / Barrett, The Honors College (Contributor)
Created2018-12
Description
Lossy compression is a form of compression that slightly degrades a signal in ways that are ideally not detectable to the human ear. This is opposite to lossless compression, in which the sample is not degraded at all. While lossless compression may seem like the best option, lossy compression, which is used in most audio and video, reduces transmission time and results in much smaller file sizes. However, this compression can affect quality if it goes too far. The more compression there is on a waveform, the more degradation there is, and once a file is lossy compressed, this process is not reversible. This project will observe the degradation of an audio signal after the application of Singular Value Decomposition compression, a lossy compression that eliminates singular values from a signal’s matrix.
ContributorsHirte, Amanda (Author) / Kosut, Oliver (Thesis director) / Bliss, Daniel (Committee member) / Electrical Engineering Program (Contributor, Contributor) / Barrett, The Honors College (Contributor)
Created2021-05
Description
Alzheimer’s disease (AD) is an irreversible brain disorder that plagues millions of people with no current cure. Current clinical research is slowly advancing to more definitive treatments in hopes of reducing the effects of progressive cognitive and behavioral decline, but none so far can slow AD’s onset. A brain area known as the nucleus incertus (NI) was recently discovered to potentially impact AD because of its connections to brain targets that degenerate; however, the NI’s role is unknown. This goal of this experiment was to use a transgenic mouse model (APP/PS1) that expresses AD pathology slowly as found in humans, and to test the mice in a variety of cognitive and anxiety assessments. Mice of both sexes and two different ages were used, with the first being young adult before AD pathology manifests (around 3-4 months old), and the second being around the cusp of when AD pathology manifests (late adult, 8-10 months old). The mice were tested in a variety of cognitive tasks that included the novel object recognition (NOR), Morris water maze (MWM), and the object placement (OP), with the latter being the focus of my thesis. Anxiety measures were taken from the open field (OF) and elevated plus maze (EPM) with the visible platform (VP) used to ensure mice could perform on the rigorous MWM task. In the OP, we found an age effect, where the older mice were less likely to explore the moved object during the OP compared to the younger mice; motor ability was unlikely to explain this effect. We did not find any significant age by genotype effects. These findings indicate that cognitive impairment only just started to affect the older cohort, since OP impairment was found on one measure and not another. Other measures currently being quantified will be helpful in understanding this data, and to see whether learning, memory, and anxiety are affected.
ContributorsDapon, Bianca (Author) / Conrad, Cheryl (Thesis director) / Bimonte-Nelson, Heather (Committee member) / Barrett, The Honors College (Contributor) / Department of Psychology (Contributor)
Created2023-05
Description
The cerebellum is recognized for its role in motor movement, balance, and more recently, social behavior. Cerebellar injury at birth and during critical periods reduces social preference in animal models and increases the risk of autism in humans. Social behavior is commonly assessed with the three-chamber test, where a mouse travels between chambers that contain a conspecific and an object confined under a wire cup. However, this test is unable to quantify interactive behaviors between pairs of mice, which could not be tracked until the recent development of machine learning programs that track animal behavior. In this study, both the three-chamber test and a novel freely-moving social interaction test assessed social behavior in untreated male and female mice, as well as in male mice injected with hM3Dq (excitatory) DREADDs. In the three-chamber test, significant differences were found in the time spent (female: p < 0.05, male: p < 0.001) and distance traveled (female: p < 0.05, male: p < 0.001) in the chamber with the familiar conspecific, compared to the chamber with the object, for untreated male, untreated female, and mice with activated hM3Dq DREADDs. A social memory test was added, where the object was replaced with a novel mouse. Untreated male mice spent significantly more time (p < 0.05) and traveled a greater distance (p < 0.05) in the chamber with the novel mouse, while male mice with activated hM3Dq DREADDs spent more time (p<0.05) in the chamber with the familiar conspecific. Data from the freely-moving social interaction test was used to calculate freely-moving interactive behaviors between pairs of mice and interactions with an object. No sex differences were found, but mice with excited hM3Dq DREADDs engaged in significantly more anogenital sniffing (p < 0.05) and side-side contact (p < 0.05) behaviors. All these results indicate how machine learning allows for nuanced insights into how both sex and chemogenetic excitation impact social behavior in freely-moving mice.
ContributorsNelson, Megan (Author) / Verpeut, Jessica (Thesis director) / Bimonte-Nelson, Heather (Committee member) / Barrett, The Honors College (Contributor) / Department of Psychology (Contributor) / School of Life Sciences (Contributor) / School of Mathematical and Statistical Sciences (Contributor)
Created2024-05