Matching Items (10)
Filtering by
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
The world of a hearing impaired person is much different than that of somebody capable of discerning different frequencies and magnitudes of sound waves via their ears. This is especially true when hearing impaired people play video games. In most video games, surround sound is fed through some sort of digital output to headphones or speakers. Based on this information, the gamer can discern where a particular stimulus is coming from and whether or not that is a threat to their wellbeing within the virtual world. People with reliable hearing have a distinct advantage over hearing impaired people in the fact that they can gather information not just from what is in front of them, but from every angle relative to the way they're facing. The purpose of this project was to find a way to even the playing field, so that a person hard of hearing could also receive the sensory feedback that any other person would get while playing video games To do this, visual surround sound was created. This is a system that takes a surround sound input, and illuminates LEDs around the periphery of glasses based on the direction, frequency and amplitude of the audio wave. This provides the user with crucial information on the whereabouts of different elements within the game. In this paper, the research and development of Visual Surround Sound is discussed along with its viability in regards to a deaf person's ability to learn the technology, and decipher the visual cues.
ContributorsKadi, Danyal (Co-author) / Burrell, Nathaneal (Co-author) / Butler, Kristi (Co-author) / Wright, Gavin (Co-author) / Kosut, Oliver (Thesis director) / Bliss, Daniel (Committee member) / Barrett, The Honors College (Contributor) / Electrical Engineering Program (Contributor)
Created2015-05
Description
Radio communication has become the dominant form of correspondence in modern society. As the demand for high speed communication grows, the problems associated with an expanding consumer base and limited spectral access become more difficult to address. One communications system in which people commonly find themselves is the multiple access cellular network. Users operate within the same geographical area and bandwidth, so providing access to every user requires advanced processing techniques and careful subdivision of spectral access. This is known as the multiple access problem. This paper addresses this challenge in the context of airborne transceivers operating at high altitudes and long ranges. These operators communicate by transmitting a signal through a target scattering field on the ground without a direct line of sight to the receiver. The objective of this investigation is to develop a model for this communications channel, identify and quantify the relevant characteristics, and evaluate the feasibility of using it to effectively communicate.
ContributorsHerschfelt, Andrew William (Author) / Bliss, Daniel (Thesis director) / Cochran, Douglas (Committee member) / Aberle, James (Committee member) / Electrical Engineering Program (Contributor) / Barrett, The Honors College (Contributor)
Created2015-12
Description
This work details the bootstrap estimation of a nonparametric information divergence measure, the Dp divergence measure, using a power law model. To address the challenge posed by computing accurate divergence estimates given finite size data, the bootstrap approach is used in conjunction with a power law curve to calculate an asymptotic value of the divergence estimator. Monte Carlo estimates of Dp are found for increasing values of sample size, and a power law fit is used to relate the divergence estimates as a function of sample size. The fit is also used to generate a confidence interval for the estimate to characterize the quality of the estimate. We compare the performance of this method with the other estimation methods. The calculated divergence is applied to the binary classification problem. Using the inherent relation between divergence measures and classification error rate, an analysis of the Bayes error rate of several data sets is conducted using the asymptotic divergence estimate.
ContributorsKadambi, Pradyumna Sanjay (Author) / Berisha, Visar (Thesis director) / Bliss, Daniel (Committee member) / Electrical Engineering Program (Contributor) / Barrett, The Honors College (Contributor)
Created2016-05
Description
Many mysteries still surround brain function, and yet greater understanding of it is vital to advancing scientific research. Studies on the brain in particular play a huge role in the medical field as analysis can lead to proper diagnosis of patients and to anticipatory treatments. The objective of this research was to apply signal processing techniques on electroencephalogram (EEG) data in order to extract features for which to quantify an activity performed or a response to stimuli. The responses by the brain were shown in eigenspectrum plots in combination with time-frequency plots for each of the sensors to provide both spatial and temporal frequency analysis. Through this method, it was revealed how the brain responds to various stimuli not typically used in current research. Future applications might include testing similar stimuli on patients with neurological diseases to gain further insight into their condition.
ContributorsJackson, Matthew Joseph (Author) / Bliss, Daniel (Thesis director) / Berisha, Visar (Committee member) / Electrical Engineering Program (Contributor) / Barrett, The Honors College (Contributor)
Created2016-05
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
Power spectral analysis is a fundamental aspect of signal processing used in the detection and \\estimation of various signal features. Signals spaced closely in frequency are problematic and lead analysts to miss crucial details surrounding the data. The Capon and Bartlett methods are non-parametric filterbank approaches to power spectrum estimation. The Capon algorithm is known as the "adaptive" approach to power spectrum estimation because its filter impulse responses are adapted to fit the characteristics of the data. The Bartlett method is known as the "conventional" approach to power spectrum estimation (PSE) and has a fixed deterministic filter. Both techniques rely on the Sample Covariance Matrix (SCM). The first objective of this project is to analyze the origins and characteristics of the Capon and Bartlett methods to understand their abilities to resolve signals closely spaced in frequency. Taking into consideration the Capon and Bartlett's reliance on the SCM, there is a novelty in combining these two algorithms using their cross-coherence. The second objective of this project is to analyze the performance of the Capon-Bartlett Cross Spectra. This study will involve Matlab simulations of known test cases and comparisons with approximate theoretical predictions.
ContributorsYoshiyama, Cassidy (Author) / Richmond, Christ (Thesis director) / Bliss, Daniel (Committee member) / Electrical Engineering Program (Contributor, Contributor, Contributor) / Barrett, The Honors College (Contributor)
Created2019-05
Description
Radar systems seek to detect targets in some search space (e.g. volume of airspace, or area on the ground surface) by actively illuminating the environment with radio waves. This illumination yields a return from targets of interest as well as highly reflective terrain features that perhaps are not of interest (called clutter). Data adaptive algorithms are therefore employed to provide robust detection of targets against a background of clutter and other forms of interference. The adaptive matched filter (AMF) is an effective, well-established detection statistic whose exact probability density function (PDF) is known under prevalent radar system model assumptions. Variations of this approach, however, lead to tests whose PDFs remain unknown or incalculable. This project will study the effectiveness of saddlepoint methods applied to approximate the known pdf of the clairvoyant matched filter, using MATLAB to complete the numerical calculations. Specifically, the approximation was used to compute tail probabilities for a range of thresholds, as well as compute the threshold and probability of detection for a specific desired probability of false alarm. This was compared to the same values computed using the known exact PDF of the filter, with the comparison demonstrating high levels of accuracy for the saddlepoint approximation. The results are encouraging, and justify further study of the approximation as applied to more strained or complicated scenarios.
ContributorsRhoades, Rachel (Author) / Richmond, Christ (Thesis director) / Cochran, Douglas (Committee member) / School of Mathematical and Statistical Sciences (Contributor) / Electrical Engineering Program (Contributor) / Barrett, The Honors College (Contributor)
Created2020-05
Description
Alzheimer's disease is the 6th leading cause of death in the United States and vastly affects millions across the world each year. Currently, there are no medications or treatments available to slow or stop the progression of Alzheimer’s Disease. The GENUS therapy out of the Massachusetts Institute of Technology presently shows positive results in slowing the progression of the disease among animal trials. This thesis is a continuation of that study, to develop and build a testing apparatus for human clinical trials. Included is a complete outline into the design, development, testing measures, and instructional aid for the final apparatus.
ContributorsScheller, Rachel D (Author) / Bliss, Daniel (Thesis director) / Corman, Steven (Committee member) / Electrical Engineering Program (Contributor, Contributor) / Barrett, The Honors College (Contributor)
Created2020-12