Matching Items (179)
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
This is a constructed language made for fictional creatures that will be featured in a novel. The creatures are feral goblins, and they are based on Irish mythology. The novel that the goblins and the language will be featured in is titled MaddConn, and it was written by Jon Bendera. It is an urban fantasy novel. The goblins have a language in the novel because there are a number of goblin characters throughout the story. One of the main characters, Maddi, has to survive amongst the feral goblins for a portion of the novel while another main character, Connor, works his way to her. She has multiple close encounters with them, and also has to find her way around their territory, so she comes into contact with the language many times. Although the language in the story was created to have developed prior to humanity, this constructed language was made to look somewhat similar to human language. As it will be involved in fiction that will be read by humans, it needs to be easily understood by humans. The language reveals features of the goblin culture and anatomy. For instance, it can be seen in the language that their shallow, wide mouths and thin lips influence their phonology. Their physiology influences much of their language. Likewise, they have three fingers on each hand, which influences their number system. As the goblins and their language developed before humans and because they are not human creatures, the typology and word order do not follow all of the correlations found in human languages. All in all, the lexicon includes many words that have to do with three of their favorite things: violence, food, and work.
ContributorsMartinez, Randi Nicole (Author) / Van Gelderen, Elly (Thesis director) / Maring, Heather (Committee member) / Schreyer, Christine (Committee member) / Department of English (Contributor, Contributor, Contributor) / Barrett, The Honors College (Contributor)
Created2017-05
Description
Current and recent trends in Galician sociolinguistics merit a study into the ongoing theoretical deadlock surrounding the standardization and normalization of Galego—the endonym of the local language. To this effect, this research aims primarily to i) evaluate the ideological frameworks of the two prevailing theories regarding the institutionalization of a Standard Galician (reintegrationism and isolationism) and the enduring conflict therein, ii) to cross-examine these theories' foundational assumptions and assertions with actual linguistic attitudes among the Galician (and, where relevant, Portuguese) public and their corresponding trends, and iii) to present relevant suggestions for practical mediation between the competing linguistic institutions advocating their own linguistic tenets with rigid austerity. By drawing upon previous academic material investigating these and other cultural, social, political and economic influences on the ongoing reestablishment of the Galician language, we can adequately appraise the transitional presence in modern Galician society as both a tool of communication and a symbol of sociocultural identity within Galicia and across its borders.
ContributorsDoyle-Matta, Joaquin (Author) / Barrett, The Honors College (Contributor)
Created2016-12
Description
Abstract:
Moldova is one of the smallest and poorest countries in Europe, yet it has a rich and multifaceted history that makes it an interesting case study when exploring the complex connections between language and identity. In this paper, I aim to explore the situation of the Soviet Union and the identity of Moldovans in regards to language policies, as well as the historic and social landscapes that allowed such policies to take hold, such has Moldova's historical roots with Romania. Although it has been over twenty years since the fall of the Soviet Union, an iron curtain still deeply divides the country of Moldova, and the cleavages are felt and defined in terms of linguistic identity. While the true conflicts and issues at stake in Moldova run much deeper than differences in linguistic identity and in issues surrounding minority language rights (for example, economic concerns), such discord is consistently framed in terms of linguistic conflict—a central theme in the Republic of Moldova ever since Soviet influence began in the 1920s.
Moldova is one of the smallest and poorest countries in Europe, yet it has a rich and multifaceted history that makes it an interesting case study when exploring the complex connections between language and identity. In this paper, I aim to explore the situation of the Soviet Union and the identity of Moldovans in regards to language policies, as well as the historic and social landscapes that allowed such policies to take hold, such has Moldova's historical roots with Romania. Although it has been over twenty years since the fall of the Soviet Union, an iron curtain still deeply divides the country of Moldova, and the cleavages are felt and defined in terms of linguistic identity. While the true conflicts and issues at stake in Moldova run much deeper than differences in linguistic identity and in issues surrounding minority language rights (for example, economic concerns), such discord is consistently framed in terms of linguistic conflict—a central theme in the Republic of Moldova ever since Soviet influence began in the 1920s.
ContributorsForee, Emily (Author) / Bahtchevanova, Mariana (Committee member) / Danton, Naomi (Contributor) / Barrett, The Honors College (Contributor)
Created2014-05
Description
This paper investigates the usage of the Japanese sentence-final construction no(da) in 27 postings collected from online question-and-answer forums. This linguistic feature appears frequently in both spoken and written Japanese discourse; however, it continues to pose difficulties to researchers when attempting to identify its meaning and functions. A major issue is that insufficient information regarding discourse context has resulted in ambiguity in many of the functions described in previous studies. Considering these limitations, the present study attempted to specify discourse contexts towards which three proposed functions of no(da) gravitate: 1) giving and asking explanation, 2) evoking politeness, and 3) organizing discourse. The results of this study indicate that two collocations, ~no desu ga and ~no deshou ka, play important roles in serving these functions in the genre of question-and-answer forums.
ContributorsAlvillar, Satomi Noelle (Author) / Tanno, Koji (Thesis director) / Shimomura, Tomoko (Committee member) / Barrett, The Honors College (Contributor) / School of International Letters and Cultures (Contributor)
Created2014-12
Description
As my year abroad in France was vastly approaching, it became apparent that the accessibility of certain resources would prove beneficial in the pursuit of my honors thesis in French. Thus, even before my departure it was decided that I would focus on the French texting language. While the specifics were not yet fully developed, it was certain that the subject was relevant as the use of communication technologies were becoming more prevalent amongst younger generations. Upon my arrival in Lyon, the objective of my thesis was realized as I began to slowly understand the descriptive nuances of both spoken French and the ever-changing texting language. As a language student, it felt necessary to understand and analyze both the prescriptive and descriptive facets of the French language, including those of the text shorthand. Therefore, it was my intention to learn the vocabulary and linguistic traits that were most frequented in this distinct jargon, not solely for myself, but also for my fellow students of French. This task was accomplished by reading and recording the text messages from ten native speakers. These texts were then compiled into a proper corpus, which was primarily used as the resource for the further applied projects I wished to create. Given this research, a type of dictionary was organized from the words that I found to be most exemplary of the French texting language. In addition, an analysis was also written concerning the common linguistics traits found in the corpus. It was my intent to provide the students of Arizona State University with relevant resources that could assist in the immersion process during or before their study abroad experience. In pursuit of any language, it seems that it is integral to maintain a sense of understanding of all common elements of a language, as they are constantly evolving. Thus, it was important for me in my attempt to master French that I understood all the nuances of the vernacular that were being used by the native speakers.
ContributorsMarquez, Monique Evangeline (Author) / Bahtchevanova, Mariana (Thesis director) / Danton, Naomi (Committee member) / Barrett, The Honors College (Contributor) / School of International Letters and Cultures (Contributor)
Created2014-12
Description
The rise of Italian in Sicily contrasts with a fierce regional pride that makes it difficult to determine the possible fate of Sicilian. This project focuses on a sociolinguistic analysis of the dialect of Sicilian spoken in and around Catania, Sicily. While there are programs in place to protect the language, the institutionalization of Italian in Sicily may be encroaching on Sicilian's use, especially with younger generations. The lure of the more industrialized North creates a culture of immigration in Sicily, which increasingly rewards the use of Italian. Using information from background research, a survey analyzing sociolinguistic factors and the individual's fluency in and use of Sicilian was created. The data from the survey showed that while understanding of Sicilian was fairly universal among participants, an individual's use and proficiency in Sicilian were most influenced by age and current place of residence (inside or outside Sicily). Younger people tended to know and use Sicilian less, and older participants tended to be more confident in their abilities and to use Sicilian more often. This is slightly complicated by an additional trend among participants currently living outside of Sicily towards a lower level of use and knowledge of Sicilian. All participants placed a significant emphasis on maintaining the ability to speak Sicilian, and on Sicilian language as an integral part of Sicilian culture.
ContributorsScaduto, Leah Christine (Author) / Dal Martello, Chiara (Thesis director) / Adams, Karen (Committee member) / Barrett, The Honors College (Contributor) / School of International Letters and Cultures (Contributor) / School of Politics and Global Studies (Contributor) / Sandra Day O'Connor College of Law (Contributor) / Department of English (Contributor)
Created2015-05