Matching Items (149)
Description
In an effort to address the lack of literature in on-campus active travel, this study aims to investigate the following primary questions:<br/>• What are the modes that students use to travel on campus?<br/>• What are the motivations that underlie the mode choice of students on campus?<br/>My first stage of research involved a series of qualitative investigations. I held one-on-one virtual interviews with students in which I asked them questions about the mode they use and why they feel that their chosen mode works best for them. These interviews served two functions. First, they provided me with insight into the various motivations underlying student mode choice. Second, they provided me with an indication of what explanatory variables should be included in a model of mode choice on campus.<br/>The first half of the research project informed a quantitative survey that was released via the Honors Digest to attract student respondents. Data was gathered on travel behavior as well as relevant explanatory variables.<br/>My analysis involved developing a logit model to predict student mode choice on campus and presenting the model estimation in conjunction with a discussion of student travel motivations based on the qualitative interviews. I use this information to make a recommendation on how campus infrastructure could be modified to better support the needs of the student population.
ContributorsMirtich, Laura Christine (Author) / Salon, Deborah (Thesis director) / Fang, Kevin (Committee member) / School of Public Affairs (Contributor) / School of Life Sciences (Contributor) / Barrett, The Honors College (Contributor)
Created2021-05
Description
Second-generation biofuel feedstocks are currently grown in land-based systems that use valuable resources like water, electricity and fertilizer. This study investigates the potential of near-shore marine (ocean) seawater filtration as a source of planktonic biomass for biofuel production. Mixed marine organisms in the size range of 20µm to 500µm were isolated from the University of California, Santa Barbara (UCSB) seawater filtration system during weekly backwash events between the months of April and August, 2011. The quantity of organic material produced was determined by sample combustion and calculation of ash-free dry weights. Qualitative investigation required density gradient separation with the heavy liquid sodium metatungstate followed by direct transesterification and gas chromatography with mass spectrometry (GC-MS) of the fatty acid methyl esters (FAME) produced. A maximum of 0.083g/L of dried organic material was produced in a single backwash event and a study average of 0.036g/L was calculated. This equates to an average weekly value of 7,674.75g of dried organic material produced from the filtration of approximately 24,417,792 liters of seawater. Temporal variations were limited. Organic quantities decreased over the course of the study. Bio-fouling effects from mussel overgrowth inexplicably increased production values when compared to un-fouled seawater supply lines. FAMEs (biodiesel) averaged 0.004% of the dried organic material with 0.36ml of biodiesel produced per week, on average. C16:0 and C22:6n3 fatty acids comprised the majority of the fatty acids in the samples. Saturated fatty acids made up 30.71% to 44.09% and unsaturated forms comprised 55.90% to 66.32% of the total chemical composition. Both quantities and qualities of organics and FAMEs were unrealistic for use as biodiesel but sample size limitations, system design, geographic and temporal factors may have impacted study results.
ContributorsPierre, Christophe (Author) / Olson, Larry (Thesis advisor) / Sommerfeld, Milton (Committee member) / Brown, Albert (Committee member) / Arizona State University (Publisher)
Created2011
Description
In 2010, a monthly sampling regimen was established to examine ecological differences in Saguaro Lake and Lake Pleasant, two Central Arizona reservoirs. Lake Pleasant is relatively deep and clear, while Saguaro Lake is relatively shallow and turbid. Preliminary results indicated that phytoplankton biomass was greater by an order of magnitude in Saguaro Lake, and that community structure differed. The purpose of this investigation was to determine why the reservoirs are different, and focused on physical characteristics of the water column, nutrient concentration, community structure of phytoplankton and zooplankton, and trophic cascades induced by fish populations. I formulated the following hypotheses: 1) Top-down control varies between the two reservoirs. The presence of piscivore fish in Lake Pleasant results in high grazer and low primary producer biomass through trophic cascades. Conversely, Saguaro Lake is controlled from the bottom-up. This hypothesis was tested through monthly analysis of zooplankton and phytoplankton communities in each reservoir. Analyses of the nutritional value of phytoplankton and DNA based molecular prey preference of zooplankton provided insight on trophic interactions between phytoplankton and zooplankton. Data from the Arizona Game and Fish Department (AZGFD) provided information on the fish communities of the two reservoirs. 2) Nutrient loads differ for each reservoir. Greater nutrient concentrations yield greater primary producer biomass; I hypothesize that Saguaro Lake is more eutrophic, while Lake Pleasant is more oligotrophic. Lake Pleasant had a larger zooplankton abundance and biomass, a larger piscivore fish community, and smaller phytoplankton abundance compared to Saguaro Lake. Thus, I conclude that Lake Pleasant was controlled top-down by the large piscivore fish population and Saguaro Lake was controlled from the bottom-up by the nutrient load in the reservoir. Hypothesis 2 stated that Saguaro Lake contains more nutrients than Lake Pleasant. However, Lake Pleasant had higher concentrations of dissolved nitrogen and phosphorus than Saguaro Lake. Additionally, an extended period of low dissolved N:P ratios in Saguaro Lake indicated N limitation, favoring dominance of N-fixing filamentous cyanobacteria in the phytoplankton community in that reservoir.
ContributorsSawyer, Tyler R (Author) / Neuer, Susanne (Thesis advisor) / Childers, Daniel L. (Committee member) / Sommerfeld, Milton (Committee member) / Arizona State University (Publisher)
Created2011
Description
Currently, autonomous vehicles are being evaluated by how well they interact with humans without evaluating how well humans interact with them. Since people are not going to unanimously switch over to using autonomous vehicles, attention must be given to how well these new vehicles signal intent to human drivers from the driver’s point of view. Ineffective communication will lead to unnecessary discomfort among drivers caused by an underlying uncertainty about what an autonomous vehicle is or isn’t about to do. Recent studies suggest that humans tend to fixate on areas of higher uncertainty so scenarios that have a higher number of vehicle fixations can be reasoned to be more uncertain. We provide a framework for measuring human uncertainty and use the framework to measure the effect of empathetic vs non-empathetic agents. We used a simulated driving environment to create recorded scenarios and manipulate the autonomous vehicle to include either an empathetic or non-empathetic agent. The driving interaction is composed of two vehicles approaching an uncontrolled intersection. These scenarios were played to twelve participants while their gaze was recorded to track what the participants were fixating on. The overall intent was to provide an analytical framework as a tool for evaluating autonomous driving features; and in this case, we choose to evaluate how effective it was for vehicles to have empathetic behaviors included in the autonomous vehicle decision making. A t-test analysis of the gaze indicated that empathy did not in fact reduce uncertainty although additional testing of this hypothesis will be needed due to the small sample size.
ContributorsGreenhagen, Tanner Patrick (Author) / Yang, Yezhou (Thesis director) / Jammula, Varun C (Committee member) / Computer Science and Engineering Program (Contributor, Contributor) / Barrett, The Honors College (Contributor)
Created2021-05
Description
Phytoplankton comprise the base of the marine food web, and, along with heterotrophic protists, they are key players in the biological pump that transports carbon from the surface to the deep ocean. In the world's subtropical oligotrophic gyres, plankton communities exhibit strong seasonality. Winter storms vent deep water into the euphotic zone, triggering a surge in primary productivity in the form of a spring phytoplankton bloom. Although the hydrographic trends of this "boom and bust" cycle have been well studied for decades, community composition and its seasonal and annual variability remains an integral subject of research. It is hypothesized here that proportions of different phytoplankton and protistan taxa vary dramatically between seasons and years, and that picoplankton represent an important component of this community and contributor to carbon in the surface ocean. Monthly samples from the Bermuda Atlantic Time-series Study (BATS) site were analyzed by epifluorescence microscopy, which permits classification by morphology, size, and trophic type. Epifluorescence counts were supplemented with flow cytometric quantification of Synechococcus, Prochlorococcus, and autotrophic pico- and nanoeukaryotes. Results from this study indicate Synechococcus and Prochlorococcus, prymnesiophytes, and hetero- and mixotrophic nano- and dinoflagellates were the major players in the BATS region plankton community. Ciliates, cryptophytes, diatoms, unidentified phototrophs, and other taxa represented rarer groups. Both flow cytometry and epifluorescence microscopy revealed Synechococcus to be most prevalent during the spring bloom. Prymnesiophytes likewise displayed distinct seasonality, with the highest concentrations again being noted during the bloom. Heterotrophic nano- and dinoflagellates, however, were most common in fall and winter. Mixotrophic dinoflagellates, while less abundant than their heterotrophic counterparts, displayed similar seasonality. A key finding of this study was the interannual variability revealed between the two years. While most taxa were more abundant in the first year, prymnesiophytes experienced much greater abundance in the second year bloom. Analyses of integrated carbon revealed further stark contrasts between the two years, both in terms of total carbon and the contributions of different groups. Total integrated carbon varied widely in the first study year but displayed less fluctuation after June 2009, and values were noticeably reduced in the second year.
ContributorsHansen, Amy (Author) / Neuer, Susanne (Thesis advisor) / Krajmalnik-Brown, Rosa (Committee member) / Sommerfeld, Milton (Committee member) / Arizona State University (Publisher)
Created2010
Description
In the last decade, a large variety of algorithms have been developed for use in object tracking, environment mapping, and object classification. It is often difficult for beginners to fully predict the constraints that multirotors place on machine vision algorithms. The purpose of this paper is to explain some of the types of algorithms that can be applied to these aerial systems, why the constraints for these algorithms exist, and what could be done to mitigate them. This paper provides a summary of the processes involved in a popular filter-based tracking algorithm called MOSSE (Minimum Output Sum of Squared Error) and a particular implementation of SLAM (Simultaneous Localization and Mapping) called LSD SLAM.
ContributorsVan Hazel, Colton (Author) / Zhang, Wenlong (Thesis director) / Yang, Yezhou (Committee member) / Engineering Programs (Contributor, Contributor) / Barrett, The Honors College (Contributor)
Created2020-05
Description
A defense-by-randomization framework is proposed as an effective defense mechanism against different types of adversarial attacks on neural networks. Experiments were conducted by selecting a combination of differently constructed image classification neural networks to observe which combinations applied to this framework were most effective in maximizing classification accuracy. Furthermore, the reasons why particular combinations were more effective than others is explored.
ContributorsMazboudi, Yassine Ahmad (Author) / Yang, Yezhou (Thesis director) / Ren, Yi (Committee member) / School of Mathematical and Statistical Sciences (Contributor) / Economics Program in CLAS (Contributor) / Barrett, The Honors College (Contributor)
Created2019-05
Description
Propaganda bots are malicious bots on Twitter that spread divisive opinions and support political accounts. This project is based on detecting propaganda bots on Twitter using machine learning. Once I began to observe patterns within propaganda followers on Twitter, I determined that I could train algorithms to detect these bots. The paper focuses on my development and process of training classifiers and using them to create a user-facing server that performs prediction functions automatically. The learning goals of this project were detailed, the focus of which was to learn some form of machine learning architecture. I needed to learn some aspect of large data handling, as well as being able to maintain these datasets for training use. I also needed to develop a server that would execute these functionalities on command. I wanted to be able to design a full-stack system that allowed me to create every aspect of a user-facing server that can execute predictions using the classifiers that I design.
Throughout this project, I decided on a number of learning goals to consider it a success. I needed to learn how to use the supporting libraries that would help me to design this system. I also learned how to use the Twitter API, as well as create the infrastructure behind it that would allow me to collect large amounts of data for machine learning. I needed to become familiar with common machine learning libraries in Python in order to create the necessary algorithms and pipelines to make predictions based on Twitter data.
This paper details the steps and decisions needed to determine how to collect this data and apply it to machine learning algorithms. I determined how to create labelled data using pre-existing Botometer ratings, and the levels of confidence I needed to label data for training. I use the scikit-learn library to create these algorithms to best detect these bots. I used a number of pre-processing routines to refine the classifiers’ precision, including natural language processing and data analysis techniques. I eventually move to remotely-hosted versions of the system on Amazon web instances to collect larger amounts of data and train more advanced classifiers. This leads to the details of my final implementation of a user-facing server, hosted on AWS and interfacing over Gmail’s IMAP server.
The current and future development of this system is laid out. This includes more advanced classifiers, better data analysis, conversions to third party Twitter data collection systems, and user features. I detail what it is I have learned from this exercise, and what it is I hope to continue working on.
Throughout this project, I decided on a number of learning goals to consider it a success. I needed to learn how to use the supporting libraries that would help me to design this system. I also learned how to use the Twitter API, as well as create the infrastructure behind it that would allow me to collect large amounts of data for machine learning. I needed to become familiar with common machine learning libraries in Python in order to create the necessary algorithms and pipelines to make predictions based on Twitter data.
This paper details the steps and decisions needed to determine how to collect this data and apply it to machine learning algorithms. I determined how to create labelled data using pre-existing Botometer ratings, and the levels of confidence I needed to label data for training. I use the scikit-learn library to create these algorithms to best detect these bots. I used a number of pre-processing routines to refine the classifiers’ precision, including natural language processing and data analysis techniques. I eventually move to remotely-hosted versions of the system on Amazon web instances to collect larger amounts of data and train more advanced classifiers. This leads to the details of my final implementation of a user-facing server, hosted on AWS and interfacing over Gmail’s IMAP server.
The current and future development of this system is laid out. This includes more advanced classifiers, better data analysis, conversions to third party Twitter data collection systems, and user features. I detail what it is I have learned from this exercise, and what it is I hope to continue working on.
ContributorsPeterson, Austin (Author) / Yang, Yezhou (Thesis director) / Sadasivam, Aadhavan (Committee member) / Computer Science and Engineering Program (Contributor) / Barrett, The Honors College (Contributor)
Created2019-05
Description
In the field of machine learning, reinforcement learning stands out for its ability to explore approaches to complex, high dimensional problems that outperform even expert humans. For robotic locomotion tasks reinforcement learning provides an approach to solving them without the need for unique controllers. In this thesis, two reinforcement learning algorithms, Deep Deterministic Policy Gradient and Group Factor Policy Search are compared based upon their performance in the bipedal walking environment provided by OpenAI gym. These algorithms are evaluated on their performance in the environment and their sample efficiency.
ContributorsMcDonald, Dax (Author) / Ben Amor, Heni (Thesis director) / Yang, Yezhou (Committee member) / Barrett, The Honors College (Contributor) / Computer Science and Engineering Program (Contributor)
Created2018-12
iLieDown - Improved Display Orientation For Handheld Devices Using Convolutional Neural Networks.pdf
Description
91% of smartphone and tablet users experience a problem with their device screen being oriented the wrong way during use [11]. In [11], the authors proposed iRotate, a previous solution which uses computer vision to solve the orientation problem. We propose iLieDown, an improved method of automatically rotating smartphones, tablets, and other device displays. This paper introduces a new algorithm to correctly orient the display relative to the user’s face using a convolutional neural network (CNN). The CNN model is trained to predict the rotation of faces in various environments through data augmentation, uses a confidence threshold, and analyzes multiple images to be accurate and robust. iLieDown is battery and CPU efficient, causes no noticeable lag to the user during use, and is 6x more accurate than iRotate.
ContributorsTallman, Riley Paul (Author) / Yang, Yezhou (Thesis director) / Fang, Zhiyuan (Committee member) / Computer Science and Engineering Program (Contributor, Contributor) / Barrett, The Honors College (Contributor)
Created2019-12