Matching Items (678)
Filtering by
- All Subjects: Machine Learning
- All Subjects: Nutrition
- Resource Type: Text
Description
As part of the recently passed Patient Protection and Affordable Care Act, chain restaurants with 20 or more locations nationwide are required to post calorie information on menus and menu boards in order to help consumers make healthier decisions when dining out. Previous studies that have evaluated menu-labeling policies show mixed results and the majority have been conducted in urban cities along the east coast. This study was the first to look at the effectiveness of menu labeling in a southwest population. The primary objective of this cross-sectional study was to determine if noticing or using calorie menu labels in a fast food restaurant was associated with purchasing fewer calories. A second aim of this study was to evaluate the relationship between socio-demographic characteristics and the likelihood of noticing and using menu labeling. Customer receipts and survey data were collected from 329 participants using street-intercept survey methodology at 29 McDonald's locations in low- and high-income neighborhoods throughout the Phoenix metropolitan area. The study population was 63.5% male, 53.8% non-Hispanic white, and 50.8% low-income. Results showed that almost 60% of the study sample noticed calorie menu labeling and only 16% of participants reported using the information for food or beverage purchases. Income was the only socio-demographic characteristic that was associated with noticing menu labeling, with higher-income individuals being more likely to notice the information (p=0.029). Income was also found to be associated with using menu labels, with higher income individuals being more likely to use the information (p=0.04). Additionally, individuals with a bachelors degree or higher were more likely to use the information (p=0.023) and individuals aged 36 to 49 were least likely to use the information (p=0.046). There were no significant differences in average calories purchased among those who noticed menu labeling; however, those who reported using calorie information purchased 146 fewer calories than those who did not use the information (p=0.001). Based on these findings it is concluded that calorie menu labeling is an effective public policy and that nutrition education campaigns should accompany national menu labeling implementation in order to make the policy more effective across all socio-demographic groups.
ContributorsGreen, Jessie (Author) / Ohri-Vachaspati, Punam (Thesis advisor) / Bruening, Meg (Committee member) / Wharton, Christopher (Christopher Mack), 1977- (Committee member) / Arizona State University (Publisher)
Created2014
Description
ABSTRACT The hormone leptin is an important regulator of body weight and energy balance, while nitric oxide (NO) produced in the blood vessels is beneficial for preventing disease-induced impaired vasodilation and hypertension. Elevations in the free radical superoxide can result in impaired vasodilation through scavenging of NO. Omega 3 is a polyunsaturated fatty acid that is beneficial at reducing body weight and in lowering many cardiovascular risk factors like atherosclerosis. The present study was designed to examine the change in plasma concentrations of leptin, nitric oxide, and the antioxidant superoxide dismutase in addition to examining the association between leptin and NO in healthy normal weight adult female subjects before and following omega 3 intakes. Participants were randomly assigned to either a fish oil group (600 mg per day) or a control group (1000 mg of coconut oil per day) for 8 weeks. Results showed no significant difference in the percent change of leptin over the 8 week supplementation period for either group (15.3±31.9 for fish oil group, 7.83±27 for control group; p=0.763). The percent change in NO was similarly not significantly altered in either group (-1.97±22 decline in fish oil group, 11.8±53.9 in control group; p=0.960). Likewise, the percent change in superoxide dismutase for each group was not significant following 8 weeks of supplementation (fish oil group: 11.94±20.94; control group: 11.8±53.9; p=0.362). The Pearson correlation co-efficient comparing the percent change of both leptin and NO was r2= -0.251 demonstrating a mildly negative, albeit insignificant, relationship between these factors. Together, these findings suggest that daily supplementation with 600 mg omega 3 in healthy females is not beneficial for improving these cardiovascular risk markers. Future studies in this area should include male subjects as well as overweight subjects with larger doses of fish oil that are equivalent to three or more servings per week. The importance of gender cannot be underestimated since estrogen has protective effects in the vasculature of females that may have masked any further protective effects of the fish oil. In addition, overweight individuals are often leptin-resistant and develop impaired vasodilation resulting from superoxide-mediated scavenging of nitric oxide. Therefore, the reported antioxidant and weight loss properties of omega 3 supplementation may greatly benefit overweight individuals.
ContributorsAlanbagy, Samer (Author) / Sweazea, Karen (Thesis advisor) / Johnston, Carol (Committee member) / Shepard, Christina (Committee member) / Lespron, Christy (Committee member) / Arizona State University (Publisher)
Created2014
Description
Multidimensional data have various representations. Thanks to their simplicity in modeling multidimensional data and the availability of various mathematical tools (such as tensor decompositions) that support multi-aspect analysis of such data, tensors are increasingly being used in many application domains including scientific data management, sensor data management, and social network data analysis. Relational model, on the other hand, enables semantic manipulation of data using relational operators, such as projection, selection, Cartesian-product, and set operators. For many multidimensional data applications, tensor operations as well as relational operations need to be supported throughout the data life cycle. In this thesis, we introduce a tensor-based relational data model (TRM), which enables both tensor- based data analysis and relational manipulations of multidimensional data, and define tensor-relational operations on this model. Then we introduce a tensor-relational data management system, so called, TensorDB. TensorDB is based on TRM, which brings together relational algebraic operations (for data manipulation and integration) and tensor algebraic operations (for data analysis). We develop optimization strategies for tensor-relational operations in both in-memory and in-database TensorDB. The goal of the TRM and TensorDB is to serve as a single environment that supports the entire life cycle of data; that is, data can be manipulated, integrated, processed, and analyzed.
ContributorsKim, Mijung (Author) / Candan, K. Selcuk (Thesis advisor) / Davulcu, Hasan (Committee member) / Sundaram, Hari (Committee member) / Ye, Jieping (Committee member) / Arizona State University (Publisher)
Created2014
Description
This thesis is an initial test of the hypothesis that superficial measures suffice for measuring collaboration among pairs of students solving complex math problems, where the degree of collaboration is categorized at a high level. Data were collected
in the form of logs from students' tablets and the vocal interaction between pairs of students. Thousands of different features were defined, and then extracted computationally from the audio and log data. Human coders used richer data (several video streams) and a thorough understand of the tasks to code episodes as
collaborative, cooperative or asymmetric contribution. Machine learning was used to induce a detector, based on random forests, that outputs one of these three codes for an episode given only a characterization of the episode in terms of superficial features. An overall accuracy of 92.00% (kappa = 0.82) was obtained when
comparing the detector's codes to the humans' codes. However, due irregularities in running the study (e.g., the tablet software kept crashing), these results should be viewed as preliminary.
in the form of logs from students' tablets and the vocal interaction between pairs of students. Thousands of different features were defined, and then extracted computationally from the audio and log data. Human coders used richer data (several video streams) and a thorough understand of the tasks to code episodes as
collaborative, cooperative or asymmetric contribution. Machine learning was used to induce a detector, based on random forests, that outputs one of these three codes for an episode given only a characterization of the episode in terms of superficial features. An overall accuracy of 92.00% (kappa = 0.82) was obtained when
comparing the detector's codes to the humans' codes. However, due irregularities in running the study (e.g., the tablet software kept crashing), these results should be viewed as preliminary.
ContributorsViswanathan, Sree Aurovindh (Author) / VanLehn, Kurt (Thesis advisor) / T.H CHI, Michelene (Committee member) / Walker, Erin (Committee member) / Arizona State University (Publisher)
Created2014
Description
In many fields one needs to build predictive models for a set of related machine learning tasks, such as information retrieval, computer vision and biomedical informatics. Traditionally these tasks are treated independently and the inference is done separately for each task, which ignores important connections among the tasks. Multi-task learning aims at simultaneously building models for all tasks in order to improve the generalization performance, leveraging inherent relatedness of these tasks. In this thesis, I firstly propose a clustered multi-task learning (CMTL) formulation, which simultaneously learns task models and performs task clustering. I provide theoretical analysis to establish the equivalence between the CMTL formulation and the alternating structure optimization, which learns a shared low-dimensional hypothesis space for different tasks. Then I present two real-world biomedical informatics applications which can benefit from multi-task learning. In the first application, I study the disease progression problem and present multi-task learning formulations for disease progression. In the formulations, the prediction at each point is a regression task and multiple tasks at different time points are learned simultaneously, leveraging the temporal smoothness among the tasks. The proposed formulations have been tested extensively on predicting the progression of the Alzheimer's disease, and experimental results demonstrate the effectiveness of the proposed models. In the second application, I present a novel data-driven framework for densifying the electronic medical records (EMR) to overcome the sparsity problem in predictive modeling using EMR. The densification of each patient is a learning task, and the proposed algorithm simultaneously densify all patients. As such, the densification of one patient leverages useful information from other patients.
ContributorsZhou, Jiayu (Author) / Ye, Jieping (Thesis advisor) / Mittelmann, Hans (Committee member) / Li, Baoxin (Committee member) / Wang, Yalin (Committee member) / Arizona State University (Publisher)
Created2014
Description
Many learning models have been proposed for various tasks in visual computing. Popular examples include hidden Markov models and support vector machines. Recently, sparse-representation-based learning methods have attracted a lot of attention in the computer vision field, largely because of their impressive performance in many applications. In the literature, many of such sparse learning methods focus on designing or application of some learning techniques for certain feature space without much explicit consideration on possible interaction between the underlying semantics of the visual data and the employed learning technique. Rich semantic information in most visual data, if properly incorporated into algorithm design, should help achieving improved performance while delivering intuitive interpretation of the algorithmic outcomes. My study addresses the problem of how to explicitly consider the semantic information of the visual data in the sparse learning algorithms. In this work, we identify four problems which are of great importance and broad interest to the community. Specifically, a novel approach is proposed to incorporate label information to learn a dictionary which is not only reconstructive but also discriminative; considering the formation process of face images, a novel image decomposition approach for an ensemble of correlated images is proposed, where a subspace is built from the decomposition and applied to face recognition; based on the observation that, the foreground (or salient) objects are sparse in input domain and the background is sparse in frequency domain, a novel and efficient spatio-temporal saliency detection algorithm is proposed to identify the salient regions in video; and a novel hidden Markov model learning approach is proposed by utilizing a sparse set of pairwise comparisons among the data, which is easier to obtain and more meaningful, consistent than tradition labels, in many scenarios, e.g., evaluating motion skills in surgical simulations. In those four problems, different types of semantic information are modeled and incorporated in designing sparse learning algorithms for the corresponding visual computing tasks. Several real world applications are selected to demonstrate the effectiveness of the proposed methods, including, face recognition, spatio-temporal saliency detection, abnormality detection, spatio-temporal interest point detection, motion analysis and emotion recognition. In those applications, data of different modalities are involved, ranging from audio signal, image to video. Experiments on large scale real world data with comparisons to state-of-art methods confirm the proposed approaches deliver salient advantages, showing adding those semantic information dramatically improve the performances of the general sparse learning methods.
ContributorsZhang, Qiang (Author) / Li, Baoxin (Thesis advisor) / Turaga, Pavan (Committee member) / Wang, Yalin (Committee member) / Ye, Jieping (Committee member) / Arizona State University (Publisher)
Created2014
Description
Research in the learning sciences suggests that students learn better by collaborating with their peers than learning individually. Students working together as a group tend to generate new ideas more frequently and exhibit a higher level of reasoning. In this internet age with the advent of massive open online courses (MOOCs), students across the world are able to access and learn material remotely. This creates a need for tools that support distant or remote collaboration. In order to build such tools we need to understand the basic elements of remote collaboration and how it differs from traditional face-to-face collaboration.
The main goal of this thesis is to explore how spoken dialogue varies in face-to-face and remote collaborative learning settings. Speech data is collected from student participants solving mathematical problems collaboratively on a tablet. Spoken dialogue is analyzed based on conversational and acoustic features in both the settings. Looking for collaborative differences of transactivity and dialogue initiative, both settings are compared in detail using machine learning classification techniques based on acoustic and prosodic features of speech. Transactivity is defined as a joint construction of knowledge by peers. The main contributions of this thesis are: a speech corpus to analyze spoken dialogue in face-to-face and remote settings and an empirical analysis of conversation, collaboration, and speech prosody in both the settings. The results from the experiments show that amount of overlap is lower in remote dialogue than in the face-to-face setting. There is a significant difference in transactivity among strangers. My research benefits the computer-supported collaborative learning community by providing an analysis that can be used to build more efficient tools for supporting remote collaborative learning.
The main goal of this thesis is to explore how spoken dialogue varies in face-to-face and remote collaborative learning settings. Speech data is collected from student participants solving mathematical problems collaboratively on a tablet. Spoken dialogue is analyzed based on conversational and acoustic features in both the settings. Looking for collaborative differences of transactivity and dialogue initiative, both settings are compared in detail using machine learning classification techniques based on acoustic and prosodic features of speech. Transactivity is defined as a joint construction of knowledge by peers. The main contributions of this thesis are: a speech corpus to analyze spoken dialogue in face-to-face and remote settings and an empirical analysis of conversation, collaboration, and speech prosody in both the settings. The results from the experiments show that amount of overlap is lower in remote dialogue than in the face-to-face setting. There is a significant difference in transactivity among strangers. My research benefits the computer-supported collaborative learning community by providing an analysis that can be used to build more efficient tools for supporting remote collaborative learning.
ContributorsNelakurthi, Arun Reddy (Author) / Pon-Barry, Heather (Thesis advisor) / VanLehn, Kurt (Committee member) / Walker, Erin (Committee member) / Arizona State University (Publisher)
Created2014
Description
Diet quality is closely intertwined with overall health status and deserves close examination. Healthcare providers are stretched thin in the current stressed system and would benefit from a validated tool for rapid assessment of diet quality. The Rapid Eating and Activity Assessment for Participants Short Version (REAP-S) represents one such option. The objective of the current study was to evaluate the effectiveness of the REAP-S and Healthy Eating Index 2010 (HEI-2010) for scoring the diet quality of omnivorous, vegetarian and vegan diets. Eighty-one healthy male and female subjects with an average age of 30.9 years completed the REAP-S as well as a 24-hour dietary recall. REAP-S and HEI-2010 scores were calculated for each subject and evaluated against each other using Spearman correlations and Chi Square. Further analysis was completed to compare diet quality scores of the HEI-2010 and REAP-S by tertiles to examine how closely these two tools score diet quality. The mean HEI-2010 score was 47.4/100 and the mean REAP-S score was 33.5/39. The correlation coefficient comparing the REAP-S to the HEI-2010 was 0.309 (p=0.005), and the REAP-S exhibited a precision of 44.4% to the HEI-2010 for diet quality. The REAP-S significantly correlated with the HEI-2010 for whole fruit (r=0.247, p=0.026), greens and beans (r=0.276, p=0.013), seafood proteins (r=0.298, p=0.007), and fatty acids (r=0.400, p<0.001). When evaluated by diet type, the REAP-S proved to have increased precision in plant-based diets, 50% for vegetarian and 52% for vegan, over omnivorous diets (32%). The REAP-S is a desirable tool to rapidly assess diet quality in the community setting as it is significantly correlated to the HEI-2010 and requires less time, labor and money to score and assess than the HEI-2010. More studies are needed to evaluate the precision and validity of REAP-S in a broader, more diverse population.
ContributorsBliss, Courtney (Author) / Johnston, Carol (Thesis advisor) / Tasevska, Natasha (Committee member) / Levinson, Simin (Committee member) / Arizona State University (Publisher)
Created2015
Description
Although many studies have looked into the benefits and consequences of consuming breakfast, most have not looked into the unintended consequences of breakfast being served at school; specifically the consumption of an additional breakfast. This cross-sectional study investigated the prevalence and health related outcomes of the consumption of an additional breakfast at school amongst youth using a survey assessing possible predictors (i.e. parental education, morning activities, race), the ASA-kids 24-hr dietary recall, and height and weight measurements. A total of fifty-eight participants (aged 13.5±1.6 years; 55.2% male) were recruited at after school library programs and Boys and Girls Clubs in the Phoenix, Arizona Metro Area during 2014. The main outcomes measured were BMI percentile, total calories, iron, sodium, carbohydrates, added sugar, and fiber. In the study, the prevalence of consumption of an additional breakfast at school at least once a week or more was 32.7%. There were no significant differences between the consumption of an additional breakfast and not an additional breakfast amongst the main outcomes measures. The directionality of the relationship between the consumption of an additional breakfast and overweight/obesity amongst youth was inverse (OR = 0.309; p-value = 0.121), but this was not significant. This study found that the consumption of an additional breakfast at school is not contributing to overweight/obesity in youth, nor does it alter overall caloric and nutrient intake. School breakfast programs are important for providing breakfast and key nutrients to youth.
ContributorsSimpson, Julie (Author) / Bruening, Meg (Committee member) / Ohri-Vachaspati, Punam (Committee member) / Rider, Linda (Committee member) / Arizona State University (Publisher)
Created2015
Description
ABSTRACT
Asthma is a high-stress, chronic medical condition; 1 in 12 adults in the United States combat the bronchoconstriction from asthma. However, there are very few strong studies indicating any alternative therapy for asthmatics, particularly following a cold incidence. Vitamin C has been proven to be effective for other high-stress populations, but the asthmatic population has not yet been trialed. This study examined the effectiveness of vitamin C supplementation during the cold season on cold incidence and asthmatic symptoms. Asthmatics, otherwise-healthy, who were non-smokers and non-athletes between the ages of 18 and 55 with low plasma vitamin C concentrations were separated by anthropometrics and vitamin C status into two groups: either vitamin C (500 mg vitamin C capsule consumed twice per day) or control (placebo capsule consumed twice per day). Subjects were instructed to complete the Wisconsin Upper Respiratory Symptom Survey-21 and a short asthma symptoms questionnaire daily along with a shortened vitamin C Food Frequency Questionnaire and physical activity questionnaire weekly for eight weeks. Blood samples were drawn at Week 0 (baseline), Week 4, and Week 8. Compliance was monitored through a calendar check sheet. The vitamin C levels of both groups increased from Week 0 to Week 4, but decreased in the vitamin C group at Week 8. The vitamin C group had a 19% decrease in plasma histamine while the control group had a 53% increase in plasma histamine at the end of the trial, but this was not statistically significant (p>0.05). Total symptoms recorded from WURSS-21 were 129.3±120.7 for the vitamin C and 271.0±293.9, but the difference was not statistically significant (p=0.724). Total asthma symptoms also slightly varied between the groups, but again was not statistically significant (p=0.154). These results were hindered by the low number of subjects recruited. Continued research in this study approach is necessary to definitively reject or accept the potential role of vitamin C in asthma and cold care.
Asthma is a high-stress, chronic medical condition; 1 in 12 adults in the United States combat the bronchoconstriction from asthma. However, there are very few strong studies indicating any alternative therapy for asthmatics, particularly following a cold incidence. Vitamin C has been proven to be effective for other high-stress populations, but the asthmatic population has not yet been trialed. This study examined the effectiveness of vitamin C supplementation during the cold season on cold incidence and asthmatic symptoms. Asthmatics, otherwise-healthy, who were non-smokers and non-athletes between the ages of 18 and 55 with low plasma vitamin C concentrations were separated by anthropometrics and vitamin C status into two groups: either vitamin C (500 mg vitamin C capsule consumed twice per day) or control (placebo capsule consumed twice per day). Subjects were instructed to complete the Wisconsin Upper Respiratory Symptom Survey-21 and a short asthma symptoms questionnaire daily along with a shortened vitamin C Food Frequency Questionnaire and physical activity questionnaire weekly for eight weeks. Blood samples were drawn at Week 0 (baseline), Week 4, and Week 8. Compliance was monitored through a calendar check sheet. The vitamin C levels of both groups increased from Week 0 to Week 4, but decreased in the vitamin C group at Week 8. The vitamin C group had a 19% decrease in plasma histamine while the control group had a 53% increase in plasma histamine at the end of the trial, but this was not statistically significant (p>0.05). Total symptoms recorded from WURSS-21 were 129.3±120.7 for the vitamin C and 271.0±293.9, but the difference was not statistically significant (p=0.724). Total asthma symptoms also slightly varied between the groups, but again was not statistically significant (p=0.154). These results were hindered by the low number of subjects recruited. Continued research in this study approach is necessary to definitively reject or accept the potential role of vitamin C in asthma and cold care.
ContributorsEarhart, Kathryn Michelle (Author) / Johnston, Carol (Thesis advisor) / Sweazea, Karen (Committee member) / Lespron, Christy (Committee member) / Arizona State University (Publisher)
Created2015