Matching Items (4)
Filtering by
- Creators: Arizona State University
Description
Current work in planning assumes that user preferences and/or domain dynamics are completely specified in advance, and aims to search for a single solution plan to satisfy these. In many real world scenarios, however, providing a complete specification of user preferences and domain dynamics becomes a time-consuming and error-prone task. More often than not, a user may provide no knowledge or at best partial knowledge of her preferences with respect to a desired plan. Similarly, a domain writer may only be able to determine certain parts, not all, of the model of some actions in a domain. Such modeling issues requires new concepts on what a solution should be, and novel techniques in solving the problem. When user preferences are incomplete, rather than presenting a single plan, the planner must instead provide a set of plans containing one or more plans that are similar to the one that the user prefers. This research first proposes the usage of different measures to capture the quality of such plan sets. These are domain-independent distance measures based on plan elements if no knowledge of the user preferences is given, or the Integrated Preference Function measure in case incomplete knowledge of such preferences is provided. It then investigates various heuristic approaches to generate plan sets in accordance with these measures, and presents empirical results demonstrating the promise of the methods. The second part of this research addresses planning problems with incomplete domain models, specifically those annotated with possible preconditions and effects of actions. It formalizes the notion of plan robustness capturing the probability of success for plans during execution. A method of assessing plan robustness based on the weighted model counting approach is proposed. Two approaches for synthesizing robust plans are introduced. The first one compiles the robust plan synthesis problems to the conformant probabilistic planning problems. The second approximates the robustness measure with lower and upper bounds, incorporating them into a stochastic local search for estimating distance heuristic to a goal state. The resulting planner outperforms a state-of-the-art planner that can handle incomplete domain models in both plan quality and planning time.
ContributorsNguyễn, Tuấn Anh (Author) / Kambhampati, Subbarao (Thesis advisor) / Baral, Chitta (Committee member) / Do, Minh (Committee member) / Lee, Joohyung (Committee member) / Smith, David E. (Committee member) / Arizona State University (Publisher)
Created2014
Description
Skyline queries are a well-established technique used in multi criteria decision applications. There is a recent interest among the research community to efficiently compute skylines but the problem of presenting the skyline that takes into account the preferences of the user is still open. Each user has varying interests towards each attribute and hence "one size fits all" methodology might not satisfy all the users. True user satisfaction can be obtained only when the skyline is tailored specifically for each user based on his preferences.
This research investigates the problem of preference aware skyline processing which consists of inferring the preferences of users and computing a skyline specific to that user, taking into account his preferences. This research proposes a model that transforms the data from a given space to a user preferential space where each attribute represents the preference of the user. This study proposes two techniques "Preferential Skyline Processing" and "Latent Skyline Processing" to efficiently compute preference aware skylines in the user preferential space. Finally, through extensive experiments and performance analysis the correctness of the recommendations and the algorithm's ability to outperform the naïve ones is confirmed.
This research investigates the problem of preference aware skyline processing which consists of inferring the preferences of users and computing a skyline specific to that user, taking into account his preferences. This research proposes a model that transforms the data from a given space to a user preferential space where each attribute represents the preference of the user. This study proposes two techniques "Preferential Skyline Processing" and "Latent Skyline Processing" to efficiently compute preference aware skylines in the user preferential space. Finally, through extensive experiments and performance analysis the correctness of the recommendations and the algorithm's ability to outperform the naïve ones is confirmed.
ContributorsRathinavelu, Sriram (Author) / Candan, Kasim Selcuk (Thesis advisor) / Davulcu, Hasan (Committee member) / Sarwat, Mohamed (Committee member) / Arizona State University (Publisher)
Created2014
Description
This thesis seeks to defend transitivity as a rational constraint on preferences against two putative counterexamples to transitivity. This thesis is divided into three sections. In the first section, I consider two famous and popular arguments in defense of transitivity and argue they are insufficient to adequately defend transitivity. I then outline a desiderata for successful arguments in defense of transitivity and identify some basic assumptions I will be making throughout the thesis. In section two, I consider the first putative counterexample to transitivity: Quinn’s Puzzle of the Self-Torturer. I offer two plausible interpretations of Quinn’s puzzle and argue that both fail. One because it does not genuinely induce intransitive preferences, and the other because the situation it requires is logically impossible. I conclude this section by defending my arguments against known objections in the literature. Finally, in the third section, I consider a counterexample to transitivity from Larry Temkin that has received little attention in the literature. I argue that while the initial counterexample is unpersuasive it can be augmented and made into a more forceful argument. I then argue that this improved counterexample fails due to some erroneous assumptions prevalent in the literature on incomparability. I conclude the thesis with a brief summary and some closing remarks.
ContributorsCalloway, Carson (Author) / Armendt, Brad (Thesis advisor) / Portmore, Douglas (Committee member) / Pinillos, Nestor (Committee member) / Arizona State University (Publisher)
Created2015
Description
ABSTRACT
The purpose of this study was to investigate physical activity (PA) program characteristics preferred by low-income childbearing age Latinas and the relationship with the participants’ personal characteristics, cultural values, and acculturation. This was an exploratory study guided by the Preferences and Health Behavior Model (PaHBM), developed by this investigator. Recruitment occurred at three sites; two sites were located in Phoenix, AZ and one site was located in Houston, TX. Non pregnant Latinas between 18 to 35 years old were included (N=275). Latinas were excluded if they were pregnant, incarcerated, physically or mentally disabled, or had chronic diseases (e.g. cardiovascular disease). Quantitative data were collected using the Predictors and Preferences of Physical Activity Research Intervention Participation in an Underserved Latina Community Questionnaire, developed by this author, along with the Brief Acculturation Rating Scale for Mexican Americans, and the Mexican American Cultural Values Scale. The hypotheses were tested utilizing Chi-square, Pearson correlation and logistic regression. Annual family income, parity, country of origin, BMI and acculturation were the personal characteristics significantly associated with preferred PA program by this group of Latinas. Latino women were heterogeneous in their preferences. In general, sixty percent endorsed dancing as the type of activity preferred, 20% preferred PA education and 20% preferred walking. Major differences were found between the types of activity the Latino women were currently participating in compared to their preferred type of activity. Of the 124 who reported to be walking/jogging, almost half (49) preferred dancing, 22 preferred PA education and only 12 preferred walking. The study findings add to the existing knowledge by looking at factors that should be considered when developing PA interventions as well as when prescribing or recommending PA to this population. These results demonstrate the need to identify the preferred PA program characteristics of Latinas prior to developing interventions. Failure to know the patient’s preferred PA program characteristics may result in prescribing or recommending an undesired activity and decrease participation in PA interventions.
RESUMEN
El propósito de este estudio fue identificar las características preferidas en un programa de actividad física por una comunidad de mujeres Latinas de bajos recursos económicos y en edad fértil, así como la relación de esas características con sus propias características personales, sus valores culturales y su adaptación a la comunidad Anglosajona. Este fue un estudio exploratorio guiado por el “Modelo Preferencias y Comportamiento Saludables” (PaHBM), por sus siglas en Ingles, desarrollado por esta investigadora. El reclutamiento de las Latinas ocurrió en tres sedes: Una en Houston, TX y dos en Phoenix, AZ. Las mujeres Latinas fueron incluidas si tenían entre 18 y 35 años de edad. Se excluyeron mujeres que estaban embarazadas, estuvieran encarceladas, físicamente o mentalmente incapacitadas o que sufrieran alguna enfermedad crónica. Los datos cuantitativos fueron recolectados a través de una encuesta llamada “Predictores y preferencias de participación en un programa investigativo de actividad física”, desarrollada por la autora de este estudio, además utilizando la escala breve de aculturación para Mejicanos Americanos y la escala de valores culturales en Mejicanos Americanos. Las hipótesis fueron probadas utilizando el Chi-cuadrado, la correlación de Pearson, y la regresión lógica. Las características personales más asociadas con las características del programa preferido fueron el salario anual de la familia, el número de hijos, el país de origen, y el índice de masa corporal. En general, 60% prefirieron bailar, 20% clases de actividad física y 20% caminar. Mayores diferencias se encontraron en el tipo de actividad en las que las mujeres Latinas estaban participando, comparado con lo que ellas preferían. De 124 participantes que estaban caminando o trotando, 49 Latinas (39%) preferían bailar, 22 Latinas (17%) preferían clases de actividad física y solo 12 Latinas (10%) prefirieron caminar. Estos resultados demuestran la necesidad de identificar las características del programa de actividad física antes de crear dicho programa. Estos resultados son una adición a los conocimientos existentes, en los que se identificaron factores que deben ser considerados cuando se planea un programa así como cuando se prescribe o se recomienda actividad física a esta población. Sera un fracaso no conocer las preferencias de una paciente para mantenerse físicamente activa porque puede resultar en la prescripción o recomendación de actividades que la paciente no desea y esto se traducirá en reducción de la participación en programas de actividad física.
The purpose of this study was to investigate physical activity (PA) program characteristics preferred by low-income childbearing age Latinas and the relationship with the participants’ personal characteristics, cultural values, and acculturation. This was an exploratory study guided by the Preferences and Health Behavior Model (PaHBM), developed by this investigator. Recruitment occurred at three sites; two sites were located in Phoenix, AZ and one site was located in Houston, TX. Non pregnant Latinas between 18 to 35 years old were included (N=275). Latinas were excluded if they were pregnant, incarcerated, physically or mentally disabled, or had chronic diseases (e.g. cardiovascular disease). Quantitative data were collected using the Predictors and Preferences of Physical Activity Research Intervention Participation in an Underserved Latina Community Questionnaire, developed by this author, along with the Brief Acculturation Rating Scale for Mexican Americans, and the Mexican American Cultural Values Scale. The hypotheses were tested utilizing Chi-square, Pearson correlation and logistic regression. Annual family income, parity, country of origin, BMI and acculturation were the personal characteristics significantly associated with preferred PA program by this group of Latinas. Latino women were heterogeneous in their preferences. In general, sixty percent endorsed dancing as the type of activity preferred, 20% preferred PA education and 20% preferred walking. Major differences were found between the types of activity the Latino women were currently participating in compared to their preferred type of activity. Of the 124 who reported to be walking/jogging, almost half (49) preferred dancing, 22 preferred PA education and only 12 preferred walking. The study findings add to the existing knowledge by looking at factors that should be considered when developing PA interventions as well as when prescribing or recommending PA to this population. These results demonstrate the need to identify the preferred PA program characteristics of Latinas prior to developing interventions. Failure to know the patient’s preferred PA program characteristics may result in prescribing or recommending an undesired activity and decrease participation in PA interventions.
RESUMEN
El propósito de este estudio fue identificar las características preferidas en un programa de actividad física por una comunidad de mujeres Latinas de bajos recursos económicos y en edad fértil, así como la relación de esas características con sus propias características personales, sus valores culturales y su adaptación a la comunidad Anglosajona. Este fue un estudio exploratorio guiado por el “Modelo Preferencias y Comportamiento Saludables” (PaHBM), por sus siglas en Ingles, desarrollado por esta investigadora. El reclutamiento de las Latinas ocurrió en tres sedes: Una en Houston, TX y dos en Phoenix, AZ. Las mujeres Latinas fueron incluidas si tenían entre 18 y 35 años de edad. Se excluyeron mujeres que estaban embarazadas, estuvieran encarceladas, físicamente o mentalmente incapacitadas o que sufrieran alguna enfermedad crónica. Los datos cuantitativos fueron recolectados a través de una encuesta llamada “Predictores y preferencias de participación en un programa investigativo de actividad física”, desarrollada por la autora de este estudio, además utilizando la escala breve de aculturación para Mejicanos Americanos y la escala de valores culturales en Mejicanos Americanos. Las hipótesis fueron probadas utilizando el Chi-cuadrado, la correlación de Pearson, y la regresión lógica. Las características personales más asociadas con las características del programa preferido fueron el salario anual de la familia, el número de hijos, el país de origen, y el índice de masa corporal. En general, 60% prefirieron bailar, 20% clases de actividad física y 20% caminar. Mayores diferencias se encontraron en el tipo de actividad en las que las mujeres Latinas estaban participando, comparado con lo que ellas preferían. De 124 participantes que estaban caminando o trotando, 49 Latinas (39%) preferían bailar, 22 Latinas (17%) preferían clases de actividad física y solo 12 Latinas (10%) prefirieron caminar. Estos resultados demuestran la necesidad de identificar las características del programa de actividad física antes de crear dicho programa. Estos resultados son una adición a los conocimientos existentes, en los que se identificaron factores que deben ser considerados cuando se planea un programa así como cuando se prescribe o se recomienda actividad física a esta población. Sera un fracaso no conocer las preferencias de una paciente para mantenerse físicamente activa porque puede resultar en la prescripción o recomendación de actividades que la paciente no desea y esto se traducirá en reducción de la participación en programas de actividad física.
ContributorsJiménez, Blanca Flor (Author) / Reifsnider, Elizabeth G. (Thesis advisor) / Belyea, Michael (Committee member) / Shin, Cha-Nam (Committee member) / Arizona State University (Publisher)
Created2016