Matching Items (77)
Filtering by
- Member of: Theses and Dissertations
Description
Currently, recommender systems are used extensively to find the right audience with the "right" content over various platforms. Recommendations generated by these systems aim to offer relevant items to users. Different approaches have been suggested to solve this problem mainly by using the rating history of the user or by identifying the preferences of similar users. Most of the existing recommendation systems are formulated in an identical fashion, where a model is trained to capture the underlying preferences of users over different kinds of items. Once it is deployed, the model suggests personalized recommendations precisely, and it is assumed that the preferences of users are perfectly reflected by the historical data. However, such user data might be limited in practice, and the characteristics of users may constantly evolve during their intensive interaction between recommendation systems.
Moreover, most of these recommender systems suffer from the cold-start problems where insufficient data for new users or products results in reduced overall recommendation output. In the current study, we have built a recommender system to recommend movies to users. Biclustering algorithm is used to cluster the users and movies simultaneously at the beginning to generate explainable recommendations, and these biclusters are used to form a gridworld where Q-Learning is used to learn the policy to traverse through the grid. The reward function uses the Jaccard Index, which is a measure of common users between two biclusters. Demographic details of new users are used to generate recommendations that solve the cold-start problem too.
Lastly, the implemented algorithm is examined with a real-world dataset against the widely used recommendation algorithm and the performance for the cold-start cases.
Moreover, most of these recommender systems suffer from the cold-start problems where insufficient data for new users or products results in reduced overall recommendation output. In the current study, we have built a recommender system to recommend movies to users. Biclustering algorithm is used to cluster the users and movies simultaneously at the beginning to generate explainable recommendations, and these biclusters are used to form a gridworld where Q-Learning is used to learn the policy to traverse through the grid. The reward function uses the Jaccard Index, which is a measure of common users between two biclusters. Demographic details of new users are used to generate recommendations that solve the cold-start problem too.
Lastly, the implemented algorithm is examined with a real-world dataset against the widely used recommendation algorithm and the performance for the cold-start cases.
ContributorsSargar, Rushikesh Bapu (Author) / Atkinson, Robert K (Thesis advisor) / Chen, Yinong (Thesis advisor) / Chavez-Echeagaray, Maria Elena (Committee member) / Arizona State University (Publisher)
Created2020
Description
The focus of this study was to investigate better learning opportunities at the epicenter of field-level aircraft maintenance technical training for the United States Air Force. While narrow in focus, this project may be informative for training communities across diverse industries. The intent of this project is to improve the transfer of training from the classroom to the workplace by implementing a blended learning classroom pedagogy, successively enhancing class time for more meaningful construction of student-centered learning. This mixed-methods research study utilized surveys, observations, and interviews with students, instructors and supervisors to explore perceptions that aircraft maintainers have about the current and potential value of curriculum. The first significant finding was that aircraft maintainers do believe there is opportunity to improve the current rote transmission style of curriculum and make it more learner-centered. The second significant finding is that aircraft maintainers do see a blended learning classroom as a means to explore the curriculum in more depth and improve the transfer of their knowledge in a more meaningful way to the workplace.
ContributorsDawes, Scott (Author) / Gee, Betty (Thesis advisor) / Mertler, Craig (Committee member) / Archambault, Leanna (Committee member) / Arizona State University (Publisher)
Created2019
Description
Universities and colleges in the United States (U.S.) are in a period of rapid transformation. Driven by the need for an educated workforce, higher education institutions are responding to rapid innovation, globalization, economic realities, and sociodemographic shifts. Simultaneously, extensive educational online networks connect millions of people worldwide enable learning and knowledge sharing beyond what society has experienced to date. In light of technological advancements, the preservation and presentation of certain ideals that undergird academia and the communication and application of knowledge are undergoing dramatic change. Within higher education, this is both a challenge and an opportunity to re-envision the commitment to educate the public. This research discusses potential forms of this redesign and how it can build upon and depart from previous iterations of higher education. How colleges and universities will adapt to become more relevant, engaging, and accessible is a pressing question that must be addressed.
Using case studies focused on creating sustainability education materials, this dissertation develops knowledge related to three interconnected areas of study that will contribute to redesigning higher education through participatory action research methodology. First, higher education has a civic responsibility to provide new ways of thinking, being, and doing globally and providing more access to education to broader society, especially through public research institutions. Second, with a vast array of available learning materials, higher education should invest in elegantly-designed experiences consisting of well-reasoned, meticulously-curated, and high-quality content that is aesthetically appealing, engaging, and accessible to a broad audience. Third, as universities transition from the gatekeepers of knowledge to the connectors of knowledge, they also need to ensure that a coherent mission is articulated and invested in by stakeholders to create an intentionally beneficial transformational effort. The transformation of higher education toward a more inclusive learning environment through new ways of thinking and elegantly-designed learning experiences will serve to improve our learning institutions. As part of the necessary core for an educated democracy, higher education institutions must strive to create a more equitable, inclusive, and diverse society.
Using case studies focused on creating sustainability education materials, this dissertation develops knowledge related to three interconnected areas of study that will contribute to redesigning higher education through participatory action research methodology. First, higher education has a civic responsibility to provide new ways of thinking, being, and doing globally and providing more access to education to broader society, especially through public research institutions. Second, with a vast array of available learning materials, higher education should invest in elegantly-designed experiences consisting of well-reasoned, meticulously-curated, and high-quality content that is aesthetically appealing, engaging, and accessible to a broad audience. Third, as universities transition from the gatekeepers of knowledge to the connectors of knowledge, they also need to ensure that a coherent mission is articulated and invested in by stakeholders to create an intentionally beneficial transformational effort. The transformation of higher education toward a more inclusive learning environment through new ways of thinking and elegantly-designed learning experiences will serve to improve our learning institutions. As part of the necessary core for an educated democracy, higher education institutions must strive to create a more equitable, inclusive, and diverse society.
ContributorsHale, Anne Elizabeth (Author) / Archambault, Leanna (Thesis advisor) / Johnston, Erik W., 1977- (Thesis advisor) / Richter, Jennifer (Committee member) / Arizona State University (Publisher)
Created2020
Description
The purpose of this study was to investigate the impact of immersion on knowledge, cognitive load, and presence in a simulation designed to deliver a lesson on science lab safety training. 108 participants were randomly assigned to one of three conditions: high immersion (played an interactive simulation about lab safety in a VR headset), medium immersion (played the same interactive simulation on the computer), or low immersion (watched a video and read about lab safety procedures). Participants completed a pretest, a science lab safety training, a posttest (same as the pretest), a questionnaire with subjective presence questions, and a questionnaire with subjective cognitive load questions. Participants were again asked to complete a follow-up test (same as the pretest and posttest) a week later.
The results revealed three significant findings:
(a) Participants in the high and medium immersion conditions had significantly higher knowledge scores at posttest and follow-up than their peers in the low immersion condition,
(b) Participants in the high and medium immersion conditions reported higher presence scores than participants in the low immersion conditions.
(c) Correlation coefficients suggested that the higher the immersion and presence, the higher the knowledge scores are at posttest and follow-up.
In addition, multiple hierarchical linear regression models were conducted out of which one was significant.
The results revealed three significant findings:
(a) Participants in the high and medium immersion conditions had significantly higher knowledge scores at posttest and follow-up than their peers in the low immersion condition,
(b) Participants in the high and medium immersion conditions reported higher presence scores than participants in the low immersion conditions.
(c) Correlation coefficients suggested that the higher the immersion and presence, the higher the knowledge scores are at posttest and follow-up.
In addition, multiple hierarchical linear regression models were conducted out of which one was significant.
ContributorsSavvides, Philippos (Author) / Nelson, Brian (Thesis advisor) / Johnson-Glenberg, Mina (Committee member) / Atkinson, Robert (Committee member) / Arizona State University (Publisher)
Created2018
Description
Virtual Reality (hereafter VR) and Mixed Reality (hereafter MR) have opened a new line of applications and possibilities. Amidst a vast network of potential applications, little research has been done to provide real time collaboration capability between users of VR and MR. The idea of this thesis study is to develop and test a real time collaboration system between VR and MR. The system works similar to a Google document where two or more users can see what others are doing i.e. writing, modifying, viewing, etc. Similarly, the system developed during this study will enable users in VR and MR to collaborate in real time.
The study of developing a real-time cross-platform collaboration system between VR and MR takes into consideration a scenario in which multiple device users are connected to a multiplayer network where they are guided to perform various tasks concurrently.
Usability testing was conducted to evaluate participant perceptions of the system. Users were required to assemble a chair in alternating turns; thereafter users were required to fill a survey and give an audio interview. Results collected from the participants showed positive feedback towards using VR and MR for collaboration. However, there are several limitations with the current generation of devices that hinder mass adoption. Devices with better performance factors will lead to wider adoption.
The study of developing a real-time cross-platform collaboration system between VR and MR takes into consideration a scenario in which multiple device users are connected to a multiplayer network where they are guided to perform various tasks concurrently.
Usability testing was conducted to evaluate participant perceptions of the system. Users were required to assemble a chair in alternating turns; thereafter users were required to fill a survey and give an audio interview. Results collected from the participants showed positive feedback towards using VR and MR for collaboration. However, there are several limitations with the current generation of devices that hinder mass adoption. Devices with better performance factors will lead to wider adoption.
ContributorsSeth, Nayan Sateesh (Author) / Nelson, Brian (Thesis advisor) / Walker, Erin (Committee member) / Atkinson, Robert (Committee member) / Arizona State University (Publisher)
Created2017
Description
Affect signals what humans care about and is involved in rational decision-making and action selection. Many technologies may be improved by the capability to recognize human affect and to respond adaptively by appropriately modifying their operation. This capability, named affect-driven self-adaptation, benefits systems as diverse as learning environments, healthcare applications, and video games, and indeed has the potential to improve systems that interact intimately with users across all sectors of society. The main challenge is that existing approaches to advancing affect-driven self-adaptive systems typically limit their applicability by supporting the creation of one-of-a-kind systems with hard-wired affect recognition and self-adaptation capabilities, which are brittle, costly to change, and difficult to reuse. A solution to this limitation is to leverage the development of affect-driven self-adaptive systems with a manufacturing vision.
This dissertation demonstrates how using a software product line paradigm can jumpstart the development of affect-driven self-adaptive systems with that manufacturing vision. Applying a software product line approach to the affect-driven self-adaptive domain provides a comprehensive, flexible and reusable infrastructure of components with mechanisms to monitor a user’s affect and his/her contextual interaction with a system, to detect opportunities for improvements, to select a course of action, and to effect changes. It also provides a domain-specific architecture and well-documented process guidelines, which facilitate an understanding of the organization of affect-driven self-adaptive systems and their implementation by systematically customizing the infrastructure to effectively address the particular requirements of specific systems.
The software product line approach is evaluated by applying it in the development of learning environments and video games that demonstrate the significant potential of the solution, across diverse development scenarios and applications.
The key contributions of this work include extending self-adaptive system modeling, implementing a reusable infrastructure, and leveraging the use of patterns to exploit the commonalities between systems in the affect-driven self-adaptation domain.
This dissertation demonstrates how using a software product line paradigm can jumpstart the development of affect-driven self-adaptive systems with that manufacturing vision. Applying a software product line approach to the affect-driven self-adaptive domain provides a comprehensive, flexible and reusable infrastructure of components with mechanisms to monitor a user’s affect and his/her contextual interaction with a system, to detect opportunities for improvements, to select a course of action, and to effect changes. It also provides a domain-specific architecture and well-documented process guidelines, which facilitate an understanding of the organization of affect-driven self-adaptive systems and their implementation by systematically customizing the infrastructure to effectively address the particular requirements of specific systems.
The software product line approach is evaluated by applying it in the development of learning environments and video games that demonstrate the significant potential of the solution, across diverse development scenarios and applications.
The key contributions of this work include extending self-adaptive system modeling, implementing a reusable infrastructure, and leveraging the use of patterns to exploit the commonalities between systems in the affect-driven self-adaptation domain.
ContributorsGonzalez-Sanchez, Javier (Author) / Burleson, Winslow (Thesis advisor) / Collofello, James (Thesis advisor) / Garlan, David (Committee member) / Sarjoughian, Hessam S. (Committee member) / Atkinson, Robert (Committee member) / Arizona State University (Publisher)
Created2016
Description
Guitar Hero III and similar games potentially offer a vehicle for improvement of musical rhythmic accuracy with training delivered in both visual and auditory formats and by use of its novel guitar-shaped interface; however, some theories regarding multimedia learning suggest sound is a possible source of extraneous cognitive load while playing so players may score higher with sound turned off. Also, existing studies have shown that differences in the physical format of interfaces affect learning outcomes. This study sought to determine whether (a) the game’s audio content affects rhythmic accuracy, and (b) the type of game controller used affects learning of rhythmic accuracy. One hundred participants were randomly assigned in approximately equal numbers (ns = 25) to the four cells of a 2x2 between-subjects design. The first variable was the audio content of the game with two levels: on or off. The second variable was the type of game controller: the standard guitar-style controller or tablet interface. Participants across all conditions completed a pre- and post-test with a system that required them to tap along with repeated rhythmic patterns on an electronic drum pad. Statistical evidence showed better outcomes with a tablet controller with respect to input time error, reduction of extra notes played, and reduction of missed notes; however, the guitar-style controller produced superior outcomes in terms of avoiding missed notes and was associated with higher satisfaction by participants. When audio was present better outcomes were achieved at multiple factor-levels of reduction of missed responses, but superior outcomes in input time error were seen without audio. There was no evidence to suggest an interaction between controller type and the presence or absence of audio.
ContributorsThomas, James William (Author) / Zuiker, Steven J (Thesis advisor) / Atkinson, Robert (Thesis advisor) / Savenye, Wilhelmina C (Committee member) / Arizona State University (Publisher)
Created2017