05 Fakultät Informatik, Elektrotechnik und Informationstechnik
Permanent URI for this collectionhttps://elib.uni-stuttgart.de/handle/11682/6
Browse
2 results
Search Results
Item Open Access Deep learning based prediction and visual analytics for temporal environmental data(2022) Harbola, Shubhi; Coors, Volker (Prof. Dr.)The objective of this thesis is to focus on developing Machine Learning methods and their visualisation for environmental data. The presented approaches primarily focus on devising an accurate Machine Learning framework that supports the user in understanding and comparing the model accuracy in relation to essential aspects of the respective parameter selection, trends, time frame, and correlating together with considered meteorological and pollution parameters. Later, this thesis develops approaches for the interactive visualisation of environmental data that are wrapped over the time series prediction as an application. Moreover, these approaches provide an interactive application that supports: 1. a Visual Analytics platform to interact with the sensors data and enhance the representation of the environmental data visually by identifying patterns that mostly go unnoticed in large temporal datasets, 2. a seasonality deduction platform presenting analyses of the results that clearly demonstrate the relationship between these parameters in a combined temporal activities frame, and 3. air quality analyses that successfully discovers spatio-temporal relationships among complex air quality data interactively in different time frames by harnessing the user’s knowledge of factors influencing the past, present, and future behaviour with Machine Learning models' aid. Some of the above pieces of work contribute to the field of Explainable Artificial Intelligence which is an area concerned with the development of methods that help understand, explain and interpret Machine Learning algorithms. In summary, this thesis describes Machine Learning prediction algorithms together with several visualisation approaches for visually analysing the temporal relationships among complex environmental data in different time frames interactively in a robust web platform. The developed interactive visualisation system for environmental data assimilates visual prediction, sensors’ spatial locations, measurements of the parameters, detailed patterns analyses, and change in conditions over time. This provides a new combined approach to the existing visual analytics research. The algorithms developed in this thesis can be used to infer spatio-temporal environmental data, enabling the interactive exploration processes, thus helping manage the cities smartly.Item Open Access Implications of the uncanny valley of avatars and virtual characters for human-computer interaction(2018) Schwind, Valentin; Henze, Niels (Prof. Dr.)Technological innovations made it possible to create more and more realistic figures. Such figures are often created according to human appearance and behavior allowing interaction with artificial systems in a natural and familiar way. In 1970, the Japanese roboticist Masahiro Mori observed, however, that robots and prostheses with a very - but not perfect - human-like appearance can elicit eerie, uncomfortable, and even repulsive feelings. While real people or stylized figures do not seem to evoke such negative feelings, human depictions with only minor imperfections fall into the "uncanny valley," as Mori put it. Today, further innovations in computer graphics led virtual characters into the uncanny valley. Thus, they have been subject of a number of disciplines. For research, virtual characters created by computer graphics are particularly interesting as they are easy to manipulate and, thus, can significantly contribute to a better understanding of the uncanny valley and human perception. For designers and developers of virtual characters such as in animated movies or games, it is important to understand how the appearance and human-likeness or virtual realism influence the experience and interaction of the user and how they can create believable and acceptable avatars and virtual characters despite the uncanny valley. This work investigates these aspects and is the next step in the exploration of the uncanny valley. This dissertation presents the results of nine studies examining the effects of the uncanny valley on human perception, how it affects interaction with computing systems, which cognitive processes are involved, and which causes may be responsible for the phenomenon. Furthermore, we examine not only methods for avoiding uncanny or unpleasant effects but also the preferred characteristics of virtual faces. We bring the uncanny valley into context with related phenomena causing similar effects. By exploring the eeriness of virtual animals, we found evidence that the uncanny valley is not only related to the dimension of human-likeness, which significantly change our view on the phenomenon. Furthermore, using advanced hand tracking and virtual reality technologies, we discovered that avatar realism is connected to other factors, which are related to the uncanny valley and depend on avatar realism. Affinity with the virtual ego and the feeling of presence in the virtual world were also affected by gender and deviating body structures such as a reduced number of fingers. Considering the performance while typing on keyboards in virtual reality, we also found that the perception of the own avatar depends on the user's individual task proficiencies. This thesis concludes with implications that not only extends existing knowledge about virtual characters, avatars and the uncanny valley but also provide new design guidelines for human-computer interaction and virtual reality.