Logo des Repositoriums

Auflistung nach Autor:in "Mitschick, Annett"

1 - 6 von 6
  • Konferenzbeitrag
    Achiever or explorer? gamifying the creation process of training data for machine learning
    (Mensch und Computer 2020 - Tagungsband, 2020) Alaghbari, Sarah; Mitschick, Annett; Blichmann, Gregor; Voigt, Martin; Dachselt, Raimund
    The development of artificial intelligence, e. g., for Computer Vision, through supervised learning requires the input of large amounts of annotated or labeled data objects as training data. The creation of high-quality training data is usually done manually which can be repetitive and tiring. Gamification, the use of game elements in a non-game context, is one method to make tedious tasks more interesting. This paper proposes a multi-step process for gamifying the manual creation of training data for machine learning purposes. We choose a user-adapted approach based on the results of a preceding user study with the target group (employees of an AI software development company) which helped us to identify annotation use cases and the users' player characteristics. The resulting concept includes levels of increasing difficulty, tutorials, progress indicators and a narrative built around a robot character which at the same time is a user assistant. The implemented prototype is an extension of the company’s existing annotation tool and serves as a basis for further observations.
  • Konferenzbeitrag
    CoFind: a browser plugin for investigating co-located collaborative web search
    (Mensch und Computer 2020 - Tagungsband, 2020) Fuhrmann, Robert; Lehmann, Anke; Mitschick, Annett; Langner, Ricardo; Dachselt, Raimund
    Group awareness is a prominent challenge in the field of co-located collaboration in Multi-display Environments (MDE), where several personal and shared devices are operated simultaneously by multiple users. With a focus on Collaborative Information Seeking (CIS) and particularly different levels of information sharing, our overall goal is to investigate aspects that influence this group awareness as well as the general group performance in such MDE. In this work, we present the conceptual foundation and approach of a research tool, called CoFind. Developed as a lightweight web browser plugin, which connects collaborators by sharing information resources, it provides comprehensive data and activity logging in the context of user studies and their evaluation. Based on an initial lab experiment, we also present first insights on the feasibility of our approach and the utility of our developed tool, allowing to plan and carry out further user studies in this challenging research field.
  • Konferenzbeitrag
    Growing Green Habits: Unobtrusive Gamified Eco-Feedback to Motivate Sustainable Behavior
    (Mensch und Computer 2023 - Tagungsband, 2023) Plichta, Fabian; Mitschick, Annett; Klamka, Konstantin; Dachselt, Raimund
    Promoting environmental awareness and sustainable behavior is an important action for climate protection. In this paper, we introduce a gamified eco-feedback approach using an interactive plant-like physical interface to encourage lower heating energy consumption in households. The interface is designed to be a part of the user’s environment and evoke a caretaker relationship. It measures indoor climate parameters via sensors, awards users with points for environmentally friendly and healthy heating and ventilation habits, and changes its shape to mimic growing and flourishing. Through their mobile device, the users can retrieve detailed information in a companion app. A prototype implementation demonstrates the feasibility of the concept and serves as a basis for further work in this emerging research area.
  • Workshopbeitrag
    HANDle: A Novel Tangible Device for Hand Therapy Exergames
    (Mensch und Computer 2018 - Tagungsband, 2018) Klamka, Konstantin; Mitschick, Annett; Dachselt, Raimund
    Today's working environments are characterized by and at the same time highly depending on many repetitive hand movements, such as typing or assembling tasks. The physical health of hands is thereby becoming increasingly valuable. Guided by the idea of Tangible User Interfaces (TUIs), we introduce a novel graspable device, called HANDle, that we developed to train wrist agility, finger strength as well as its coordination in a motivational game. Therefore, we iteratively prototyped a fully-functional controller that senses multiple finger forces, its relative position in space and that provides visual and vibro-tactile feedback. In addition, we implemented a therapy game that combines different physiotherapeutic motion and grasp exercises supporting custom-defined levels that match to the patient needs.
  • Konferenzbeitrag
    A stepwise modeling approach for individual media semantics
    (INFORMATIK 2006 – Informatik für Menschen – Band 2, Beiträge der 36. Jahrestagung der Gesellschaft für Informatik e.V. (GI), 2006) Mitschick, Annett; Meißner, Klaus
    The generation of appropriate media descriptions is one of the key issues when developing suitable media management systems for every-day use. One of the more practical problems is the deduction of knowledge from partly large but varying, ambiguous, or just too specific information sources (metadata, attributes, features, etc.). This paper presents a stepwise knowledge modeling approach based on two self-contained, trainable rule sets. Following the principle of divide-and-conquer, the supposed approach separately tackles the problem of general translation (normalization) of diverse information sources and their individual interpretation and semantics for the user.
  • Zeitschriftenartikel
    A User-Centered Approach to Gamify the Manual Creation of Training Data for Machine Learning
    (i-com: Vol. 20, No. 1, 2021) Alaghbari, Sarah; Mitschick, Annett; Blichmann, Gregor; Voigt, Martin; Dachselt, Raimund
    The development of artificial intelligence, e. g. for Computer Vision, through supervised learning requires the input of large amounts of annotated or labeled data objects as training data. Usually, the creation of high-quality training data is done manually which can be repetitive and tiring. Gamification , the use of game elements in a non-game context, is one method to make such tedious tasks more interesting. We propose a multi-step process for gamifying the manual creation of training data for machine learning purposes. In this article, we give an overview of related concepts and existing implementations and present a user-centered approach for a real-life use case. Based on a survey within the target user group we identified annotation use cases and dominant player characteristics. The results served as a foundation for designing the gamification concepts which were then discussed with the participants. The final concept includes levels of increasing difficulty, tutorials, progress indicators and a narrative built around a robot character which at the same time is a user assistant. The implemented prototype is an extension of an existing annotation tool at an AI product company and serves as a basis for further observations.