Logo des Repositoriums

Auflistung nach Schlagwort "Classification"

1 - 10 von 21
  • Zeitschriftenartikel
    A System for Probabilistic Linking of Thesauri and Classification Systems
    (KI - Künstliche Intelligenz: Vol. 30, No. 2, 2016) Posch, Lisa; Schaer, Philipp; Bleier, Arnim; Strohmaier, Markus
    This paper presents a system which creates and visualizes probabilistic semantic links between concepts in a thesaurus and classes in a classification system. For creating the links, we build on the Polylingual Labeled Topic Model (PLL-TM) (Posch et al., in KI 2015: advances in artificial intelligence, 2015). PLL-TM identifies probable thesaurus descriptors for each class in the classification system by using information from the natural language text of documents, their assigned thesaurus descriptors and their designated classes. The links are then presented to users of the system in an interactive visualization, providing them with an automatically generated overview of the relations between the thesaurus and the classification system.
  • Konferenzbeitrag
    Analysis and Classification of Serious Games for Elderly
    (Mensch & Computer 2012: interaktiv informiert – allgegenwärtig und allumfassend!?, 2012) Klauser, Matthias; Kötteritzsch, Anna; Niesenhaus, Jörg; Budweg, Steffen
    Serious games aim at providing benefits beyond pure entertainment and are a growing area of research. Furthermore, not only the number of serious games increases but also the range of application areas. Today, serious games address physical cognitive social and psychological needs for a different target audience with multiple devices. Serious games are often classified by benefits or purpose within a specific application area, but classifications focused on different user- and game-specific aspects are still rare. In this paper we provide an overview on a selection of serious games for elderly people by extracting and summarizing common categories used to classify games on a general level and especially serious games. Furthermore, a collection of serious games for elderly based on literature research as well as a classification using the summarized categories is presented. By those means, serious games for elderly shall be structured and not sufficiently covered approaches of providing benefits be identified.
  • Konferenzbeitrag
    Approach to Synthetic Data Generation for Imbalanced Multi-class Problems with Heterogeneous Groups
    (BTW 2023, 2023) Treder-Tschechlov, Dennis; Reimann, Peter; Schwarz, Holger; Mitschang, Bernhard
    To benchmark novel classification algorithms, these algorithms should be evaluated on data with characteristics that also appear in real-world use cases. Important data characteristics that often lead to challenges for classification approaches are multi-class imbalance and heterogeneous groups. Real-world data that comprise these characteristics are usually not publicly available, e. g., because they constitute sensible patient information or due to privacy concerns. Further, the manifestations of the characteristics cannot be controlled specifically on real-world data. A more rigorous approach is to synthetically generate data such that different manifestations of the characteristics can be controlled. However, existing data generators are not able to generate data that feature both data characteristics, i. e., multi-class imbalance and heterogeneous groups. In this paper, we propose an approach that fills this gap as it allows to synthetically generate data that exhibit both characteristics. In particular, we make use of a taxonomy model that organizes real-world entities in domain-specific heterogeneous groups to generate data reflecting the characteristics of these groups. In addition, we incorporate probability distributions to reflect the imbalances of multiple classes and groups from real-world use cases. Our approach is applicable in different domains, as taxonomies are the simplest form of knowledge models and thus are available in many domains. The evaluation shows that our approach can generate data that feature the data characteristics multi-class imbalance and heterogeneous groups and that it allows to control different manifestations of these characteristics.
  • Zeitschriftenartikel
    Automatic Classification of Bloodstains with Deep Learning Methods
    (KI - Künstliche Intelligenz: Vol. 36, No. 2, 2022) Bergman, Tommy; Klöden, Martin; Dreßler, Jan; Labudde, Dirk
    The classification of detected bloodstains into predetermined categories is a crucial component of the so-called bloodstain pattern analysis. As in other forensic disciplines, deep learning methods may help to reduce human subjectivity within this process, may increase the classification accuracy, shorten the calculation time and thus, enable high-throughput analysis. In this work, an approach is presented in which a convolutional neural network (Inception v3) was trained from 965 drip stains (passive origin) and 1595 blood spatters (active origin). The trained CNN was evaluated with a test data set consisting of 366 images of drip stains and blood spatters. The success rate was 99.73% which suggests that neural networks could also be used to automatically classify other classes of bloodstain patterns to speed up the investigation process in the future.
  • Konferenzbeitrag
    Benchmarking Univariate Time Series Classifiers
    (Datenbanksysteme für Business, Technologie und Web (BTW 2017), 2017) Schäfer, Patrick; Leser, Ulf
    Time series are a collection of values sequentially recorded over time. Nowadays, sensors for recording time series are omnipresent as RFID chips, wearables, smart homes, or event-based systems. Time series classification aims at predicting a class label for a time series whose label is unknown. Therefore, a classifier has to train a model using labeled samples. Classification time is a key challenge given new applications like event-based monitoring, real-time decision or streaming systems. This paper is the first benchmark that compares 12 state of the art time series classifiers based on prediction and classification times. We observed that most of the state-of-the-art classifiers require extensive train and classification times, and might not be applicable for these new applications.
  • Konferenzbeitrag
    Classification of Music Preferences Using EEG Data in Machine Learning Models
    (Mensch und Computer 2024 - Workshopband, 2024) Vedder, Helen; Stano, Fabio; Knierim, Michael
    In this paper, we investigate how EEG data can be used to predict individual music preferences. Our study relies on machine learning and specially developed models such as EEGNet to analyze participants' brain activity while listening to music. Participants listened to music excerpts, rated them, and their EEG data were recorded. We extracted relevant features from the EEG data and used convolutional neural networks (CNNs) to classify music preferences. Our results show that our models are able to predict music preferences with an accuracy of up to 69%. This confirms the potential of EEG in personalized music recommendation and demonstrates the feasibility of integrating EEG into wearable devices to improve the user experience.
  • Konferenzbeitrag
    Comparison of Classifiers for Eye-Tracking Data
    (INFORMATIK 2024, 2024) Landes, Jennifer; Köppl, Sonja; Klettke, Meike
    This paper delves into the initial stages of data analysis, focusing on the classification of eye-tracking data. Six machine learning algorithms, namely XGBoost, Random Forest, Naive Bayes, Logistic Regression, Gradient Boosting Machines, and Neural Networks, were employed to predict cheating behavior based on a dataset comprising records from 25 students. Their performance was evaluated using metrics such as accuracy, precision, recall, F1 score, confusion matrix, and feature importance. Results indicate that Random Forest and its optimized version exhibit balanced performance, making them promising candidates for cheating prediction. The overarching research project investigates academic misconduct in the realm of online assessments, seeking to comprehend the behaviors and methodologies involved. An eye-tracking experiment was conducted to gain deeper insights into the timing and mannerisms of students engaging in academic misconduct.
  • Konferenzbeitrag
    A Comprehensive Classification of 3D Selection and Manipulation Techniques
    (Mensch und Computer 2019 - Tagungsband, 2019) Weise, Matthias; Zender, Raphael; Lucke, Ulrike
    The importance of 3D interaction is constantly increasing – not least because of new developments in ubiquitous computing and augmented and virtual reality. Current 3D user interfaces allow for an expressive and accurate input in three-dimensional space. 3D interaction techniques are responsible for mapping the three-dimensional input onto actions within the system and for returning appropriate feedback to the user. For developers of applications using 3D interaction and for designers of new 3D interaction techniques it is important to understand how existing techniques differ and how they can be classified. In this work we summarize existing characterizations of 3D interaction and adopt them to allow a comprehensive classification of 3D interaction techniques for selection and manipulation of virtual objects.
  • Konferenzbeitrag
    The Decentralized Autonomous Organization – Applications and Potentials for IT Projects
    (Projektmanagement und Vorgehensmodelle 2022 - Virtuelle Zusammenarbeit und verlorene Kulturen?, 2022) Rauer, Hans Peter; Schroeder, Daniel
    The DAO is an innovative, blockchain-based platform to virtually manage organizations. Thereby, it challenges traditional project funding and hierarchical (project) management concepts. This paper introduces the DAO, its general functionality and the overall purpose of blockchain technology. Then, current applications of DAOs are depicted. Finally, we draft opportunities and challenges in the application of DAOs for project management with the aid of a model of project classification. Managerial implications of these findings are presented by recommending the DAO for selected IT project management scenarios.
  • Konferenzbeitrag
    A Deep Learning-based Approach for Banana Leaf Diseases Classification
    (Datenbanksysteme für Business, Technologie und Web (BTW 2017) - Workshopband, 2017) Amara, Jihen; Bouaziz, Bassem; Algergawy, Alsayed
    Plant diseases are important factors as they result in serious reduction in quality and quantity of agriculture products. Therefore, early detection and diagnosis of these diseases are important. To this end, we propose a deep learning-based approach that automates the process of classifying ba- nana leaves diseases. In particular, we make use of the LeNet architecture as a convolutional neural network to classify image data sets. The preliminary results demonstrate the effectiveness of the proposed approach even under challenging conditions such as illumination, complex background, different resolution, size, pose, and orientation of real scene images.