EuroVA18

Permanent URI for this collection

https://diglib.eg.org/handle/10.2312/2632398

Browse

Browsing EuroVA18 by Subject "Machine learning"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Personalized Visual-Interactive Music Classification
    (The Eurographics Association, 2018) Ritter, Christian; Altenhofen, Christian; Zeppelzauer, Matthias; Kuijper, Arjan; Schreck, Tobias; Bernard, Jürgen; Christian Tominski and Tatiana von Landesberger
    We present an interactive visual music classification tool that will allow users to automatically structure music collections in a personalized way. With our approach, users play an active role in an iterative process of building classification models, using different interactive interfaces for labeling songs. The interactive tool conflates interfaces for the detailed analysis at different granularities, i.e., audio features, music songs, as well as classification results at a glance. Interactive labeling is provided with three complementary interfaces, combining model-centered and human-centered labeling-support principles. A clean visual design of the individual interfaces depicts complex model characteristics for experts, and indicates our work-inprogress towards the abilities of non-experts. The result of a preliminary usage scenario shows that, with our system, hardly any knowledge about machine learning is needed to create classification models of high accuracy with less than 50 labels.
  • Thumbnail Image
    Item
    Visual Predictive Analytics using iFuseML
    (The Eurographics Association, 2018) Sehgal, Gunjan; Rawat, Mrinal; Gupta, Bindu; Gupta, Garima; Sharma, Geetika; Shroff, Gautam; Christian Tominski and Tatiana von Landesberger
    Solving a predictive analytics problem involves multiple machine learning tasks in a workflow. Directing such workflows efficiently requires an understanding of data so as to identify and handle missing values and outliers, compute feature correlations and to select appropriate models and hyper-parameters. While traditional machine learning techniques are capable of handling these challenges to a certain extent, visual analysis of data and results at each stage can significantly assist in optimal processing of the workflow. We present iFuseML , a visual interactive framework to support analysts in machine learning workflows via insightful data visualizations as well as natural language interfaces where appropriate. Our platform lets the user intuitively search and explore datasets, join relevant datasets using natural language queries, detect and visualize multidimensional outliers and explore feature relationships using Bayesian coordinated views. We also demonstrate how visualization assists in comparing prediction errors to guide ensemble models so as to generate more accurate predictions. We illustrate our framework using a house price dataset from Kaggle, where using iFuseML simplified the machine learning workflow and helped improve the resulting prediction accuracy.