Refine
Year of publication
- 2012 (85) (remove)
Document Type
- Article (33)
- Conference Proceeding (30)
- Article trade magazine (9)
- Part of a Book (8)
- Workingpaper / Report (4)
- Book (1)
Language
- German (42)
- English (41)
- Multiple languages (1)
- Russian (1)
Has Fulltext
- no (85) (remove)
Keywords
- Forena (3)
- VSVR (3)
- Virtual (TV) Studio (3)
- Eigene Methodik (2)
- FHD (2)
- Kraft-Wärme-Kälte-Kopplung im Leistungsbereich von 10 kW (2)
- Querschnittsauswertung (2)
- law (2)
- requirements engineering (2)
- security (2)
Department/institution
- Fachbereich - Maschinenbau und Verfahrenstechnik (24)
- Fachbereich - Medien (24)
- Fachbereich - Sozial- & Kulturwissenschaften (16)
- Fachbereich - Architektur (7)
- Digitale Vernetzung und Informationssicherheit (6)
- Fachbereich - Elektro- & Informationstechnik (6)
- Creative Media Production and Entertainment Computing (5)
- Fachbereich - Wirtschaftswissenschaften (4)
- Campus IT (1)
- Digital Learning and Digital Literacy (1)
The present study describes the development and validation of a German questionnaire assessing motivation to change in individuals with eating disorders (Stages of Change Questionnaire-Eating Disorders, SOCQ-ED). The SOCQ-ED measures stages of change separately for each eating disorder symptom domain. Psychometric properties were assessed in a sample of N=63 women with Anorexia Nervosa or Bulimia Nervosa. Test-retest reliability ranged from rtt=0.42 to 0.78 (Mdn=0.56), correlations with the University of Rhode Island Change Assessment were between r=0.21 and 0.32 and correlations with measurements of eating pathology ranged from r=0.19 to 0.46. The results provide initial support for the reliability and validity of the SOCQ-ED.
We present an approach to feature extraction that is a generalization of the classical linear discriminant analysis (LDA) on the basis of deep neural networks (DNNs). As for LDA, discriminative features generated from independent Gaussian class conditionals are assumed. This modeling has the advantages that the intrinsic dimensionality of the feature space is bounded by the number of classes and that the optimal discriminant function is linear. Unfortunately, linear transformations are insufficient to extract optimal discriminative features from arbitrarily distributed raw measurements. The generalized discriminant analysis (GerDA) proposed in this paper uses nonlinear transformations that are learnt by DNNs in a semisupervised fashion. We show that the feature extraction based on our approach displays excellent performance on real-world recognition and detection tasks, such as handwritten digit recognition and face detection. In a series of experiments, we evaluate GerDA features with respect to dimensionality reduction, visualization, classification, and detection. Moreover, we show that GerDA DNNs can preprocess truly high-dimensional input data to low-dimensional representations that facilitate accurate predictions even if simple linear predictors or measures of similarity are used.