Time series are series of values ordered by time. This kind of data can be found in many real world settings. Classifying time series is a difficult task and an active area of research. This paper investigates the use of transfer learning in Deep Neural Networks and a 2D representation of time series known as Recurrence Plots. In order to utilize the research done in the area of image classification, where Deep Neural Networks have achieved very good results, we use a Residual Neural Networks architecture known as ResNet. As preprocessing of time series is a major part of every time series classification pipeline, the method proposed simplifies this step and requires only few parameters. For the first time we propose a method for multi time series classification: Training a single network to classify all datasets in the archive with one network. We are among the first to evaluate the method on the latest 2018 release of the UCR archive, a well established time series classification benchmarking dataset.
Stuttering is a complex speech disorder identified by repeti-tions, prolongations of sounds, syllables or words and blockswhile speaking. Specific stuttering behaviour differs strongly,thus needing personalized therapy. Therapy sessions requirea high level of concentration by the therapist. We introduceSTAN, a system to aid speech therapists in stuttering therapysessions. Such an automated feedback system can lower thecognitive load on the therapist and thereby enable a more con-sistent therapy as well as allowing analysis of stuttering overthe span of multiple therapy sessions.
The use of electrophotographic polymer powder transfer for the preparation of patterned powder layers is discussed with respect to a possible multimaterial application in powder bed-based additive manufacturing technologies such as selective laser sintering (SLS). Therefore, an experimental setup with a two-chamber design was realized, enabling the electrophotographic transfer of SLS powder materials at typical process conditions. The powder development (pick-up) step was investigated thoroughly for different powder materials to provide deep understanding of the underlying electrostatic effects and the influence of distinct powder properties. While using two different development modes, differences in the development results were correlated to differences in their particle size distribution, bulk density, and relative permittivity. Moreover, a new strategy was invented, allowing the residual electrophotographic powder deposition to be in general independent from the already produced part height. This is known to be a huge challenge but is mandatory for the buildup of three-dimensional multimaterial components.