Keine peer reviewed Publikation (Wissenschaftlicher Artikel und Aufsatz, Proceeding, Artikel in Tagungsband)
Refine
Document Type
- Conference Proceeding (11)
- Article (7)
- Part of a Book (4)
- Working Paper (4)
- Report (1)
Has Fulltext
- yes (27) (remove)
Keywords
- 3D Extended Object Tracking (1)
- Abtragsprinzip (1)
- Additive manufacturing (1)
- Bernstein polynomial (1)
- Climate communication (1)
- Climate crisis (1)
- Complex interval (1)
- Complex polynomial (1)
- Corporate Responsibility (1)
- Crowdmanagement (1)
Institute
- Fakultät Bauingenieurwesen (1)
- Fakultät Maschinenbau (1)
- Fakultät Wirtschafts-, Kultur- und Rechtswissenschaften (3)
- Institut für Angewandte Forschung - IAF (1)
- Institut für Optische Systeme - IOS (4)
- Institut für Strategische Innovation und Technologiemanagement - IST (2)
- Institut für Systemdynamik - ISD (2)
- Institut für Werkstoffsystemtechnik Konstanz - WIK (1)
- Konstanz Institut für Corporate Governance - KICG (4)
In the reverse engineering process one has to classify parts of point clouds with the correct type of geometric primitive. Features based on different geometric properties like point relations, normals, and curvature information can be used, to train classifiers like Support Vector Machines (SVM). These geometric features are estimated in the local neighborhood of a point of the point cloud. The multitude of different features makes an in-depth comparison necessary. In this work we evaluate 23 features for the classification of geometric primitives in point clouds. Their performance is evaluated on SVMs when used to classify geometric primitives in simulated and real laser scanned point clouds. We also introduce a normalization of point cloud density to improve classification generalization.
InBetween
(2017)
Offline handwriting recognition systems often use LSTM networks, trained with line- or word-images. Multi-line text makes it necessary to use segmentation to explicitly obtain these images. Skewed, curved, overlapping, incorrectly written text, or noise can lead to errors during segmentation of multi-line text and reduces the overall recognition capacity of the system. Last year has seen the introduction of deep learning methods capable of segmentation-free recognition of whole paragraphs. Our method uses Conditional Random Fields to represent text and align it with the network output to calculate a loss function for training. Experiments are promising and show that the technique is capable of training a LSTM multi-line text recognition system.
Algorithms for calculating the string edit distance are used in e.g. information retrieval and document analysis systems or for evaluation of text recognizers. Text recognition based on CTC-trained LSTM networks includes a decoding step to produce a string, possibly using a language model, and evaluation using the string edit distance. The decoded string can further be used as a query for database search, e.g. in document retrieval. We propose to closely integrate dictionary search with text recognition to train both combined in a continuous fashion. This work shows that LSTM networks are capable of calculating the string edit distance while allowing for an exchangeable dictionary to separate learned algorithm from data. This could be a step towards integrating text recognition and dictionary search in one deep network.
Today’s markets are characterized by fast and radical changes, posing an essential challenge to established companies. Startups, yet, seem to be more capable in developing radical innovations to succeed in those volatile markets. Thus, established companies started to experiment with various approaches to implement startup-like structures in their organization. Internal corporate accelerators (ICAs) are a novel form of corporate venturing, aiming to foster bottom-up innovations through intrapreneurship. However, ICAs still lack empirical investigations. This work contributes to a deeper understanding of the interface between the ICA and the core organization and the respective support activities (resource access and support services) that create an innovation-supportive work environment for the intrapreneurial team. The results of this qualitative study, comprising 12 interviews with ICA teams out of two German high-tech companies, show that the resources provided by ICAs differ from the support activities of external accelerators. Further, the study shows that some resources show both supportive as well as obstructive potential for the intrapreneurial teams within the ICA.
Thermal shape memory alloys show extraordinary material properties and can be used as actuators, dampers and sensors. Since their discovery in the middle of the last century they have been investigated and further developed. The majority of the industrial applications with the highest material sales can still be found in the medical industry, where they are used due to their superelastic and thermal shape memory effect, e.g. as stents or as guidewires and tools in the minimal invasive surgery. Particularly in recent years, more and more applications have been developed for other industrial fields, e.g. for the household goods, civil engineering and automotive sector. In this context it is worth mentioning that for the latter sector, million seller series applications have found their way into some European automobile manufacturers. The German VDI guideline for shape memory alloys introduced in 2017 will give the material a further boost in application. Last but not least the new production technologies of additive manufacturing with metal laser sintering plants open up additional applications for these multifunctional materials. This paper gives an overview of the extraordinary material properties of shape memory components, shows examples of different applications and discusses European trends against the background of the most recent standard and new production technologies.