Social media can be a useful tool in order to interact with customers and open up innovation efforts. Our case studies of firms aim to outline if, how and why social media is utilised in their product development processes. Our results show that the use of social media within product development is limited among our respondents, mainly due to limited resources in combination with a low amount of customers. The results show that a low number of customers impede the ability to realise the possible gains of using social media to facilitate communication among a large number of users. Additional challenges are perceived to be the difficulty in controlling content, measuring gains and dealing with security issues. There is no consensus among the respondents with regard to social media's perceived future potential within product development; some are quite hesitant, other companies anticipate increased potential in the future. 274 G. Berendsen et al.

This paper describes the use of two different deep-learning algorithms for object detection to recognize different badgers. We use recordings of four different badgers under varying background illuminations. In total four different object detection algorithms based on deep neural networks are compared: The single shot multi-box detector (SSD) with the Inception-V2 or MobileNet as a backbone, and the faster region-based convolutional neural network (Faster R-CNN) combined with Inception-V2 or residual networks. Furthermore, two different activation functions are compared to compute probabilities that some badger is in the detected region: the softmax and sigmoid functions. The results of all eight models show that SSD obtains higher recognition accuracies (97.8%-98.6%) than Faster R-CNN (84.8%-91.7%). However, the training time of Faster R-CNN is much shorter than that of SSD. The use of different output activation functions seems not to matter much.

No abstract