Name and full contact address (surface, fax, email) of the individual responsible for submitting and receiving inquiries about the submission: Contact Lutz Dickmann, AbstractThe next big step in video-based life logging is to exploit image processing and context inference from multiple sensors. Automatic segmentation and classification of personal experiences recorded with always-on wearable devices may forge entirely new pragmatics of human interaction. Yet, how do we anticipate social dynamics to tackle critical ethical matters? Are we supposed to fit a design concept onto a to this point non-existent market or technology? We aim to contribute to the digital age discourse by making this emergent domain viable for responsible iterative design approaches. This sketch outlines how we address the novel technology at hand by integrating technical development and design strategies in a convergent full-circle approach.

Abstract. In this paper, we investigate how discourse context in the form of short-term memory can be exploited to automatically group consecutive strokes in digital freehand sketching. With this machine learning approach, no database of explicit object representations is used for template matching on a complete scene-instead, grouping decisions are based on limited spatio-temporal context. We employ two different classifier formalisms for this time series analysis task, namely Echo State Networks (ESNs) and Support Vector Machines (SVMs). ESNs present internal-state classifiers with inherent memory capabilities. For the conventional static SVM, short-term memory is supplied externally via fixed-length feature vector expansion. We compare the respective setup heuristics and conduct experiments with two exemplary problems. Promising results are achieved with both formalisms. Yet, our experiments indicate that using ESNs for variable-length memory tasks alleviates the risk of overfitting due to non-expressive features or improperly determined temporal embedding dimensions.

No abstract

No abstract