Skill Memory in Biped Locomotion

Robots must be able to adapt their motor behavior to unexpected situations in order to safely move among humans. A necessary step is to be able to predict failures, which result in behavior abnormalities and may cause irrecoverable damage to the robot and its surroundings, i.e. humans. In this paper we build a predictive model of sensor traces that enables early failure detection by means of a skill memory. Specifically, we propose an architecture based on a biped locomotion solution with improved robustness due to sensory feedback, and extend the concept of Associative Skill Memories (ASM) to periodic movements by introducing several mechanisms into the training workflow, such as linear interpolation and regression into a Dynamical Motion Primitive (DMP) system such that representation becomes time invariant and easily parameterizable. The failure detection mechanism applies statistical tests to determine the optimal operating conditions. Both training and failure testing were conducted on a DARwIn-OP inside a simulation environment to assess and validate the failure detection system proposed. Results show that the system performance in terms of the compromise between sensitivity and specificity is similar with and without the proposed mechanism, while achieving a significant data size reduction due to the periodic approach taken.     

Lightfield Recovery from Its Focal Stack

The Focal Stack Transform integrates a 4D lightfield over a set of appropriately chosen 2D planes. The result of such integration is an image focused on a determined depth in 3D space. The set of such images is the Focal Stack of the lightfield. This paper studies the existence of an inverse for this transform. Such inverse could be used to obtain a 4D lightfield from a set of images focused on several depths of the scene. In this paper, we show that this inversion cannot be obtained for a general lightfield and introduce a subset of lightfields where this inversion can be computed exactly. We examine the numerical properties of such inversion process for general lightfields and examine several regularization approaches to stabilize the transform. Experimental results are provided for focal stacks obtained from several plenoptic cameras. From a practical point of view, results show how this inversion procedure can be used to recover, compress, and denoise the original 4D lightfield.     

A Minimal Closed-form Solution for the Perspective Three Orthogonal Angles (P3oA) Problem: Application To Visual Odometry

We provide a simple closed-form solution to the Perspective three orthogonal angles (P3oA) problem: given the projection of three orthogonal lines in a calibrated camera, find their 3D directions. Upon this solution, an algorithm for the estimation of the camera relative rotation between two frames is proposed. The key idea is to detect triplets of orthogonal lines in a hypothesize-and-test framework and use all of them to compute the camera rotation in a robust way. This approach is suitable for human-made environments where numerous groups of orthogonal lines exist. We evaluate the numerical stability of the P3oA solution and the estimation of the relative rotation with synthetic and real data, comparing our results to other state-of-the-art approaches.     

Democratizing Journalism – How User‐Generated Content and User Communities Affect Publishers’ Business Models

Publishers, today, are struggling with their business model: Their efforts to convert traditional content into digital products seem to be insufficient as recipients expect more than simply the mere digitalization of content. Dissatisfied with solely being informed by selected journalists, modern recipients are often interested in acquiring information from various sources, in discussing with others, or even in contributing with their own content. Hence, recipients seem to evolve from being simply readers to contributors themselves. With regard to the established term ‘user‐generated content’, we refer to those co‐creating recipients as users. To underline these assumptions, the present study explores (1) users’ expectations of sources of content and (2) their willingness to provide their own content. Our findings show that both user‐generated content and professional journalists’ content is of value to users. Second, we show that users are mainly driven to contribute by their own expertise, welfare of others, and personal acceptance in the community. With this study, we consider mainly the changed user behaviour in order to derive implications of user involvement for future business models of publishers, in particular on the customer value proposition as well as key resources and key processes.     

Set‐based fault detection and isolation for detectable linear parameter‐varying systems

In the context of fault detection and isolation of linear parameter‐varying systems, a challenging task appears when the dynamics and the available measurements render the model unobservable, which invalidates the use of standard set‐valued observers. Two results are obtained in this paper, namely, using a left‐coprime factorization, one can achieve set‐valued estimates with ultimately bounded hyper‐volume and convergence dependent on the slowest unobservable mode; and by rewriting the set‐valued observer equations and taking advantage of a coprime factorization, it is possible to have a low‐complexity fault detection and isolation method. Performance is assessed through simulation, illustrating, in particular, the detection time for various types of faults. Copyright © 2017 John Wiley & Sons, Ltd.     

Authorship verification applied to detection of compromised accounts on online social networks

Compromising legitimate accounts has been the most used strategy to spread malicious content on OSN (Online Social Network). To address this problem, we propose a pure text mining approach to check if an account has been compromised based on its posts content. In the first step, the proposed approach extracts the writing style from the user account. The second step comprehends the k-Nearest Neighbors algorithm (k-NN) to evaluate the post content and identify the user. Finally, Baseline Updating (third step) consists of a continuous updating of the user baseline to support the current trends and seasonality issues of user’s posts. Experiments were carried out using a dataset from Twitter composed by tweets of 1000 users. All the three steps were individually evaluated, and the results show that the developed method is stable and can detect the compromised accounts. An important observation is the Baseline Updating contribution, which leads to an enhancement of accuracy superior of 60 %. Regarding average accuracy, the developed method achieved results over 93 %.     

From software extensions to product lines of dataflow programs

Dataflow programs are widely used. Each program is a directed graph where nodes are computations and edges indicate the flow of data. In prior work, we reverse-engineered legacy dataflow programs by deriving their optimized implementations from a simple specification graph using graph transformations called refinements and optimizations. In MDE speak, our derivations were PIM-to-PSM mappings. In this paper, we show how extensions complement refinements, optimizations, and PIM-to-PSM derivations to make the process of reverse engineering complex legacy dataflow programs tractable. We explain how optional functionality in transformations can be encoded, thereby enabling us to encode product lines of transformations as well as product lines of dataflow programs. We describe the implementation of extensions in the \(\mathtt{ReFlO}\) tool and present two non-trivial case studies as evidence of our work’s generality.     

Active learning paradigms for CBIR systems based on optimum-path forest classification

This paper discusses methods for content-based image retrieval (CBIR) systems based on relevance feedback according to two active learning paradigms, named greedy and planned. In greedy methods, the system aims to return the most relevant images for a query at each iteration. In planned methods, the most informative images are returned during a few iterations and the most relevant ones are only presented afterward. In the past, we proposed a greedy approach based on optimum-path forest classification (OPF) and demonstrated its gain in effectiveness with respect to a planned method based on support-vector machines and another greedy approach based on multi-point query. In this work, we introduce a planned approach based on the OPF classifier and demonstrate its gain in effectiveness over all methods above using more image databases. In our tests, the most informative images are better obtained from images that are classified as relevant, which differs from the original definition. The results also indicate that both OPF-based methods require less user involvement (efficiency) to satisfy the user's expectation (effectiveness), and provide interactive response times.     

IsoGeometric analysis using T-splines on two-patch geometries

We develop optimal approximation estimates for T-splines in the case of geometries obtained by gluing two standard tensor product patches. We derive results both for the T-spline space in the parametric domain and the mapped T-NURBS in the physical one. A set of numerical tests in complete accordance with the theoretical developments is also presented.