ResumoNeste estudo são apresentadas as normas de (Nelson, 1977, p. 102).

Human motion analysis provides useful information for the diagnosis and recovery assessment of people suffering from pathologies, such as those affecting the way of walking, i.e., gait. With recent developments in deep learning, state-of-the-art performance can now be achieved using a single 2D-RGB-camera-based gait analysis system, offering an objective assessment of gait-related pathologies. Such systems provide a valuable complement/alternative to the current standard practice of subjective assessment. Most 2D-RGB-camera-based gait analysis approaches rely on compact gait representations, such as the gait energy image, which summarize the characteristics of a walking sequence into one single image. However, such compact representations do not fully capture the temporal information and dependencies between successive gait movements. This limitation is addressed by proposing a spatiotemporal deep learning approach that uses a selection of key frames to represent a gait cycle. Convolutional and recurrent deep neural networks were combined, processing each gait cycle as a collection of silhouette key frames, allowing the system to learn temporal patterns among the spatial features extracted at individual time instants. Trained with gait sequences from the GAIT-IT dataset, the proposed system is able to improve gait pathology classification accuracy, outperforming state-of-the-art solutions and achieving improved generalization on cross-dataset tests.

ResearchSPAce http://researchspace.bathspa.ac.uk/ This pre-published version is made available in accordance with publisher policies. Please cite only the published version using the reference above. Your access and use of this document is based on your acceptance of the ResearchSPAce Metadata and Data Policies, as well as applicable law:https://researchspace.bathspa.ac.uk/policies.html Unless you accept the terms of these Policies in full, you do not have permission to download this document.This cover sheet may not be removed from the document.

We examined the effect of memory instructions on false memory using the Deese/Roediger–McDermott paradigm in second-language learners. Participants studied lists of words in L1 and L2 (e.g., note, sound, piano…) associatively related to a non-presented critical lure (e.g., MUSIC). In a later recognition test, critical lures appeared in the same or the other language of their lists (i.e., within- and between-language conditions). In Experiment 1, participants should only endorse an item when study and test languages matched (i.e., restrictive instructions); that is, they should retrieve language information. In Experiment 2, participants should endorse studied items regardless of the language (i.e., inclusive instructions). With restrictive instructions, false recognition was higher in within- than between-language conditions, whereas with inclusive instructions, this result was replicated only when words were studied in L1, but not L2. Results suggested that second-language learners show false memory in their L2 and that the effect of language shift on false recognition depended on the study language.