ON THE REPRESENTATION, LEARNING AND TRANSFER OF SPATIO-TEMPORAL MOVEMENT CHARACTERISTICS

2004 ◽  
Vol 01 (04) ◽  
pp. 613-636 ◽  
Author(s):  
WINFRIED ILG ◽  
GÖKHAN H. BAKIR ◽  
JOHANNES MEZGER ◽  
MARTIN A. GIESE
Keyword(s):  
Representation Learning ◽  
Movement Sequences ◽  
Movement Trajectories ◽  
Movement Characteristics ◽  
Human Movements ◽  
Complex Sequences ◽  
Movement Representation ◽  
Spatio Temporal ◽  
Morphable Models ◽  
Complex Movement

In this paper we present a learning-based approach for the modeling of complex movement sequences. Based on the method of Spatio-Temporal Morphable Models (STMMs) we derive a hierarchical algorithm that, in a first step, identifies automatically movement elements in movement sequences based on a coarse spatio-temporal description, and in a second step models these movement primitives by approximation through linear combinations of learned example movement trajectories. We describe the different steps of the algorithm and show how it can be applied for modeling and synthesis of complex sequences of human movements that contain movement elements with a variable style. The proposed method is demonstrated on different applications of movement representation relevant for imitation learning of movement styles in humanoid robotics.

App2Vec: Context-Aware Application Usage Prediction

2021 ◽  
Vol 15 (6) ◽  
pp. 1-21
Author(s):  
Huandong Wang ◽  
Yong Li ◽  
Mu Du ◽  
Zhenhui Li ◽  
Depeng Jin
Keyword(s):  
Dirichlet Process ◽  
Service Providers ◽  
State Of The Art ◽  
Representation Learning ◽  
Context Aware ◽  
Challenging Problem ◽  
Performance Gap ◽  
Bayesian Mixture Model ◽  
Bayesian Mixture ◽  
Spatio Temporal

Both app developers and service providers have strong motivations to understand when and where certain apps are used by users. However, it has been a challenging problem due to the highly skewed and noisy app usage data. Moreover, apps are regarded as independent items in existing studies, which fail to capture the hidden semantics in app usage traces. In this article, we propose App2Vec, a powerful representation learning model to learn the semantic embedding of apps with the consideration of spatio-temporal context. Based on the obtained semantic embeddings, we develop a probabilistic model based on the Bayesian mixture model and Dirichlet process to capture when , where , and what semantics of apps are used to predict the future usage. We evaluate our model using two different app usage datasets, which involve over 1.7 million users and 2,000+ apps. Evaluation results show that our proposed App2Vec algorithm outperforms the state-of-the-art algorithms in app usage prediction with a performance gap of over 17.0%.

scholarly journals Ensemble model for estimating continental-scale patterns of human movement: a case study of Australia

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Karen McCulloch ◽  
Nick Golding ◽  
Jodie McVernon ◽  
Sarah Goodwin ◽  
Martin Tomko
Keyword(s):  
Spatial Scales ◽  
Predictive Ability ◽  
Movement Patterns ◽  
Human Movement ◽  
Continental Scale ◽  
Movement Characteristics ◽  
Human Movements ◽  
Movement Models ◽  
Epidemiology Data

AbstractUnderstanding human movement patterns at local, national and international scales is critical in a range of fields, including transportation, logistics and epidemiology. Data on human movement is increasingly available, and when combined with statistical models, enables predictions of movement patterns across broad regions. Movement characteristics, however, strongly depend on the scale and type of movement captured for a given study. The models that have so far been proposed for human movement are best suited to specific spatial scales and types of movement. Selecting both the scale of data collection, and the appropriate model for the data remains a key challenge in predicting human movements. We used two different data sources on human movement in Australia, at different spatial scales, to train a range of statistical movement models and evaluate their ability to predict movement patterns for each data type and scale. Whilst the five commonly-used movement models we evaluated varied markedly between datasets in their predictive ability, we show that an ensemble modelling approach that combines the predictions of these models consistently outperformed all individual models against hold-out data.

Multi-modal transportation recommendation with unified route representation learning

2020 ◽  
Vol 14 (3) ◽  
pp. 342-350
Author(s):  
Hao Liu ◽  
Jindong Han ◽  
Yanjie Fu ◽  
Jingbo Zhou ◽  
Xinjiang Lu ◽  
...  
Keyword(s):  
Large Scale ◽  
Transportation Networks ◽  
Representation Learning ◽  
Transportation Systems ◽  
Graph Representation ◽  
Dynamic Graph ◽  
Arbitrary Length ◽  
Task Learning ◽  
Semantic Coherence ◽  
Spatio Temporal

Multi-modal transportation recommendation aims to provide the most appropriate travel route with various transportation modes according to certain criteria. After analyzing large-scale navigation data, we find that route representations exhibit two patterns: spatio-temporal autocorrelations within transportation networks and the semantic coherence of route sequences. However, there are few studies that consider both patterns when developing multi-modal transportation systems. To this end, in this paper, we study multi-modal transportation recommendation with unified route representation learning by exploiting both spatio-temporal dependencies in transportation networks and the semantic coherence of historical routes. Specifically, we propose to unify both dynamic graph representation learning and hierarchical multi-task learning for multi-modal transportation recommendations. Along this line, we first transform the multi-modal transportation network into time-dependent multi-view transportation graphs and propose a spatiotemporal graph neural network module to capture the spatial and temporal autocorrelation. Then, we introduce a coherent-aware attentive route representation learning module to project arbitrary-length routes into fixed-length representation vectors, with explicit modeling of route coherence from historical routes. Moreover, we develop a hierarchical multi-task learning module to differentiate route representations for different transport modes, and this is guided by the final recommendation feedback as well as multiple auxiliary tasks equipped in different network layers. Extensive experimental results on two large-scale real-world datasets demonstrate the performance of the proposed system outperforms eight baselines.

scholarly journals Multi-scale imaging and analysis identify pan-embryo cell dynamics of germlayer formation in zebrafish

2019 ◽  
Vol 10 (1) ◽  
Author(s):  
Gopi Shah ◽  
Konstantin Thierbach ◽  
Benjamin Schmid ◽  
Johannes Waschke ◽  
Anna Reade ◽  
...  
Keyword(s):  
Cell Movement ◽  
Automated Analysis ◽  
Embryo Cell ◽  
Tissue Formation ◽  
Cell Dynamics ◽  
Multi Scale ◽  
Movement Characteristics ◽  
Global Movement ◽  
Spatio Temporal ◽  
Distinct Distribution

AbstractThe coordination of cell movements across spatio-temporal scales ensures precise positioning of organs during vertebrate gastrulation. Mechanisms governing such morphogenetic movements have been studied only within a local region, a single germlayer or in whole embryos without cell identity. Scale-bridging imaging and automated analysis of cell dynamics are needed for a deeper understanding of tissue formation during gastrulation. Here, we report pan-embryo analyses of formation and dynamics of all three germlayers simultaneously within a developing zebrafish embryo. We show that a distinct distribution of cells in each germlayer is established during early gastrulation via cell movement characteristics that are predominantly determined by their position in the embryo. The differences in initial germlayer distributions are subsequently amplified by a global movement, which organizes the organ precursors along the embryonic body axis, giving rise to the blueprint of organ formation. The tools and data are available as a resource for the community.

Short article: Effects of interlimb practice on coding and learning of movement sequences

2009 ◽  
Vol 62 (7) ◽  
pp. 1265-1276 ◽  
Author(s):  
Stefan Panzer ◽  
Thomas Muehlbauer ◽  
Melanie Krueger ◽  
Dirk Buesch ◽  
Falk Naundorf ◽  
...  
Keyword(s):  
Dominant Role ◽  
Short Article ◽  
Independent Manner ◽  
Contralateral Limb ◽  
Activation Patterns ◽  
Movement Sequences ◽  
Visual Spatial ◽  
Spatial Coordinates ◽  
Element Movement ◽  
Complex Movement

An interlimb practice paradigm was designed to determine the role that visual–spatial (Cartesian) and motor (joint angles, activation patterns) coordinates play in the coding and learning of complex movement sequences. Participants practised a 16-element movement sequence by moving a lever to sequentially presented targets with one limb on Day 1 and the contralateral limb on Day 2. Practice involved the same sequence with either the same visual–spatial or motor coordinates on the two days. A unilateral practice condition (control) was also tested where both coordinate systems were changed but the same limb was used. Retention tests were conducted on Day 3. Regardless of the order in which the limbs were used during practice, results indicated that keeping the visual–spatial coordinates the same during acquisition resulted in superior retention. This provides strong evidence that the visual–spatial code plays a dominant role in complex movement sequences, and this code is represented in an effector-independent manner.

Age-related effects in interlimb practice on coding complex movement sequences

2011 ◽  
Vol 30 (3) ◽  
pp. 459-474 ◽  
Author(s):  
Stefan Panzer ◽  
Nicole Gruetzmacher ◽  
Udo Fries ◽  
Melanie Krueger ◽  
Charles H. Shea
Keyword(s):  
Movement Sequences ◽  
Age Related ◽  
Complex Movement

Basal ganglia neural mechanisms of natural movement sequences

2004 ◽  
Vol 82 (8-9) ◽  
pp. 732-739 ◽  
Author(s):  
J Wayne Aldridge ◽  
Kent C Berridge ◽  
Alyssa R Rosen
Keyword(s):  
Basal Ganglia ◽  
Neural Mechanisms ◽  
Sequential Patterns ◽  
Striatal Neurons ◽  
Warm Up ◽  
Movement Sequences ◽  
Natural Movement ◽  
Baseline Levels ◽  
Instinctive Behavior ◽  
Complex Movement

Natural rodent grooming and other instinctive behavior serves as a natural model of complex movement sequences. Rodent grooming has syntactic (rule-driven) sequences and more random movement patterns. Both incorporate the same movements—only the serial structure differs. Recordings of neural activity in the dorsolateral striatum and the substantia nigra pars reticulata indicate preferential activation during syntactic sequences over more random sequences. Neurons that are responsive during syntactic grooming sequences are often unresponsive or have reverse activation profiles during kinematically similar movements that occur in flexible or random grooming sequences. Few neurons could be categorized as strictly movement related—instead they were activated only in the context of particular sequential patterns of movements. Particular sequential patterns included "syntactic chain" grooming sequences of paw, head, and body movements and also "warm-up" sequences, which consist of head and body/limb movements that precede locomotion after a period of quiet resting (Golani 1992). Activation during warm-up was less intense and less frequent than during grooming sequences, but both sequences activated neurons above baseline levels, and the same neurons sometimes responded to both sequences. The fact that striatal neurons code 2 natural sequences which are made up of different constituent movements suggests that the basal ganglia may have a generalized role in sequence control. The basal ganglia are modulated by the context of the sequence and may play an executive function in the complex natural patterns of sequenced behaviour.Key words: movement, basal ganglia, striatum, movement sequences, sensorimotor behaviour.

Sign in / Sign up

Export Citation Format

Share Document