TripTracker: Unsupervised Learning of Fishing Vessel Routine Activity Patterns

2021 ◽  
Author(s):  
Amir Yaghoubi Shahir ◽  
Tilemachos Charalampous ◽  
Mohammad A. Tayebi ◽  
Uwe Glasser ◽  
Hans Wehn
Keyword(s):  
Unsupervised Learning ◽  
Activity Patterns ◽  
Routine Activity ◽  
Fishing Vessel

Activity locations, residential segregation and the significance of residential neighbourhood boundary perceptions

Urban Studies ◽  
2020 ◽  
pp. 004209802096626
Author(s):  
Nicolo P Pinchak ◽  
Christopher R Browning ◽  
Catherine A Calder ◽  
Bethany Boettner
Keyword(s):  
Residential Segregation ◽  
Activity Patterns ◽  
Social Processes ◽  
Routine Activity ◽  
Urban Residents ◽  
Census Tracts ◽  
Activity Spaces ◽  
Measurement Strategies ◽  
Urban Activity ◽  
Residential Neighbourhood

The inadequacies of residential census geography in capturing urban residents’ routine exposures have motivated efforts to more directly measure residents’ activity spaces. In turn, insights regarding urban activity patterns have been used to motivate alternative residential neighbourhood measurement strategies incorporating dimensions of activity space in the form of egocentric neighbourhoods – measurement approaches that place individuals at the centre of their own residential neighbourhood units. Unexamined, however, is the extent to which the boundaries of residents’ own self-defined residential neighbourhoods compare with census-based and egocentric neighbourhood measurement approaches in aligning with residents’ routine activity locations. We first assess this question, examining whether the boundaries of residents’ self-defined residential neighbourhoods are in closer proximity to the coordinates of a range of activity location types than are the boundaries of their census and egocentric residential neighbourhood measurement approaches. We find little evidence that egocentric or, crucially, self-defined residential neighbourhoods better align with activity locations, suggesting a division in residents’ activity locations and conceptions of their residential neighbourhoods. We then examine opposing hypotheses about how self-defined residential neighbourhoods and census tracts compare in socioeconomic and racial composition. Overall, our findings suggest that residents bound less segregated neighbourhoods than those produced by census geography, but self-defined residential neighbourhoods still reflect a preference towards homophily when considering areas beyond the immediate environment of their residence. These findings underscore the significance of individuals’ conceptions of residential neighbourhoods to understanding and measuring urban social processes such as residential segregation and social disorganisation.

scholarly journals Unsupervised learning and clustered connectivity enhance reinforcement learning in spiking neural networks

2020 ◽  
Author(s):  
Philipp Weidel ◽  
Renato Duarte ◽  
Abigail Morrison
Keyword(s):  
Reinforcement Learning ◽  
Unsupervised Learning ◽  
Activity Patterns ◽  
Receptive Fields ◽  
Place Cells ◽  
Spiking Neural Networks ◽  
Complex Environments ◽  
Proposed Model ◽  
Clustered Network ◽  
Better Than

ABSTRACTReinforcement learning is a learning paradigm that can account for how organisms learn to adapt their behavior in complex environments with sparse rewards. However, implementations in spiking neuronal networks typically rely on input architectures involving place cells or receptive fields. This is problematic, as such approaches either scale badly as the environment grows in size or complexity, or presuppose knowledge on how the environment should be partitioned. Here, we propose a learning architecture that combines unsupervised learning on the input projections with clustered connectivity within the representation layer. This combination allows input features to be mapped to clusters; thus the network self-organizes to produce task-relevant activity patterns that can serve as the basis for reinforcement learning on the output projections. On the basis of the MNIST and Mountain Car tasks, we show that our proposed model performs better than either a comparable unclustered network or a clustered network with static input projections. We conclude that the combination of unsupervised learning and clustered connectivity provides a generic representational substrate suitable for further computation.

scholarly journals Unsupervised Learning and Clustered Connectivity Enhance Reinforcement Learning in Spiking Neural Networks

2021 ◽  
Vol 15 ◽  
Author(s):  
Philipp Weidel ◽  
Renato Duarte ◽  
Abigail Morrison
Keyword(s):  
Reinforcement Learning ◽  
Unsupervised Learning ◽  
Ad Hoc ◽  
Activity Patterns ◽  
Receptive Fields ◽  
Complex Environments ◽  
Self Organized ◽  
Proposed Model ◽  
The Brain ◽  
Clustered Network

Reinforcement learning is a paradigm that can account for how organisms learn to adapt their behavior in complex environments with sparse rewards. To partition an environment into discrete states, implementations in spiking neuronal networks typically rely on input architectures involving place cells or receptive fields specified ad hoc by the researcher. This is problematic as a model for how an organism can learn appropriate behavioral sequences in unknown environments, as it fails to account for the unsupervised and self-organized nature of the required representations. Additionally, this approach presupposes knowledge on the part of the researcher on how the environment should be partitioned and represented and scales poorly with the size or complexity of the environment. To address these issues and gain insights into how the brain generates its own task-relevant mappings, we propose a learning architecture that combines unsupervised learning on the input projections with biologically motivated clustered connectivity within the representation layer. This combination allows input features to be mapped to clusters; thus the network self-organizes to produce clearly distinguishable activity patterns that can serve as the basis for reinforcement learning on the output projections. On the basis of the MNIST and Mountain Car tasks, we show that our proposed model performs better than either a comparable unclustered network or a clustered network with static input projections. We conclude that the combination of unsupervised learning and clustered connectivity provides a generic representational substrate suitable for further computation.

scholarly journals Guardianship in Action (GIA) Within Brisbane Suburbs

2017 ◽  
Vol 42 (3) ◽  
pp. 254-269 ◽  
Author(s):  
Emily Moir ◽  
Anna Stewart ◽  
Danielle M. Reynald ◽  
Timothy C. Hart
Keyword(s):  
Activity Patterns ◽  
Property Crime ◽  
Time Of Day ◽  
Routine Activity ◽  
Future Research ◽  
Multiple Observations ◽  
Residential Context ◽  
High Crime ◽  
Street Segments ◽  
Different Levels

Using Reynald’s guardianship in action (GIA) model, direct observations of properties along high- and low-crime street segments, within one low-crime and one high-crime suburb of Brisbane, Australia, were conducted ( N = 1,113). Multiple observations of properties were recorded across multiple times of the day and day of the week, in order to determine (a) the guardianship intensity exhibited by suburban residents, (b) whether areas that experience different levels of property crime were associated with different levels of guardianship intensity, and (c) whether guardianship intensity differed across time of day and day of week. Results show that guardianship intensity was significantly higher on the high-crime street segments. Although levels of occupancy differed significantly in line with expected routine activity patterns, there were no significant differences in monitoring and intervention behaviors observed over time. Current findings are discussed in light of the unique suburban residential context of Brisbane, and avenues for future research are examined.

scholarly journals Routine Activities and Delinquency: The Significance of Bonds to Society and Peer Context

2016 ◽  
Vol 64 (4) ◽  
pp. 472-509 ◽  
Author(s):  
Lizabeth A. Crawford ◽  
Katherine B. Novak ◽  
Amia K. Foston
Keyword(s):  
Social Relations ◽  
Peer Group ◽  
Activity Patterns ◽  
Social Bonding ◽  
Routine Activities ◽  
Routine Activity ◽  
Group Norms ◽  
Consistent Manner ◽  
The Relationship ◽  
Peer Context

This article extends prior research on routine activities and youth deviance by focusing on a broader range of routine activity patterns (RAPs) and on how their effects are conditioned by bonds to society and peer context. As hypothesized, the RAPs with the most consistent effects on delinquency were those lowest, or highest, in both structure and visibility. However, the relationship between school-related activities and delinquency was complex and varied across levels of the moderators in unexpected ways, given the structure and visibility of this RAP. Other RAPs, including unstructured peer interaction, affected delinquency independent of adolescents’ social relations, suggesting that neither social bonding nor external social control, via peer group norms, shapes the effects of situationally based opportunities for deviance on adolescents’ behaviors in a consistent manner.

scholarly journals Time-varying relationships between land use and crime: A spatio-temporal analysis of small-area seasonal property crime trends

2017 ◽  
Vol 46 (6) ◽  
pp. 1018-1035 ◽  
Author(s):  
Matthew Quick ◽  
Jane Law ◽  
Guangquan Li
Keyword(s):  
Land Use ◽  
Built Environment ◽  
Small Area ◽  
Activity Patterns ◽  
Property Crime ◽  
Routine Activity ◽  
Time Varying ◽  
Crime Trends ◽  
Substantial Impact ◽  
Spatio Temporal

Neighborhood land use composition influences the geographical patterns of property crime. Few studies, however, have investigated if, and how, the relationships between land use and crime change over time. This research applies a Bayesian spatio-temporal regression model to analyze 12 seasons of property crime at the small-area scale. Time-varying regression coefficients estimate the seasonally varying relationships between land use and crime and distinguish both time-constant and season-specific effects. Seasonal property crime trends are commonly hypothesized to be associated with fluctuating routine activity patterns around specific land uses, but past studies do not quantify the time-varying effects of neighborhood characteristics on small-area crime risk. Results show that, accounting for sociodemographic contexts, parks are more positively associated with property crime during spring and summer seasons, and eating and drinking establishments are more positively associated during autumn and winter seasons. Land use is found to have a more substantial impact on spatial, rather than spatio-temporal, crime patterns. Proposed explanations for results focus on seasonal activity patterns and corresponding spatio-temporal interactions with the built environment. The theoretical and analytical implications of this modeling approach are discussed. This research advances past cross-sectional spatial analyses of crime by identifying built environment characteristics that simultaneously shape both where and when crime occurs.

Predicting spatial activity patterns in a neural map from a probabilistic atlas of 3-D reconstructed neurons

1995 ◽  
Vol 53 ◽  
pp. 812-813
Author(s):  
G. Jacobs ◽  
F. Theunissen
Keyword(s):  
Activity Patterns ◽  
Three Dimensional ◽  
Sensory System ◽  
Neural System ◽  
Probabilistic Atlas ◽  
Uniform Sample ◽  
Dimensional Reconstruction ◽  
The Time Domain ◽  
And Function ◽  
Visualization Techniques

In order to understand how the algorithms underlying neural computation are implemented within any neural system, it is necessary to understand details of the anatomy, physiology and global organization of the neurons from which the system is constructed. Information is represented in neural systems by patterns of activity that vary in both their spatial extent and in the time domain. One of the great challenges to microscopists is to devise methods for imaging these patterns of activity and to correlate them with the underlying neuroanatomy and physiology. We have addressed this problem by using a combination of three dimensional reconstruction techniques, quantitative analysis and computer visualization techniques to build a probabilistic atlas of a neural map in an insect sensory system. The principal goal of this study was to derive a quantitative representation of the map, based on a uniform sample of afferents that was of sufficient size to allow statistically meaningful analyses of the relationships between structure and function.

Inducing Unconscious Stress

2020 ◽  
Vol 34 (3) ◽  
pp. 192-201
Author(s):  
Melanie M. van der Ploeg ◽  
Jos F. Brosschot ◽  
Markus Quirin ◽  
Richard D. Lane ◽  
Bart Verkuil
Keyword(s):  
Repeated Measures ◽  
Activity Patterns ◽  
Physiological Changes ◽  
Implicit Measures ◽  
Prime Word ◽  
Student Sample ◽  
Priming Task ◽  
Subject Design ◽  
The Relationship ◽  
Stress And Health

Abstract. Stress-related stimuli may be presented outside of awareness and may ultimately influence health by causing repetitive increases in physiological parameters, such as blood pressure (BP). In this study, we aimed to corroborate previous studies that demonstrated BP effects of subliminally presented stress-related stimuli. This would add evidence to the hypothesis that unconscious manifestations of stress can affect somatic health. Additionally, we suggest that these findings may be extended by measuring affective changes relating to these physiological changes, using measures for self-reported and implicit positive and negative affectivity. Using a repeated measures between-subject design, we presented either the prime word “angry” ( n = 26) or “relax” ( n = 28) subliminally (17 ms) for 100 trials to a student sample and measured systolic and diastolic BP, heart rate (HR), and affect. The “angry” prime, compared to the “relax” prime, did not affect any of the outcome variables. During the priming task, a higher level of implicit negative affect (INA) was associated with a lower systolic BP and diastolic BP. No association was found with HR. Self-reported affect and implicit positive affect were not related to the cardiovascular (CV) activity. In sum, anger and relax primes elicited similar CV activity patterns, but implicit measures of affect may provide a new method to examine the relationship between (unconscious) stress and health.

Sign in / Sign up

Export Citation Format

Share Document