A Wearable-HAR Oriented Sensory Data Generation Method Based on Spatio-temporal Reinforced Conditional GANs

2022 ◽  
Author(s):  
Jiwei Wang ◽  
Yiqiang Chen ◽  
Yang Gu
Keyword(s):  
Data Generation ◽  
Sensory Data ◽  
Spatio Temporal

STPC-Net: Learn Massive Geo-Sensory Data as Spatio-Temporal Point Clouds

2021 ◽  
pp. 1-11
Author(s):  
Chuanpan Zheng ◽  
Cheng Wang ◽  
Xiaoliang Fan ◽  
Jianzhong Qi ◽  
Xu Yan
Keyword(s):  
Point Clouds ◽  
Sensory Data ◽  
Spatio Temporal

TOOLS FOR EXPERIENTIAL RECOGNITION

1992 ◽  
Vol 01 (03) ◽  
pp. 427-461 ◽  
Author(s):  
PANOS A. LIGOMENIDES
Keyword(s):  
Decision Maker ◽  
Formal Description ◽  
Two Stage ◽  
One Dimensional ◽  
Human Expert ◽  
Sensory Data ◽  
Structural Identity ◽  
Perceptual Recognition ◽  
Perceptual Ability ◽  
Spatio Temporal

Our objective in the interactive formulation of the "formal description schema - fds" model is the modeling of the prototypical, i.e. the subjective, perceptual ability of a human "expert", the ultimate human or robotic decision maker. In this paper, we present our fds-approach and methodology for solving the problem of modeling and exercising perceptual recognition [3–6]. We limit our discussion to one-dimensional variational profiles. We view the fds-model as a two-stage procedural model. Concerning the "early" (pre-attentive) recognition stage, we define the "structural identity of a k-norm class, k∈K" — SkID — as a tool for quick shadowing of sensory data and positioning instantiations of sufficient resemblance to interactively pre-defined spatio–temporal norm classes. Attentive recognition tools follow for assessing conformity of SkID-pointed occurrences.

scholarly journals On stay at home orders: Using the power of data science for spatial and temporal modeling and visualization of COVID-19

2021 ◽  
Author(s):  
Christopher R Prentice ◽  
Rachel Carroll
Keyword(s):  
United States ◽  
Data Science ◽  
The United States ◽  
Data Generation ◽  
Community Members ◽  
Temporal Modeling ◽  
Related Research ◽  
Mapping Model ◽  
Spatio Temporal ◽  
At Home

Abstract Coronavirus disease 2019 dominated and augmented many aspects of life beginning in early 2020. Related research and data generation developed alongside its spread. We developed a Bayesian spatio-temporal Poisson disease mapping model for estimating real-time characteristics of the coronavirus disease in the United States. We also created several dashboards for visualization of the statistical model for fellow researchers and simpler spatial and temporal representations of the disease for consumption by community members in our region. Findings suggest that the risk of confirmed cases is higher for health regions under partial stay at home orders and lower in health regions under full stay at home orders, when compared to before stay at home orders were declared. These results confirm the benefit of state-issued stay at home orders as well as suggest compliance to the directives towards the older population for adhering to social distancing guidelines.

scholarly journals The evolution of humanitarian mapping within the OpenStreetMap community

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Benjamin Herfort ◽  
Sven Lautenbach ◽  
João Porto de Albuquerque ◽  
Jennings Anderson ◽  
Alexander Zipf
Keyword(s):  
Human Development ◽  
Large Scale ◽  
Data Generation ◽  
Structural Barriers ◽  
The Sustainable Development ◽  
Major Development ◽  
Spatial Coverage ◽  
Development Goals ◽  
Spatio Temporal ◽  
Global Population

AbstractIn the past 10 years, the collaborative maps of OpenStreetMap (OSM) have been used to support humanitarian efforts around the world as well as to fill important data gaps for implementing major development frameworks such as the Sustainable Development Goals. This paper provides a comprehensive assessment of the evolution of humanitarian mapping within the OSM community, seeking to understand the spatial and temporal footprint of these large-scale mapping efforts. The spatio-temporal statistical analysis of OSM’s full history since 2008 showed that humanitarian mapping efforts added 60.5 million buildings and 4.5 million roads to the map. Overall, mapping in OSM was strongly biased towards regions with very high Human Development Index. However, humanitarian mapping efforts had a different footprint, predominantly focused on regions with medium and low human development. Despite these efforts, regions with low and medium human development only accounted for 28% of the buildings and 16% of the roads mapped in OSM although they were home to 46% of the global population. Our results highlight the formidable impact of humanitarian mapping efforts such as post-disaster mapping campaigns to improve the spatial coverage of existing open geographic data and maps, but they also reveal the need to address the remaining stark data inequalities, which vary significantly across countries. We conclude with three recommendations directed at the humanitarian mapping community: (1) Improve methods to monitor mapping activity and identify where mapping is needed. (2) Rethink the design of projects which include humanitarian data generation to avoid non-sustainable outcomes. (3) Remove structural barriers to empower local communities and develop capacity.

scholarly journals Conditional Deep 3D-Convolutional Generative Adversarial Nets for RGB-D Generation

2021 ◽  
Vol 2021 ◽  
pp. 1-8
Author(s):  
Richa Sharma ◽  
Manoj Sharma ◽  
Ankit Shukla ◽  
Santanu Chaudhury
Keyword(s):  
Object Tracking ◽  
Action Recognition ◽  
Synthetic Data ◽  
Depth Map ◽  
Generative Adversarial Networks ◽  
Data Generation ◽  
Adversarial Networks ◽  
Proposed Model ◽  
Spatio Temporal ◽  
Class Labels

Generation of synthetic data is a challenging task. There are only a few significant works on RGB video generation and no pertinent works on RGB-D data generation. In the present work, we focus our attention on synthesizing RGB-D data which can further be used as dataset for various applications like object tracking, gesture recognition, and action recognition. This paper has put forward a proposal for a novel architecture that uses conditional deep 3D-convolutional generative adversarial networks to synthesize RGB-D data by exploiting 3D spatio-temporal convolutional framework. The proposed architecture can be used to generate virtually unlimited data. In this work, we have presented the architecture to generate RGB-D data conditioned on class labels. In the architecture, two parallel paths were used, one to generate RGB data and the second to synthesize depth map. The output from the two parallel paths is combined to generate RGB-D data. The proposed model is used for video generation at 30 fps (frames per second). The frame referred here is an RGB-D with the spatial resolution of 512 × 512.

Spatio-Temporal Variability of Observed Ground Water Level at Peat Hydrology Unit in South Sumatera

2020 ◽  
Vol 17 (2) ◽  
pp. 1414-1421
Author(s):  
Muhammad Irfan ◽  
Wijaya Mardiansyah ◽  
Heron Surbakti ◽  
Menik Ariani ◽  
Albert Sulaiman ◽  
...  
Keyword(s):  
Ground Water ◽  
Water Level ◽  
Data Transmission ◽  
Temporal Variability ◽  
The Other ◽  
Ground Water Level ◽  
Observation System ◽  
Sensory Data ◽  
Coefficient Corrélation ◽  
Spatio Temporal

An integrated observation system, so-called SEnsory data transmission Service Assisted by Midori Engineering laboratory (SESAME) has been deployed to measure hydrological and climatological parameters at peatlands of South Sumatera since June 2017. One of the observed hydrological parameters is the Ground Water Level (GWL). This study evaluates the spatio-temporal variability of GWL observed at 4 locations, namely, Peat Hydrology Unit (PHU) Sungai Saleh 1 (SS1), Sungai Saleh 2 (SS2), Sungai Lumpur 1 (SL1), and Sungai Lumpur 2 (SL2). The data covered a period of July 1, 2017 to June 30, 2018. This study focused on analyzing types of observed tides at each SESAME location. It was found that at the study location SL2, SS1, and SS2 the tidal type was a mixed tide prevailing diurnal. On the other hand, the observed GWL at the SL1 was dominated by a mixed tide prevailing semidiurnal. Further analysis on the observed GWL indicates that the lowest GWL was observed in period September-October, while the highest GWL occurs in period March-April. Statistical analysis shows that the observed GWL was significantly correlated with the observed soil moisture at the SL1 and the SL2. The coefficient correlation at those SL1 and SL2 were 0.85 and 0.95, respectively. It was also found that GWL had a significant correlation with Rainfall (RF).

scholarly journals Using spatial and temporal modeling to visualize the effects of U.S. state issued stay at home orders on COVID-19

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Rachel Carroll ◽  
Christopher R. Prentice
Keyword(s):  
United States ◽  
Statistical Model ◽  
Real Time ◽  
The United States ◽  
Data Generation ◽  
Temporal Modeling ◽  
Related Research ◽  
Mapping Model ◽  
Spatio Temporal ◽  
At Home

AbstractCoronavirus disease 2019 dominated and augmented many aspects of life beginning in early 2020. Related research and data generation developed alongside its spread. We developed a Bayesian spatio-temporal Poisson disease mapping model for estimating real-time characteristics of the coronavirus disease in the United States. We also created several dashboards for visualization of the statistical model for fellow researchers and simpler spatial and temporal representations of the disease for consumption by analysts and data scientists in the policymaking community in our region. Findings suggest that the risk of confirmed cases is higher for health regions under partial stay at home orders and lower in health regions under full stay at home orders, when compared to before stay at home orders were declared. These results confirm the benefit of state-issued stay at home orders as well as suggest compliance to the directives towards the older population for adhering to social distancing guidelines.

scholarly journals A method for well log data generation based on a spatio-temporal neural network

2021 ◽  
Vol 18 (5) ◽  
pp. 700-711
Author(s):  
Jun Wang ◽  
Junxing Cao ◽  
Jiachun You ◽  
Ming Cheng ◽  
Peng Zhou
Keyword(s):  
Neural Network ◽  
Gamma Ray ◽  
Short Term Memory ◽  
Field Trials ◽  
Well Log ◽  
Data Generation ◽  
Log Data ◽  
Depth Direction ◽  
Spatio Temporal ◽  
Pseudo Data

Abstract Well logging helps geologists find hidden oil, natural gas and other resources. However, well log data are systematically insufficient because they can only be obtained by drilling, which involves costly and time-consuming field trials. Additionally, missing or distorted well log data are common in old oilfields owing to shutdowns, poor borehole conditions, damaged instruments and so on. As a workaround, pseudo-data can be generated from actual field data. In this study, we propose a spatio-temporal neural network (STNN) algorithm, which is built by leveraging the combined strengths of a convolutional neural network (CNN) and a long short-term memory network (LSTM). The STNN exploits the ability of the CNN to effectively extract features related to pseudo-well log data and the ability of the LSTM to extract the key features from well log data along the depth direction. The STNN method allows full consideration of the well log data trend with depth, the correlation across different log series and the actual depth accumulation effect. The method proved successful in predicting acoustic sonic log data from gamma-ray, density, compensated neutron, formation resistivity and borehole diameter logs. Results show that the proposed method achieves higher prediction accuracy because it takes into account the spatio-temporal information of well logs.

Sign in / Sign up

Export Citation Format

Share Document